Mercurial > repos > rnateam > graphclust_postprocessing_no_align
changeset 0:0a48b2db75e7 draft default tip
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/GraphClust/CollectResultsNoAlign commit 2a6fd70c1bcec36ffdf0bba2ec82489b39cfc84e
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/evaluation.py Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,105 @@ +#!/usr/bin/env python +import glob +from os import system +import re +from sklearn import metrics +from shutil import make_archive +import sys +import fnmatch, os + +def sh(script): + system("bash -c '%s'" % script) + +fasta_dir = sys.argv[1] +results_dir = sys.argv[2] +dataNames = os.path.join(fasta_dir,"data.names") + +listOfClusters = [] +listOfHeaders = [] +headersNames = set() +idsNames = set() + + +names = os.listdir(results_dir) +cluster_seqs_stats_files = fnmatch.filter(names, '*.cluster.all') +with open(dataNames, "r") as names: + for line2 in names: + splits2 = line2.split() + fullHeader = '' + if len(splits2) >= 6: + fullHeader = splits2[5] + headersNames.add(fullHeader) + fullID = splits2[3] + idsNames.add(fullID) + +blackList = [] +numberOfClusters = 0 +for singleFile in sorted(cluster_seqs_stats_files): + singleFile = os.path.join(results_dir,singleFile) + numberOfClusters += 1 + with open(singleFile, "r") as f: + for line in f: + splits = line.split() + header = '' + idd = '' + if len(splits) >= 11: + header = splits[10] + idd = splits[8] + clustNum = splits[2] + listOfHeaders.append(header) + listOfClusters.append(clustNum) + if idd in idsNames: #header in headersNames: + blackList.append(idd) + +numberOfClusters += 1 # 1 cluster for all unassigned seqs +ignoreBlackList = False +with open(dataNames, "r") as names: + for line in names: + splits = line.split() + fullUniqeId = splits[3] + fullHeader = '' + fullID = '' + if len(splits) >= 6: + fullHeader = line.split()[5] + fullID = line.split()[3] + if ignoreBlackList or ( fullID not in blackList #fullHeader not in blackList + or len(fullHeader) == 0): + listOfHeaders.append(fullHeader) + listOfClusters.append(str(numberOfClusters)) + numberOfClusters += 1 # separate cluster for all unassigned seqs + # else: + # print ("Skip header", fullHeader) + +toWrite = "" +for i in range(len(listOfClusters)): + toWrite += "%s\t%s\n" % (listOfHeaders[i], listOfClusters[i]) + +with open(os.path.join(results_dir,"fullTab.tabular"), "w") as full: + full.write(toWrite) + + +pattern = re.compile("^RF.*$") + +if len(listOfHeaders) > 1: # and pattern.match(str(listOfHeaders[0])): + + completeness_score = metrics.completeness_score(listOfHeaders, listOfClusters) + homogeneity_score = metrics.homogeneity_score(listOfHeaders, listOfClusters) + adjusted_rand_score = metrics.adjusted_rand_score(listOfHeaders, listOfClusters) + adjusted_mutual_info_score = metrics.adjusted_mutual_info_score(listOfHeaders, listOfClusters) + v_measure_score = metrics.v_measure_score(listOfHeaders, listOfClusters) + + toWrite = "completeness_score : {}\n".format(completeness_score) + toWrite += "homogeneity_score : {}\n".format(homogeneity_score) + toWrite += "adjusted_rand_score : {}\n".format(adjusted_rand_score) + toWrite += "adjusted_mutual_info_score : {}\n".format(adjusted_mutual_info_score) + toWrite += "v_measure_score : {}\n".format(v_measure_score) + + +else: + toWrite = "completeness_score : NA \nhomogeneity_score : NA \nadjusted_rand_score : NA \nadjusted_mutual_info_score : NA \nv_measure_score : NA" + +with open(os.path.join(results_dir,"evaluation.txt"), "w") as fOut: + fOut.write(toWrite) + + +make_archive('RESULTS', 'zip', root_dir=results_dir)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/glob_report_no_align.xml Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,171 @@ +<tool id="graphclust_glob_report_no_align" name="Graphclust glob_report collect clusters" version="0.5" > + <requirements> + <requirement type="package" version="0.6.0">graphclust-wrappers</requirement> + <requirement type="package" version='0.5'>perl-array-utils</requirement> + <requirement type="package" version='0.18.1'>scikit-learn</requirement> + <requirement type="package" version='1.8.10'>locarna</requirement> + <requirement type="package" version='2.1'>rnaz</requirement> + <requirement type="package" version="1.1.2">infernal</requirement> + <requirement type="package" version='2.2.10'>viennarna</requirement> + <requirement type="package" version='1.3.30'>graphicsmagick</requirement> + <requirement type="package" version='0.6.1'>rscape</requirement> + <requirement type="package" version='6.0'>unzip</requirement> + </requirements> + <command detect_errors="exit_code"> + <![CDATA[ + unzip $FASTA &> /dev/null && + mkdir ./CMSEARCH && + mkdir ./MODEL && + #import re + #for $cms_res in $cmsearch_results: + #set $safename_cm = re.sub('[^\w\-_\.]', '_', $cms_res.element_identifier) + ln -f -s '$cms_res' ./CMSEARCH/$safename_cm && + #end for + #for $mods in $model_tree_files: + #set $safename_tr = re.sub('[^\w\-_\.]', '_', $mods.element_identifier) + ln -f -s '$mods' ./MODEL/$safename_tr && + #end for + + 'glob_res.pl' + $merge_cluster_ol + $merge_overlap + $min_cluster_size + $cm_min_bitscore + $cm_max_eval + 1 ## cm_bitscore_sig + $partition_type '' + $cut_type + 0 ## zero means do not align + #if $iteration_num.iteration_num_selector: + $iteration_num.CI + $final_partition_soft + $final_partition_used_cmsearch + '$combined_cm' + + #end if + + && + python '$__tool_directory__/evaluation.py' FASTA/ RESULTS/ + + #if $cdhit: + && + python '$__tool_directory__/addCdhitseqs.py' '$cdhit' + #end if +]]> + </command> + <inputs> + <param type="data" name="FASTA" format="zip" help="FASTA.zip from pre-processing step"/> + <param type="data" name="cmsearch_results" format="tabular" multiple="True" + help="Tabular cmsearch results of the candidate clusters from the cmsearch step"/> + <param type="data" name="model_tree_files" format="txt" multiple="True" label="model-tree-stk" + help="model.tree.stk files from pgma_graphclust candidate clustering step"/> + <param name="partition_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Hard partition" + help="Whether to do hard partitioning (no overlap) or soft mode(cluster elements may overlap) "/> + <param name="cut_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Use CM score for cutoff" help="otherwise use E-value"/> + <param name="cm_min_bitscore" type="integer" value="20" size="5" label="cm_min_bitscore" help=""/> + <param name="cm_max_eval" type="float" value="0.001" size="5" label="cm_max_E-val" help=""/> + <param type="data" name="cdhit" format="txt" optional="true" label="CD-HIT output" + help="Optional CD-HIT pre-clustering output to be combined into the final clustering output"/> + <param name="merge_cluster_ol" type="float" value="0.66" size="5" label="merge_cluster_ovelap" + help="Overlapping ratio criteria to merge overlapping clusters or keep separate clusters (soft partitioning)"/> + <param name="merge_overlap" type="float" value="0.51" size="5" label="merge_fraction_overlap" + help="Overlapping ratio criteria to merge overlapping sequence fractions from same input sequence"/> + <param name="min_cluster_size" type="integer" value="3" size="5" label="minimum cluster size" + help="Minimum number of elements that can form a cluster. Higher values discard small clusters and may produce larger merged clusters"/> + <!-- <param name="cm_bitscore_sig" type="integer" value="1" size="5" label="cm_bitscore_sig" help=""/> --> + + <conditional name="iteration_num"> + <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/> + <when value="true"> + <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/> + <param type="data" name="final_partition_soft" format="txt" /> + <param type="data" name="final_partition_used_cmsearch" format="txt" /> + <param type="data" name="combined_cm" format="txt" /> + </when> + <when value="false" ></when> + </conditional> + + </inputs> + <outputs> + <data name="final_stats" format="txt" from_work_dir="RESULTS/cluster.final.stats" label="cluster.final.stats" /> + <data name="tableForEval" format="tabular" from_work_dir="RESULTS/fullTab.tabular" label="tableForEval" /> + <data name="final_soft" format="txt" from_work_dir="RESULTS/partitions/final_partition.soft" label="soft_part" /> + <data name="final_used_cmsearch" format="txt" from_work_dir="RESULTS/partitions/final_partition.used_cmsearch" label="final_partition_used_cmsearch" /> + <data name="evaluation" format="txt" from_work_dir="RESULTS/evaluation.txt" label="evaluation_of_clusters" /> + <data name="combined_cm_out" format="txt" from_work_dir="combined_cm_out" label="combined_cmsearch_output" /> + <collection name="clusters" type="list" label="CLUSTERS-cmsearch"> + <discover_datasets format="txt" pattern="(?P<name>^.*\.all$)" directory="RESULTS" /> + </collection> + <collection name="allFastaSorted" type="list" label="cluster-sequences-sorted"> + <discover_datasets format="fasta" pattern="(?P<name>^.*\.sorted.fa$)" directory="RESULTS" /> + </collection> + + <collection name="partitions" type="list" label="Partitions"> + <discover_datasets pattern="(?P<name>^.*$)" directory="RESULTS/partitions" /> + </collection> + <data name="RESULTS_zip" format="zip" from_work_dir="RESULTS.zip" label="RESULTS.zip" /> + </outputs> + <tests> + <test> + <param name="FASTA" value="FASTA.zip" ftype="searchgui_archive"/> + <param name="cmsearch_results" value="1.1.tree,1.2.tree"/> + <param name="model_tree_files" value="1.1.model.tree.fa,1.2.model.tree.fa"/> + <param name="partition_type" value="0"/> + <param name="cut_type" value="0"/> + <conditional name="iteration_num"> + <param name="iteration_num_selector" value="false"/> + </conditional> + <param name="merge_cluster_ol" value="0.66"/> + <param name="merge_overlap" value="0.51"/> + <param name="min_cluster_size" value="3"/> + <param name="cm_min_bitscore" value="20"/> + <param name="cm_max_eval" value="0.001"/> + <!-- <param name="cm_bitscore_sig" value="0"/> --> + <output name="final_stats" file="RESULTS/cluster.final.stats" /> + <output name="combined_cm_out" file="combined_cm_out"/> + <output name="evaluation" file="evaluation1.txt"/> + <output_collection name="clusters" type="list"> + <element name="1.cluster.all" file="RESULTS/1.cluster.all" compare="contains"/> + <element name="2.cluster.all" file="RESULTS/2.cluster.all" compare="contains"/> + + </output_collection> + <output_collection name="partitions"> + <element name="final_overlap.map" file="RESULTS/partitions/final_overlap.map" compare="contains"> + <assert_contents> + <has_text text="1.1 1.1 " /> + <has_text text="1.2 1.2" /> + </assert_contents> + </element> + <element name="final_overlap.matrix" file="RESULTS/partitions/final_overlap.matrix" compare="contains"> + <assert_contents> + <has_text text="MODEL CLASS 0 0" /> + <!--has_text text="1.2" /> + <has_text text="1.1" /--> + </assert_contents> + </element> + <element name="final_partition.hard.best" file="RESULTS/partitions/final_partition.hard.best" /> + <element name="final_partition.hard.merged" file="RESULTS/partitions/final_partition.hard.merged" /> + <element name="final_partition.soft" file="RESULTS/partitions/final_partition.soft" /> + <element name="final_partition.used_cmsearch" file="RESULTS/partitions/final_partition.used_cmsearch" compare="contains"/> + </output_collection> + + <output name="RESULTS_zip" file="RESULTS.zip" ftype="zip" compare="sim_size" delta="20000"/> + + </test> + </tests> + <help> + <![CDATA[ + +**What it does** + +Post-processing. Redundant clusters are merged and instances that belong to multiple clusters +are assigned unambiguously. For every pair of clusters, the relative overlap (i.e. the fraction of +instances that occur in both clusters) is computed and clusters are merged if the overlap exceeds 50%. +Cluster members are finally ranked by their CM bitscore. + + ]]> + </help> + <citations> + <citation type="doi">10.5281/zenodo.597695</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/1.1.model.tree.fa Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,40 @@ +>9 SEQ7#1#83#+ ORIGID RF00005_rep.12_AC108081.2/59868-59786_7 ORIGHEAD RF00005 +GUCAGGAUGGCCGAGCGGUCUAAGGCGCUGCGUUCAGGUCGCAGUCUCCCCUGGAGGCGUGGGUUCGAAUCCCACUUCUGACA +>11 SEQ9#1#73#+ ORIGID RF00005_rep.14_AL021808.2/65570-65498_9 ORIGHEAD RF00005 +GCUUCUGUAGUGUAGUGGUUAUCACGUUCGCCUCACACGCGAAAGGUCCCCGGUUCGAAACCGGGCAGAAGCA +>12 SEQ10#1#73#+ ORIGID RF00005_rep.15_AC008443.10/42590-42518_10 ORIGHEAD RF00005 +GCCCGGCUAGCUCAGUCGGUAGAGCAUGAGACUCUUAAUCUCAGGGUCGUGGGUUCGAGCCCCACGUUGGGCG +>15 SEQ13#1#82#+ ORIGID RF00005_rep.18_AL021918.1/81116-81197_13 ORIGHEAD RF00005 +GUAGUCGUGGCCGAGUGGUUAAGGCGAUGGACUAGAAAUCCAUUGGGGUUUCCCCACGCAGGUUCGAAUCCUGCCGACUACG +>18 SEQ16#1#72#+ ORIGID RF00005_rep.20_AL671879.2/100356-100285_16 ORIGHEAD RF00005 +GGGGAUGUAGCUCAGUGGUAGAGCGCAUGCUUCGCAUGUAUGAGGCCCCGGGUUCGAUCCCCGGCAUCUCCA +>19 SEQ17#1#71#+ ORIGID RF00005_rep.21_AL355149.13/15278-15208_17 ORIGHEAD RF00005 +GCAUUGGUGGUUCAGUGGUAGAAUUCUCGCCUCCCACGCGGGAGACCCGGGUUCAAUUCCCGGCCAAUGCA +>20 SEQ18#1#72#+ ORIGID RF00005_rep.22_AL590385.23/26487-26416_18 ORIGHEAD RF00005 +GCGUUGGUGGUAUAGUGGUGAGCAUAGCUGCCUUCCAAGCAGUUGACCCGGGUUCGAUUCCCGGCCAACGCA +>25 SEQ23#1#74#+ ORIGID RF00005_rep.27_AL352978.6/119697-119770_23 ORIGHEAD RF00005 +GGCCGGUUAGCUCAGUUGGUUAGAGCGUGGUGCUAAUAACGCCAAGGUCGCGGGUUCGAUCCCCGUACGGGCCA +>30 SEQ28#1#71#+ ORIGID RF00005_rep.31_AC092686.3/29631-29561_28 ORIGHEAD RF00005 +GCAUUGGUGGUUCAGUGGUAGAAUUCUCGCCUGCCACGCGGGAGGCCCGGGUUCGAUUCCCGGCCAAUGCA +>32 SEQ30#1#72#+ ORIGID RF00005_rep.33_AC018638.5/4694-4623_30 ORIGHEAD RF00005 +GGCUCGUUGGUCUAGGGGUAUGAUUCUCGCUUAGGGUGCGAGAGGUCCCGGGUUCAAAUCCCGGACGAGCCC +>33 SEQ31#1#73#+ ORIGID RF00005_rep.34_AC008443.10/43006-42934_31 ORIGHEAD RF00005 +GUUUCCGUAGUGUAGUGGUUAUCACGUUCGCCUCACACGCGAAAGGUCCCCGGUUCGAAACCGGGCGGAAACA +>34 SEQ32#1#73#+ ORIGID RF00005_rep.35_AC005783.1/27398-27326_32 ORIGHEAD RF00005 +GUUUCCGUAGUGUAGCGGUUAUCACAUUCGCCUCACACGCGAAAGGUCCCCGGUUCGAUCCCGGGCGGAAACA +>35 SEQ33#1#72#+ ORIGID RF00005_rep.36_AC007298.17/145366-145295_33 ORIGHEAD RF00005 +UCCUCGUUAGUAUAGUGGUGAGUAUCCCCGCCUGUCACGCGGGAGACCGGGGUUCGAUUCCCCGACGGGGAG +>37 SEQ35#1#72#+ ORIGID RF00005_rep.38_J00309.1/356-427_35 ORIGHEAD RF00005 +UCCCUGGUGGUCUAGUGGCUAGGAUUCGGCGCUUUCACCGCCGCGCCCCGGGUUCGAUUCCCGGCCAGGAAU +>39 SEQ37#1#82#+ ORIGID RF00005_rep.3_Z54587.1/126-45_37 ORIGHEAD RF00005 +GGUAGCGUGGCCGAGCGGUCUAAGGCGCUGGAUUUAGGCUCCAGUCUCUUCGGAGGCGUGGGUUCGAAUCCCACCGCUGCCA +>48 SEQ46#1#72#+ ORIGID RF00005_rep.5_AL590385.23/26129-26058_46 ORIGHEAD RF00005 +UCCCUGGUGGUCUAGUGGUUAGGAUUCGGCGCUCUCACCGCCGCGGCCCGGGUUCGAUUCCCGGUCAGGGAA +>53 SEQ51#1#88#+ ORIGID RF00006_rep.0_AF045145.1/1-88_51 ORIGHEAD RF00006 +GGCUGGCUUUAGCUCAGCGGUUACUUCGCGUGUCAUCAAACCACCUCUCUGGGUUGUUCGAGACCCGCGGGCGCUCUCCAGCCCUCUU +>54 SEQ52#2#101#+ ORIGID RF00006_rep.1_AC005219.1/49914-50014_52 ORIGHEAD RF00006 +GGUCGGAGUUAGCUCAAGCGGUUACCUCCUCAUGCCGGACUUUCUAUCUGUCCAUCUCUGUGCUGGGGUUCGAGACCCGCGGGUGCUUACUGACCCUUUU +>55 SEQ53#1#98#+ ORIGID RF00006_rep.2_AF045143.1/1-98_53 ORIGHEAD RF00006 +GGCUGGCUUUAGCUCAGCGGUUACUUCGACAGUUCUUUAAUUGAAACAAGCAACCUGUCUGGGUUGUUCGAGACCCGCGGGCGCUCUCCAGUCCUUUU +>56 SEQ54#1#88#+ ORIGID RF00006_rep.3_AF045144.1/1-88_54 ORIGHEAD RF00006 +GGCUGGCUUUAGCUCAGCGGUUACUUCGAGUACAUUGUAACCACCUCUCUGGGUGGUUCGAGACCCGCGGGUGCUUUCCAGCUCUUUU
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/1.1.tree Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,47 @@ +SEQ31 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 88.9 1.2e-150 ! ORIGID RF00005_rep.34_AC008443.10/43006-42934_31 ORIGHEAD RF00005 +SEQ11 - dataset_60 - cm 1 73 1 82 + no 1 0.62 0.0 88.3 8e-150 ! ORIGID RF00005_rep.16_AL133551.13/12355-12436_11 ORIGHEAD RF00005 +SEQ9 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 87.8 4.6e-149 ! ORIGID RF00005_rep.14_AL021808.2/65570-65498_9 ORIGHEAD RF00005 +SEQ32 - dataset_60 - cm 1 73 1 73 + no 1 0.58 0.0 87.3 2.6e-148 ! ORIGID RF00005_rep.35_AC005783.1/27398-27326_32 ORIGHEAD RF00005 +SEQ13 - dataset_60 - cm 1 73 1 82 + no 1 0.56 0.0 86.3 8.9e-147 ! ORIGID RF00005_rep.18_AL021918.1/81116-81197_13 ORIGHEAD RF00005 +SEQ36 - dataset_60 - cm 1 73 1 73 + no 1 0.51 0.0 83.0 1.1e-141 ! ORIGID RF00005_rep.39_AL031229.2/40502-40430_36 ORIGHEAD RF00005 +SEQ12 - dataset_60 - cm 1 73 1 82 + no 1 0.57 0.0 82.7 3.1e-141 ! ORIGID RF00005_rep.17_AL021918.1/54817-54736_12 ORIGHEAD RF00005 +SEQ26 - dataset_60 - cm 1 73 1 72 + no 1 0.50 0.0 82.0 4.9e-140 ! ORIGID RF00005_rep.2_AL662865.4/12206-12135_26 ORIGHEAD RF00005 +SEQ5 - dataset_60 - cm 1 73 1 72 + no 1 0.51 0.0 81.7 1.3e-139 ! ORIGID RF00005_rep.10_X58792.1/174-245_5 ORIGHEAD RF00005 +SEQ50 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 80.8 3.1e-138 ! ORIGID RF00005_rep.9_AP000442.6/2022-1950_50 ORIGHEAD RF00005 +SEQ28 - dataset_60 - cm 1 73 1 71 + no 1 0.62 0.0 80.7 4.6e-138 ! ORIGID RF00005_rep.31_AC092686.3/29631-29561_28 ORIGHEAD RF00005 +SEQ15 - dataset_60 - cm 1 73 1 73 + no 1 0.53 0.0 80.6 5.9e-138 ! ORIGID RF00005_rep.1_AC005329.1/7043-6971_15 ORIGHEAD RF00005 +SEQ24 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 80.3 1.5e-137 ! ORIGID RF00005_rep.28_X04779.1/1-73_24 ORIGHEAD RF00005 +SEQ4 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 79.2 7.3e-136 ! ORIGID RF00005_rep.0_M15347.1/1040-968_4 ORIGHEAD RF00005 +SEQ46 - dataset_60 - cm 1 73 1 72 + no 1 0.65 0.0 78.4 1.3e-134 ! ORIGID RF00005_rep.5_AL590385.23/26129-26058_46 ORIGHEAD RF00005 +SEQ17 - dataset_60 - cm 1 73 1 71 + no 1 0.59 0.0 77.7 1.6e-133 ! ORIGID RF00005_rep.21_AL355149.13/15278-15208_17 ORIGHEAD RF00005 +SEQ37 - dataset_60 - cm 1 73 1 82 + no 1 0.63 0.0 76.3 2.5e-131 ! ORIGID RF00005_rep.3_Z54587.1/126-45_37 ORIGHEAD RF00005 +SEQ10 - dataset_60 - cm 1 73 1 73 + no 1 0.62 0.0 76.3 2.8e-131 ! ORIGID RF00005_rep.15_AC008443.10/42590-42518_10 ORIGHEAD RF00005 +SEQ23 - dataset_60 - cm 1 73 1 74 + no 1 0.61 0.0 75.9 1.2e-130 ! ORIGID RF00005_rep.27_AL352978.6/119697-119770_23 ORIGHEAD RF00005 +SEQ20 - dataset_60 - cm 1 73 1 72 + no 1 0.56 0.0 75.8 1.7e-130 ! ORIGID RF00005_rep.24_AC004941.2/32735-32806_20 ORIGHEAD RF00005 +SEQ30 - dataset_60 - cm 1 73 1 72 + no 1 0.61 0.0 74.9 4e-129 ! ORIGID RF00005_rep.33_AC018638.5/4694-4623_30 ORIGHEAD RF00005 +SEQ16 - dataset_60 - cm 1 73 1 72 + no 1 0.61 0.0 74.9 4e-129 ! ORIGID RF00005_rep.20_AL671879.2/100356-100285_16 ORIGHEAD RF00005 +SEQ21 - dataset_60 - cm 1 73 1 74 + no 1 0.61 0.0 74.8 4.8e-129 ! ORIGID RF00005_rep.25_AC006449.19/196857-196784_21 ORIGHEAD RF00005 +SEQ18 - dataset_60 - cm 1 73 1 72 + no 1 0.58 0.0 72.9 4.3e-126 ! ORIGID RF00005_rep.22_AL590385.23/26487-26416_18 ORIGHEAD RF00005 +SEQ35 - dataset_60 - cm 1 73 1 72 + no 1 0.65 0.0 71.9 1.2e-124 ! ORIGID RF00005_rep.38_J00309.1/356-427_35 ORIGHEAD RF00005 +SEQ45 - dataset_60 - cm 1 73 1 72 + no 1 0.60 0.0 71.6 4.5e-124 ! ORIGID RF00005_rep.4_Z98744.2/66305-66234_45 ORIGHEAD RF00005 +SEQ7 - dataset_60 - cm 1 73 1 83 + no 1 0.63 0.0 71.2 2e-123 ! ORIGID RF00005_rep.12_AC108081.2/59868-59786_7 ORIGHEAD RF00005 +SEQ33 - dataset_60 - cm 1 73 1 72 + no 1 0.62 0.0 69.2 2e-120 ! ORIGID RF00005_rep.36_AC007298.17/145366-145295_33 ORIGHEAD RF00005 +SEQ19 - dataset_60 - cm 1 73 1 82 + no 1 0.59 0.0 69.0 4e-120 ! ORIGID RF00005_rep.23_M16479.1/42-123_19 ORIGHEAD RF00005 +SEQ22 - dataset_60 - cm 1 73 1 72 + no 1 0.49 0.0 48.1 5.1e-88 ! ORIGID RF00005_rep.26_AF346999.1/4402-4331_22 ORIGHEAD RF00005 +SEQ40 - dataset_60 - cm 1 73 1 66 + no 1 0.45 0.0 44.2 4.7e-82 ! ORIGID RF00005_rep.42_AF347015.1/5827-5762_40 ORIGHEAD RF00005 +SEQ29 - dataset_60 - cm 1 73 1 66 + no 1 0.42 0.0 31.0 8.7e-62 ! ORIGID RF00005_rep.32_AF347015.1/5892-5827_29 ORIGHEAD RF00005 +SEQ14 - dataset_60 - cm 1 73 1 73 + no 1 0.41 0.0 29.5 2.2e-59 ! ORIGID RF00005_rep.19_AF134583.1/1816-1744_14 ORIGHEAD RF00005 +SEQ39 - dataset_60 - cm 1 73 1 69 + no 1 0.39 0.0 21.6 2.5e-47 ! ORIGID RF00005_rep.41_AC093311.2/140036-139968_39 ORIGHEAD RF00005 +SEQ48 - dataset_60 - cm 1 73 1 71 + no 1 0.35 0.0 12.9 5.7e-34 ! ORIGID RF00005_rep.7_AF347005.1/12268-12338_48 ORIGHEAD RF00005 +SEQ34 - dataset_60 - cm 1 73 1 68 + no 1 0.34 0.0 12.8 9.6e-34 ! ORIGID RF00005_rep.37_AF347001.1/16015-15948_34 ORIGHEAD RF00005 +SEQ6 - dataset_60 - cm 1 73 1 66 + no 1 0.38 0.0 12.1 1.1e-32 ! ORIGID RF00005_rep.11_AF346992.1/15890-15955_6 ORIGHEAD RF00005 +SEQ42 - dataset_60 - cm 1 73 1 69 + no 1 0.38 0.0 9.4 1.4e-28 ! ORIGID RF00005_rep.44_AC008670.6/83597-83665_42 ORIGHEAD RF00005 +SEQ8 - dataset_60 - cm 1 73 1 70 + no 1 0.33 0.0 9.0 6.2e-28 ! ORIGID RF00005_rep.13_AC067849.6/4771-4840_8 ORIGHEAD RF00005 +SEQ27 - dataset_60 - cm 1 73 1 69 + no 1 0.43 0.0 8.6 3.1e-27 ! ORIGID RF00005_rep.30_AL132988.4/95773-95841_27 ORIGHEAD RF00005 +SEQ41 - dataset_60 - cm 1 73 1 68 + no 1 0.26 0.1 7.7 6e-26 ! ORIGID RF00005_rep.43_L23320.1/77-10_41 ORIGHEAD RF00005 +SEQ43 - dataset_60 - cm 1 73 1 71 + no 1 0.41 0.0 4.3 1.1e-20 ! ORIGID RF00005_rep.45_AF382005.1/581-651_43 ORIGHEAD RF00005 +SEQ25 - dataset_60 - cm 1 73 1 69 + no 1 0.29 0.0 4.2 1.8e-20 ! ORIGID RF00005_rep.29_AF381996.2/4265-4333_25 ORIGHEAD RF00005 +SEQ44 - dataset_60 - cm 1 73 1 69 + no 1 0.42 0.0 1.2 6.2e-16 ! ORIGID RF00005_rep.46_AF347015.1/1604-1672_44 ORIGHEAD RF00005 +SEQ38 - dataset_60 - cm 1 73 1 65 + no 1 0.23 0.5 -0.9 1.1e-12 ! ORIGID RF00005_rep.40_AF382013.1/10403-10467_38 ORIGHEAD RF00005 +SEQ47 - dataset_60 - cm 1 73 1 68 + no 1 0.24 0.5 -1.5 9.1e-12 ! ORIGID RF00005_rep.6_X93334.1/6942-7009_47 ORIGHEAD RF00005 +SEQ49 - dataset_60 - cm 1 73 1 68 + no 1 0.35 0.0 -4.4 2.9e-07 ! ORIGID RF00005_rep.8_AF134583.1/1599-1666_49 ORIGHEAD RF00005
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/1.2.model.tree.fa Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,40 @@ +>1 SEQ1#1#100#+ ORIGID RF00001_rep.0_AL096764.11/46123-46004_1 ORIGHEAD RF00001 +GUCUAUGGCCAUACCACCCUGAAUGUGCUUGAUCUCAUCUGAUCUCGUGAAGCCAAGCAGGGUGGGGCCUAGUUAGUACUUGGAUGGGAGACUUCCUGGG +>2 SEQ1#21#120#+ ORIGID RF00001_rep.0_AL096764.11/46123-46004_1 ORIGHEAD RF00001 +GAAUGUGCUUGAUCUCAUCUGAUCUCGUGAAGCCAAGCAGGGUGGGGCCUAGUUAGUACUUGGAUGGGAGACUUCCUGGGAAUAUAAGCUGCUGUUGGCU +>3 SEQ2#1#100#+ ORIGID RF00001_rep.1_U89919.1/939-1056_2 ORIGHEAD RF00001 +CUUUACGGCCACACCACCCUGAACGCACCGGAUCUCGACUGACCUUGAAAGCUAAGCAGGAUCGGGCCUGGUUAGUAUUGGGAUGGCAGACCCCCUGGAA +>4 SEQ2#19#118#+ ORIGID RF00001_rep.1_U89919.1/939-1056_2 ORIGHEAD RF00001 +CUGAACGCACCGGAUCUCGACUGACCUUGAAAGCUAAGCAGGAUCGGGCCUGGUUAGUAUUGGGAUGGCAGACCCCCUGGAAAUACAGGGUGCUGAAGGU +>5 SEQ3#5#104#+ ORIGID RF00001_rep.2_AJ508600.1/161-58_3 ORIGHEAD RF00001 +ACAGCCAUACCAUCCUGAACAUGCCAGAUCUUGUCUGACCUCUGAAGCUAAGCAGGGUCAAGCCUGGUUAGUACUUGGGAGAAGCUGGUGUGGCUAGACC +>31 SEQ29#1#66#+ ORIGID RF00005_rep.32_AF347015.1/5892-5827_29 ORIGHEAD RF00005 +GGUAAAAUGGCUGAGUGAAGCAUUGGACUGUAAAUCUAAAGACAGGGGUUAGGCCUCUUUUUACCA +>59 SEQ56#1#95#+ ORIGID RF00019_rep.1_L32608.1/283-377_56 ORIGHEAD RF00019 +GGCUGGUCCGAUGGUAGUGGGUUAUCAGAACUUAUUAACAUUAGUGUCACUAAAGUUGGUAUACAACCCCCCACUGCUAAAUUUGACUGGCUUUU +>60 SEQ57#3#102#+ ORIGID RF00019_rep.2_ABBA01033605.1/1707-1808_57 ORIGHEAD RF00019 +CUGGUCCGAGUGCAGUGGUGUUUACAACUAAUUGAUCACAACCAGUUACAGAUUUCUUUGUUCCUUCUCCACUCCCACUGCUUCACUUGACUAGCCUUUU +>62 SEQ59#1#79#+ ORIGID RF00027_rep.0_AF480570.1/1-79_59 ORIGHEAD RF00027 +GUGAGGUAGUAAGUUGUAUUGUUGUGGGGUAGGGAUAUUAGGCCCCAAUUAGAAGAUAACUAUACAACUUACUACUUUC +>69 SEQ66#1#71#+ ORIGID RF00031_rep.4_AF195141.1/689-759_66 ORIGHEAD RF00031 +GACUGACAUUAUGAAGGCCUGUACUGAAGACAGCAAGCUGUUAGUACAGACCAGAUGCUUUCUUGGCAGGC +>75 SEQ72#1#100#+ ORIGID RF00618_rep.0_AL135914.25/92223-92098_72 ORIGHEAD RF00618 +ACCAUCCUUUUCUUGGGGUUGCACUACUGUCCAAUGGGUACCUAGUGAGGGCAGUACUGCUAACUCCUGCACAACACACCGAAAUCAACUAGAGCUUUGC +>76 SEQ72#27#126#+ ORIGID RF00618_rep.0_AL135914.25/92223-92098_72 ORIGHEAD RF00618 +CUGUCCAAUGGGUACCUAGUGAGGGCAGUACUGCUAACUCCUGCACAACACACCGAAAUCAACUAGAGCUUUGCUUUGCCUUGGUGCAGUUUUUGGAGAA +>77 SEQ73#1#100#+ ORIGID RF00618_rep.1_AL161445.10/77816-77941_73 ORIGHEAD RF00618 +ACCAUCCUUUUCUUGGGGUUGCACUACUGUCCAAAGAGCAUGUAGUGAGGGCAGUACUGCUAACGUCUACACAACACACCCACCUCAACUAGAGCUUUGC +>78 SEQ73#27#126#+ ORIGID RF00618_rep.1_AL161445.10/77816-77941_73 ORIGHEAD RF00618 +CUGUCCAAAGAGCAUGUAGUGAGGGCAGUACUGCUAACGUCUACACAACACACCCACCUCAACUAGAGCUUUGCUUUAGCUUGGUGUAAUUUUUGGAAAA +>79 SEQ74#1#100#+ ORIGID RF00618_rep.2_U62822.1/2-128_74 ORIGHEAD RF00618 +ACCAUCCUUUUCUUGGGGUUGCGCUACUGUCCAAUGAGCGCAUAGUGAGGGCAGUACUGCUAACGCCUGAACAACACACCCGCAUCAACUAGAGCUUUUG +>80 SEQ74#28#127#+ ORIGID RF00618_rep.2_U62822.1/2-128_74 ORIGHEAD RF00618 +UGUCCAAUGAGCGCAUAGUGAGGGCAGUACUGCUAACGCCUGAACAACACACCCGCAUCAACUAGAGCUUUUGCUUUAUUUUGGUGCAAUUUUUGGAAAA +>81 SEQ75#1#100#+ ORIGID RF00618_rep.3_AL389925.10/20736-20611_75 ORIGHEAD RF00618 +ACCAUCCUUUUCUUGGGGUUGCACUACUGUCUAAUGAGUGCAUAAUGAGGGCAGUAUUGCUAACGCCUAUACAAUGCACCUGCAUCAACUAGAACUUUGC +>82 SEQ75#27#126#+ ORIGID RF00618_rep.3_AL389925.10/20736-20611_75 ORIGHEAD RF00618 +CUGUCUAAUGAGUGCAUAAUGAGGGCAGUAUUGCUAACGCCUAUACAAUGCACCUGCAUCAACUAGAACUUUGCUUUACCUUGGUACAAUUUUUGGAAAA +>90 SEQ83#1#79#+ ORIGID RF00641_rep.3_AADD01141098.1/2614-2692_83 ORIGHEAD RF00641 +GCUACUUGAAGAGAGGUAAUCCUUCAUGCAUUUGCUUUACUUGCAAUGAUUAUACAAGGGCAGACUCUCUCUGGGGAGC +>94 SEQ87#1#78#+ ORIGID RF00641_rep.7_AL132709.5/54880-54803_87 ORIGHEAD RF00641 +GGUACCUGAAAUAGGUUGCCUGUGAGGUGUUCACUUUCUAUAUGAUGAAUAUUAUACAGUCAACCUCUUUCCGAUAUC
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/1.2.tree Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,4 @@ +SEQ74 - dataset_61 - cm 1 100 1 100 + no 1 0.51 0.0 163.2 7.9e-68 ! ORIGID RF00618_rep.2_U62822.1/2-128_74 ORIGHEAD RF00618 +SEQ72 - dataset_61 - cm 1 100 1 100 + no 1 0.49 0.0 163.1 8.9e-68 ! ORIGID RF00618_rep.0_AL135914.25/92223-92098_72 ORIGHEAD RF00618 +SEQ73 - dataset_61 - cm 1 100 1 100 + no 1 0.49 0.0 161.5 3.4e-67 ! ORIGID RF00618_rep.1_AL161445.10/77816-77941_73 ORIGHEAD RF00618 +SEQ75 - dataset_61 - cm 1 100 1 100 + no 1 0.44 0.0 160.5 8.2e-67 ! ORIGID RF00618_rep.3_AL389925.10/20736-20611_75 ORIGHEAD RF00618
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/1.cluster.all Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,34 @@ +SEQ31#1#73#+ RESULT 1 CM_SCORE 88.9 MODEL 1.1 ORIGID RF00005_rep.34_AC008443.10/43006-42934_31 ORIGHEAD RF00005 +SEQ9#1#73#+ RESULT 1 CM_SCORE 87.8 MODEL 1.1 ORIGID RF00005_rep.14_AL021808.2/65570-65498_9 ORIGHEAD RF00005 +SEQ32#1#73#+ RESULT 1 CM_SCORE 87.3 MODEL 1.1 ORIGID RF00005_rep.35_AC005783.1/27398-27326_32 ORIGHEAD RF00005 +SEQ13#1#82#+ RESULT 1 CM_SCORE 86.3 MODEL 1.1 ORIGID RF00005_rep.18_AL021918.1/81116-81197_13 ORIGHEAD RF00005 +SEQ28#1#71#+ RESULT 1 CM_SCORE 80.7 MODEL 1.1 ORIGID RF00005_rep.31_AC092686.3/29631-29561_28 ORIGHEAD RF00005 +SEQ46#1#72#+ RESULT 1 CM_SCORE 78.4 MODEL 1.1 ORIGID RF00005_rep.5_AL590385.23/26129-26058_46 ORIGHEAD RF00005 +SEQ17#1#71#+ RESULT 1 CM_SCORE 77.7 MODEL 1.1 ORIGID RF00005_rep.21_AL355149.13/15278-15208_17 ORIGHEAD RF00005 +SEQ37#1#82#+ RESULT 1 CM_SCORE 76.3 MODEL 1.1 ORIGID RF00005_rep.3_Z54587.1/126-45_37 ORIGHEAD RF00005 +SEQ10#1#73#+ RESULT 1 CM_SCORE 76.3 MODEL 1.1 ORIGID RF00005_rep.15_AC008443.10/42590-42518_10 ORIGHEAD RF00005 +SEQ23#1#74#+ RESULT 1 CM_SCORE 75.9 MODEL 1.1 ORIGID RF00005_rep.27_AL352978.6/119697-119770_23 ORIGHEAD RF00005 +SEQ30#1#72#+ RESULT 1 CM_SCORE 74.9 MODEL 1.1 ORIGID RF00005_rep.33_AC018638.5/4694-4623_30 ORIGHEAD RF00005 +SEQ16#1#72#+ RESULT 1 CM_SCORE 74.9 MODEL 1.1 ORIGID RF00005_rep.20_AL671879.2/100356-100285_16 ORIGHEAD RF00005 +SEQ18#1#72#+ RESULT 1 CM_SCORE 72.9 MODEL 1.1 ORIGID RF00005_rep.22_AL590385.23/26487-26416_18 ORIGHEAD RF00005 +SEQ35#1#72#+ RESULT 1 CM_SCORE 71.9 MODEL 1.1 ORIGID RF00005_rep.38_J00309.1/356-427_35 ORIGHEAD RF00005 +SEQ7#1#83#+ RESULT 1 CM_SCORE 71.2 MODEL 1.1 ORIGID RF00005_rep.12_AC108081.2/59868-59786_7 ORIGHEAD RF00005 +SEQ33#1#72#+ RESULT 1 CM_SCORE 69.2 MODEL 1.1 ORIGID RF00005_rep.36_AC007298.17/145366-145295_33 ORIGHEAD RF00005 +SEQ29#1#66#+ RESULT 1 CM_SCORE 31.0 MODEL 1.1 ORIGID RF00005_rep.32_AF347015.1/5892-5827_29 ORIGHEAD RF00005 +SEQ11#1#82#+ RESULT 1 CM_SCORE 88.3 CMSEARCH 1.1 ORIGID RF00005_rep.16_AL133551.13/12355-12436_11 ORIGHEAD RF00005 +SEQ36#1#73#+ RESULT 1 CM_SCORE 83.0 CMSEARCH 1.1 ORIGID RF00005_rep.39_AL031229.2/40502-40430_36 ORIGHEAD RF00005 +SEQ12#1#82#+ RESULT 1 CM_SCORE 82.7 CMSEARCH 1.1 ORIGID RF00005_rep.17_AL021918.1/54817-54736_12 ORIGHEAD RF00005 +SEQ26#1#72#+ RESULT 1 CM_SCORE 82.0 CMSEARCH 1.1 ORIGID RF00005_rep.2_AL662865.4/12206-12135_26 ORIGHEAD RF00005 +SEQ5#1#72#+ RESULT 1 CM_SCORE 81.7 CMSEARCH 1.1 ORIGID RF00005_rep.10_X58792.1/174-245_5 ORIGHEAD RF00005 +SEQ50#1#73#+ RESULT 1 CM_SCORE 80.8 CMSEARCH 1.1 ORIGID RF00005_rep.9_AP000442.6/2022-1950_50 ORIGHEAD RF00005 +SEQ15#1#73#+ RESULT 1 CM_SCORE 80.6 CMSEARCH 1.1 ORIGID RF00005_rep.1_AC005329.1/7043-6971_15 ORIGHEAD RF00005 +SEQ24#1#73#+ RESULT 1 CM_SCORE 80.3 CMSEARCH 1.1 ORIGID RF00005_rep.28_X04779.1/1-73_24 ORIGHEAD RF00005 +SEQ4#1#73#+ RESULT 1 CM_SCORE 79.2 CMSEARCH 1.1 ORIGID RF00005_rep.0_M15347.1/1040-968_4 ORIGHEAD RF00005 +SEQ20#1#72#+ RESULT 1 CM_SCORE 75.8 CMSEARCH 1.1 ORIGID RF00005_rep.24_AC004941.2/32735-32806_20 ORIGHEAD RF00005 +SEQ21#1#74#+ RESULT 1 CM_SCORE 74.8 CMSEARCH 1.1 ORIGID RF00005_rep.25_AC006449.19/196857-196784_21 ORIGHEAD RF00005 +SEQ45#1#72#+ RESULT 1 CM_SCORE 71.6 CMSEARCH 1.1 ORIGID RF00005_rep.4_Z98744.2/66305-66234_45 ORIGHEAD RF00005 +SEQ19#1#82#+ RESULT 1 CM_SCORE 69.0 CMSEARCH 1.1 ORIGID RF00005_rep.23_M16479.1/42-123_19 ORIGHEAD RF00005 +SEQ22#1#72#+ RESULT 1 CM_SCORE 48.1 CMSEARCH 1.1 ORIGID RF00005_rep.26_AF346999.1/4402-4331_22 ORIGHEAD RF00005 +SEQ40#1#66#+ RESULT 1 CM_SCORE 44.2 CMSEARCH 1.1 ORIGID RF00005_rep.42_AF347015.1/5827-5762_40 ORIGHEAD RF00005 +SEQ14#1#73#+ RESULT 1 CM_SCORE 29.5 CMSEARCH 1.1 ORIGID RF00005_rep.19_AF134583.1/1816-1744_14 ORIGHEAD RF00005 +SEQ39#1#69#+ RESULT 1 CM_SCORE 21.6 CMSEARCH 1.1 ORIGID RF00005_rep.41_AC093311.2/140036-139968_39 ORIGHEAD RF00005
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/2.cluster.all Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,4 @@ +SEQ74#1#100#+ RESULT 2 CM_SCORE 163.2 MODEL 1.2 ORIGID RF00618_rep.2_U62822.1/2-128_74 ORIGHEAD RF00618 +SEQ72#1#100#+ RESULT 2 CM_SCORE 163.1 MODEL 1.2 ORIGID RF00618_rep.0_AL135914.25/92223-92098_72 ORIGHEAD RF00618 +SEQ73#1#100#+ RESULT 2 CM_SCORE 161.5 MODEL 1.2 ORIGID RF00618_rep.1_AL161445.10/77816-77941_73 ORIGHEAD RF00618 +SEQ75#1#100#+ RESULT 2 CM_SCORE 160.5 MODEL 1.2 ORIGID RF00618_rep.3_AL389925.10/20736-20611_75 ORIGHEAD RF00618
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/cluster.final.stats Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,2 @@ +CLUSTER 1 SEQS 34 IDS_UNIQUE 34 MODELS 1 +CLUSTER 2 SEQS 4 IDS_UNIQUE 4 MODELS 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_overlap.map Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,2 @@ +1.1 1.1 +1.2 1.2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_overlap.matrix Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,4 @@ +# MODEL 1.1 1.2 +MODEL CLASS 0 0 +1.1 0 0 0 +1.2 0 0 0
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_partition.hard.best Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,38 @@ +SEQ31#1#73#+ 88.9 1.2e-150 1.1 1.1 1 +SEQ11#1#82#+ 88.3 8e-150 1.1 1.1 1 +SEQ9#1#73#+ 87.8 4.6e-149 1.1 1.1 1 +SEQ32#1#73#+ 87.3 2.6e-148 1.1 1.1 1 +SEQ13#1#82#+ 86.3 8.9e-147 1.1 1.1 1 +SEQ36#1#73#+ 83.0 1.1e-141 1.1 1.1 1 +SEQ12#1#82#+ 82.7 3.1e-141 1.1 1.1 1 +SEQ26#1#72#+ 82.0 4.9e-140 1.1 1.1 1 +SEQ5#1#72#+ 81.7 1.3e-139 1.1 1.1 1 +SEQ50#1#73#+ 80.8 3.1e-138 1.1 1.1 1 +SEQ28#1#71#+ 80.7 4.6e-138 1.1 1.1 1 +SEQ15#1#73#+ 80.6 5.9e-138 1.1 1.1 1 +SEQ24#1#73#+ 80.3 1.5e-137 1.1 1.1 1 +SEQ4#1#73#+ 79.2 7.3e-136 1.1 1.1 1 +SEQ46#1#72#+ 78.4 1.3e-134 1.1 1.1 1 +SEQ17#1#71#+ 77.7 1.6e-133 1.1 1.1 1 +SEQ10#1#73#+ 76.3 2.8e-131 1.1 1.1 1 +SEQ37#1#82#+ 76.3 2.5e-131 1.1 1.1 1 +SEQ23#1#74#+ 75.9 1.2e-130 1.1 1.1 1 +SEQ20#1#72#+ 75.8 1.7e-130 1.1 1.1 1 +SEQ16#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ30#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ21#1#74#+ 74.8 4.8e-129 1.1 1.1 1 +SEQ18#1#72#+ 72.9 4.3e-126 1.1 1.1 1 +SEQ35#1#72#+ 71.9 1.2e-124 1.1 1.1 1 +SEQ45#1#72#+ 71.6 4.5e-124 1.1 1.1 1 +SEQ7#1#83#+ 71.2 2e-123 1.1 1.1 1 +SEQ33#1#72#+ 69.2 2e-120 1.1 1.1 1 +SEQ19#1#82#+ 69.0 4e-120 1.1 1.1 1 +SEQ22#1#72#+ 48.1 5.1e-88 1.1 1.1 1 +SEQ40#1#66#+ 44.2 4.7e-82 1.1 1.1 1 +SEQ29#1#66#+ 31.0 8.7e-62 1.1 1.1 1 +SEQ14#1#73#+ 29.5 2.2e-59 1.1 1.1 1 +SEQ39#1#69#+ 21.6 2.5e-47 1.1 1.1 1 +SEQ74#1#100#+ 163.2 7.9e-68 1.2 1.2 2 +SEQ72#1#100#+ 163.1 8.9e-68 1.2 1.2 2 +SEQ73#1#100#+ 161.5 3.4e-67 1.2 1.2 2 +SEQ75#1#100#+ 160.5 8.2e-67 1.2 1.2 2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_partition.hard.merged Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,38 @@ +SEQ31#1#73#+ 88.9 1.2e-150 1.1 1.1 1 +SEQ11#1#82#+ 88.3 8e-150 1.1 1.1 1 +SEQ9#1#73#+ 87.8 4.6e-149 1.1 1.1 1 +SEQ32#1#73#+ 87.3 2.6e-148 1.1 1.1 1 +SEQ13#1#82#+ 86.3 8.9e-147 1.1 1.1 1 +SEQ36#1#73#+ 83.0 1.1e-141 1.1 1.1 1 +SEQ12#1#82#+ 82.7 3.1e-141 1.1 1.1 1 +SEQ26#1#72#+ 82.0 4.9e-140 1.1 1.1 1 +SEQ5#1#72#+ 81.7 1.3e-139 1.1 1.1 1 +SEQ50#1#73#+ 80.8 3.1e-138 1.1 1.1 1 +SEQ28#1#71#+ 80.7 4.6e-138 1.1 1.1 1 +SEQ15#1#73#+ 80.6 5.9e-138 1.1 1.1 1 +SEQ24#1#73#+ 80.3 1.5e-137 1.1 1.1 1 +SEQ4#1#73#+ 79.2 7.3e-136 1.1 1.1 1 +SEQ46#1#72#+ 78.4 1.3e-134 1.1 1.1 1 +SEQ17#1#71#+ 77.7 1.6e-133 1.1 1.1 1 +SEQ10#1#73#+ 76.3 2.8e-131 1.1 1.1 1 +SEQ37#1#82#+ 76.3 2.5e-131 1.1 1.1 1 +SEQ23#1#74#+ 75.9 1.2e-130 1.1 1.1 1 +SEQ20#1#72#+ 75.8 1.7e-130 1.1 1.1 1 +SEQ16#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ30#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ21#1#74#+ 74.8 4.8e-129 1.1 1.1 1 +SEQ18#1#72#+ 72.9 4.3e-126 1.1 1.1 1 +SEQ35#1#72#+ 71.9 1.2e-124 1.1 1.1 1 +SEQ45#1#72#+ 71.6 4.5e-124 1.1 1.1 1 +SEQ7#1#83#+ 71.2 2e-123 1.1 1.1 1 +SEQ33#1#72#+ 69.2 2e-120 1.1 1.1 1 +SEQ19#1#82#+ 69.0 4e-120 1.1 1.1 1 +SEQ22#1#72#+ 48.1 5.1e-88 1.1 1.1 1 +SEQ40#1#66#+ 44.2 4.7e-82 1.1 1.1 1 +SEQ29#1#66#+ 31.0 8.7e-62 1.1 1.1 1 +SEQ14#1#73#+ 29.5 2.2e-59 1.1 1.1 1 +SEQ39#1#69#+ 21.6 2.5e-47 1.1 1.1 1 +SEQ74#1#100#+ 163.2 7.9e-68 1.2 1.2 2 +SEQ72#1#100#+ 163.1 8.9e-68 1.2 1.2 2 +SEQ73#1#100#+ 161.5 3.4e-67 1.2 1.2 2 +SEQ75#1#100#+ 160.5 8.2e-67 1.2 1.2 2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_partition.soft Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,38 @@ +SEQ31#1#73#+ 88.9 1.2e-150 1.1 1.1 1 +SEQ11#1#82#+ 88.3 8e-150 1.1 1.1 1 +SEQ9#1#73#+ 87.8 4.6e-149 1.1 1.1 1 +SEQ32#1#73#+ 87.3 2.6e-148 1.1 1.1 1 +SEQ13#1#82#+ 86.3 8.9e-147 1.1 1.1 1 +SEQ36#1#73#+ 83.0 1.1e-141 1.1 1.1 1 +SEQ12#1#82#+ 82.7 3.1e-141 1.1 1.1 1 +SEQ26#1#72#+ 82.0 4.9e-140 1.1 1.1 1 +SEQ5#1#72#+ 81.7 1.3e-139 1.1 1.1 1 +SEQ50#1#73#+ 80.8 3.1e-138 1.1 1.1 1 +SEQ28#1#71#+ 80.7 4.6e-138 1.1 1.1 1 +SEQ15#1#73#+ 80.6 5.9e-138 1.1 1.1 1 +SEQ24#1#73#+ 80.3 1.5e-137 1.1 1.1 1 +SEQ4#1#73#+ 79.2 7.3e-136 1.1 1.1 1 +SEQ46#1#72#+ 78.4 1.3e-134 1.1 1.1 1 +SEQ17#1#71#+ 77.7 1.6e-133 1.1 1.1 1 +SEQ10#1#73#+ 76.3 2.8e-131 1.1 1.1 1 +SEQ37#1#82#+ 76.3 2.5e-131 1.1 1.1 1 +SEQ23#1#74#+ 75.9 1.2e-130 1.1 1.1 1 +SEQ20#1#72#+ 75.8 1.7e-130 1.1 1.1 1 +SEQ16#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ30#1#72#+ 74.9 4e-129 1.1 1.1 1 +SEQ21#1#74#+ 74.8 4.8e-129 1.1 1.1 1 +SEQ18#1#72#+ 72.9 4.3e-126 1.1 1.1 1 +SEQ35#1#72#+ 71.9 1.2e-124 1.1 1.1 1 +SEQ45#1#72#+ 71.6 4.5e-124 1.1 1.1 1 +SEQ7#1#83#+ 71.2 2e-123 1.1 1.1 1 +SEQ33#1#72#+ 69.2 2e-120 1.1 1.1 1 +SEQ19#1#82#+ 69.0 4e-120 1.1 1.1 1 +SEQ22#1#72#+ 48.1 5.1e-88 1.1 1.1 1 +SEQ40#1#66#+ 44.2 4.7e-82 1.1 1.1 1 +SEQ29#1#66#+ 31.0 8.7e-62 1.1 1.1 1 +SEQ14#1#73#+ 29.5 2.2e-59 1.1 1.1 1 +SEQ39#1#69#+ 21.6 2.5e-47 1.1 1.1 1 +SEQ74#1#100#+ 163.2 7.9e-68 1.2 1.2 2 +SEQ72#1#100#+ 163.1 8.9e-68 1.2 1.2 2 +SEQ73#1#100#+ 161.5 3.4e-67 1.2 1.2 2 +SEQ75#1#100#+ 160.5 8.2e-67 1.2 1.2 2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/RESULTS/partitions/final_partition.used_cmsearch Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,2 @@ +1.1 +1.2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/combined_cm_out Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,53 @@ +##.1.1 +SEQ31 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 88.9 1.2e-150 ! ORIGID RF00005_rep.34_AC008443.10/43006-42934_31 ORIGHEAD RF00005 +SEQ11 - dataset_60 - cm 1 73 1 82 + no 1 0.62 0.0 88.3 8e-150 ! ORIGID RF00005_rep.16_AL133551.13/12355-12436_11 ORIGHEAD RF00005 +SEQ9 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 87.8 4.6e-149 ! ORIGID RF00005_rep.14_AL021808.2/65570-65498_9 ORIGHEAD RF00005 +SEQ32 - dataset_60 - cm 1 73 1 73 + no 1 0.58 0.0 87.3 2.6e-148 ! ORIGID RF00005_rep.35_AC005783.1/27398-27326_32 ORIGHEAD RF00005 +SEQ13 - dataset_60 - cm 1 73 1 82 + no 1 0.56 0.0 86.3 8.9e-147 ! ORIGID RF00005_rep.18_AL021918.1/81116-81197_13 ORIGHEAD RF00005 +SEQ36 - dataset_60 - cm 1 73 1 73 + no 1 0.51 0.0 83.0 1.1e-141 ! ORIGID RF00005_rep.39_AL031229.2/40502-40430_36 ORIGHEAD RF00005 +SEQ12 - dataset_60 - cm 1 73 1 82 + no 1 0.57 0.0 82.7 3.1e-141 ! ORIGID RF00005_rep.17_AL021918.1/54817-54736_12 ORIGHEAD RF00005 +SEQ26 - dataset_60 - cm 1 73 1 72 + no 1 0.50 0.0 82.0 4.9e-140 ! ORIGID RF00005_rep.2_AL662865.4/12206-12135_26 ORIGHEAD RF00005 +SEQ5 - dataset_60 - cm 1 73 1 72 + no 1 0.51 0.0 81.7 1.3e-139 ! ORIGID RF00005_rep.10_X58792.1/174-245_5 ORIGHEAD RF00005 +SEQ50 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 80.8 3.1e-138 ! ORIGID RF00005_rep.9_AP000442.6/2022-1950_50 ORIGHEAD RF00005 +SEQ28 - dataset_60 - cm 1 73 1 71 + no 1 0.62 0.0 80.7 4.6e-138 ! ORIGID RF00005_rep.31_AC092686.3/29631-29561_28 ORIGHEAD RF00005 +SEQ15 - dataset_60 - cm 1 73 1 73 + no 1 0.53 0.0 80.6 5.9e-138 ! ORIGID RF00005_rep.1_AC005329.1/7043-6971_15 ORIGHEAD RF00005 +SEQ24 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 80.3 1.5e-137 ! ORIGID RF00005_rep.28_X04779.1/1-73_24 ORIGHEAD RF00005 +SEQ4 - dataset_60 - cm 1 73 1 73 + no 1 0.56 0.0 79.2 7.3e-136 ! ORIGID RF00005_rep.0_M15347.1/1040-968_4 ORIGHEAD RF00005 +SEQ46 - dataset_60 - cm 1 73 1 72 + no 1 0.65 0.0 78.4 1.3e-134 ! ORIGID RF00005_rep.5_AL590385.23/26129-26058_46 ORIGHEAD RF00005 +SEQ17 - dataset_60 - cm 1 73 1 71 + no 1 0.59 0.0 77.7 1.6e-133 ! ORIGID RF00005_rep.21_AL355149.13/15278-15208_17 ORIGHEAD RF00005 +SEQ37 - dataset_60 - cm 1 73 1 82 + no 1 0.63 0.0 76.3 2.5e-131 ! ORIGID RF00005_rep.3_Z54587.1/126-45_37 ORIGHEAD RF00005 +SEQ10 - dataset_60 - cm 1 73 1 73 + no 1 0.62 0.0 76.3 2.8e-131 ! ORIGID RF00005_rep.15_AC008443.10/42590-42518_10 ORIGHEAD RF00005 +SEQ23 - dataset_60 - cm 1 73 1 74 + no 1 0.61 0.0 75.9 1.2e-130 ! ORIGID RF00005_rep.27_AL352978.6/119697-119770_23 ORIGHEAD RF00005 +SEQ20 - dataset_60 - cm 1 73 1 72 + no 1 0.56 0.0 75.8 1.7e-130 ! ORIGID RF00005_rep.24_AC004941.2/32735-32806_20 ORIGHEAD RF00005 +SEQ30 - dataset_60 - cm 1 73 1 72 + no 1 0.61 0.0 74.9 4e-129 ! ORIGID RF00005_rep.33_AC018638.5/4694-4623_30 ORIGHEAD RF00005 +SEQ16 - dataset_60 - cm 1 73 1 72 + no 1 0.61 0.0 74.9 4e-129 ! ORIGID RF00005_rep.20_AL671879.2/100356-100285_16 ORIGHEAD RF00005 +SEQ21 - dataset_60 - cm 1 73 1 74 + no 1 0.61 0.0 74.8 4.8e-129 ! ORIGID RF00005_rep.25_AC006449.19/196857-196784_21 ORIGHEAD RF00005 +SEQ18 - dataset_60 - cm 1 73 1 72 + no 1 0.58 0.0 72.9 4.3e-126 ! ORIGID RF00005_rep.22_AL590385.23/26487-26416_18 ORIGHEAD RF00005 +SEQ35 - dataset_60 - cm 1 73 1 72 + no 1 0.65 0.0 71.9 1.2e-124 ! ORIGID RF00005_rep.38_J00309.1/356-427_35 ORIGHEAD RF00005 +SEQ45 - dataset_60 - cm 1 73 1 72 + no 1 0.60 0.0 71.6 4.5e-124 ! ORIGID RF00005_rep.4_Z98744.2/66305-66234_45 ORIGHEAD RF00005 +SEQ7 - dataset_60 - cm 1 73 1 83 + no 1 0.63 0.0 71.2 2e-123 ! ORIGID RF00005_rep.12_AC108081.2/59868-59786_7 ORIGHEAD RF00005 +SEQ33 - dataset_60 - cm 1 73 1 72 + no 1 0.62 0.0 69.2 2e-120 ! ORIGID RF00005_rep.36_AC007298.17/145366-145295_33 ORIGHEAD RF00005 +SEQ19 - dataset_60 - cm 1 73 1 82 + no 1 0.59 0.0 69.0 4e-120 ! ORIGID RF00005_rep.23_M16479.1/42-123_19 ORIGHEAD RF00005 +SEQ22 - dataset_60 - cm 1 73 1 72 + no 1 0.49 0.0 48.1 5.1e-88 ! ORIGID RF00005_rep.26_AF346999.1/4402-4331_22 ORIGHEAD RF00005 +SEQ40 - dataset_60 - cm 1 73 1 66 + no 1 0.45 0.0 44.2 4.7e-82 ! ORIGID RF00005_rep.42_AF347015.1/5827-5762_40 ORIGHEAD RF00005 +SEQ29 - dataset_60 - cm 1 73 1 66 + no 1 0.42 0.0 31.0 8.7e-62 ! ORIGID RF00005_rep.32_AF347015.1/5892-5827_29 ORIGHEAD RF00005 +SEQ14 - dataset_60 - cm 1 73 1 73 + no 1 0.41 0.0 29.5 2.2e-59 ! ORIGID RF00005_rep.19_AF134583.1/1816-1744_14 ORIGHEAD RF00005 +SEQ39 - dataset_60 - cm 1 73 1 69 + no 1 0.39 0.0 21.6 2.5e-47 ! ORIGID RF00005_rep.41_AC093311.2/140036-139968_39 ORIGHEAD RF00005 +SEQ48 - dataset_60 - cm 1 73 1 71 + no 1 0.35 0.0 12.9 5.7e-34 ! ORIGID RF00005_rep.7_AF347005.1/12268-12338_48 ORIGHEAD RF00005 +SEQ34 - dataset_60 - cm 1 73 1 68 + no 1 0.34 0.0 12.8 9.6e-34 ! ORIGID RF00005_rep.37_AF347001.1/16015-15948_34 ORIGHEAD RF00005 +SEQ6 - dataset_60 - cm 1 73 1 66 + no 1 0.38 0.0 12.1 1.1e-32 ! ORIGID RF00005_rep.11_AF346992.1/15890-15955_6 ORIGHEAD RF00005 +SEQ42 - dataset_60 - cm 1 73 1 69 + no 1 0.38 0.0 9.4 1.4e-28 ! ORIGID RF00005_rep.44_AC008670.6/83597-83665_42 ORIGHEAD RF00005 +SEQ8 - dataset_60 - cm 1 73 1 70 + no 1 0.33 0.0 9.0 6.2e-28 ! ORIGID RF00005_rep.13_AC067849.6/4771-4840_8 ORIGHEAD RF00005 +SEQ27 - dataset_60 - cm 1 73 1 69 + no 1 0.43 0.0 8.6 3.1e-27 ! ORIGID RF00005_rep.30_AL132988.4/95773-95841_27 ORIGHEAD RF00005 +SEQ41 - dataset_60 - cm 1 73 1 68 + no 1 0.26 0.1 7.7 6e-26 ! ORIGID RF00005_rep.43_L23320.1/77-10_41 ORIGHEAD RF00005 +SEQ43 - dataset_60 - cm 1 73 1 71 + no 1 0.41 0.0 4.3 1.1e-20 ! ORIGID RF00005_rep.45_AF382005.1/581-651_43 ORIGHEAD RF00005 +SEQ25 - dataset_60 - cm 1 73 1 69 + no 1 0.29 0.0 4.2 1.8e-20 ! ORIGID RF00005_rep.29_AF381996.2/4265-4333_25 ORIGHEAD RF00005 +SEQ44 - dataset_60 - cm 1 73 1 69 + no 1 0.42 0.0 1.2 6.2e-16 ! ORIGID RF00005_rep.46_AF347015.1/1604-1672_44 ORIGHEAD RF00005 +SEQ38 - dataset_60 - cm 1 73 1 65 + no 1 0.23 0.5 -0.9 1.1e-12 ! ORIGID RF00005_rep.40_AF382013.1/10403-10467_38 ORIGHEAD RF00005 +SEQ47 - dataset_60 - cm 1 73 1 68 + no 1 0.24 0.5 -1.5 9.1e-12 ! ORIGID RF00005_rep.6_X93334.1/6942-7009_47 ORIGHEAD RF00005 +SEQ49 - dataset_60 - cm 1 73 1 68 + no 1 0.35 0.0 -4.4 2.9e-07 ! ORIGID RF00005_rep.8_AF134583.1/1599-1666_49 ORIGHEAD RF00005 +##.1.2 +SEQ74 - dataset_61 - cm 1 100 1 100 + no 1 0.51 0.0 163.2 7.9e-68 ! ORIGID RF00618_rep.2_U62822.1/2-128_74 ORIGHEAD RF00618 +SEQ72 - dataset_61 - cm 1 100 1 100 + no 1 0.49 0.0 163.1 8.9e-68 ! ORIGID RF00618_rep.0_AL135914.25/92223-92098_72 ORIGHEAD RF00618 +SEQ73 - dataset_61 - cm 1 100 1 100 + no 1 0.49 0.0 161.5 3.4e-67 ! ORIGID RF00618_rep.1_AL161445.10/77816-77941_73 ORIGHEAD RF00618 +SEQ75 - dataset_61 - cm 1 100 1 100 + no 1 0.44 0.0 160.5 8.2e-67 ! ORIGID RF00618_rep.3_AL389925.10/20736-20611_75 ORIGHEAD RF00618
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/evaluation1.txt Sat Oct 27 13:49:00 2018 -0400 @@ -0,0 +1,5 @@ +completeness_score : 0.533962565156 +homogeneity_score : 1.0 +adjusted_rand_score : 0.551625093777 +adjusted_mutual_info_score : 0.291033044987 +v_measure_score : 0.696187217713