# HG changeset patch # User mcharles # Date 1410355095 14400 # Node ID 442a7c88b88631bf9726a3cbfe1c5e83c1e499d2 Uploaded diff -r 000000000000 -r 442a7c88b886 rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-1x.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-1x.ga Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,590 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "rapsosnp v1.15 -1x", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "ASSEMBLY" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 258, + "top": 733.9833374023438 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"ASSEMBLY\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ1" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 258, + "top": 818.9833374023438 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ1\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ2" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 258, + "top": 903.9833374023438 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ2\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "DUBIOUS" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 258, + "top": 988.9833374023438 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"DUBIOUS\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "input_fasta": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "fastaGroomerForMakeBlastdb", + "outputs": [ + { + "name": "output_fasta", + "type": "fasta" + } + ], + "position": { + "left": 486, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/genephys/fastaGroomerForMakeBlastdb/0.01", + "tool_state": "{\"input_fasta\": \"null\", \"__rerun_remap_job_id__\": null, \"__page__\": 0}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "5": { + "annotation": "", + "id": 5, + "input_connections": { + "input_read1_file": { + "id": 1, + "output_name": "output" + }, + "input_read2_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 486, + "top": 864.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "input_file": { + "id": 4, + "output_name": "output_fasta" + } + }, + "inputs": [], + "name": "NCBI BLAST+ makeblastdb", + "outputs": [ + { + "name": "outfile", + "type": "data" + } + ], + "position": { + "left": 814, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_makeblastdb/0.1.00", + "tool_state": "{\"__page__\": 0, \"mask_data_file\": \"null\", \"input_file\": \"null\", \"dbtype\": \"\\\"nucl\\\"\", \"__rerun_remap_job_id__\": null, \"hash_index\": \"\\\"True\\\"\", \"tax\": \"{\\\"taxselect\\\": \\\"\\\", \\\"__current_case__\\\": 0}\", \"title\": \"\\\"\\\"\", \"parse_seqids\": \"\\\"False\\\"\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "7": { + "annotation": "", + "id": 7, + "input_connections": { + "genomeSource|ownFile": { + "id": 0, + "output_name": "output" + }, + "paired|input1": { + "id": 5, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 5, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 814, + "top": 891.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "8": { + "annotation": "", + "id": 8, + "input_connections": { + "input_sam_file": { + "id": 7, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1142, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "9": { + "annotation": "", + "id": 9, + "input_connections": { + "source|input1": { + "id": 8, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1470, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "10": { + "annotation": "", + "id": 10, + "input_connections": { + "reference_source|input_bams_0|input_bam": { + "id": 9, + "output_name": "output1" + }, + "reference_source|ref_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "MPileup", + "outputs": [ + { + "name": "output_mpileup", + "type": "pileup" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 1698, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_mpileup/samtools_mpileup/0.0.3", + "tool_state": "{\"__page__\": 0, \"genotype_likelihood_computation_type\": \"{\\\"genotype_likelihood_computation_type_selector\\\": \\\"do_not_perform_genotype_likelihood_computation\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"advanced_options\": \"{\\\"max_reads_per_bam\\\": \\\"250\\\", \\\"advanced_options_selector\\\": \\\"advanced\\\", \\\"extended_BAQ_computation\\\": \\\"False\\\", \\\"region_string\\\": \\\"\\\", \\\"output_per_sample_strand_bias_p_value\\\": \\\"False\\\", \\\"minimum_base_quality\\\": \\\"30\\\", \\\"disable_probabilistic_realignment\\\": \\\"False\\\", \\\"skip_anomalous_read_pairs\\\": \\\"False\\\", \\\"minimum_mapping_quality\\\": \\\"0\\\", \\\"output_per_sample_read_depth\\\": \\\"False\\\", \\\"__current_case__\\\": 0, \\\"position_list\\\": null, \\\"coefficient_for_downgrading\\\": \\\"0\\\"}\", \"reference_source\": \"{\\\"ref_file\\\": null, \\\"reference_source_selector\\\": \\\"history\\\", \\\"input_bams\\\": [{\\\"__index__\\\": 0, \\\"input_bam\\\": null}], \\\"__current_case__\\\": 1}\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "0.0.3", + "type": "tool", + "user_outputs": [] + }, + "11": { + "annotation": "", + "id": 11, + "input_connections": { + "input_file": { + "id": 10, + "output_name": "output_mpileup" + } + }, + "inputs": [], + "name": "PileupVariant", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2024, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PileupVariant", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "12": { + "annotation": "", + "id": 12, + "input_connections": { + "input_listA": { + "id": 11, + "output_name": "output_file" + }, + "input_listB": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "name": "listfiltering", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2352, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/listfiltering/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_listB\": \"null\", \"nb_col\": \"\\\"2\\\"\", \"input_listA\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "13": { + "annotation": "", + "id": 13, + "input_connections": { + "input_assembly_file": { + "id": 0, + "output_name": "output" + }, + "input_variant_file": { + "id": 12, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 2680, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "14": { + "annotation": "", + "id": 14, + "input_connections": { + "db_opts|histdb": { + "id": 6, + "output_name": "outfile" + }, + "query": { + "id": 13, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3008, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "15": { + "annotation": "", + "id": 15, + "input_connections": { + "input_blast_file": { + "id": 14, + "output_name": "output1" + }, + "input_variant_file": { + "id": 12, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 3310, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "16": { + "annotation": "", + "id": 16, + "input_connections": { + "input_file": { + "id": 15, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "mpileupfilterandstat", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 3638, + "top": 733.9833374023438 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "mpileupfilterandstat", + "tool_state": "{\"__page__\": 0, \"stat\": \"{\\\"stat_dist_step\\\": \\\"50\\\", \\\"stat_min_depth_step\\\": \\\"2\\\", \\\"stat_max_depth_max\\\": \\\"200\\\", \\\"stat_min_depth_max\\\": \\\"10\\\", \\\"stat_freq_max\\\": \\\"1.0\\\", \\\"stat_min_depth_min\\\": \\\"2\\\", \\\"stat_max_depth_min\\\": \\\"100\\\", \\\"do_stat\\\": \\\"YES\\\", \\\"stat_dist_min\\\": \\\"0\\\", \\\"__current_case__\\\": 0, \\\"stat_max_depth_step\\\": \\\"100\\\", \\\"stat_dist_max\\\": \\\"50\\\", \\\"stat_freq_step\\\": \\\"0.1\\\", \\\"stat_freq_min\\\": \\\"0.8\\\"}\", \"input_file\": \"null\", \"min_frequency\": \"\\\"0.8\\\"\", \"do_stat\": \"\\\"YES\\\"\", \"min_depth\": \"\\\"2\\\"\", \"__rerun_remap_job_id__\": null, \"min_forward_and_reverse\": \"\\\"0\\\"\", \"max_depth\": \"\\\"100\\\"\", \"min_distance\": \"\\\"0\\\"\"}", + "tool_version": "0.08", + "type": "tool", + "user_outputs": [] + }, + "17": { + "annotation": "", + "id": 17, + "input_connections": { + "input_blast_filtered_file": { + "id": 15, + "output_name": "output_file" + }, + "input_list_filtered_file": { + "id": 12, + "output_name": "output_file" + }, + "input_mpileup_variant_file": { + "id": 11, + "output_name": "output_file" + }, + "input_read1_row_file": { + "id": 1, + "output_name": "output" + }, + "input_read1_trimmed_file": { + "id": 5, + "output_name": "output_read1_file" + }, + "input_read2_row_file": { + "id": 2, + "output_name": "output" + }, + "input_read2_trimmed_file": { + "id": 5, + "output_name": "output_read2_file" + }, + "input_sam_filtered_file": { + "id": 8, + "output_name": "output_file" + }, + "input_sam_row_file": { + "id": 7, + "output_name": "output" + }, + "input_snp_selected_file": { + "id": 16, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "rapsosnp_stats", + "outputs": [ + { + "name": "output_file", + "type": "txt" + } + ], + "position": { + "left": 3584, + "top": 191 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "rapsosnp_stats", + "tool_state": "{\"input_read1_trimmed_file\": \"null\", \"__page__\": 0, \"input_read2_trimmed_file\": \"null\", \"input_sam_row_file\": \"null\", \"__rerun_remap_job_id__\": null, \"input_read2_row_file\": \"null\", \"input_mpileup_variant_file\": \"null\", \"input_sam_filtered_file\": \"null\", \"input_read1_row_file\": \"null\", \"input_snp_selected_file\": \"null\", \"input_list_filtered_file\": \"null\", \"input_blast_filtered_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + } + } +} \ No newline at end of file diff -r 000000000000 -r 442a7c88b886 rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-_2x.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-_2x.ga Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,1014 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "rapsosnp v1.15 - 2x", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "ASSEMBLY" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 200.000244140625, + "top": 211 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"ASSEMBLY\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ1" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 200.000244140625, + "top": 296 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ1\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ2" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 200.000244140625, + "top": 381 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ2\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "DUBIOUS" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 200.000244140625, + "top": 466 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"DUBIOUS\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "input_fasta": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "fastaGroomerForMakeBlastdb", + "outputs": [ + { + "name": "output_fasta", + "type": "fasta" + } + ], + "position": { + "left": 428.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/genephys/fastaGroomerForMakeBlastdb/0.01", + "tool_state": "{\"input_fasta\": \"null\", \"__rerun_remap_job_id__\": null, \"__page__\": 0}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "5": { + "annotation": "", + "id": 5, + "input_connections": { + "input_file": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "name": "SplitFile2x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + } + ], + "position": { + "left": 428.000244140625, + "top": 342 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile2x", + "tool_state": "{\"out_format\": \"\\\"fastq\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "input_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "SplitFile2x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + } + ], + "position": { + "left": 428.000244140625, + "top": 534 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile2x", + "tool_state": "{\"out_format\": \"\\\"fastq\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "7": { + "annotation": "", + "id": 7, + "input_connections": { + "input_file": { + "id": 4, + "output_name": "output_fasta" + } + }, + "inputs": [], + "name": "NCBI BLAST+ makeblastdb", + "outputs": [ + { + "name": "outfile", + "type": "data" + } + ], + "position": { + "left": 756.000244140625, + "top": 615.0000305175781 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_makeblastdb/0.1.00", + "tool_state": "{\"__page__\": 0, \"mask_data_file\": \"null\", \"input_file\": \"null\", \"dbtype\": \"\\\"nucl\\\"\", \"__rerun_remap_job_id__\": null, \"hash_index\": \"\\\"True\\\"\", \"tax\": \"{\\\"taxselect\\\": \\\"\\\", \\\"__current_case__\\\": 0}\", \"title\": \"\\\"\\\"\", \"parse_seqids\": \"\\\"False\\\"\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "8": { + "annotation": "", + "id": 8, + "input_connections": { + "input_read1_file": { + "id": 5, + "output_name": "output_file1" + }, + "input_read2_file": { + "id": 6, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 756.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "9": { + "annotation": "", + "id": 9, + "input_connections": { + "input_read1_file": { + "id": 5, + "output_name": "output_file2" + }, + "input_read2_file": { + "id": 6, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 756.000244140625, + "top": 413 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "10": { + "annotation": "", + "id": 10, + "input_connections": { + "genomeSource|ownFile": { + "id": 0, + "output_name": "output" + }, + "paired|input1": { + "id": 8, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 8, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1084.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "11": { + "annotation": "", + "id": 11, + "input_connections": { + "genomeSource|ownFile": { + "id": 0, + "output_name": "output" + }, + "paired|input1": { + "id": 9, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 9, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1084.000244140625, + "top": 396 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "12": { + "annotation": "", + "id": 12, + "input_connections": { + "input_sam_file": { + "id": 10, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1348.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "13": { + "annotation": "", + "id": 13, + "input_connections": { + "input_sam_file": { + "id": 11, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1348.000244140625, + "top": 342 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "14": { + "annotation": "", + "id": 14, + "input_connections": { + "source|input1": { + "id": 12, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1676.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "15": { + "annotation": "", + "id": 15, + "input_connections": { + "source|input1": { + "id": 13, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1676.000244140625, + "top": 352 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "16": { + "annotation": "", + "id": 16, + "input_connections": { + "input1": { + "id": 14, + "output_name": "output1" + }, + "input2": { + "id": 15, + "output_name": "output1" + } + }, + "inputs": [], + "name": "Merge BAM Files", + "outputs": [ + { + "name": "output1", + "type": "bam" + }, + { + "name": "outlog", + "type": "txt" + } + ], + "position": { + "left": 1904.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_merge/sam_merge2/1.1.2", + "tool_state": "{\"input2\": \"null\", \"inputs\": \"[]\", \"input1\": \"null\", \"title\": \"\\\"merge bam\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"mergeSD\": \"\\\"True\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.1.2", + "type": "tool", + "user_outputs": [] + }, + "17": { + "annotation": "", + "id": 17, + "input_connections": { + "reference_source|input_bams_0|input_bam": { + "id": 16, + "output_name": "output1" + }, + "reference_source|ref_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "MPileup", + "outputs": [ + { + "name": "output_mpileup", + "type": "pileup" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 2132.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_mpileup/samtools_mpileup/0.0.3", + "tool_state": "{\"__page__\": 0, \"genotype_likelihood_computation_type\": \"{\\\"genotype_likelihood_computation_type_selector\\\": \\\"do_not_perform_genotype_likelihood_computation\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"advanced_options\": \"{\\\"max_reads_per_bam\\\": \\\"250\\\", \\\"advanced_options_selector\\\": \\\"advanced\\\", \\\"extended_BAQ_computation\\\": \\\"False\\\", \\\"region_string\\\": \\\"\\\", \\\"output_per_sample_strand_bias_p_value\\\": \\\"False\\\", \\\"minimum_base_quality\\\": \\\"30\\\", \\\"disable_probabilistic_realignment\\\": \\\"False\\\", \\\"skip_anomalous_read_pairs\\\": \\\"False\\\", \\\"minimum_mapping_quality\\\": \\\"0\\\", \\\"output_per_sample_read_depth\\\": \\\"False\\\", \\\"__current_case__\\\": 0, \\\"position_list\\\": null, \\\"coefficient_for_downgrading\\\": \\\"0\\\"}\", \"reference_source\": \"{\\\"ref_file\\\": null, \\\"reference_source_selector\\\": \\\"history\\\", \\\"input_bams\\\": [{\\\"__index__\\\": 0, \\\"input_bam\\\": null}], \\\"__current_case__\\\": 1}\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "0.0.3", + "type": "tool", + "user_outputs": [] + }, + "18": { + "annotation": "", + "id": 18, + "input_connections": { + "input_file": { + "id": 17, + "output_name": "output_mpileup" + } + }, + "inputs": [], + "name": "PileupVariant", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2458.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PileupVariant", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "19": { + "annotation": "", + "id": 19, + "input_connections": { + "input_listA": { + "id": 18, + "output_name": "output_file" + }, + "input_listB": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "name": "listfiltering", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2786.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/listfiltering/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_listB\": \"null\", \"nb_col\": \"\\\"2\\\"\", \"input_listA\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "20": { + "annotation": "", + "id": 20, + "input_connections": { + "input_file": { + "id": 19, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "SplitFile2x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + } + ], + "position": { + "left": 3114.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile2x", + "tool_state": "{\"out_format\": \"\\\"pileup\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "21": { + "annotation": "", + "id": 21, + "input_connections": { + "input_assembly_file": { + "id": 0, + "output_name": "output" + }, + "input_variant_file": { + "id": 20, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3442.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "22": { + "annotation": "", + "id": 22, + "input_connections": { + "input_assembly_file": { + "id": 0, + "output_name": "output" + }, + "input_variant_file": { + "id": 20, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3442.000244140625, + "top": 386 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "23": { + "annotation": "", + "id": 23, + "input_connections": { + "db_opts|histdb": { + "id": 7, + "output_name": "outfile" + }, + "query": { + "id": 21, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3770.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "24": { + "annotation": "", + "id": 24, + "input_connections": { + "db_opts|histdb": { + "id": 7, + "output_name": "outfile" + }, + "query": { + "id": 22, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3770.000244140625, + "top": 352 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"0\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "25": { + "annotation": "", + "id": 25, + "input_connections": { + "input_blast_file": { + "id": 23, + "output_name": "output1" + }, + "input_variant_file": { + "id": 20, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4072.000228881836, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "26": { + "annotation": "", + "id": 26, + "input_connections": { + "input_blast_file": { + "id": 24, + "output_name": "output1" + }, + "input_variant_file": { + "id": 20, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4072.000228881836, + "top": 420 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "27": { + "annotation": "", + "id": 27, + "input_connections": { + "input_file1": { + "id": 25, + "output_name": "output_file" + }, + "input_file2": { + "id": 26, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "MergeFile2x", + "outputs": [ + { + "name": "output_file", + "type": "txt" + } + ], + "position": { + "left": 4400.000228881836, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "MergeFile2x", + "tool_state": "{\"out_format\": \"\\\"pileup\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file1\": \"null\", \"input_file2\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "28": { + "annotation": "", + "id": 28, + "input_connections": { + "input_file": { + "id": 27, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "mpileupfilterandstat", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 4728.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "mpileupfilterandstat", + "tool_state": "{\"__page__\": 0, \"stat\": \"{\\\"stat_dist_step\\\": \\\"50\\\", \\\"stat_min_depth_step\\\": \\\"2\\\", \\\"stat_max_depth_max\\\": \\\"200\\\", \\\"stat_min_depth_max\\\": \\\"10\\\", \\\"stat_freq_max\\\": \\\"1.0\\\", \\\"stat_min_depth_min\\\": \\\"2\\\", \\\"stat_max_depth_min\\\": \\\"100\\\", \\\"do_stat\\\": \\\"YES\\\", \\\"stat_dist_min\\\": \\\"0\\\", \\\"__current_case__\\\": 0, \\\"stat_max_depth_step\\\": \\\"100\\\", \\\"stat_dist_max\\\": \\\"50\\\", \\\"stat_freq_step\\\": \\\"0.1\\\", \\\"stat_freq_min\\\": \\\"0.8\\\"}\", \"input_file\": \"null\", \"min_frequency\": \"\\\"0.8\\\"\", \"do_stat\": \"\\\"YES\\\"\", \"min_depth\": \"\\\"2\\\"\", \"__rerun_remap_job_id__\": null, \"min_forward_and_reverse\": \"\\\"0\\\"\", \"max_depth\": \"\\\"100\\\"\", \"min_distance\": \"\\\"0\\\"\"}", + "tool_version": "0.08", + "type": "tool", + "user_outputs": [] + }, + "29": { + "annotation": "", + "id": 29, + "input_connections": { + "input_blast_filtered_part1_file": { + "id": 25, + "output_name": "output_file" + }, + "input_blast_filtered_part2_file": { + "id": 26, + "output_name": "output_file" + }, + "input_list_filtered_file": { + "id": 19, + "output_name": "output_file" + }, + "input_mpileup_variant_file": { + "id": 18, + "output_name": "output_file" + }, + "input_read1_part1_trimmed_file": { + "id": 8, + "output_name": "output_read1_file" + }, + "input_read1_part2_trimmed_file": { + "id": 9, + "output_name": "output_read1_file" + }, + "input_read1_row_file": { + "id": 1, + "output_name": "output" + }, + "input_read2_part1_trimmed_file": { + "id": 8, + "output_name": "output_read2_file" + }, + "input_read2_part2_trimmed_file": { + "id": 9, + "output_name": "output_read2_file" + }, + "input_read2_row_file": { + "id": 2, + "output_name": "output" + }, + "input_sam_filtered_part1_file": { + "id": 12, + "output_name": "output_file" + }, + "input_sam_filtered_part2_file": { + "id": 13, + "output_name": "output_file" + }, + "input_sam_row_part1_file": { + "id": 10, + "output_name": "output" + }, + "input_sam_row_part2_file": { + "id": 11, + "output_name": "output" + }, + "input_snp_selected_file": { + "id": 28, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "rapsosnp_stats2x", + "outputs": [ + { + "name": "output_file", + "type": "txt" + } + ], + "position": { + "left": 5056.000244140625, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "rapsosnp_stats2x", + "tool_state": "{\"input_blast_filtered_part1_file\": \"null\", \"input_blast_filtered_part2_file\": \"null\", \"input_sam_row_part2_file\": \"null\", \"input_read1_part1_trimmed_file\": \"null\", \"__page__\": 0, \"input_list_filtered_file\": \"null\", \"__rerun_remap_job_id__\": null, \"input_read2_row_file\": \"null\", \"input_mpileup_variant_file\": \"null\", \"input_read2_part1_trimmed_file\": \"null\", \"input_read1_row_file\": \"null\", \"input_sam_row_part1_file\": \"null\", \"input_sam_filtered_part2_file\": \"null\", \"input_read2_part2_trimmed_file\": \"null\", \"input_snp_selected_file\": \"null\", \"input_read1_part2_trimmed_file\": \"null\", \"input_sam_filtered_part1_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + } + } +} \ No newline at end of file diff -r 000000000000 -r 442a7c88b886 rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-_4x.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/Galaxy-Workflow-rapsosnp_v1.15_-_4x.ga Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,1564 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "rapsosnp v1.15 - 4x", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ1" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 214.7666015625, + "top": 723 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ1\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "1": { + "annotation": "", + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "READ2" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 219.7666015625, + "top": 1105 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"READ2\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "2": { + "annotation": "", + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "ASSEMBLY" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 2639.7666015625, + "top": 587 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"ASSEMBLY\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "3": { + "annotation": "", + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "DUBIUS" + } + ], + "name": "Input dataset", + "outputs": [], + "position": { + "left": 2449.7666015625, + "top": 1405 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"DUBIUS\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [] + }, + "4": { + "annotation": "", + "id": 4, + "input_connections": { + "input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "name": "SplitFile4x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + }, + { + "name": "output_file3", + "type": "txt" + }, + { + "name": "output_file4", + "type": "txt" + } + ], + "position": { + "left": 516.7666015625, + "top": 602.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile4x", + "tool_state": "{\"out_format\": \"\\\"fastq\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "5": { + "annotation": "", + "id": 5, + "input_connections": { + "input_file": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "name": "SplitFile4x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + }, + { + "name": "output_file3", + "type": "txt" + }, + { + "name": "output_file4", + "type": "txt" + } + ], + "position": { + "left": 519.7666015625, + "top": 920.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile4x", + "tool_state": "{\"out_format\": \"\\\"fastq\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "6": { + "annotation": "", + "id": 6, + "input_connections": { + "input_fasta": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "fastaGroomerForMakeBlastdb", + "outputs": [ + { + "name": "output_fasta", + "type": "fasta" + } + ], + "position": { + "left": 2796.7666015625, + "top": 404.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/genephys/fastaGroomerForMakeBlastdb/0.01", + "tool_state": "{\"input_fasta\": \"null\", \"__rerun_remap_job_id__\": null, \"__page__\": 0}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "7": { + "annotation": "", + "id": 7, + "input_connections": { + "input_read1_file": { + "id": 4, + "output_name": "output_file1" + }, + "input_read2_file": { + "id": 5, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 891.7666015625, + "top": 481.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "8": { + "annotation": "", + "id": 8, + "input_connections": { + "input_read1_file": { + "id": 4, + "output_name": "output_file2" + }, + "input_read2_file": { + "id": 5, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 900.7666015625, + "top": 722.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "9": { + "annotation": "", + "id": 9, + "input_connections": { + "input_read1_file": { + "id": 4, + "output_name": "output_file3" + }, + "input_read2_file": { + "id": 5, + "output_name": "output_file3" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 890.7666015625, + "top": 947.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "10": { + "annotation": "", + "id": 10, + "input_connections": { + "input_read1_file": { + "id": 4, + "output_name": "output_file4" + }, + "input_read2_file": { + "id": 5, + "output_name": "output_file4" + } + }, + "inputs": [], + "name": "PrepareFastqLight", + "outputs": [ + { + "name": "output_read1_file", + "type": "fastqsanger" + }, + { + "name": "output_read2_file", + "type": "fastqsanger" + } + ], + "position": { + "left": 894.7666015625, + "top": 1175.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PrepareFastqLight", + "tool_state": "{\"__page__\": 0, \"quality_type\": \"\\\"illumina\\\"\", \"min_length\": \"\\\"30\\\"\", \"__rerun_remap_job_id__\": null, \"min_quality\": \"\\\"30\\\"\", \"input_read1_file\": \"null\", \"input_read2_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "11": { + "annotation": "", + "id": 11, + "input_connections": { + "input_file": { + "id": 6, + "output_name": "output_fasta" + } + }, + "inputs": [], + "name": "NCBI BLAST+ makeblastdb", + "outputs": [ + { + "name": "outfile", + "type": "data" + } + ], + "position": { + "left": 3514.2666625976562, + "top": 427.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_makeblastdb/0.1.00", + "tool_state": "{\"__page__\": 0, \"mask_data_file\": \"null\", \"input_file\": \"null\", \"dbtype\": \"\\\"nucl\\\"\", \"__rerun_remap_job_id__\": null, \"hash_index\": \"\\\"True\\\"\", \"tax\": \"{\\\"taxselect\\\": \\\"\\\", \\\"__current_case__\\\": 0}\", \"title\": \"\\\"\\\"\", \"parse_seqids\": \"\\\"False\\\"\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "12": { + "annotation": "", + "id": 12, + "input_connections": { + "genomeSource|ownFile": { + "id": 2, + "output_name": "output" + }, + "paired|input1": { + "id": 7, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 7, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1355.7666015625, + "top": 563 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "13": { + "annotation": "", + "id": 13, + "input_connections": { + "genomeSource|ownFile": { + "id": 2, + "output_name": "output" + }, + "paired|input1": { + "id": 8, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 8, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1349.7666015625, + "top": 745 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "14": { + "annotation": "", + "id": 14, + "input_connections": { + "genomeSource|ownFile": { + "id": 2, + "output_name": "output" + }, + "paired|input1": { + "id": 9, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 9, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1349.7666015625, + "top": 914 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "15": { + "annotation": "", + "id": 15, + "input_connections": { + "genomeSource|ownFile": { + "id": 2, + "output_name": "output" + }, + "paired|input1": { + "id": 10, + "output_name": "output_read1_file" + }, + "paired|input2": { + "id": 10, + "output_name": "output_read2_file" + } + }, + "inputs": [], + "name": "Map with BWA for Illumina", + "outputs": [ + { + "name": "output", + "type": "sam" + } + ], + "position": { + "left": 1349.7666015625, + "top": 1094 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/bwa_wrappers/bwa_wrapper/1.2.3", + "tool_state": "{\"genomeSource\": \"{\\\"refGenomeSource\\\": \\\"history\\\", \\\"ownFile\\\": null, \\\"__current_case__\\\": 1}\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"paired\": \"{\\\"input2\\\": null, \\\"sPaired\\\": \\\"paired\\\", \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"params\": \"{\\\"__current_case__\\\": 0, \\\"source_select\\\": \\\"pre_set\\\"}\", \"suppressHeader\": \"\\\"False\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.2.3", + "type": "tool", + "user_outputs": [] + }, + "16": { + "annotation": "", + "id": 16, + "input_connections": { + "input_sam_file": { + "id": 12, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1628.7666015625, + "top": 711 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "17": { + "annotation": "", + "id": 17, + "input_connections": { + "input_sam_file": { + "id": 13, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1628.7666015625, + "top": 856 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "18": { + "annotation": "", + "id": 18, + "input_connections": { + "input_sam_file": { + "id": 14, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1633.7666015625, + "top": 995 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "19": { + "annotation": "", + "id": 19, + "input_connections": { + "input_sam_file": { + "id": 15, + "output_name": "output" + } + }, + "inputs": [], + "name": "filtersam_mapped_and_unique", + "outputs": [ + { + "name": "output_file", + "type": "sam" + } + ], + "position": { + "left": 1632.7666015625, + "top": 1149 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/filtersam_mapped_and_unique/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"input_sam_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "20": { + "annotation": "", + "id": 20, + "input_connections": { + "source|input1": { + "id": 16, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1952.7666015625, + "top": 756 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "21": { + "annotation": "", + "id": 21, + "input_connections": { + "source|input1": { + "id": 17, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1948.7666015625, + "top": 903 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "22": { + "annotation": "", + "id": 22, + "input_connections": { + "source|input1": { + "id": 18, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1948.7666015625, + "top": 1041 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "23": { + "annotation": "", + "id": 23, + "input_connections": { + "source|input1": { + "id": 19, + "output_name": "output_file" + }, + "source|ref_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "SAM-to-BAM", + "outputs": [ + { + "name": "output1", + "type": "bam" + } + ], + "position": { + "left": 1948.7666015625, + "top": 1193 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_to_bam/sam_to_bam/1.1.4", + "tool_state": "{\"source\": \"{\\\"index_source\\\": \\\"history\\\", \\\"ref_file\\\": null, \\\"input1\\\": null, \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__page__\": 0}", + "tool_version": "1.1.4", + "type": "tool", + "user_outputs": [] + }, + "24": { + "annotation": "", + "id": 24, + "input_connections": { + "input1": { + "id": 20, + "output_name": "output1" + }, + "input2": { + "id": 21, + "output_name": "output1" + }, + "inputs_0|input": { + "id": 22, + "output_name": "output1" + }, + "inputs_1|input": { + "id": 23, + "output_name": "output1" + } + }, + "inputs": [], + "name": "Merge BAM Files", + "outputs": [ + { + "name": "output1", + "type": "bam" + }, + { + "name": "outlog", + "type": "txt" + } + ], + "position": { + "left": 2265.7666015625, + "top": 1038 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/sam_merge/sam_merge2/1.1.2", + "tool_state": "{\"input2\": \"null\", \"inputs\": \"[{\\\"__index__\\\": 0, \\\"input\\\": null}, {\\\"__index__\\\": 1, \\\"input\\\": null}]\", \"input1\": \"null\", \"title\": \"\\\"merge bam\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"mergeSD\": \"\\\"True\\\"\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "1.1.2", + "type": "tool", + "user_outputs": [] + }, + "25": { + "annotation": "", + "id": 25, + "input_connections": { + "reference_source|input_bams_0|input_bam": { + "id": 24, + "output_name": "output1" + }, + "reference_source|ref_file": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "name": "MPileup", + "outputs": [ + { + "name": "output_mpileup", + "type": "pileup" + }, + { + "name": "output_log", + "type": "txt" + } + ], + "position": { + "left": 2401.7666015625, + "top": 764 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/samtools_mpileup/samtools_mpileup/0.0.3", + "tool_state": "{\"__page__\": 0, \"genotype_likelihood_computation_type\": \"{\\\"genotype_likelihood_computation_type_selector\\\": \\\"do_not_perform_genotype_likelihood_computation\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"advanced_options\": \"{\\\"max_reads_per_bam\\\": \\\"250\\\", \\\"advanced_options_selector\\\": \\\"advanced\\\", \\\"extended_BAQ_computation\\\": \\\"False\\\", \\\"region_string\\\": \\\"\\\", \\\"output_per_sample_strand_bias_p_value\\\": \\\"False\\\", \\\"minimum_base_quality\\\": \\\"30\\\", \\\"disable_probabilistic_realignment\\\": \\\"False\\\", \\\"skip_anomalous_read_pairs\\\": \\\"False\\\", \\\"minimum_mapping_quality\\\": \\\"0\\\", \\\"output_per_sample_read_depth\\\": \\\"False\\\", \\\"__current_case__\\\": 0, \\\"position_list\\\": null, \\\"coefficient_for_downgrading\\\": \\\"0\\\"}\", \"reference_source\": \"{\\\"ref_file\\\": null, \\\"reference_source_selector\\\": \\\"history\\\", \\\"input_bams\\\": [{\\\"__index__\\\": 0, \\\"input_bam\\\": null}], \\\"__current_case__\\\": 1}\", \"chromInfo\": \"\\\"/home/galaxy/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}", + "tool_version": "0.0.3", + "type": "tool", + "user_outputs": [] + }, + "26": { + "annotation": "", + "id": 26, + "input_connections": { + "input_file": { + "id": 25, + "output_name": "output_mpileup" + } + }, + "inputs": [], + "name": "PileupVariant", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2694.7666015625, + "top": 1264.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "PileupVariant", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "27": { + "annotation": "", + "id": 27, + "input_connections": { + "input_listA": { + "id": 26, + "output_name": "output_file" + }, + "input_listB": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "name": "listfiltering", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 2778.7666015625, + "top": 956.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/listfiltering/0.01", + "tool_state": "{\"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_listB\": \"null\", \"nb_col\": \"\\\"2\\\"\", \"input_listA\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "28": { + "annotation": "", + "id": 28, + "input_connections": { + "input_file": { + "id": 27, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "SplitFile4x", + "outputs": [ + { + "name": "output_file1", + "type": "txt" + }, + { + "name": "output_file2", + "type": "txt" + }, + { + "name": "output_file3", + "type": "txt" + }, + { + "name": "output_file4", + "type": "txt" + } + ], + "position": { + "left": 3154, + "top": 906.88330078125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "SplitFile4x", + "tool_state": "{\"out_format\": \"\\\"pileup\\\"\", \"line_number\": \"\\\"4\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "29": { + "annotation": "", + "id": 29, + "input_connections": { + "input_assembly_file": { + "id": 2, + "output_name": "output" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3512, + "top": 711.8833312988281 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "30": { + "annotation": "", + "id": 30, + "input_connections": { + "input_assembly_file": { + "id": 2, + "output_name": "output" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3517, + "top": 880.8833312988281 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "31": { + "annotation": "", + "id": 31, + "input_connections": { + "input_assembly_file": { + "id": 2, + "output_name": "output" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file3" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3518, + "top": 1049.88330078125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "32": { + "annotation": "", + "id": 32, + "input_connections": { + "input_assembly_file": { + "id": 2, + "output_name": "output" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file4" + } + }, + "inputs": [], + "name": "extractseq", + "outputs": [ + { + "name": "output_file", + "type": "fasta" + } + ], + "position": { + "left": 3525, + "top": 1216.88330078125 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/mcharles/rapsodyn/extractseq/0.03", + "tool_state": "{\"__page__\": 0, \"input_variant_file\": \"null\", \"__rerun_remap_job_id__\": null, \"window_length\": \"\\\"50\\\"\", \"input_assembly_file\": \"null\"}", + "tool_version": "0.03", + "type": "tool", + "user_outputs": [] + }, + "33": { + "annotation": "", + "id": 33, + "input_connections": { + "db_opts|histdb": { + "id": 11, + "output_name": "outfile" + }, + "query": { + "id": 29, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3959.7666625976562, + "top": 695.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "34": { + "annotation": "", + "id": 34, + "input_connections": { + "db_opts|histdb": { + "id": 11, + "output_name": "outfile" + }, + "query": { + "id": 30, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3961.7666625976562, + "top": 886.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "35": { + "annotation": "", + "id": 35, + "input_connections": { + "db_opts|histdb": { + "id": 11, + "output_name": "outfile" + }, + "query": { + "id": 31, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3965.7666625976562, + "top": 1052.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "36": { + "annotation": "", + "id": 36, + "input_connections": { + "db_opts|histdb": { + "id": 11, + "output_name": "outfile" + }, + "query": { + "id": 32, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "NCBI BLAST+ blastn", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 3971.7666625976562, + "top": 1220.5 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastn_wrapper/0.1.00", + "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"identity_cutoff\\\": \\\"0.0\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"False\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"8\\\"}\", \"__rerun_remap_job_id__\": null, \"blast_type\": \"\\\"megablast\\\"\", \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"histdb\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": null, \\\"__current_case__\\\": 1, \\\"database\\\": \\\"\\\"}\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"qstart\\\", \\\"qend\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": null, \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": [\\\"qseq\\\", \\\"sseq\\\"]}\", \"query\": \"null\"}", + "tool_version": "0.1.00", + "type": "tool", + "user_outputs": [] + }, + "37": { + "annotation": "", + "id": 37, + "input_connections": { + "input_blast_file": { + "id": 33, + "output_name": "output1" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file1" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4286.5, + "top": 705 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "38": { + "annotation": "", + "id": 38, + "input_connections": { + "input_blast_file": { + "id": 34, + "output_name": "output1" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file2" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4284.5, + "top": 904 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "39": { + "annotation": "", + "id": 39, + "input_connections": { + "input_blast_file": { + "id": 35, + "output_name": "output1" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file3" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4287.5, + "top": 1103 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "40": { + "annotation": "", + "id": 40, + "input_connections": { + "input_blast_file": { + "id": 36, + "output_name": "output1" + }, + "input_variant_file": { + "id": 28, + "output_name": "output_file4" + } + }, + "inputs": [], + "name": "ParseBlastForUniqueMatch", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + } + ], + "position": { + "left": 4281.5, + "top": 1305 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "ParseBlastForUniqueMatch", + "tool_state": "{\"input_variant_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_blast_file\": \"null\", \"window_length\": \"\\\"50\\\"\", \"nb_mismatch_max\": \"\\\"3\\\"\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "41": { + "annotation": "", + "id": 41, + "input_connections": { + "input_file1": { + "id": 37, + "output_name": "output_file" + }, + "input_file2": { + "id": 38, + "output_name": "output_file" + }, + "input_file3": { + "id": 39, + "output_name": "output_file" + }, + "input_file4": { + "id": 40, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "MergeFile4x", + "outputs": [ + { + "name": "output_file", + "type": "txt" + } + ], + "position": { + "left": 4700, + "top": 841.8833312988281 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "MergeFile4x", + "tool_state": "{\"out_format\": \"\\\"pileup\\\"\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_file4\": \"null\", \"input_file1\": \"null\", \"input_file2\": \"null\", \"input_file3\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + }, + "42": { + "annotation": "", + "id": 42, + "input_connections": { + "input_file": { + "id": 41, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "mpileupfilterandstat", + "outputs": [ + { + "name": "output_file", + "type": "pileup" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 5056, + "top": 886.8833312988281 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "mpileupfilterandstat", + "tool_state": "{\"__page__\": 0, \"stat\": \"{\\\"stat_dist_step\\\": \\\"50\\\", \\\"stat_min_depth_step\\\": \\\"2\\\", \\\"stat_max_depth_max\\\": \\\"200\\\", \\\"stat_min_depth_max\\\": \\\"10\\\", \\\"stat_freq_max\\\": \\\"1.0\\\", \\\"stat_min_depth_min\\\": \\\"2\\\", \\\"stat_max_depth_min\\\": \\\"100\\\", \\\"do_stat\\\": \\\"YES\\\", \\\"stat_dist_min\\\": \\\"0\\\", \\\"__current_case__\\\": 0, \\\"stat_max_depth_step\\\": \\\"100\\\", \\\"stat_dist_max\\\": \\\"50\\\", \\\"stat_freq_step\\\": \\\"0.1\\\", \\\"stat_freq_min\\\": \\\"0.8\\\"}\", \"input_file\": \"null\", \"min_frequency\": \"\\\"0.8\\\"\", \"do_stat\": \"\\\"YES\\\"\", \"min_depth\": \"\\\"2\\\"\", \"__rerun_remap_job_id__\": null, \"min_forward_and_reverse\": \"\\\"0\\\"\", \"max_depth\": \"\\\"100\\\"\", \"min_distance\": \"\\\"0\\\"\"}", + "tool_version": "0.08", + "type": "tool", + "user_outputs": [] + }, + "43": { + "annotation": "", + "id": 43, + "input_connections": { + "input_blast_filtered_part1_file": { + "id": 37, + "output_name": "output_file" + }, + "input_blast_filtered_part2_file": { + "id": 38, + "output_name": "output_file" + }, + "input_blast_filtered_part3_file": { + "id": 39, + "output_name": "output_file" + }, + "input_blast_filtered_part4_file": { + "id": 40, + "output_name": "output_file" + }, + "input_list_filtered_file": { + "id": 27, + "output_name": "output_file" + }, + "input_mpileup_variant_file": { + "id": 26, + "output_name": "output_file" + }, + "input_read1_part1_trimmed_file": { + "id": 7, + "output_name": "output_read1_file" + }, + "input_read1_part2_trimmed_file": { + "id": 8, + "output_name": "output_read1_file" + }, + "input_read1_part3_trimmed_file": { + "id": 9, + "output_name": "output_read1_file" + }, + "input_read1_part4_trimmed_file": { + "id": 10, + "output_name": "output_read1_file" + }, + "input_read1_row_file": { + "id": 0, + "output_name": "output" + }, + "input_read2_part1_trimmed_file": { + "id": 7, + "output_name": "output_read2_file" + }, + "input_read2_part2_trimmed_file": { + "id": 8, + "output_name": "output_read2_file" + }, + "input_read2_part3_trimmed_file": { + "id": 9, + "output_name": "output_read2_file" + }, + "input_read2_part4_trimmed_file": { + "id": 10, + "output_name": "output_read2_file" + }, + "input_read2_row_file": { + "id": 1, + "output_name": "output" + }, + "input_sam_filtered_part1_file": { + "id": 16, + "output_name": "output_file" + }, + "input_sam_filtered_part2_file": { + "id": 17, + "output_name": "output_file" + }, + "input_sam_filtered_part3_file": { + "id": 18, + "output_name": "output_file" + }, + "input_sam_filtered_part4_file": { + "id": 19, + "output_name": "output_file" + }, + "input_sam_row_part1_file": { + "id": 12, + "output_name": "output" + }, + "input_sam_row_part2_file": { + "id": 13, + "output_name": "output" + }, + "input_sam_row_part3_file": { + "id": 14, + "output_name": "output" + }, + "input_sam_row_part4_file": { + "id": 15, + "output_name": "output" + }, + "input_snp_selected_file": { + "id": 42, + "output_name": "output_file" + } + }, + "inputs": [], + "name": "rapsosnp_stats4x", + "outputs": [ + { + "name": "output_file", + "type": "txt" + } + ], + "position": { + "left": 5447.5, + "top": 211 + }, + "post_job_actions": {}, + "tool_errors": null, + "tool_id": "rapsosnp_stats4x", + "tool_state": "{\"input_blast_filtered_part2_file\": \"null\", \"input_blast_filtered_part3_file\": \"null\", \"input_read2_part1_trimmed_file\": \"null\", \"input_read1_row_file\": \"null\", \"input_read1_part2_trimmed_file\": \"null\", \"input_read1_part4_trimmed_file\": \"null\", \"input_read1_part3_trimmed_file\": \"null\", \"__page__\": 0, \"__rerun_remap_job_id__\": null, \"input_mpileup_variant_file\": \"null\", \"input_sam_row_part1_file\": \"null\", \"input_blast_filtered_part1_file\": \"null\", \"input_sam_row_part4_file\": \"null\", \"input_sam_filtered_part1_file\": \"null\", \"input_read2_part3_trimmed_file\": \"null\", \"input_read2_part4_trimmed_file\": \"null\", \"input_sam_filtered_part3_file\": \"null\", \"input_sam_filtered_part4_file\": \"null\", \"input_sam_row_part2_file\": \"null\", \"input_read1_part1_trimmed_file\": \"null\", \"input_read2_row_file\": \"null\", \"input_blast_filtered_part4_file\": \"null\", \"input_sam_row_part3_file\": \"null\", \"input_sam_filtered_part2_file\": \"null\", \"input_read2_part2_trimmed_file\": \"null\", \"input_snp_selected_file\": \"null\", \"input_list_filtered_file\": \"null\"}", + "tool_version": "0.01", + "type": "tool", + "user_outputs": [] + } + } +} \ No newline at end of file diff -r 000000000000 -r 442a7c88b886 rapsodyn/ParseBlastForUniqueMatch.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/ParseBlastForUniqueMatch.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,176 @@ +#!/usr/bin/perl +use strict; +use warnings; + + +my $input_variant_file = $ARGV[0]; +my $input_blast_file = $ARGV[1]; +my $window_length = $ARGV[2]; +my $nb_mismatch_max = $ARGV[3]; + +my %hash_name; + +open(INB, $input_blast_file) or die ("Can't open $input_blast_file\n"); +while (my $line =){ + my @fields = split (/\s+/,$line); + # print $#fields,"\n"; + # print $line; + # exit(0); + my $query_name; + my $query_start; + my $query_stop; + my $query_aln; + my $subject_aln; + my $compt_mismatch_5p=0; + my $compt_mismatch_3p=0; + + if ($#fields == 24){ + $query_name = $fields[0]; + $query_start = $fields[6]; + $query_stop = $fields[7]; + $query_aln = $fields[20]; + $subject_aln = $fields[21]; + } + elsif ($#fields == 4){ + $query_name = $fields[0]; + $query_start = $fields[1]; + $query_stop = $fields[2]; + $query_aln = $fields[3]; + $subject_aln = $fields[4]; + } + else { + print STDERR "Unrecongnized tabular format for blast result\nScript works with 25 column or 5 custom column(qseqid,qstart,qend,ssseq,sseq)\n"; + exit(0); + } + + + my @field_name = split (/\_/,$query_name); + my $name = $field_name[0]."_".$field_name[1]; + if ($query_name =~ /random/){ + $name .= "_".$field_name[2]; + # print $name."\n"; + + } + if (!$hash_name{$name}){ + $hash_name{$name}=0; + } + elsif ($hash_name{$name}>1){ + next; + } + # if ($query_name eq "chrUnn_random_8279117_1_M1_a"){ + # print "READ : $query_name\n$name\n"; + # print "HASH : ",$hash_name{$name},"\n"; + # # exit(0); + # } + + + + chomp($query_aln); + chomp($subject_aln); + + my $nb_gap_query=0; + + if (length($query_aln) == length($subject_aln)){ + if (length($query_aln)<$window_length-$nb_mismatch_max){ + } + else { + my @q = split(//,$query_aln); + my @s = split(//,$subject_aln); + for (my $i=0;$i<=$#q;$i++){ + my $global_idx = $query_start-1+$i-$nb_gap_query; + if ($q[$i] eq "-"){ + if ($global_idx < $window_length){ + $compt_mismatch_5p++; + } + elsif ($global_idx > $window_length){ + $compt_mismatch_3p++; + } + $nb_gap_query++; #On compte les gap dans la query pour les soustraire de l'index global + } + else { + if ($q[$i] ne $s[$i]){ + if ($global_idx < $window_length){ + $compt_mismatch_5p++; + } + elsif ($global_idx > $window_length){ + $compt_mismatch_3p++; + } + } + } + } + $compt_mismatch_5p += $query_start-1; + $compt_mismatch_3p += $window_length *2 + 1 - $query_stop; + + # for (my $i=0;$i<$window_length;$i++){ + # if ($tbl_q_aln[$i] eq "#"){ + # $compt_mismatch_5p++; + # } + # elsif ($tbl_q_aln[$i] ne $tbl_s_aln[$i]){ + # $compt_mismatch_5p++; + # } + # else { + # } + + # } + # for (my $i=$window_length+1;$i<=$window_length*2;$i++){ + # if ($tbl_q_aln[$i] eq "#"){ + # $compt_mismatch_3p++; + # } + # elsif ($tbl_q_aln[$i] ne $tbl_s_aln[$i]){ + # $compt_mismatch_3p++; + # } + # else { + # } + # } + if (($compt_mismatch_5p <= $nb_mismatch_max)||($compt_mismatch_3p <= $nb_mismatch_max)){ + $hash_name{$name}++; + } + + } + } + else { + print STDERR "incompatible subject and query alignement length\n $query_aln\n$subject_aln\n"; + } + + # if ($line=~/chrCnn_random_49828229/){ + # print $line; + # print $query_aln,"\n"; + # print $subject_aln,"\n"; + # print $compt_mismatch_5p,"\t",$compt_mismatch_3p,"\n"; + # print $hash_name{"chrCnn_random_49828229"},"\n"; + # print "\n"; + # } + + + +} +# exit(0); + +close (INB); + +open(INV, $input_variant_file) or die ("Can't open $input_variant_file\n"); + +while (my $ligne = ) { + + my @champs = split (/\s+/,$ligne); + my $header = $champs[0]."_".$champs[1]; + + if ($hash_name{$header}){ + if ($hash_name{$header}==1){ + print $ligne; + } + } + else { + #print STDERR "No blast result for ",$header,"\n"; + } + + +} + +close(INV); + + +# foreach my $key (sort keys %hash_name){ + # print $key,"\t",$hash_name{$key},"\n"; + +# } diff -r 000000000000 -r 442a7c88b886 rapsodyn/ParseBlastForUniqueMatch.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/ParseBlastForUniqueMatch.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,21 @@ + +Filter mpileup with blast results + + ParseBlastForUniqueMatch.pl $input_variant_file $input_blast_file $window_length $nb_mismatch_max > $output_file + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/PileupVariant.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/PileupVariant.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,19 @@ +#!/usr/bin/perl +use strict; + +my $inputfile = $ARGV[0]; +open(IF, $inputfile) or die("Can't open $inputfile\n"); + +#Extraction des variants +my $nb_line=0; +while (my $line=){ + my $test = $line; + $test =~ s/\$//g; #the read start at this position + $test =~ s/\^.//g; #the read end at this position followed by quality char + my @field = split(/\s+/,$test); + + if ($field[4]=~/[ATGCN]/i){ + print $line; + } +} +close(IF); diff -r 000000000000 -r 442a7c88b886 rapsodyn/PileupVariant.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/PileupVariant.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,18 @@ + +Keep only mpileup line with variant + + PileupVariant.pl $input_file > $output_file + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/PrepareFastqLight.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/PrepareFastqLight.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,420 @@ +#!/usr/bin/perl +use strict; +use warnings; + +my $read1 = $ARGV[0]; +my $read2 = $ARGV[1]; + +my $output1 = $ARGV[2]; +my $output2 = $ARGV[3]; + +my $TYPE = $ARGV[4]; +my $MIN_LENGTH = $ARGV[5]; +my $MIN_QUALITY = $ARGV[6]; + +my $VERBOSE = $ARGV[7]; + +if (!$VERBOSE){ + $VERBOSE ="OFF"; +} + +open(READ1, $read1) or die ("Can't open $read1\n"); +open(READ2, $read2) or die ("Can't open $read2\n"); +open(OUT1, ">$output1") or die ("Can't open $output1\n"); +open(OUT2, ">$output2") or die ("Can't open $output2\n"); + + +my $error1=0; +my $error2=0; +my $error3=0; +my $error4=0; +my $error5=0; +my $error6=0; +my $error7=0; +my $error8=0; +my $error9=0; +my $error10=0; + +while (my $ligne1_r1 =){ + my $ligne2_r1 =; + my $ligne3_r1 =; + my $ligne4_r1 =; + my $ligne1_r2 =; + my $ligne2_r2 =; + my $ligne3_r2 =; + my $ligne4_r2 =; + +#@ 1 sec + if ((!$ligne1_r1)||(!$ligne2_r1)||(!$ligne3_r1)||(!$ligne4_r1)||(!$ligne1_r2)||(!$ligne2_r2)||(!$ligne3_r2)||(!$ligne4_r2)){ + if ($VERBOSE eq "ON"){ + print "Error in file format"; + if ($ligne1_r1){print $ligne1_r1;} + if ($ligne2_r1){print $ligne2_r1;} + if ($ligne3_r1){print $ligne3_r1;} + if ($ligne4_r1){print $ligne4_r1;} + if ($ligne1_r2){print $ligne1_r2;} + if ($ligne2_r2){print $ligne2_r2;} + if ($ligne3_r2){print $ligne3_r2;} + if ($ligne4_r2){print $ligne4_r2;} + print "\n"; + } + $error1++; + } + elsif(($ligne1_r1 !~/^\@/)||($ligne1_r2 !~/^\@/)||($ligne3_r1 !~/^\+/)||($ligne3_r2 !~/^\+/)){ + if ($VERBOSE eq "ON"){ + print "Error in header : format\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error2++; + } +#@ 1 - 2 sec + else { + + my $length_seq1 = length($ligne2_r1); + my $length_qual1 =length($ligne4_r1); + my $seq1; + my $qual1; + + my $length_seq2 = length($ligne2_r2); + my $length_qual2 =length($ligne4_r2); + my $seq2; + my $qual2; + my $header1=""; + my $header2=""; + my $repheader1=""; + my $repheader2=""; + + if ($ligne1_r1 =~/^\@(.*?)\#/){ + $header1 = $1; + } + + if ($ligne3_r1 =~/^\+(.*?)\#/){ + $repheader1 = $1; + } + + if ($ligne1_r2 =~/^\@(.*?)\#/){ + $header2 = $1; + } + + if ($ligne3_r2 =~/^\+(.*?)\#/){ + $repheader2 = $1; + } +#@ 2 sec + + ### Verification de la coherence sequence /qualité @ 1 sec + if (($TYPE eq "illumina")&&((!$header1)||(!$header2)||(!$repheader1)||(!$repheader2))){ + if ($VERBOSE eq "ON"){ + print "Error in header : empty\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error3++; + } + elsif (($TYPE eq "sanger")&&((!$header1)||(!$header2))){ + if ($VERBOSE eq "ON"){ + print "Error in header refgsd : empty\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error3++; + } + elsif (($TYPE eq "illumina")&&(($header1 ne $repheader1)||($header2 ne $repheader2)||($header1 ne $header2))){ + if ($VERBOSE eq "ON"){ + print "Error in header : different\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error4++; + } + elsif (($TYPE eq "sanger")&&($header1 ne $header2)){ + if ($VERBOSE eq "ON"){ + print "Error in header : different\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error4++; + } + elsif (($length_seq1 != $length_qual1)||($length_seq2 != $length_qual2)){ + if ($VERBOSE eq "ON"){ + print "Error in seq/qual length\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error5++; + } +#@ 1 - 2 sec + else { + ### Parsing sequence & qualité + if ($ligne2_r1 =~ /^([ATGCNX]+)\s*$/i){ + $seq1 = $1; + } + if ($ligne2_r2 =~ /^([ATGCNX]+)\s*$/i){ + $seq2 = $1; + } + if ($ligne4_r1 =~ /^(.*)\s*$/i){ + $qual1 = $1; + } + if ($ligne4_r2 =~ /^(.*)\s*$/i){ + $qual2 = $1; + } +#@ 2 sec + ### Verification du parsing et de la coherence sequence /qualité (n°2) + if ((!$seq1)||(!$seq2)||(!$qual1)||(!$qual2)){ + if ($VERBOSE eq "ON"){ + print "Error parsing seq / quality \n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error6++; + } + elsif ((length($seq1) != length($qual1))||(length($seq2) != length($qual2))){ + if ($VERBOSE eq "ON"){ + print "Error in seq/qual length after parsing\n"; + print $ligne1_r1; + print $ligne2_r1; + print $ligne3_r1; + print $ligne4_r1; + print $ligne1_r2; + print $ligne2_r2; + print $ligne3_r2; + print $ligne4_r2; + print "\n"; + } + $error7++; + } +#@ <1 sec + else { + my $fastq_lines_r1=""; + my $fastq_lines_r2=""; + $fastq_lines_r1 = &grooming_and_trimming($ligne1_r1,$seq1,$qual1); + if ($fastq_lines_r1){ + $fastq_lines_r2 = &grooming_and_trimming($ligne1_r2,$seq2,$qual2); + } + if ($fastq_lines_r2){ + print OUT1 $fastq_lines_r1; + print OUT2 $fastq_lines_r2; + } + } + } + + # print OUT1 $ligne1_r1; + # print OUT1 $ligne2_r1; + # print OUT1 $ligne3_r1; + # print OUT1 $ligne4_r1; + # print OUT2 $ligne1_r2; + # print OUT2 $ligne2_r2; + # print OUT2 $ligne3_r2; + # print OUT2 $ligne4_r2; + +#@ 7 sec + } +} + + + +close (READ1); +close (READ2); +close (OUT1); +close (OUT2); + + + + +sub grooming_and_trimming{ + my $header = shift; + my $seq = shift; + my $quality = shift; + my $quality_converted=""; + + my $startnoN = 0; + my $stopnoN = length($quality)-1; + + #print "SEQ :\n$seq\n"; + + my $chercheN = $seq; + my @bad_position; + my $current_index = index($chercheN,"N"); + my $abs_index = $current_index; + while ($current_index >=0){ + push (@bad_position,$abs_index); + + if ($current_index=0){ + my %coord=%{&extract_longer_string_coordinates_from_bad_position($startnoN,$stopnoN,\@bad_position)}; + $startnoN = $coord{"start"}; + $stopnoN = $coord{"stop"}; + } + my $lengthnoN = $stopnoN - $startnoN + 1; + my $seqnoN = substr($seq,$startnoN,$lengthnoN); + #print "$seqnoN\n"; + + if ($lengthnoN >= $MIN_LENGTH){ + my $startTrim = $startnoN; + my $stopTrim = $stopnoN; + + my $quality_converted=""; + my @bad_position; + + my @q = split(//,$quality); + #print "QUALITY\n"; + #print "$quality\n"; + for (my $i=0;$i<=$stopnoN;$i++){ + my $chr = $q[$i]; + my $num = ord($q[$i]); + if ($TYPE eq "illumina"){ + $num = $num -64+33; + $quality_converted .= chr($num); + } + + if ($num <$MIN_QUALITY + 64 - 33 ){ + push(@bad_position,$i+$startnoN); + } + } + if ($quality_converted){$quality = $quality_converted;} + #print "$quality\n"; + + + + if ($#bad_position>=0){ + # for (my $i=0;$i<=$#bad_position;$i++){ + # print $bad_position[$i]."\t"; + # } + # print "\n"; + my %coord=%{&extract_longer_string_coordinates_from_bad_position($startnoN,$stopnoN,\@bad_position)}; + $startTrim = $coord{"start"}; + $stopTrim = $coord{"stop"}; + #print "$startTrim .. $stopTrim\n"; + + } + my $lengthTrim = $stopTrim - $startTrim +1; + + + my $fastq_lines=""; + + if ($lengthTrim >= $MIN_LENGTH){ + $fastq_lines .= $header; + $fastq_lines .= substr($seq,$startTrim,$lengthTrim)."\n"; + $fastq_lines .= "+\n"; + $fastq_lines .= substr($quality,$startTrim,$lengthTrim)."\n"; + return $fastq_lines; + } + else { + return ""; + } + + + + } + else { + return ""; + } + + + # my @s = split(//,$seq); + # my $sanger_quality=""; + + + + + # return $sanger_quality; +} + +sub extract_longer_string_coordinates_from_bad_position{ + my $start=shift; + my $stop =shift; + my $refbad = shift; + my @bad_position = @$refbad; + my %coord; + + my $current_start = $start; + my $current_stop = $bad_position[0]-1; + if ($current_stop < $start){$current_stop = $start;} + + + #debut -> premier N + my $current_length = $current_stop - $current_start +1; + my $test_length; + + #entre les N + for (my $i=1;$i<=$#bad_position;$i++){ + $test_length = $bad_position[$i]+1-$bad_position[$i-1]-1; + if ( $test_length > $current_length){ + $current_start = $bad_position[$i-1]+1; + $current_stop = $bad_position[$i]-1; + $current_length = $current_stop - $current_start +1; + } + } + + #dernier N -> fin + $test_length = $stop-$bad_position[$#bad_position]+1; + if ( $test_length > $current_length){ + $current_start = $bad_position[$#bad_position]+1; + if ($current_start > $stop){$current_start=$stop;} + $current_stop = $stop; + } + $coord{"start"}=$current_start; + $coord{"stop"}= $current_stop; + $coord{"lenght"}=$current_stop-$current_start+1; + + return \%coord; +} diff -r 000000000000 -r 442a7c88b886 rapsodyn/PrepareFastqLight.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/PrepareFastqLight.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,26 @@ + +Fastq preparation + + PrepareFastqLight.pl $input_read1_file $input_read2_file $output_read1_file $output_read2_file $quality_type $min_quality $min_length + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/SplitFile2x.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/SplitFile2x.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,54 @@ +#!/usr/bin/perl +use strict; +use warnings; + +my $in = $ARGV[0]; +my $NB_LINE_GROUP = $ARGV[1]; +my $NB_FILE = 2; +my $out1 = $ARGV[2]; +my $out2 = $ARGV[3]; + +if (!$NB_LINE_GROUP){ + $NB_LINE_GROUP=4; +} + +if (!$NB_FILE){ + $NB_FILE=2; +} + +my $file_nb = 1; + +my @in; +my $current_aggregate; +open(IN, $in) or die ("Can't open $in\n"); +while (my $line =){ + $current_aggregate = $line; + my $nb_line=1; + if ($NB_LINE_GROUP>1){ + while (my $add_line = ){ + $current_aggregate .= $add_line; + $nb_line++; + if ($nb_line == $NB_LINE_GROUP){ + last; + } + } + } + push (@in,$current_aggregate); +} +close (IN); + +open (OUT1,">$out1") or die ("Can't open $out1"); +open (OUT2,">$out2") or die ("Can't open $out2"); + +for (my $i=0;$i<=$#in;$i++){ + if ($i <= $#in/2){ + print OUT1 $in[$i]; + } + else { + print OUT2 $in[$i]; + } + + +} +close (OUT1); +close (OUT2); diff -r 000000000000 -r 442a7c88b886 rapsodyn/SplitFile2x.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/SplitFile2x.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,44 @@ + +Split file in 2 + + SplitFile2x.pl $input_file $line_number $output_file1 $output_file2 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/SplitFile4x.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/SplitFile4x.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,70 @@ +#!/usr/bin/perl +use strict; +use warnings; + +my $in = $ARGV[0]; +my $NB_LINE_GROUP = $ARGV[1]; +my $NB_FILE = 4; +my $out1 = $ARGV[2]; +my $out2 = $ARGV[3]; +my $out3 = $ARGV[4]; +my $out4 = $ARGV[5]; + +if (!$NB_LINE_GROUP){ + $NB_LINE_GROUP=4; +} + +if (!$NB_FILE){ + $NB_FILE=4; +} + +my $file_nb = 1; + +my @in; +my $current_aggregate; +open(IN, $in) or die ("Can't open $in\n"); +while (my $line =){ + $current_aggregate = $line; + my $nb_line=1; + if ($NB_LINE_GROUP>1){ + while (my $add_line = ){ + $current_aggregate .= $add_line; + $nb_line++; + if ($nb_line == $NB_LINE_GROUP){ + last; + } + } + } + push (@in,$current_aggregate); +} +close (IN); + +open (OUT1,">$out1") or die ("Can't open $out1"); +open (OUT2,">$out2") or die ("Can't open $out2"); +open (OUT3,">$out3") or die ("Can't open $out3"); +open (OUT4,">$out4") or die ("Can't open $out4"); + + +for (my $i=0;$i<=$#in;$i++){ + if ($i <= $#in/4){ + print OUT1 $in[$i]; + } + elsif ($i <= $#in/2){ + print OUT2 $in[$i]; + } + elsif ($i <= $#in*3/4){ + print OUT3 $in[$i]; + } + elsif ($i <= $#in){ + print OUT4 $in[$i]; + } + else { + + } + + +} +close (OUT1); +close (OUT2); +close (OUT3); +close (OUT4); diff -r 000000000000 -r 442a7c88b886 rapsodyn/SplitFile4x.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/SplitFile4x.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,62 @@ + +Split file in 4 + + SplitFile4x.pl $input_file $line_number $output_file1 $output_file2 $output_file3 $output_file4 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/extractseq.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/extractseq.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,132 @@ +#!/usr/bin/perl +#V1.10 + +use strict; +use warnings; +use Getopt::Long; + +my $input_variant_file; +my $input_assembly_file; +my $WINDOWS_LENGTH = 50; + +GetOptions ( +"input_variant_file=s" => \$input_variant_file, +"input_assembly_file=s" => \$input_assembly_file, +"window_length=i" => \$WINDOWS_LENGTH +) or die("Error in command line arguments\n"); + +open(INV, $input_variant_file) or die ("Can't open $input_variant_file\n"); +open(INA, $input_assembly_file) or die ("Can't open $input_assembly_file\n"); + +my @variant_list; + + +### Retrieving the assembly +my %genome; + +my $current_header=""; +my $current_seq=""; +while (my $ligne = ){ + if ($ligne =~ /^\>(.*?)\s*$/){ + if ($current_header){ + $genome{$current_header} = $current_seq; + } + $current_header=$1; + $current_seq = ""; + } + else { + if ($ligne=~/^([ATGCNXatgcnx]+)\s*$/){ + $current_seq .= $1; + } + else { + print STDERR "Erreur Parsing n°2\n$ligne\n"; + } + } +} +#TRAITEMENT DU DERNIER +if ($current_header){ + $genome{$current_header} = $current_seq; + undef($current_seq); +} +close (INA); + + +### Retrieving the variant +while (my $ligne=){ + if ($ligne !~ /^\s*$/){ + my %variant; + my @fields = split (/\s+/,$ligne); + $variant{"ref"}=$fields[0]; + $variant{"position"}=$fields[1]; + $variant{"baseref"}=$fields[2]; + $variant{"depth"}=$fields[3]; + $variant{"pileup"}=$fields[4]; + + + my $start = &max($variant{"position"} - $WINDOWS_LENGTH,1); + my $stop = &min ($variant{"position"} + $WINDOWS_LENGTH,length($genome{$variant{"ref"}})); + my $length = $stop-$start+1; + + #print $variant{"position"}," / ",length($genome{$variant{"ref"}})," / ","$start / $stop / $length \n"; + + $variant{"SEQ"} = substr $genome{$variant{"ref"}},$start-1,$length; + + my $pileup = $variant{"pileup"}; + $pileup =~ s/\$//g; #the read start at this position + $pileup =~ s/\^.//g; #the read end at this position + my $descriptor = $variant{"position"}."_".$variant{"depth"}."_"; + if ($pileup=~/\+([0-9]+)([ACGTNacgtn]+)/){ + $descriptor .="I".$1."_".$2; + } + elsif ($pileup=~/\-([0-9]+)([ACGTNacgtn]+)/){ + $descriptor .="D".$1."_".$2; + } + elsif ($pileup=~/([ACGTNacgtn])/){ + $descriptor.="M1"."_".$1; + } + else { + $descriptor.="?_?"; + } + $variant{"desc"}=$descriptor; + + print ">",$variant{"ref"},"_",$descriptor,"\n",$variant{"SEQ"},"\n"; + + + + #print ">",$variant{"ref"},"_",$variant{"position"},"_",$variant{"depth"},"\n",$variant{"SEQ"},"\n"; + + push(@variant_list,\%variant); + } +} +close (INV); + + + + + + + + + +#*********** +sub min{ + my $first = shift; + my $second = shift; + if ($first <= $second){ + return $first; + } + else { + return $second; + } +} + +sub max { + my $first = shift; + my $second = shift; + if ($first >= $second){ + return $first; + } + else { + return $second; + } +} \ No newline at end of file diff -r 000000000000 -r 442a7c88b886 rapsodyn/extractseq.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/extractseq.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,20 @@ + +Extract Sequence around variant position + + extractseq.pl -input_variant_file $input_variant_file -input_assembly_file $input_assembly_file -window_length $window_length > $output_file + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/fastaGroomerForMakeBlastdb.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/fastaGroomerForMakeBlastdb.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,22 @@ +#!/usr/bin/perl +my $inputfasta = $ARGV[0]; + +open(IB, $inputfasta) or die ("Can't open $inputfasta \n"); + +while (my $ligne = ){ + if ($ligne=~/\[.*?\=.*?\]/){ + $ligne =~ s/[\[\]]//g; + print $ligne; + } + elsif ($ligne =~/^\>/){ + print $ligne; + $ligne = ; + $ligne =~ s/N/a/g; + print $ligne; + } + else { + print $ligne; + } +} + +close (IB); diff -r 000000000000 -r 442a7c88b886 rapsodyn/fastaGroomerForMakeBlastdb.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/fastaGroomerForMakeBlastdb.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,20 @@ + +fasta Groomer For MakeBlastdb + + fastaGroomerForMakeBlastdb.pl $input_fasta > $output_fasta + + + + + + + + + +MakeBlastDb has several warning handled has error which is problematic on galaxyn This groomer ensure that the fasta file will not generate this warnings / error : + +- First line of the sequence is more than 40% of N => replace all the 'N' of the first line by 'a' (not elegant but low impact and efficient) + +- Header line should not have [xxx=xxx] kind of text because MakeBlastdb try to interpret it => remove the [] when this feature is detected + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/filtersam_mapped_and_unique.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/filtersam_mapped_and_unique.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,23 @@ +#!/usr/bin/perl +use strict; +use warnings; + +open(IN, $ARGV[0]) or die ("Can't open $ARGV[0]\n"); +while (my $line=){ + if ($line =~ /^\@/){ + #Header conservation + print $line; + } + else { + #Optionnal flag verification + if (($line =~ /XT\:A\:U/)&&($line =~ /X0\:i\:1/)&&($line =~ /X1\:i\:0\s/)){ + my @fields = split (/\s+/,$line); + if (($fields[1]==83)||($fields[1]==163)||($fields[1]==147)||($fields[1]==99)){ + print $line; + } + } + } +} + + +close (IN); \ No newline at end of file diff -r 000000000000 -r 442a7c88b886 rapsodyn/filtersam_mapped_and_unique.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/filtersam_mapped_and_unique.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,18 @@ + +Filter SAM file for uniq and well mapped pair-end reads + + filtersam_mapped_and_unique.pl $input_sam_file > $output_file + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/listfiltering.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/listfiltering.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,61 @@ +#!/usr/bin/perl +use strict; +use Getopt::Long; + +my $inputfile; +my $headerfile; +my $nb_col=1; +my %header; + +if ($#ARGV<0){ + print "\n"; + print "perl 021_ListFiltering.pl -input_file -header_file -nb_col [1]\n"; + exit(0); +} + +GetOptions ( +"input_file=s" => \$inputfile, +"header_file=s" => \$headerfile, +"nb_col=i" => \$nb_col +) or die("Error in command line arguments\n"); + +open(HF, $headerfile) or die("Can't open $headerfile\n"); +while (my $line=){ + chomp($line); + my @fields = split(/\s+/,$line); + my $ref=""; + my $compt=0; + while ($compt<$nb_col){ + if ($ref){$ref.="\t";} + $ref.=$fields[$compt]; + $compt++; + } + # my $ref = "$fields[0]\t$fields[1]"; + $header{$ref}=$line; +} +close (HF); + + +open(IF, $inputfile) or die("Can't open $inputfile\n"); +while (my $line=){ + my @fields = split(/\s+/,$line); + my $ref=""; + my $compt=0; + while ($compt<$nb_col){ + if ($ref){$ref.="\t";} + $ref.=$fields[$compt]; + $compt++; + } + # my $ref = "$fields[0]\t$fields[1]"; + + if ($header{$ref}){ + # print $line; + # print $header{$ref},"\n"; + } + else { + print $line; + } + +} +close(IF); + diff -r 000000000000 -r 442a7c88b886 rapsodyn/listfiltering.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/listfiltering.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,20 @@ + +Compare listA and listB first X column and remove from listA the elements present in listB + + listfiltering.pl -input_file $input_listA -header_file $input_listB -nb_col $nb_col > $output_file + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/mpileupfilterandstat.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/mpileupfilterandstat.pl Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,482 @@ +#!/usr/bin/perl +use strict; +use Getopt::Long; + +# +# Filter a pileup file on forward/reverse presence and %read having the variant +# The error code +# 1 : multiple variant type detected insertion/deletion/mutation +# 1i : inconsistency in insertion +# 1d : inconsistency in deletion +# 1m : inconsistency in mutation +# 2 : insufficient depth +# 3 : insufficient variant frequency +# 4 : variant position not covered by forward and reverse reads +# 5 : variant with other variant in neighbourhood +# 6 : too much depth +# 8 : parsing error (couldn't parse the mpileup line correctly) +# 9 : parsing error (couldn't parse the readbase string correctly) + + +my $inputfile; +my $logfile; +my $MIN_DISTANCE=0; +my $MIN_VARIANTFREQUENCY=0; +my $MIN_FORWARDREVERSE=0; +my $MIN_DEPTH=0; +my $MAX_DEPTH=500; +my $VERBOSE=0; +my $ONLY_UNFILTERED_VARIANT="OFF"; +my $DO_STAT="NO"; + + +my $STAT_MIN_DEPTH_MIN = 2; +my $STAT_MIN_DEPTH_MAX = 10; +my $STAT_MIN_DEPTH_STEP = 2; +my $STAT_MAX_DEPTH_MIN = 100; +my $STAT_MAX_DEPTH_MAX = 200; +my $STAT_MAX_DEPTH_STEP = 100; +my $STAT_FREQ_MIN = 0.8; +my $STAT_FREQ_MAX = 1; +my $STAT_FREQ_STEP = 0.1; +my $STAT_DIST_MIN = 0; +my $STAT_DIST_MAX = 50; +my $STAT_DIST_STEP = 50; + +GetOptions ( +"input_file=s" => \$inputfile, +"log_file=s" => \$logfile, +"min_depth=i" => \$MIN_DEPTH, +"max_depth=i" => \$MAX_DEPTH, +"min_frequency=f" => \$MIN_VARIANTFREQUENCY, +"min_distance=i" => \$MIN_DISTANCE, +"min_forward_and_reverse=i" => \$MIN_FORWARDREVERSE, +"variant_only=s" => \$ONLY_UNFILTERED_VARIANT, +"v=i" => \$VERBOSE, +"do_stat=s" => \$DO_STAT, +"stat_min_depth_min=i" => \$STAT_MIN_DEPTH_MIN, +"stat_min_depth_max=i" => \$STAT_MIN_DEPTH_MAX, +"stat_min_depth_step=i" => \$STAT_MIN_DEPTH_STEP, +"stat_max_depth_min=i" => \$STAT_MAX_DEPTH_MIN, +"stat_max_depth_max=i" => \$STAT_MAX_DEPTH_MAX, +"stat_max_depth_step=i" => \$STAT_MAX_DEPTH_STEP, +"stat_freq_min=f" => \$STAT_FREQ_MIN, +"stat_freq_max=f" => \$STAT_FREQ_MAX, +"stat_freq_step=f" => \$STAT_FREQ_STEP, +"stat_dist_min=i" => \$STAT_DIST_MIN, +"stat_dist_max=i" => \$STAT_DIST_MAX, +"stat_dist_step=i" => \$STAT_DIST_STEP +) or die("Error in command line arguments\n"); + +open(IF, $inputfile) or die("Can't open $inputfile\n"); + +my @tbl_line; +my %USR_PARAM; +$USR_PARAM{"min_depth"} = $MIN_DEPTH; +$USR_PARAM{"max_depth"} = $MAX_DEPTH; +$USR_PARAM{"min_freq"} = $MIN_VARIANTFREQUENCY; +$USR_PARAM{"min_dist"} = $MIN_DISTANCE; +$USR_PARAM{"min_fr"} = $MIN_FORWARDREVERSE; + + + +#Extraction des variants +my $nb_line=0; +while (my $line=){ + $nb_line++; + if (($nb_line % 1000000 == 0)&&($VERBOSE==1)){ + print "$nb_line\n"; + } + my $error_code=0; + if ($line=~/(.*?)\s+(\d+)\s+([ATGCN])\s+(\d+)\s+(.*?)\s+(.*?)$/){ + my $current_chromosome = $1; + my $current_position = $2; + my $current_refbase = $3; + my $current_coverage = $4; + my $current_readbase_string = $5; + my $current_quality_string = $6; + + #Suppression of mPileUp special character + $current_readbase_string =~ s/\$//g; #the read start at this position + $current_readbase_string =~ s/\^.//g; #the read end at this position followed by quality char + + if ($current_readbase_string =~ /[ATGCNatgcn\d]/){ + my %variant; + $variant{"line"} = $line; + $variant{"chr"} = $current_chromosome; + $variant{"pos"} = $current_position; + $variant{"refbase"} = $current_refbase; + $variant{"coverage"} = $current_coverage; + $variant{"readbase"} = $current_readbase_string; + $variant{"quality"} = $current_quality_string; + push(@tbl_line,\%variant); + + if ($ONLY_UNFILTERED_VARIANT eq "ON"){ + print $line; + } + + } + else { + #Position with no variant + } + + } + else { + #Error Parsing + print STDERR "$line #8"; + } +} +close(IF); + +if ($ONLY_UNFILTERED_VARIANT eq "ON"){ + exit(0); +} + +####Checking the distance between variant and other filter + + +my @error; +for (my $i=0;$i<=$#tbl_line;$i++){ + # print "ligne : $tbl_line[$i]\n"; + my $before=""; + my $after=""; + my %line = %{$tbl_line[$i]}; + + if ($tbl_line[$i-1]){ + $before = $tbl_line[$i-1]; + } + if ($tbl_line[$i+1]){ + $after = $tbl_line[$i+1]; + } + my $error_code = check_error($tbl_line[$i],$before,$after,\%USR_PARAM); + if ($error_code == 0){ + print $line{"line"}; + } + else { + push(@error,$error_code,"\t",$line{"line"}); + } +} + +### LOG +open(LF,">$logfile") or die ("Can't open $logfile\n"); + +if ($DO_STAT eq "YES"){ + for (my $idx_min_depth=$STAT_MIN_DEPTH_MIN;$idx_min_depth<=$STAT_MIN_DEPTH_MAX;$idx_min_depth = $idx_min_depth + $STAT_MIN_DEPTH_STEP ){ + for (my $idx_max_depth=$STAT_MAX_DEPTH_MIN;$idx_max_depth<=$STAT_MAX_DEPTH_MAX;$idx_max_depth = $idx_max_depth + $STAT_MAX_DEPTH_STEP ){ + for (my $idx_freq = $STAT_FREQ_MIN;$idx_freq<=$STAT_FREQ_MAX;$idx_freq= $idx_freq+$STAT_FREQ_STEP){ + for (my $idx_dist=$STAT_DIST_MIN;$idx_dist<=$STAT_DIST_MAX;$idx_dist = $idx_dist + $STAT_DIST_STEP){ + for (my $idx_fr=0;$idx_fr<=1;$idx_fr++){ + my %stat_param; + $stat_param{"min_depth"}=$idx_min_depth; + $stat_param{"max_depth"}=$idx_max_depth; + $stat_param{"min_freq"}=$idx_freq; + $stat_param{"min_fr"}=$idx_fr; + $stat_param{"min_dist"}=$idx_dist; + + print LF "#SNP = ",&test_check(\@tbl_line,\%stat_param),"\tdepth (min/max) = ",$stat_param{"min_depth"}," / ",$stat_param{"max_depth"},"\tmin_dist=",$stat_param{"min_dist"},"\tmin_freq=",$stat_param{"min_freq"},"\tmin_forwardreverse = ",$stat_param{"min_fr"},"\n"; + } + } + } + print "\n"; + } + } +} + + +for (my $i=0;$i<=$#error;$i++){ + print LF $error[$i]; +} +close (LF); + + + + +sub test_check{ + my $ref_tbl_line = shift; + my $ref_param = shift; + my @tbl_line = @$ref_tbl_line; + my %param = %$ref_param; + my $nb=0; + + for (my $i=0;$i<=$#tbl_line;$i++){ + my $before=""; + my $after=""; + my %line = %{$tbl_line[$i]}; + + if ($tbl_line[$i-1]){ + $before = $tbl_line[$i-1]; + } + if ($tbl_line[$i+1]){ + $after = $tbl_line[$i+1]; + } + my $error_code = check_error($tbl_line[$i],$before,$after,\%param); + if ($error_code == 0){ + $nb++; + } + } + + return $nb; +} + +sub check_error{ + my $refline = shift; + my %line = %$refline; + my $refbefore = shift; + my $refafter = shift; + my $refparam = shift; + my %param = %$refparam; + + + my $current_chromosome = $line{"chr"}; + my $current_position = $line{"pos"}; + my $current_refbase = $line{"refbase"}; + my $current_coverage = $line{"coverage"}; + my $current_readbase_string = $line{"readbase"}; + + + my $min_depth = $param{"min_depth"}; + my $max_depth = $param{"max_depth"}; + my $min_variant_frequency = $param{"min_freq"}; + my $min_forward_reverse = $param{"min_fr"}; + my $min_dist = $param{"min_dist"}; + + #Verification of neightbourhood + if ($refbefore){ + my %compareline = %$refbefore; + my $compare_chromosome = $compareline{"chr"}; + my $compare_position = $compareline{"pos"}; + my $compare_refbase = $compareline{"refbase"}; + my $compare_coverage = $compareline{"coverage"}; + my $compare_readbase_string = $compareline{"readbase"}; + + if (($current_chromosome eq $compare_chromosome )&&($compare_position + $min_dist >= $current_position)){ + return 5; + } + } + + if ($refafter){ + my %compareline = %$refafter; + my $compare_chromosome = $compareline{"chr"}; + my $compare_position = $compareline{"pos"}; + my $compare_refbase = $compareline{"refbase"}; + my $compare_coverage = $compareline{"coverage"}; + my $compare_readbase_string = $compareline{"readbase"}; + + if (($current_chromosome eq $compare_chromosome )&&($current_position + $min_dist >= $compare_position)){ + return 5; + } + } + + + + + #Extraction of insertions + + ################################################################## + # my @IN = $current_readbase_string =~ m/\+[0-9]+[ACGTNacgtn]+/g; + # my @DEL = $current_readbase_string =~ m/\-[0-9]+[ACGTNacgtn]+/g; + # print "IN : @IN\n"; + # print "DEL :@DEL\n"; + #$current_readbase_string=~s/[\+\-][0-9]+[ACGTNacgtn]+//g; + ################################################################## + #!!! marche pas : exemple .+1Ct. correspond a . / +1C / t /. mais le match de l'expression vire +1Ct + ################################################################## + + # => parcours de boucle + my @readbase = split(//,$current_readbase_string); + my $cleaned_readbase_string=""; + my @IN; + my @DEL; + my $current_IN=""; + my $current_DEL=""; + my $current_size=0; + + for (my $i=0;$i<=$#readbase;$i++){ + if ($readbase[$i] eq "+"){ + #Ouverture de IN + $current_IN="+"; + + #Recuperation de la taille + my $sub = substr $current_readbase_string,$i; + if ($sub=~/^\+(\d+)/){ + $current_size = $1; + } + my $remaining_size = $current_size; + while (($remaining_size>0)&&($i<=$#readbase)){ + $i++; + $current_IN.=$readbase[$i]; + if ($readbase[$i]=~ /[ATGCNatgcn]/){ + $remaining_size--; + } + } + push(@IN,$current_IN); + } + elsif ($readbase[$i] eq "-"){ + #Ouverture de DEL + $current_DEL="-"; + + #Recuperation de la taille + my $sub = substr $current_readbase_string,$i; + if ($sub=~/^\-(\d+)/){ + $current_size = $1; + } + my $remaining_size = $current_size; + while (($remaining_size>0)&&($i<=$#readbase)){ + $i++; + $current_DEL.=$readbase[$i]; + if ($readbase[$i]=~ /[ATGCNatgcn]/){ + $remaining_size--; + } + } + push(@DEL,$current_DEL); + + } + else { + #Ajout a la string + $cleaned_readbase_string .= $readbase[$i]; + } + } + + + # print "IN : @IN\n"; + # print "DEL :@DEL\n"; + # print "$cleaned_readbase_string\n"; + + my @current_readbase_array = split(//,$cleaned_readbase_string); + + #Filtering : error detection + + if ($#current_readbase_array+1 != $current_coverage){ + return 9; + #parsing error (couldn't parse the readbase string correctly) + } + elsif ($current_coverage<$min_depth){ + return 2; + # 2 : insufficient depth + } + elsif ($current_coverage>$max_depth){ + return 6; + # 6 : too much depth + } + else { + if ($#IN>=0){ + if (($cleaned_readbase_string=~/[ACGTNacgtn]/)){ + return 1; + # 1 : variant type overload (multiple variant type detected insertion/deletion/mutation) + } + else { + ########## TEST de coherence des insertions ################ + # for (my $i=0;$i<=$#IN;$i++){ + # if (uc($IN[0]) ne uc($IN[$i])){ + # print uc($IN[0]),"\n"; + # print uc($IN[$i]),"\n"; + # return "1i"; + # } + # } + ########################################################### + + if($#IN+1 < $current_coverage*$min_variant_frequency ){ + return 3; + # 3 : insufficient variant frequency + } + } + } + elsif ($#DEL>=0){ + if (($cleaned_readbase_string=~/[ACGTNacgtn]/)){ + return 1; + # 1 : variant type overload (multiple variant type detected insertion/deletion/mutation) + } + else { + ########## TEST de coherence des deletions ################ + # for (my $i=0;$i<=$#DEL;$i++){ + # if (uc($DEL[0]) ne uc($DEL[$i])){ + # print uc($DEL[0]),"\n"; + # print uc($DEL[$i]),"\n"; + # return "1d"; + # } + # } + ########################################################### + + if($#DEL+1 < $current_coverage*$min_variant_frequency){ + return 3; + # 3 : insufficient variant frequency + } + } + } + else { + my $nbA=0; + $nbA++ while ($current_readbase_string =~ m/A/g); + my $nbC=0; + $nbC++ while ($current_readbase_string =~ m/C/g); + my $nbT=0; + $nbT++ while ($current_readbase_string =~ m/T/g); + my $nbG=0; + $nbG++ while ($current_readbase_string =~ m/G/g); + my $nbN=0; + $nbN++ while ($current_readbase_string =~ m/N/g); + my $nba=0; + $nba++ while ($current_readbase_string =~ m/a/g); + my $nbc=0; + $nbc++ while ($current_readbase_string =~ m/c/g); + my $nbt=0; + $nbt++ while ($current_readbase_string =~ m/t/g); + my $nbg=0; + $nbg++ while ($current_readbase_string =~ m/g/g); + my $nbn=0; + $nbn++ while ($current_readbase_string =~ m/n/g); + + if (($nbA+$nba>0)&&($nbT+$nbt+$nbG+$nbg+$nbC+$nbc+$nbN+$nbn>0)){ + return "1m"; + } + if (($nbT+$nbt>0)&&($nbA+$nba+$nbG+$nbg+$nbC+$nbc+$nbN+$nbn>0)){ + return "1m"; + } + if (($nbG+$nbg>0)&&($nbA+$nba+$nbT+$nbt+$nbC+$nbc+$nbN+$nbn>0)){ + return "1m"; + } + if (($nbC+$nbc>0)&&($nbA+$nba+$nbT+$nbt+$nbG+$nbg+$nbN+$nbn>0)){ + return "1m"; + } + if (($nbN+$nbn>0)&&($nbA+$nba+$nbT+$nbt+$nbG+$nbg+$nbC+$nbc>0)){ + return "1m"; + } + + if ($nbA+$nba >= $current_coverage*$min_variant_frequency){ + if (($nbA<$min_forward_reverse)||($nba<$min_forward_reverse)){ + return 4; + # 4 : variant position not covered by forward and reverse reads + } + } + elsif ($nbT+$nbt >= $current_coverage*$min_variant_frequency){ + if (($nbT<$min_forward_reverse)||($nbt<$min_forward_reverse)){ + return 4; + # 4 : variant position not covered by forward and reverse reads + } + } + elsif ($nbG+$nbg >= $current_coverage*$min_variant_frequency){ + if (($nbG<$min_forward_reverse)||($nbg<$min_forward_reverse)){ + return 4; + # 4 : variant position not covered by forward and reverse reads + } + } + elsif ($nbC+$nbc >= $current_coverage*$min_variant_frequency){ + if (($nbC<$min_forward_reverse)||($nbc<$min_forward_reverse)){ + return 4; + # 4 : variant position not covered by forward and reverse reads + } + } + elsif ($nbN+$nbn >= $current_coverage*$min_variant_frequency){ + if (($nbN<$min_forward_reverse)||($nbn<$min_forward_reverse)){ + return 4; + # 4 : variant position not covered by forward and reverse reads + } + } + else { + return 3; + # 3 : insufficient variant frequency + } + } + } + + return 0; +} diff -r 000000000000 -r 442a7c88b886 rapsodyn/mpileupfilterandstat.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/mpileupfilterandstat.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,59 @@ + +Filter mpileup file entry + + #if $stat.do_stat=="YES" + mpileupfilterandstat.pl -input_file $input_file -log_file $log_file -min_depth $min_depth -min_frequency $min_frequency -min_distance $min_distance -min_forward_and_reverse $min_forward_and_reverse -max_depth $max_depth -do_stat $stat.do_stat +-stat_min_depth_min $stat.stat_min_depth_min -stat_min_depth_max $stat.stat_min_depth_max -stat_min_depth_step $stat.stat_min_depth_step +-stat_max_depth_min $stat.stat_max_depth_min -stat_max_depth_max $stat.stat_max_depth_max -stat_max_depth_step $stat.stat_max_depth_step +-stat_freq_min $stat.stat_freq_min -stat_freq_max $stat.stat_freq_max -stat_freq_step $stat.stat_freq_step +-stat_dist_min $stat.stat_dist_min -stat_dist_max $stat.stat_dist_max -stat_dist_step $stat.stat_dist_step > $output_file + #else + mpileupfilterandstat.pl -input_file $input_file -log_file $log_file -min_depth $min_depth -min_frequency $min_frequency -min_distance $min_distance -min_forward_and_reverse $min_forward_and_reverse -max_depth $max_depth -do_stat $stat.do_stat > $output_file + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 442a7c88b886 rapsodyn/repository_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rapsodyn/repository_dependencies.xml Wed Sep 10 09:18:15 2014 -0400 @@ -0,0 +1,8 @@ + + + + + + + +