Mercurial > repos > iuc > qiime_extract_barcodes

comparison generate_test_data.sh @ 0:c7eeac78cb64 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/qiime/ commit 3b54163c4f7daff76fcc589c4a9057bb03904380
author iuc
date Sat, 05 Aug 2017 07:28:39 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:c7eeac78cb64
1 #!/usr/bin/env bash
2
3 # Data are from test data in https://github.com/biocore/qiime
4
5 # align_seqs
6 align_seqs.py \
7 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
8 -o 'align_seqs_pynast_uclust' \
9 --alignment_method 'pynast' \
10 --pairwise_alignment_method 'uclust' \
11 --template_fp 'test-data/align_seqs/core_set_aligned.fasta.imputed' \
12 --min_percent_id '0.75'
13
14 align_seqs.py \
15 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
16 -o 'align_seqs_pynast_muscle' \
17 --alignment_method 'pynast' \
18 --pairwise_alignment_method 'muscle' \
19 --min_length '50' \
20 --min_percent_id '0.75'
21
22 align_seqs.py \
23 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
24 -o 'align_seqs_pynast_pair_hmm' \
25 --alignment_method 'pynast' \
26 --pairwise_alignment_method 'pair_hmm' \
27 --min_percent_id '0.75'
28
29 #align_seqs.py \
30 # --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
31 # -o 'align_seqs_pynast_clustal' \
32 # --alignment_method 'pynast' \
33 # --pairwise_alignment_method 'clustal' \
34 # --min_percent_id '0.75'
35
36 align_seqs.py \
37 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
38 -o 'align_seqs_pynast_blast' \
39 --alignment_method 'pynast' \
40 --pairwise_alignment_method 'blast' \
41 --min_percent_id '0.75'
42
43 align_seqs.py \
44 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
45 -o 'align_seqs_pynast_mafft' \
46 --alignment_method 'pynast' \
47 --pairwise_alignment_method 'mafft' \
48 --min_percent_id '0.75'
49
50 #align_seqs.py \
51 # --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
52 # -o 'align_seqs_infernal' \
53 # --alignment_method 'infernal' \
54 # --template_fp 'test-data/align_seqs/seed.16s.reference_model.sto' \
55 # --min_percent_id '0.75'
56
57 #align_seqs.py \
58 # --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
59 # -o 'align_seqs_clustalw' \
60 # --alignment_method 'clustalw' \
61 # --min_percent_id '0.75'
62
63 align_seqs.py \
64 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
65 -o 'align_seqs_muscle' \
66 --alignment_method 'muscle' \
67 --min_percent_id '0.75'
68
69 align_seqs.py \
70 --input_fasta_fp 'test-data/align_seqs/unaligned.fna' \
71 -o 'align_seqs_mafft' \
72 --alignment_method 'mafft' \
73 --min_percent_id '0.75'
74
75 #alpha_rarefaction
76 alpha_rarefaction.py \
77 --otu_table_fp "test-data/alpha_rarefaction/otu_table.biom" \
78 --mapping_fp "test-data/alpha_rarefaction/mapping_file.txt" \
79 -o alpha_rarefaction \
80 --num_steps '2' \
81 --tree_fp "test-data/alpha_rarefaction/rep_set.tre" \
82 --min_rare_depth '10' \
83 --max_rare_depth '50' \
84 --retain_intermediate_files
85 rm -rf alpha_rarefaction
86
87 # assign_taxonomy
88 assign_taxonomy.py \
89 --input_fasta_fp 'test-data/assign_taxonomy/uclust_input_seqs.fasta' \
90 --assignment_method 'uclust' \
91 --min_consensus_fraction '0.51' \
92 --similarity '0.9' \
93 --uclust_max_accepts '3' \
94 -o assign_taxonomy_uclust
95 ls assign_taxonomy_uclust
96 md5sum 'assign_taxonomy_uclust/uclust_input_seqs_tax_assignments.txt'
97 rm -rf assign_taxonomy_uclust
98
99 assign_taxonomy.py \
100 --input_fasta_fp 'test-data/assign_taxonomy/mothur_repr_set_seqs.fasta' \
101 --id_to_taxonomy_fp 'test-data/assign_taxonomy/mothur_id_to_taxonomy.txt' \
102 --assignment_method 'mothur' \
103 --reference_seqs_fp 'test-data/assign_taxonomy/mothur_ref_seq_set.fna' \
104 --confidence '0.5' \
105 -o assign_taxonomy_mothur
106 ls assign_taxonomy_mothur
107 md5sum 'assign_taxonomy_mothur/mothur_repr_set_seqs_tax_assignments.txt'
108 rm -rf assign_taxonomy_mothur
109
110 assign_taxonomy.py \
111 --input_fasta_fp 'test-data/assign_taxonomy/mothur_repr_set_seqs.fasta' \
112 --id_to_taxonomy_fp 'test-data/assign_taxonomy/mothur_id_to_taxonomy.txt' \
113 --assignment_method 'mothur' \
114 --reference_seqs_fp 'test-data/assign_taxonomy/mothur_ref_seq_set.fna' \
115 --blast_e_value '0.001' \
116 -o assign_taxonomy_blast
117 ls assign_taxonomy_blast
118 md5sum 'assign_taxonomy_blast/mothur_repr_set_seqs_tax_assignments.txt'
119 rm -rf assign_taxonomy_blast
120
121 #assign_taxonomy.py \
122 # --input_fasta_fp 'test-data/assign_taxonomy/rdp_input_seqs.fasta' \
123 # --id_to_taxonomy_fp 'test-data/assign_taxonomy/rdp_id_to_taxonomy.txt' \
124 # --assignment_method 'rdp' \
125 # --confidence '3' \
126 # -o assign_taxonomy_rdp
127
128 #assign_taxonomy.py \
129 # --input_fasta_fp 'test-data/assign_taxonomy/rtax_ref_seq_set.fna' \
130 # --id_to_taxonomy_fp 'test-data/assign_taxonomy/rtax_id_to_taxonomy.txt' \
131 # --assignment_method 'rtax' \
132 # --read_1_seqs_fp 'test-data/assign_taxonomy/read_1.seqs.fna' \
133 # --read_2_seqs_fp 'test-data/assign_taxonomy/read_2.seqs.fna' \
134 # --single_ok \
135 # --no_single_ok_generic \
136 # --read_id_regex "\S+\s+(\S+)" \
137 # --amplicon_id_regex "(\S+)\s+(\S+?)\/" \
138 # --header_id_regex "\S+\s+(\S+?)\/" \
139 # -o assign_taxonomy_rtax
140 #ls assign_taxonomy_rtax
141
142 assign_taxonomy.py \
143 --input_fasta_fp 'test-data/assign_taxonomy/mothur_ref_seq_set.fna' \
144 --assignment_method 'sortmerna' \
145 --min_consensus_fraction "0.51" \
146 --similarity "0.9" \
147 --sortmerna_e_value "1.0" \
148 --sortmerna_coverage "0.9" \
149 --sortmerna_best_N_alignments "5" \
150 -o assign_taxonomy_sortmerna
151 ls assign_taxonomy_sortmerna
152 md5sum 'assign_taxonomy_sortmerna/mothur_ref_seq_set_tax_assignments.txt'
153 md5sum 'assign_taxonomy_sortmerna/sortmerna_map.blast'
154 rm -rf assign_taxonomy_sortmerna
155
156 #beta_diversity
157 beta_diversity.py \
158 --input_path 'test-data/beta_diversity/otu_table.biom' \
159 -o beta_diversity_1 \
160 --metrics 'unweighted_unifrac,weighted_unifrac' \
161 --tree_path 'test-data/beta_diversity/rep_set.tre'
162 md5 'beta_diversity_1/unweighted_unifrac_otu_table.txt'
163 md5 'beta_diversity_1/weighted_unifrac_otu_table.txt'
164 rm -rf beta_diversity_1
165
166 beta_diversity.py \
167 --input_path 'test-data/beta_diversity/otu_table.biom' \
168 -o beta_diversity_2 \
169 --metrics 'abund_jaccard,binary_chisq,binary_chord,binary_euclidean,binary_hamming,binary_jaccard,binary_lennon,binary_ochiai,binary_pearson,binary_sorensen_dice,bray_curtis,canberra,chisq,chord,euclidean,gower,hellinger,kulczynski,manhattan,morisita_horn,pearson,soergel,spearman_approx,specprof,unifrac_g,unifrac_g_full_tree,unweighted_unifrac,unweighted_unifrac_full_tree,weighted_normalized_unifrac,weighted_unifrac' \
170 --tree_path 'test-data/beta_diversity/rep_set.tre'
171 md5 'beta_diversity_2/canberra_otu_table.txt'
172 md5 'beta_diversity_2/pearson_otu_table.txt'
173 rm -rf beta_diversity_2
174
175 #beta_diversity_through_plots
176 beta_diversity_through_plots.py \
177 --otu_table_fp 'test-data/beta_diversity_through_plots/otu_table.biom' \
178 --mapping_fp 'test-data/beta_diversity_through_plots/map.txt' \
179 --output_dir beta_diversity_through_plots \
180 --tree_fp 'test-data/beta_diversity_through_plots/rep_set.tre' \
181 --parallel
182 cp beta_diversity_through_plots/unweighted_unifrac_dm.txt 'test-data/beta_diversity_through_plots/'
183 cp beta_diversity_through_plots/unweighted_unifrac_pc.txt 'test-data/beta_diversity_through_plots/'
184 cp beta_diversity_through_plots/weighted_unifrac_dm.txt 'test-data/beta_diversity_through_plots/'
185 cp beta_diversity_through_plots/weighted_unifrac_pc.txt 'test-data/beta_diversity_through_plots/'
186 rm -rf beta_diversity_through_plots
187
188 # compare_categories
189 compare_categories.py \
190 --method 'adonis' \
191 --input_dm 'test-data/compare_categories/unweighted_unifrac_dm.txt' \
192 --mapping_file 'test-data/compare_categories/map.txt' \
193 --categories 'Treatment' \
194 -o compare_categories_1 \
195 --num_permutations '999'
196 cp compare_categories_1/adonis_results.txt "test-data/compare_categories/adonis_results.txt"
197 rm -rf compare_categories_1
198
199 compare_categories.py \
200 --method 'dbrda' \
201 --input_dm 'test-data/compare_categories/unweighted_unifrac_dm.txt' \
202 --mapping_file 'test-data/compare_categories/map.txt' \
203 --categories 'Treatment' \
204 -o compare_categories_2 \
205 --num_permutations '99'
206 cp compare_categories_2/* "test-data/compare_categories/"
207 rm -rf compare_categories_2
208
209 # core_diversity_analyses
210 core_diversity_analyses.py \
211 --input_biom_fp 'test-data/core_diversity_analyses/otu_table.biom' \
212 -o core_diversity_analyses_1 \
213 --mapping_fp 'test-data/core_diversity_analyses/map.txt' \
214 --sampling_depth 22 \
215 --tree_fp 'test-data/core_diversity_analyses/rep_set.tre'
216 cp core_diversity_analyses_1/bdiv_even22/unweighted_unifrac_pc.txt 'test-data/core_diversity_analyses/unweighted_unifrac_pc.txt'
217 rm -rf core_diversity_analyses_1
218
219 core_diversity_analyses.py \
220 --input_biom_fp 'test-data/core_diversity_analyses/otu_table.biom' \
221 -o core_diversity_analyses_2 \
222 --mapping_fp 'test-data/core_diversity_analyses/map.txt' \
223 --sampling_depth 22 \
224 --nonphylogenetic_diversity \
225 --suppress_taxa_summary \
226 --suppress_beta_diversity \
227 --suppress_alpha_diversity \
228 --suppress_group_significance
229 rm -rf core_diversity_analyses_2
230
231 # extract_barcodes
232 extract_barcodes.py \
233 --fastq1 'test-data/extract_barcodes/inseqs.fastq' \
234 --input_type 'barcode_single_end' \
235 -o extract_barcodes_1 \
236 --bc1_len '6' \
237 --rev_comp_bc1
238 rm -rf extract_barcodes_1
239
240 extract_barcodes.py \
241 --fastq1 'test-data/extract_barcodes/inseqs_R1.fastq' \
242 --input_type 'barcode_paired_end' \
243 --fastq2 'test-data/extract_barcodes/inseqs_R2.fastq' \
244 -o extract_barcodes_2 \
245 --bc1_len '6' \
246 --bc2_len '6'
247 rm -rf extract_barcodes_2
248
249 extract_barcodes.py \
250 --fastq1 'test-data/extract_barcodes/inseqs_R1.fastq' \
251 --input_type 'barcode_paired_end' \
252 --fastq2 'test-data/extract_barcodes/inseqs_R2.fastq' \
253 -o extract_barcodes_3 \
254 --bc1_len '6' \
255 --bc2_len '6' \
256 --mapping_fp 'test-data/extract_barcodes/mapping_data.txt' \
257 --attempt_read_reorientation \
258 --disable_header_match
259 rm -rf extract_barcodes_3
260
261 extract_barcodes.py \
262 --fastq1 'test-data/extract_barcodes/inseqs_R1.fastq' \
263 --input_type 'barcode_paired_stitched' \
264 -o extract_barcodes_4 \
265 --bc1_len '6' \
266 --bc2_len '8' \
267 --rev_comp_bc1 \
268 --rev_comp_bc2
269 rm -rf extract_barcodes_4
270
271 extract_barcodes.py \
272 --fastq1 'test-data/extract_barcodes/inseqs_R1.fastq' \
273 --input_type 'barcode_in_label' \
274 --char_delineator '#' \
275 -o extract_barcodes_5 \
276 --bc1_len '6'
277 rm -rf extract_barcodes_5
278
279 # filter_alignment
280 filter_alignment.py \
281 --input_fasta_file 'test-data/filter_alignment/alignment.fasta' \
282 -o 'filter_alignment_default' \
283 --allowed_gap_frac '0.999999' \
284 --threshold '3.0'
285
286 filter_alignment.py \
287 --input_fasta_file 'test-data/filter_alignment/alignment.fasta' \
288 -o 'filter_alignment_without_mask_filter_and_outliers' \
289 --suppress_lane_mask_filter \
290 --allowed_gap_frac '0.999999' \
291 --remove_outliers \
292 --threshold '3.0'
293
294 filter_alignment.py \
295 --input_fasta_file 'test-data/filter_alignment/alignment.fasta' \
296 -o 'filter_alignment_entropy' \
297 --allowed_gap_frac '0.999999' \
298 --threshold '3.0' \
299 --entropy_threshold '0.1'
300
301 # filter_fasta
302 filter_fasta.py \
303 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
304 --output_fasta_fp 'filter_fasta_otu_map.fasta' \
305 --otu_map 'test-data/filter_fasta/otu_map.txt'
306
307 filter_fasta.py \
308 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
309 --output_fasta_fp 'filter_fasta_otu_map_negate.fasta' \
310 --otu_map 'test-data/filter_fasta/otu_map.txt' \
311 --negate
312
313 filter_fasta.py \
314 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
315 --output_fasta_fp 'filter_fasta_seq_id.fasta' \
316 --seq_id_fp 'test-data/filter_fasta/seqs_to_keep.txt'
317
318 filter_fasta.py \
319 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
320 --output_fasta_fp 'filter_fasta_otu_table.fasta' \
321 --biom_fp 'test-data/filter_fasta/otu_table.biom'
322
323 filter_fasta.py \
324 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
325 --output_fasta_fp 'filter_fasta_subject_fasta.fasta' \
326 --subject_fasta_fp 'test-data/filter_fasta/sl_inseqs.fasta'
327
328 filter_fasta.py \
329 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
330 --output_fasta_fp 'filter_fasta_seq_id_prefix.fasta' \
331 --seq_id_prefix 'S5'
332
333 filter_fasta.py \
334 --input_fasta_fp 'test-data/filter_fasta/inseqs.fasta' \
335 --output_fasta_fp 'filter_fasta_sample_id.fasta' \
336 --sample_id_fp 'test-data/filter_fasta/map.txt'
337
338 # filter_otus_from_otu_table
339 filter_otus_from_otu_table.py \
340 --input_fp 'test-data/filter_otus_from_otu_table/otu_table.biom' \
341 --min_count '2' \
342 --max_count '1000' \
343 --min_samples '5' \
344 --max_samples '350' \
345 --output_fp 'test-data/filter_otus_from_otu_table/filtered_otu_table.biom'
346
347 filter_otus_from_otu_table.py \
348 --input_fp 'test-data/filter_otus_from_otu_table/otu_table.biom' \
349 --otu_ids_to_exclude_fp 'test-data/filter_otus_from_otu_table/chimeric_otus.txt' \
350 --output_fp 'test-data/filter_otus_from_otu_table/chimera_filtered_otu_table.biom'
351
352 filter_otus_from_otu_table.py \
353 --input_fp 'test-data/filter_otus_from_otu_table/otu_table.biom' \
354 --otu_ids_to_exclude_fp 'test-data/filter_otus_from_otu_table/chimeric_otus.txt' \
355 --negate_ids_to_exclude \
356 --output_fp 'test-data/filter_otus_from_otu_table/chimera_picked_otu_table.biom'
357
358 # filter_samples_from_otu_table
359 filter_samples_from_otu_table.py \
360 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
361 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
362 --min_count '150'
363 biom convert \
364 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
365 -o 'test-data/filter_samples_from_otu_table/abundance_min.biom' \
366 --to-json
367 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
368
369 filter_samples_from_otu_table.py \
370 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
371 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
372 --min_count '0' \
373 --max_count '149'
374 biom convert \
375 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
376 -o 'test-data/filter_samples_from_otu_table/abundance_max.biom' \
377 --to-json
378 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
379
380 filter_samples_from_otu_table.py \
381 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
382 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
383 --mapping_fp 'test-data/filter_samples_from_otu_table/map.txt' \
384 --output_mapping_fp 'test-data/filter_samples_from_otu_table/metadata_positive.txt' \
385 -s 'Treatment:Control'
386 biom convert \
387 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
388 -o 'test-data/filter_samples_from_otu_table/metadata_positive.biom' \
389 --to-json
390 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
391
392 filter_samples_from_otu_table.py \
393 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
394 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
395 --mapping_fp 'test-data/filter_samples_from_otu_table/map.txt' \
396 -s 'Treatment:*,!Control'
397 biom convert \
398 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
399 -o 'test-data/filter_samples_from_otu_table/metadata_negative.biom' \
400 --to-json
401 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
402
403 filter_samples_from_otu_table.py \
404 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
405 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
406 --sample_id_fp 'test-data/filter_samples_from_otu_table/ids.txt'
407 biom convert \
408 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
409 -o 'test-data/filter_samples_from_otu_table/id_positive.biom' \
410 --to-json
411 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
412
413 filter_samples_from_otu_table.py \
414 --input_fp 'test-data/filter_samples_from_otu_table/otu_table.biom' \
415 --output_fp 'test-data/filter_samples_from_otu_table/tmp.biom' \
416 --sample_id_fp 'test-data/filter_samples_from_otu_table/ids.txt' \
417 --negate_sample_id_fp
418 biom convert \
419 -i 'test-data/filter_samples_from_otu_table/tmp.biom' \
420 -o 'test-data/filter_samples_from_otu_table/id_negative.biom' \
421 --to-json
422 rm 'test-data/filter_samples_from_otu_table/tmp.biom'
423
424 # filter_taxa_from_otu_table
425 filter_taxa_from_otu_table.py \
426 --input_otu_table_fp 'test-data/filter_taxa_from_otu_table/otu_table.biom' \
427 --output_otu_table_fp 'test-data/filter_taxa_from_otu_table/tmp.biom' \
428 --positive_taxa 'p__Bacteroidetes,p__Firmicutes' \
429 --metadata_field 'taxonomy'
430 biom convert \
431 -i 'test-data/filter_taxa_from_otu_table/tmp.biom' \
432 -o 'test-data/filter_taxa_from_otu_table/positive_taxa.biom' \
433 --to-json
434 rm 'test-data/filter_taxa_from_otu_table/tmp.biom'
435
436 filter_taxa_from_otu_table.py \
437 --input_otu_table_fp 'test-data/filter_taxa_from_otu_table/otu_table.biom' \
438 --output_otu_table_fp 'test-data/filter_taxa_from_otu_table/tmp.biom' \
439 --negative_taxa 'p__Bacteroidetes,p__Firmicutes' \
440 --metadata_field 'taxonomy'
441 biom convert \
442 -i 'test-data/filter_taxa_from_otu_table/tmp.biom' \
443 -o 'test-data/filter_taxa_from_otu_table/negative_taxa.biom' \
444 --to-json
445 rm 'test-data/filter_taxa_from_otu_table/tmp.biom'
446
447 filter_taxa_from_otu_table.py \
448 --input_otu_table_fp 'test-data/filter_taxa_from_otu_table/otu_table.biom' \
449 --output_otu_table_fp 'test-data/filter_taxa_from_otu_table/tmp.biom' \
450 --positive_taxa 'p__Firmicutes' \
451 --negative_taxa 'c__Clostridia' \
452 --metadata_field 'taxonomy'
453 biom convert \
454 -i 'test-data/filter_taxa_from_otu_table/tmp.biom' \
455 -o 'test-data/filter_taxa_from_otu_table/positive_negative_taxa.biom' \
456 --to-json
457 rm 'test-data/filter_taxa_from_otu_table/tmp.biom'
458
459 # jackknifed_beta_diversity
460 jackknifed_beta_diversity.py \
461 --otu_table_fp 'test-data/jackknifed_beta_diversity/otu_table.biom' \
462 --mapping_fp 'test-data/jackknifed_beta_diversity/map.txt' \
463 -o jackknifed_beta_diversity \
464 --seqs_per_sample '10' \
465 --tree_fp 'test-data/jackknifed_beta_diversity/rep_set.tre' \
466 --master_tree 'consensus' \
467 --parallel
468 rm -rf jackknifed_beta_diversity
469
470 # make_emperor
471 cp 'test-data/core_diversity_analyses/unweighted_unifrac_pc.txt' 'test-data/make_emperor/unweighted_unifrac_pc.txt'
472 cp 'test-data/core_diversity_analyses/map.txt' 'test-data/make_emperor/map.txt'
473 cp 'test-data/summarize_taxa/2_L3.txt' 'test-data/make_emperor/2_L3.txt'
474
475 make_emperor.py \
476 --input_coords 'test-data/make_emperor/unweighted_unifrac_pc.txt' \
477 -o make_emperor_1 \
478 --map_fp 'test-data/make_emperor/map.txt' \
479 --number_of_axes '10' \
480 --add_unique_columns \
481 --number_of_segments 8
482 rm -rf make_emperor_1
483
484 make_emperor.py \
485 --input_coords 'test-data/make_emperor/unweighted_unifrac_pc.txt' \
486 -o make_emperor_2 \
487 --map_fp 'test-data/make_emperor/map.txt' \
488 --number_of_axes '10' \
489 --add_unique_columns \
490 --number_of_segments 8 \
491 --taxa_fp 'test-data/make_emperor/2_L3.txt' \
492 --n_taxa_to_keep 10
493 rm -rf make_emperor_2
494
495 # make_otu_heatmap
496 make_otu_heatmap.py \
497 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
498 --imagetype 'pdf' \
499 --color_scheme "YlGn" \
500 --width "5" \
501 --height "5" \
502 --dpi "200" \
503 --obs_md_category "taxonomy" \
504 --output_fp 'test-data/make_otu_heatmap/basic_heatmap.pdf'
505
506 make_otu_heatmap.py \
507 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
508 --imagetype 'png' \
509 --color_scheme "YlGn" \
510 --width "5" \
511 --height "5" \
512 --dpi "200" \
513 --obs_md_category "taxonomy" \
514 --output_fp 'test-data/make_otu_heatmap/basic_heatmap.png'
515
516 make_otu_heatmap.py \
517 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
518 --imagetype 'svg' \
519 --color_scheme "YlGn" \
520 --width "5" \
521 --height "5" \
522 --dpi "200" \
523 --obs_md_category "taxonomy" \
524 --output_fp 'test-data/make_otu_heatmap/basic_heatmap.svg'
525
526 make_otu_heatmap.py \
527 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
528 --map_fname 'test-data/make_otu_heatmap/mapping_file.txt' \
529 --imagetype 'pdf' \
530 --color_scheme "YlGn" \
531 --width "5" \
532 --height "5" \
533 --dpi "200" \
534 --obs_md_category "taxonomy" \
535 --output_fp 'test-data/make_otu_heatmap/sample_sorted_heatmap.pdf'
536
537 make_otu_heatmap.py \
538 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
539 --map_fname 'test-data/make_otu_heatmap/mapping_file.txt' \
540 --otu_tree 'test-data/make_otu_heatmap/rep_set.tre' \
541 --imagetype 'pdf' \
542 --color_scheme "YlGn" \
543 --width "5" \
544 --height "5" \
545 --dpi "200" \
546 --obs_md_category "taxonomy" \
547 --output_fp 'test-data/make_otu_heatmap/sample_otu_sorted_heatmap.pdf'
548
549 make_otu_heatmap.py \
550 --otu_table_fp 'test-data/make_otu_heatmap/otu_table.biom' \
551 --map_fname 'test-data/make_otu_heatmap/mapping_file.txt' \
552 --category "Treatment" \
553 --imagetype 'pdf' \
554 --color_scheme "YlGn" \
555 --width "5" \
556 --height "5" \
557 --dpi "200" \
558 --obs_md_category "taxonomy" \
559 --output_fp 'test-data/make_otu_heatmap/treatment_sample_sorted_heatmap.pdf'
560
561 # make_phylogeny
562 make_phylogeny.py \
563 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
564 --result_fp 'test-data/make_phylogeny/fasttree_tree_method_default.tre' \
565 --tree_method 'fasttree' \
566 --log_fp 'fasttree_tree_method_default.txt' \
567 --root_method 'tree_method_default'
568
569 make_phylogeny.py \
570 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
571 --result_fp 'raxml_v730.tre' \
572 --tree_method 'raxml_v730' \
573 --log_fp 'raxml_v730.txt' \
574 --root_method 'tree_method_default'
575
576 make_phylogeny.py \
577 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
578 --result_fp 'test-data/make_phylogeny/muscle.tre' \
579 --tree_method 'muscle' \
580 --log_fp 'muscle.txt' \
581 --root_method 'tree_method_default'
582
583 make_phylogeny.py \
584 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
585 --result_fp 'test-data/make_phylogeny/clustalw.tre' \
586 --tree_method 'clustalw' \
587 --log_fp 'clustalw.txt' \
588 --root_method 'tree_method_default'
589
590 make_phylogeny.py \
591 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
592 --result_fp 'clearcut.tre' \
593 --tree_method 'clearcut' \
594 --log_fp 'clearcut.txt' \
595 --root_method 'tree_method_default'
596
597 make_phylogeny.py \
598 --input_fp 'test-data/make_phylogeny/aligned.fasta' \
599 --result_fp 'test-data/make_phylogeny/fasttree_midpoint.tre' \
600 --tree_method 'fasttree' \
601 --log_fp 'fasttree_midpoint.txt' \
602 --root_method 'midpoint'
603
604 # multiple_join_paired_ends
605 multiple_join_paired_ends.py \
606 --input_dir 'test-data/multiple_join_paired_ends/without_barcode/' \
607 --output_dir 'test-data/multiple_join_paired_ends/output_without_barcode' \
608 --read1_indicator 'forward_' \
609 --read2_indicator 'reverse_' \
610 --leading_text '' \
611 --trailing_text ''
612
613 #multiple_join_paired_ends.py \
614 # --input_dir 'test-data/multiple_join_paired_ends/without_barcode/' \
615 # --output_dir 'multiple_join_paired_ends_without_barcode_parameter_files' \
616 # --parameter_fp 'test-data/multiple_join_paired_ends/qiime_parameters.txt' \
617 # --read1_indicator '_R1_' \
618 # --read2_indicator '_R2_' \
619 # --leading_text '' \
620 # --trailing_text ''
621
622 multiple_join_paired_ends.py \
623 --input_dir 'test-data/multiple_join_paired_ends/with_barcode/' \
624 --output_dir 'test-data/multiple_join_paired_ends/output_with_barcode' \
625 --read1_indicator 'forward_' \
626 --read2_indicator 'reverse_' \
627 --match_barcodes \
628 --barcode_indicator 'barcode_' \
629 --leading_text '' \
630 --trailing_text ''
631
632 # multiple_split_libraries_fastq
633 multiple_split_libraries_fastq.py \
634 --input_dir 'test-data/multiple_split_libraries_fastq/input' \
635 --output_dir 'multiple_split_libraries_fastq' \
636 --demultiplexing_method 'mapping_barcode_files' \
637 --read_indicator 'reads_' \
638 --barcode_indicator 'barcodes_' \
639 --mapping_indicator 'mapping_' \
640 --mapping_extensions 'txt' \
641 --leading_text '' \
642 --trailing_text '' \
643 --sampleid_indicator '.'
644
645 multiple_split_libraries_fastq.py \
646 --input_dir 'test-data/multiple_split_libraries_fastq/input' \
647 --output_dir 'multiple_split_libraries_fastq_with_parameter_file' \
648 --demultiplexing_method 'mapping_barcode_files' \
649 --parameter_fp 'test-data/multiple_split_libraries_fastq/qiime_parameters.txt' \
650 --read_indicator 'reads_' \
651 --barcode_indicator 'barcodes_' \
652 --mapping_indicator 'mapping_' \
653 --mapping_extensions 'txt' \
654 --leading_text '' \
655 --trailing_text '' \
656 --sampleid_indicator '.'
657
658 # pick_closed_reference_otus
659 pick_closed_reference_otus.py \
660 --input_fp 'test-data/pick_closed_reference_otus/seqs.fna' \
661 --output_dir 'pick_closed_reference_otus' \
662 --reference_fp 'test-data/pick_closed_reference_otus/refseqs.fna' \
663 --taxonomy_fp 'test-data/pick_closed_reference_otus/taxa.txt'
664 biom convert \
665 -i 'pick_closed_reference_otus/otu_table.biom' \
666 -o 'test-data/pick_closed_reference_otus/basic_otu_table.biom' \
667 --to-json
668
669 pick_closed_reference_otus.py \
670 --input_fp 'test-data/pick_closed_reference_otus/seqs.fna' \
671 --output_dir 'pick_closed_reference_otus_sortmerna' \
672 --reference_fp 'test-data/pick_closed_reference_otus/refseqs.fna' \
673 --taxonomy_fp 'test-data/pick_closed_reference_otus/taxa.txt' \
674 --parameter_fp 'test-data/pick_closed_reference_otus/sortmerna_params.txt'
675 biom convert \
676 -i 'pick_closed_reference_otus_sortmerna/otu_table.biom' \
677 -o 'test-data/pick_closed_reference_otus/sortmerna_otu_table.biom' \
678 --to-json
679
680 pick_closed_reference_otus.py \
681 --input_fp 'test-data/pick_closed_reference_otus/seqs.fna' \
682 --output_dir 'pick_closed_reference_otus_assign_taxonomy' \
683 --reference_fp 'test-data/pick_closed_reference_otus/refseqs.fna' \
684 --assign_taxonomy
685 biom convert \
686 -i 'pick_closed_reference_otus_assign_taxonomy/otu_table.biom' \
687 -o 'test-data/pick_closed_reference_otus/assign_taxonomy_otu_table.biom' \
688 --to-json
689
690 pick_closed_reference_otus.py \
691 --input_fp 'test-data/pick_closed_reference_otus/seqs.fna' \
692 --output_dir 'pick_closed_reference_otus_suppress_taxonomy_assignment' \
693 --reference_fp 'test-data/pick_closed_reference_otus/refseqs.fna' \
694 --suppress_taxonomy_assignment
695 biom convert \
696 -i 'pick_closed_reference_otus_suppress_taxonomy_assignment/otu_table.biom' \
697 -o 'test-data/pick_closed_reference_otus/suppress_taxonomy_assignment_otu_table.biom' \
698 --to-json
699
700 # pick_open_reference_otus
701 pick_open_reference_otus.py \
702 --input_fps 'test-data/pick_open_reference_otus/sequences.fasta' \
703 -o pick_open_reference_otus_1 \
704 --reference_fp 'test-data/gg_13_8_79_otus.fasta' \
705 --otu_picking_method 'uclust' \
706 --new_ref_set_id 'New' \
707 --parallel \
708 --percent_subsample '0.001' \
709 --prefilter_percent_id '0.0' \
710 --minimum_failure_threshold '100000' \
711 --min_otu_size '2'
712 cp pick_open_reference_otus_1/final_otu_map.txt 'test-data/pick_open_reference_otus/1_final_otu_map.txt'
713 cp pick_open_reference_otus_1/final_otu_map_mc*.txt 'test-data/pick_open_reference_otus/1_final_otu_map_mc.txt'
714 cp pick_open_reference_otus_1/rep_set.tre 'test-data/pick_open_reference_otus/1_rep_set_tree.tre'
715 rm -rf pick_open_reference_otus_1
716
717 pick_open_reference_otus.py \
718 --input_fps 'test-data/pick_open_reference_otus/sequences.fasta' \
719 -o pick_open_reference_otus_2 \
720 --reference_fp 'test-data/gg_13_8_79_otus.fasta' \
721 --otu_picking_method 'uclust' \
722 --new_ref_set_id 'New' \
723 --parallel \
724 --percent_subsample '0.001' \
725 --prefilter_percent_id '0.0' \
726 --minimum_failure_threshold '100000' \
727 --min_otu_size '3' \
728 --suppress_taxonomy_assignment \
729 --suppress_align_and_tree
730 cp pick_open_reference_otus_2/final_otu_map.txt 'test-data/pick_open_reference_otus/2_final_otu_map.txt'
731 cp pick_open_reference_otus_2/final_otu_map_mc*.txt 'test-data/pick_open_reference_otus/2_final_otu_map_mc.txt'
732 rm -rf pick_open_reference_otus_2
733
734 pick_open_reference_otus.py \
735 --input_fps 'test-data/pick_open_reference_otus/sequences.fasta' \
736 -o pick_open_reference_otus_3 \
737 --reference_fp 'test-data/gg_13_8_79_otus.fasta' \
738 --otu_picking_method 'uclust' \
739 --new_ref_set_id 'New' \
740 --parallel \
741 --percent_subsample '0.001' \
742 --prefilter_percent_id '0.0' \
743 --minimum_failure_threshold '100000' \
744 --min_otu_size '10' \
745 --suppress_taxonomy_assignment
746 cp pick_open_reference_otus_3/final_otu_map.txt 'test-data/pick_open_reference_otus/3_final_otu_map.txt'
747 cp pick_open_reference_otus_3/final_otu_map_mc*.txt 'test-data/pick_open_reference_otus/3_final_otu_map_mc.txt'
748 cp pick_open_reference_otus_3/rep_set.tre 'test-data/pick_open_reference_otus/3_rep_set_tree.tre'
749 rm -rf pick_open_reference_otus_3
750
751 # pick_otus
752 pick_otus.py \
753 -i 'test-data/pick_otus/seqs.fna' \
754 -o 'pick_otus_uclust' \
755 --otu_picking_method 'uclust' \
756 --similarity "0.97" \
757 --denovo_otu_id_prefix "denovo" \
758 --max_accepts "1" \
759 --max_rejects "8" \
760 --stepwords "8" \
761 --word_length "8" \
762 --non_chimeras_retention "union"
763
764 pick_otus.py \
765 -i 'test-data/pick_otus/seqs.fna' \
766 -o 'pick_otus_sortmerna' \
767 --otu_picking_method "sortmerna" \
768 --refseqs_fp "test-data/pick_otus/refseqs.fasta" \
769 --sortmerna_e_value "1" \
770 --sortmerna_coverage "0.97" \
771 --sortmerna_tabular \
772 --sortmerna_best_N_alignments "1" \
773 --sortmerna_max_pos "10000" \
774 --similarity "0.97" \
775 --non_chimeras_retention "union"
776
777 #pick_otus.py \
778 # -i 'test-data/pick_otus/seqs.fna' \
779 # -o 'pick_otus_mothur' \
780 # --otu_picking_method "mothur" \
781 # --clustering_algorithm "furthest" \
782 # --non_chimeras_retention "union"
783
784 pick_otus.py \
785 -i 'test-data/pick_otus/seqs.fna' \
786 -o 'pick_otus_trie' \
787 --otu_picking_method "trie" \
788 --non_chimeras_retention "union"
789
790 pick_otus.py \
791 -i 'test-data/pick_otus/seqs.fna' \
792 -o 'pick_otus_uclust_ref' \
793 --otu_picking_method "uclust_ref" \
794 --refseqs_fp "test-data/pick_otus/refseqs.fasta" \
795 --similarity "0.97" \
796 --max_accepts "1" \
797 --max_rejects "8" \
798 --stepwords "8" \
799 --word_length "8" \
800 --non_chimeras_retention "union"
801
802 #pick_otus.py \
803 # -i 'test-data/pick_otus/seqs.fna' \
804 # -o 'pick_otus_blast' \
805 # --otu_picking_method "blast" \
806 # --refseqs_fp "test-data/pick_otus/refseqs.fasta" \
807 # --similarity "0.97" \
808 # --max_e_value_blast "1e-10" \
809 # --min_aligned_percent "0.5" \
810 # --non_chimeras_retention "union"
811
812 # pick_otus.py \
813 # -i 'test-data/pick_otus/seqs.fna' \
814 # -o 'pick_otus_sumaclust' \
815 # --otu_picking_method "sumaclust" \
816 # --similarity "0.97" \
817 # --sumaclust_l \
818 # --denovo_otu_id_prefix "denovo" \
819 # --non_chimeras_retention "union"
820
821 pick_otus.py \
822 -i 'test-data/pick_otus/seqs.fna' \
823 -o 'pick_otus_swarm' \
824 --otu_picking_method "swarm" \
825 --denovo_otu_id_prefix "denovo" \
826 --swarm_resolution "1" \
827 --non_chimeras_retention "union"
828
829 pick_otus.py \
830 -i 'test-data/pick_otus/seqs.fna' \
831 -o 'pick_otus_prefix_suffix' \
832 --otu_picking_method "prefix_suffix" \
833 --prefix_length "50" \
834 --suffix_length "50" \
835 --non_chimeras_retention "union"
836
837 pick_otus.py \
838 -i 'test-data/pick_otus/seqs.fna' \
839 -o 'pick_otus_cdhit' \
840 --otu_picking_method "cdhit" \
841 --similarity "0.97" \
842 --non_chimeras_retention "union"
843
844 pick_otus.py \
845 -i 'test-data/pick_otus/seqs.fna' \
846 -o 'pick_otus_uclust_intersection' \
847 --otu_picking_method "uclust" \
848 --similarity "0.97" \
849 --denovo_otu_id_prefix "denovo" \
850 --max_accepts "1" \
851 --max_rejects "8" \
852 --stepwords "8" \
853 --word_length "8" \
854 --non_chimeras_retention "intersection"
855
856 # pick_rep_set
857 pick_rep_set.py \
858 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
859 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
860 --rep_set_picking_method 'first' \
861 --sort_by 'otu' \
862 --result_fp 'test-data/pick_rep_set/first_otu_fasta.fasta' \
863 --log_fp 'test-data/pick_rep_set/first_otu_fasta.txt'
864
865 pick_rep_set.py \
866 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
867 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
868 --reference_seqs_fp 'test-data/pick_rep_set/refseqs.fasta' \
869 --rep_set_picking_method 'first' \
870 --sort_by 'otu' \
871 --result_fp 'test-data/pick_rep_set/first_otu_fasta_ref.fasta' \
872 --log_fp 'test-data/pick_rep_set/first_otu_fasta_ref.txt'
873
874 pick_rep_set.py \
875 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
876 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
877 --rep_set_picking_method 'longest' \
878 --sort_by 'otu' \
879 --result_fp 'test-data/pick_rep_set/longest_otu_fasta.fasta' \
880 --log_fp 'test-data/pick_rep_set/longest_otu_fasta.txt'
881
882 pick_rep_set.py \
883 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
884 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
885 --rep_set_picking_method 'most_abundant' \
886 --sort_by 'otu' \
887 --result_fp 'test-data/pick_rep_set/most_abundant_otu_fasta.fasta' \
888 --log_fp 'test-data/pick_rep_set/most_abundant_otu_fasta.txt'
889
890 pick_rep_set.py \
891 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
892 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
893 --rep_set_picking_method 'random' \
894 --sort_by 'otu' \
895 --result_fp 'test-data/pick_rep_set/random_otu_fasta.fasta' \
896 --log_fp 'test-data/pick_rep_set/random_otu_fasta.txt'
897
898 pick_rep_set.py \
899 --input_file 'test-data/pick_rep_set/seqs_otus.txt' \
900 --fasta_file 'test-data/pick_rep_set/seqs.fna' \
901 --rep_set_picking_method 'first' \
902 --sort_by 'seq_id' \
903 --result_fp 'test-data/pick_rep_set/first_seq_id_fasta.fasta' \
904 --log_fp 'test-data/pick_rep_set/first_seq_id_fasta.txt'
905
906 # plot_taxa_summary
907 plot_taxa_summary.py \
908 --counts_fname 'test-data/plot_taxa_summary/phylum.txt' \
909 --dir_path 'test-data/plot_taxa_summary/phylum' \
910 --labels 'phylum' \
911 --num_categories '20' \
912 --background_color 'white' \
913 --dpi '80' \
914 --x_width '12' \
915 --y_height '12' \
916 --bar_width '0.75' \
917 --type_of_file 'png' \
918 --chart_type 'area,bar,pie' \
919 --resize_nth_label '0' \
920 --label_type 'categorical'
921
922 plot_taxa_summary.py \
923 --counts_fname 'test-data/plot_taxa_summary/phylum.txt,test-data/plot_taxa_summary/class.txt,test-data/plot_taxa_summary/genus.txt' \
924 --dir_path 'test-data/plot_taxa_summary/phylum_class_genus' \
925 --labels 'Phylum,Class,Genus' \
926 --num_categories '20' \
927 --background_color 'white' \
928 --dpi '80' \
929 --x_width '12' \
930 --y_height '12' \
931 --bar_width '0.75' \
932 --type_of_file 'png' \
933 --chart_type 'area,bar,pie' \
934 --resize_nth_label '0' \
935 --label_type 'categorical'
936
937 plot_taxa_summary.py \
938 --counts_fname 'test-data/plot_taxa_summary/class.txt' \
939 --dir_path 'test-data/plot_taxa_summary/class' \
940 --labels 'Class' \
941 --num_categories '10' \
942 --background_color 'white' \
943 --dpi '80' \
944 --x_width '12' \
945 --y_height '12' \
946 --bar_width '0.75' \
947 --chart_type 'pie' \
948 --type_of_file 'svg' \
949 --include_html_legend \
950 --resize_nth_label '0' \
951 --label_type 'categorical'
952
953 plot_taxa_summary.py \
954 --counts_fname 'test-data/plot_taxa_summary/class.txt' \
955 --dir_path 'test-data/plot_taxa_summary/class_colorby' \
956 --labels 'Class' \
957 --num_categories '20' \
958 --colorby 'PC.636,PC.635' \
959 --background_color 'white' \
960 --dpi '80' \
961 --x_width '12' \
962 --y_height '12' \
963 --bar_width '0.75' \
964 --type_of_file 'pdf' \
965 --chart_type 'area,bar,pie' \
966 --resize_nth_label '0' \
967 --label_type 'categorical'
968
969 # split_libraries
970 split_libraries.py \
971 --map 'test-data/split_libraries/mapping_file.txt' \
972 -o split_libraries \
973 --fasta 'test-data/split_libraries/reads_1.fna,test-data/split_libraries/reads_2.fna' \
974 --qual 'test-data/split_libraries/reads_1.qual,test-data/split_libraries/reads_2.qual' \
975 --min_qual_score 25 \
976 --qual_score_window 0 \
977 --record_qual_scores \
978 --min_seq_length 200 \
979 --max_seq_length 1000 \
980 --max_ambig 6 \
981 --max_homopolymer 6 \
982 --max_primer_mismatch 0 \
983 --barcode_type 'golay_12' \
984 --max_barcode_errors 1.5 \
985 --start_numbering_at 1
986 cp split_libraries/seqs.fna 'test-data/split_libraries/seqs.fna'
987 cp split_libraries/split_library_log.txt 'test-data/split_libraries/split_library_log'
988 cp split_libraries/histograms.txt 'test-data/split_libraries/histograms.txt'
989 cp split_libraries/seqs_filtered.qual 'test-data/split_libraries/seqs_filtered.qual'
990 rm -rf split_libraries
991
992 # split_libraries_fastq
993 split_libraries_fastq.py \
994 --sequence_read_fps 'test-data/split_libraries_fastq/lane1_read1.fastq.gz' \
995 -o split_libraries_1 \
996 --mapping_fps 'test-data/split_libraries_fastq/map.txt' \
997 --barcode_read_fps 'test-data/split_libraries_fastq/lane1_barcode.fastq.gz' \
998 --max_bad_run_length 3 \
999 --min_per_read_length_fraction 0.75 \
1000 --sequence_max_n 0 \
1001 --start_seq_id 0 \
1002 --rev_comp_mapping_barcodes \
1003 --phred_quality_threshold 19 \
1004 --barcode_type 'golay_12' \
1005 --max_barcode_errors 1.5
1006 rm -rf split_libraries_1
1007
1008 split_libraries_fastq.py \
1009 --sequence_read_fps 'test-data/split_libraries_fastq/lane1_read1.fastq.gz' \
1010 -o split_libraries_2 \
1011 --mapping_fps 'test-data/split_libraries_fastq/map.txt' \
1012 --barcode_read_fps 'test-data/split_libraries_fastq/lane1_barcode.fastq.gz' \
1013 --store_qual_scores \
1014 --store_demultiplexed_fastq \
1015 --max_bad_run_length 3 \
1016 --min_per_read_length_fraction 0.75 \
1017 --sequence_max_n 0 \
1018 --start_seq_id 0 \
1019 --rev_comp_mapping_barcodes \
1020 --phred_quality_threshold 19 \
1021 --barcode_type 'golay_12' \
1022 --max_barcode_errors 1.5
1023 rm -rf split_libraries_2
1024
1025 split_libraries_fastq.py \
1026 --sequence_read_fps 'test-data/split_libraries_fastq/lane1_read1.fastq.gz,test-data/split_libraries_fastq/lane2_read1.fastq.gz' \
1027 -o split_libraries_3 \
1028 --mapping_fps 'test-data/split_libraries_fastq/map.txt,test-data/split_libraries_fastq/map.txt' \
1029 --barcode_read_fps 'test-data/split_libraries_fastq/lane1_barcode.fastq.gz,test-data/split_libraries_fastq/lane2_barcode.fastq.gz' \
1030 --max_bad_run_length 3 \
1031 --min_per_read_length_fraction 0.75 \
1032 --sequence_max_n 0 \
1033 --start_seq_id 0 \
1034 --rev_comp_mapping_barcodes \
1035 --phred_quality_threshold 19 \
1036 --barcode_type 'golay_12' \
1037 --max_barcode_errors 1.5
1038 rm -rf split_libraries_3
1039
1040 split_libraries_fastq.py \
1041 --sequence_read_fps 'test-data/split_libraries_fastq/lane1_read1.fastq.gz' \
1042 -o split_libraries_4 \
1043 --sample_ids 'my.sample.1' \
1044 --max_bad_run_length 3 \
1045 --min_per_read_length_fraction 0.75 \
1046 --sequence_max_n 0 \
1047 --start_seq_id 0 \
1048 --rev_comp_mapping_barcodes \
1049 --phred_quality_threshold 19 \
1050 --barcode_type 'not-barcoded' \
1051 --max_barcode_errors 1.5
1052 rm -rf split_libraries_4
1053
1054 split_libraries_fastq.py \
1055 --sequence_read_fps 'test-data/split_libraries_fastq/lane1_read1.fastq.gz,test-data/split_libraries_fastq/lane2_read1.fastq.gz' \
1056 -o split_libraries_5 \
1057 --sample_ids 'my.sample.1,my.sample.2' \
1058 --max_bad_run_length 3 \
1059 --min_per_read_length_fraction 0.75 \
1060 --sequence_max_n 0 \
1061 --start_seq_id 0 \
1062 --rev_comp_mapping_barcodes \
1063 --phred_quality_threshold 19 \
1064 --barcode_type 'not-barcoded' \
1065 --max_barcode_errors 1.5
1066 rm -rf split_libraries_5
1067
1068 # summarize_taxa
1069 cp 'test-data/core_diversity_analyses/otu_table.biom' 'test-data/summarize_taxa/otu_table.biom'
1070 cp 'test-data/core_diversity_analyses/map.txt' 'test-data/summarize_taxa/map.txt'
1071
1072 summarize_taxa.py \
1073 -i 'test-data/summarize_taxa/otu_table.biom' \
1074 -o summarize_taxa_1 \
1075 -L '2,3,4,5,6' \
1076 -m 'test-data/summarize_taxa/map.txt' \
1077 --md_identifier "taxonomy" \
1078 --delimiter ";"
1079 cp summarize_taxa_1/*_L2.txt "test-data/summarize_taxa/1_L2.txt"
1080 cp summarize_taxa_1/*_L3.txt "test-data/summarize_taxa/1_L3.txt"
1081 cp summarize_taxa_1/*_L4.txt "test-data/summarize_taxa/1_L4.txt"
1082 cp summarize_taxa_1/*_L5.txt "test-data/summarize_taxa/1_L5.txt"
1083 cp summarize_taxa_1/*_L6.txt "test-data/summarize_taxa/1_L6.txt"
1084 rm -rf summarize_taxa_1
1085
1086 summarize_taxa.py \
1087 -i 'test-data/summarize_taxa/otu_table.biom' \
1088 -o summarize_taxa_2 \
1089 -L '3,6' \
1090 --md_identifier "taxonomy" \
1091 --delimiter ";"
1092 cp summarize_taxa_2/*_L3.txt "test-data/summarize_taxa/2_L3.txt"
1093 cp summarize_taxa_2/*_L6.txt "test-data/summarize_taxa/2_L6.txt"
1094 rm -rf summarize_taxa_2
1095
1096 # summarize_taxa_through_plots
1097 summarize_taxa_through_plots.py \
1098 --otu_table_fp 'test-data/summarize_taxa_through_plots/otu_table.biom' \
1099 --output_dir summarize_taxa_through_plots_mapping \
1100 --mapping_fp 'test-data/summarize_taxa_through_plots/Fasting_Map.txt'
1101 biom convert \
1102 -i 'summarize_taxa_through_plots_mapping/otu_table_L2.biom' \
1103 -o 'summarize_taxa_through_plots_mapping/otu_table_L2_json.biom' \
1104 --to-json
1105 biom convert \
1106 -i 'summarize_taxa_through_plots_mapping/otu_table_L3.biom' \
1107 -o 'summarize_taxa_through_plots_mapping/otu_table_L3_json.biom' \
1108 --to-json
1109 biom convert \
1110 -i 'summarize_taxa_through_plots_mapping/otu_table_L4.biom' \
1111 -o 'summarize_taxa_through_plots_mapping/otu_table_L4_json.biom' \
1112 --to-json
1113 biom convert \
1114 -i 'summarize_taxa_through_plots_mapping/otu_table_L5.biom' \
1115 -o 'summarize_taxa_through_plots_mapping/otu_table_L5_json.biom' \
1116 --to-json
1117 biom convert \
1118 -i 'summarize_taxa_through_plots_mapping/otu_table_L6.biom' \
1119 -o 'summarize_taxa_through_plots_mapping/otu_table_L6_json.biom' \
1120 --to-json
1121 cp summarize_taxa_through_plots_mapping/*.txt test-data/summarize_taxa_through_plots/mapping/
1122 cp summarize_taxa_through_plots_mapping/*_json.biom test-data/summarize_taxa_through_plots/mapping/
1123 cp summarize_taxa_through_plots_mapping/taxa_summary_plots/area_charts.html 'test-data/summarize_taxa_through_plots/mapping/area_charts.html'
1124 cp summarize_taxa_through_plots_mapping/taxa_summary_plots/bar_charts.html 'test-data/summarize_taxa_through_plots/mapping/bar_charts.html'
1125
1126 summarize_taxa_through_plots.py \
1127 --otu_table_fp 'test-data/summarize_taxa_through_plots/otu_table.biom' \
1128 --output_dir summarize_taxa_through_plots_mapping_categories \
1129 --mapping_fp 'test-data/summarize_taxa_through_plots/Fasting_Map.txt' \
1130 --mapping_category 'Treatment'
1131 biom convert \
1132 -i 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L2.biom' \
1133 -o 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L2_json.biom' \
1134 --to-json
1135 biom convert \
1136 -i 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L3.biom' \
1137 -o 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L3_json.biom' \
1138 --to-json
1139 biom convert \
1140 -i 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L4.biom' \
1141 -o 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L4_json.biom' \
1142 --to-json
1143 biom convert \
1144 -i 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L5.biom' \
1145 -o 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L5_json.biom' \
1146 --to-json
1147 biom convert \
1148 -i 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L6.biom' \
1149 -o 'summarize_taxa_through_plots_mapping_categories/Treatment_otu_table_L6_json.biom' \
1150 --to-json
1151 cp summarize_taxa_through_plots_mapping_categories/*.txt test-data/summarize_taxa_through_plots/mapping_categories/
1152 cp summarize_taxa_through_plots_mapping_categories/*_json.biom test-data/summarize_taxa_through_plots/mapping_categories/
1153 cp summarize_taxa_through_plots_mapping_categories/taxa_summary_plots/area_charts.html 'test-data/summarize_taxa_through_plots/mapping_categories/area_charts.html'
1154 cp summarize_taxa_through_plots_mapping_categories/taxa_summary_plots/bar_charts.html 'test-data/summarize_taxa_through_plots/mapping_categories/bar_charts.html'
1155
1156 summarize_taxa_through_plots.py \
1157 --otu_table_fp 'test-data/summarize_taxa_through_plots/otu_table.biom' \
1158 --output_dir summarize_taxa_through_plots_mapping_sort \
1159 --mapping_fp 'test-data/summarize_taxa_through_plots/Fasting_Map.txt' \
1160 --sort
1161 biom convert \
1162 -i 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L2.biom' \
1163 -o 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L2_json.biom' \
1164 --to-json
1165 biom convert \
1166 -i 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L3.biom' \
1167 -o 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L3_json.biom' \
1168 --to-json
1169 biom convert \
1170 -i 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L4.biom' \
1171 -o 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L4_json.biom' \
1172 --to-json
1173 biom convert \
1174 -i 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L5.biom' \
1175 -o 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L5_json.biom' \
1176 --to-json
1177 biom convert \
1178 -i 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L6.biom' \
1179 -o 'summarize_taxa_through_plots_mapping_sort/otu_table_sorted_L6_json.biom' \
1180 --to-json
1181 cp summarize_taxa_through_plots_mapping_sort/*.txt test-data/summarize_taxa_through_plots/mapping_sort/
1182 cp summarize_taxa_through_plots_mapping_sort/*_json.biom test-data/summarize_taxa_through_plots/mapping_sort/
1183 cp summarize_taxa_through_plots_mapping_sort/taxa_summary_plots/area_charts.html 'test-data/summarize_taxa_through_plots/mapping_sort/area_charts.html'
1184 cp summarize_taxa_through_plots_mapping_sort/taxa_summary_plots/bar_charts.html 'test-data/summarize_taxa_through_plots/mapping_sort/bar_charts.html'
1185
1186 summarize_taxa_through_plots.py \
1187 --otu_table_fp 'test-data/summarize_taxa_through_plots/otu_table.biom' \
1188 --output_dir summarize_taxa_through_plots_without_mapping
1189 biom convert \
1190 -i 'summarize_taxa_through_plots_without_mapping/otu_table_L2.biom' \
1191 -o 'summarize_taxa_through_plots_without_mapping/otu_table_L2_json.biom' \
1192 --to-json
1193 biom convert \
1194 -i 'summarize_taxa_through_plots_without_mapping/otu_table_L3.biom' \
1195 -o 'summarize_taxa_through_plots_without_mapping/otu_table_L3_json.biom' \
1196 --to-json
1197 biom convert \
1198 -i 'summarize_taxa_through_plots_without_mapping/otu_table_L4.biom' \
1199 -o 'summarize_taxa_through_plots_without_mapping/otu_table_L4_json.biom' \
1200 --to-json
1201 biom convert \
1202 -i 'summarize_taxa_through_plots_without_mapping/otu_table_L5.biom' \
1203 -o 'summarize_taxa_through_plots_without_mapping/otu_table_L5_json.biom' \
1204 --to-json
1205 biom convert \
1206 -i 'summarize_taxa_through_plots_without_mapping/otu_table_L6.biom' \
1207 -o 'summarize_taxa_through_plots_without_mapping/otu_table_L6_json.biom' \
1208 --to-json
1209 cp summarize_taxa_through_plots_without_mapping/*.txt test-data/summarize_taxa_through_plots/without_mapping/
1210 cp summarize_taxa_through_plots_without_mapping/*_json.biom test-data/summarize_taxa_through_plots/without_mapping/
1211 cp summarize_taxa_through_plots_without_mapping/taxa_summary_plots/area_charts.html 'test-data/summarize_taxa_through_plots/without_mapping/area_charts.html'
1212 cp summarize_taxa_through_plots_without_mapping/taxa_summary_plots/bar_charts.html 'test-data/summarize_taxa_through_plots/without_mapping/bar_charts.html'
1213
1214 # upgma_cluster
1215 upgma_cluster.py \
1216 --input_path 'test-data/upgma_cluster/' \
1217 --output_path 'test-data/upgma_cluster/'
1218
1219 # validate_mapping_file
1220 validate_mapping_file.py \
1221 -m 'test-data/validate_mapping_file/map.tsv' \
1222 -o validate_mapping_file_output \
1223 -c '_'
1224 cp validate_mapping_file_output/*.html 'test-data/validate_mapping_file/map.tsv.html'
1225 cp validate_mapping_file_output/*.log 'test-data/validate_mapping_file/map.tsv.log'
1226 cp validate_mapping_file_output/*corrected.txt 'test-data/validate_mapping_file/map.tsv_corrected.txt'
1227 rm -rf validate_mapping_file_output