changeset 100:e0db1f719af1 draft

Uploaded

--- a/assembly_post_processor.py	Fri Oct 27 13:23:10 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,66 +0,0 @@
-#!/usr/bin/env python
-import argparse
-import os
-import shutil
-
-import utils
-
-OUTPUT_DIR = 'assemblyPostProcessing_dir'
-
-parser = argparse.ArgumentParser()
-parser.add_argument('--dereplicate', dest='dereplicate', default=None, help='Remove duplicate sequences')
-parser.add_argument('--gap_trimming', dest='gap_trimming', type=float, default=0, help='Trim alignments')
-parser.add_argument('--gene_family_search', dest='gene_family_search', default=None, help='Targeted gene families')
-parser.add_argument('--method', dest='method', default=None, help='Protein clustering method')
-parser.add_argument('--min_length', dest='min_length', type=int, default=0, help='Minimum sequence length')
-parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of processors')
-parser.add_argument('--output_cds', dest='output_cds', help='Output transcripts.cds')
-parser.add_argument('--output_cleaned_cds', dest='output_cleaned_cds', help='Output transcripts.cleaned.cds')
-parser.add_argument('--output_cleaned_nr_cds', dest='output_cleaned_nr_cds', default=None, help='Output transcripts.cleaned.nr.cds')
-parser.add_argument('--output_cleaned_nr_pep', dest='output_cleaned_nr_pep', default=None, help='Output transcripts.cleaned.nr.pep')
-parser.add_argument('--output_cleaned_pep', dest='output_cleaned_pep', help='Output transcripts.cleaned.pep')
-parser.add_argument('--output_pep', dest='output_pep', help='Output transcripts.pep')
-parser.add_argument('--output_targeted_gene_families_stats', dest='output_targeted_gene_families_stats', default=None, help='Targeted gene families statistics')
-parser.add_argument('--prediction_method', dest='prediction_method', help='Coding regions prediction method')
-parser.add_argument('--scaffold', dest='scaffold', default=None, help='Gene family scaffold')
-parser.add_argument('--score_matrices', dest='score_matrices', default=None, help='Scores matrices')
-parser.add_argument('--strand_specific', dest='strand_specific', default=None, help='Strand-specific assembly')
-parser.add_argument('--transcripts', dest='transcripts', help='Transcriptome assembly fasta file')
-
-args = parser.parse_args()
-
-# Build the command line.
-cmd = 'AssemblyPostProcessor'
-if args.dereplicate is not None:
-    cmd += ' --dereplicate'
-if args.gap_trimming > 0:
-    cmd += ' --gap_trimming %4f' % args.gap_trimming
-if args.gene_family_search is not None:
-    cmd += ' --gene_family_search %s' % args.gene_family_search
-if args.method is not None:
-    cmd += ' --method %s' % args.method
-if args.min_length > 0:
-    cmd += ' --min_length %d' % args.min_length
-cmd += ' --num_threads %d' % args.num_threads
-cmd += ' --prediction_method %s' % args.prediction_method
-if args.scaffold is not None:
-    cmd += ' --scaffold %s' % args.scaffold
-if args.score_matrices is not None:
-    cmd += ' --score_matrices %s' % args.score_matrices
-if args.strand_specific is not None:
-    cmd += ' --strand_specific'
-cmd += ' --transcripts %s' % args.transcripts
-# Run the command.
-utils.run_command(cmd)
-
-# Handle outputs.
-shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cds'), args.output_cds)
-shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.cds'), args.output_cleaned_cds)
-if args.output_cleaned_nr_cds is not None:
-    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.cds'), args.output_cleaned_nr_cds)
-if args.output_cleaned_nr_pep is not None:
-    shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.nr.pep'), args.output_cleaned_nr_pep)
-shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.cleaned.pep'), args.output_cleaned_pep)
-shutil.move(os.path.join(OUTPUT_DIR, 'transcripts.pep'), args.output_pep)
-if args.output_targeted_gene_families_stats is not None:
-    shutil.move(os.path.join(OUTPUT_DIR, 'targeted_gene_family_assemblies.stats'), args.output_targeted_gene_families_stats)

--- a/test-data/output.pttgf	Fri Oct 27 13:23:10 2017 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-<html><head><h3>Targeted gene families: 1 items</h3></head>
-<body><p/><table cellpadding="2">
-<tr><b>Directories</th></b>
-<tr bgcolor="#D8D8D8"><td><a href="752" type="text/plain">752</a>
-</td></tr>
-</table></body></html>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output_targeted_gene_families_stats.tabular	Mon Oct 30 08:51:22 2017 -0400
@@ -0,0 +1,7 @@
+# seq_id = sequence identity
+# cov = sequence coverage in the orthogroup trimmed protein alignment
+# avg_cov = mean coverage of orthogroup backbone sequences in the trimmed protein alignment
+# sd_cov = standard deviation (for coverage mean) of orthogroup backbone sequences in the trimmed protein alignment
+# len = total-length of conserved regions of sequence in the orthogroup trimmed protein alignment
+# avg_len = mean total-lengths of conserved regions of backbone sequences in the trimmed orthogroup protein alignment
+# sd_len = standard deviation (for total-lengths mean) of conserved regions of backbone sequences in the trimmed orthogroup protein alignment

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/tool-data/plant_tribes/scaffolds/README.txt	Mon Oct 30 08:51:22 2017 -0400
@@ -0,0 +1,3 @@
+For functional tests to work, this directory must contain symlinks to the scaffolds data
+installed into the Galaxy instance to which planemo points via the --galaxy_root parameter.
+This would typically be something like ~/galaxy/tool-data/plant_tribes/scaffolds/22Gv1.1.