Mercurial > repos > greg > gene_family_classifier
changeset 131:656614635ebf draft
Uploaded
| author | greg |
|---|---|
| date | Thu, 06 Apr 2017 14:21:39 -0400 |
| parents | fb3feee2638d |
| children | 169504db8e43 |
| files | gene_family_classifier.py gene_family_classifier.xml macros.xml utils.py |
| diffstat | 4 files changed, 143 insertions(+), 131 deletions(-) [+] |
line wrap: on
line diff
--- a/gene_family_classifier.py Wed Mar 22 08:45:31 2017 -0400 +++ b/gene_family_classifier.py Thu Apr 06 14:21:39 2017 -0400 @@ -3,8 +3,9 @@ import os import shutil import subprocess -import sys -import tempfile + +import utils + BUFF_SIZE = 1048576 OUTPUT_DIR = 'geneFamilyClassification_dir' @@ -34,79 +35,6 @@ args = parser.parse_args() -def get_stderr_exception(tmp_err, tmp_stderr, tmp_out, tmp_stdout, include_stdout=False): - tmp_stderr.close() - """ - Return a stderr string of reasonable size. - """ - # Get stderr, allowing for case where it's very large. - tmp_stderr = open(tmp_err, 'rb') - stderr_str = '' - buffsize = BUFF_SIZE - try: - while True: - stderr_str += tmp_stderr.read(buffsize) - if not stderr_str or len(stderr_str) % buffsize != 0: - break - except OverflowError: - pass - tmp_stderr.close() - if include_stdout: - tmp_stdout = open(tmp_out, 'rb') - stdout_str = '' - buffsize = BUFF_SIZE - try: - while True: - stdout_str += tmp_stdout.read(buffsize) - if not stdout_str or len(stdout_str) % buffsize != 0: - break - except OverflowError: - pass - tmp_stdout.close() - if include_stdout: - return 'STDOUT\n%s\n\nSTDERR\n%s\n' % (stdout_str, stderr_str) - return stderr_str - - -def move_directory_files(source_dir, destination_dir): - source_directory = os.path.abspath(source_dir) - destination_directory = os.path.abspath(destination_dir) - if not os.path.isdir(destination_directory): - os.makedirs(destination_directory) - for dir_entry in os.listdir(source_directory): - source_entry = os.path.join(source_directory, dir_entry) - shutil.move(source_entry, destination_directory) - - -def stop_err(msg): - sys.stderr.write(msg) - sys.exit(1) - - -def write_html_output(output, title, dir): - with open(output, 'w') as fh: - fh.write('<html><head><h3>%s</h3></head>\n' % title) - fh.write('<body><p/><table cellpadding="2">\n') - fh.write('<tr><th>Size</th><th>Name</th></tr>\n') - for index, fname in enumerate(sorted(os.listdir(dir))): - if index % 2 == 0: - bgcolor = '#D8D8D8' - else: - bgcolor = '#FFFFFF' - try: - size = str(os.path.getsize(os.path.join(dir, fname))) - except: - size = 'unknown' - link = '<a href="%s" type="text/plain">%s</a>\n' % (fname, fname) - fh.write('<tr bgcolor="%s"><td>%s</td><td>%s</td></tr>\n' % (bgcolor, size, link)) - fh.write('</table></body></html>\n') - - -# Define command response buffers. -tmp_out = tempfile.NamedTemporaryFile().name -tmp_stdout = open(tmp_out, 'wb') -tmp_err = tempfile.NamedTemporaryFile().name -tmp_stderr = open(tmp_err, 'wb') # Build the command line. cmd = 'GeneFamilyClassifier' cmd += ' --proteins %s' % args.input @@ -134,12 +62,9 @@ create_corresponding_coding_sequences = True cmd += ' --coding_sequences %s' % args.coding_sequences # Run the command. -proc = subprocess.Popen(args=cmd, stderr=tmp_stderr, stdout=tmp_stdout, shell=True) +proc = subprocess.Popen(args=cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE, shell=True) rc = proc.wait() -# Handle execution errors. -if rc != 0: - error_message = get_stderr_exception(tmp_err, tmp_stderr, tmp_out, tmp_stdout) - stop_err( error_message ) +utils.check_execution_errors(rc, proc.stderr) # Handle hmmscan.log output. if args.classifier in ['hmmscan', 'both']: src_hmmscan_log = os.path.join(OUTPUT_DIR, 'hmmscan.log') @@ -159,12 +84,12 @@ orthogroups_fasta_dest_dir = args.output_ptortho_dir title = 'Orthogroups files' orthogroups_fasta_src_dir = os.path.join(OUTPUT_DIR, 'orthogroups_fasta') - move_directory_files(orthogroups_fasta_src_dir, orthogroups_fasta_dest_dir) - write_html_output(out_file, title, orthogroups_fasta_dest_dir) + utils.move_directory_files(orthogroups_fasta_src_dir, orthogroups_fasta_dest_dir) + utils.write_html_output(out_file, title, orthogroups_fasta_dest_dir) # Handle single copy orthogroup outputs. if args.output_ptsco is not None: single_copy_fasta_src_dir = os.path.join(OUTPUT_DIR, 'single_copy_fasta') single_copy_fasta_dest_dir = args.output_ptsco_dir title = 'Single copy orthogroups files' - move_directory_files(single_copy_fasta_src_dir, single_copy_fasta_dest_dir) - write_html_output(args.output_ptsco, title, single_copy_fasta_dest_dir) + utils.move_directory_files(single_copy_fasta_src_dir, single_copy_fasta_dest_dir) + utils.write_html_output(args.output_ptsco, title, single_copy_fasta_dest_dir)
--- a/gene_family_classifier.xml Wed Mar 22 08:45:31 2017 -0400 +++ b/gene_family_classifier.xml Thu Apr 06 14:21:39 2017 -0400 @@ -1,16 +1,10 @@ <tool id="plant_tribes_gene_family_classifier" name="GeneFamilyClassifier" version="0.4.0"> <description>classifies gene sequences into pre-computed orthologous plant gene family clusters</description> - <requirements> - <requirement type="package" version="0.4">plant_tribes_gene_family_classifier</requirement> - </requirements> - <stdio> - <!-- Anything other than zero is an error --> - <exit_code range="1:" /> - <exit_code range=":-1" /> - <!-- In case the return code has not been set propery check stderr too --> - <regex match="Error:" /> - <regex match="Exception:" /> - </stdio> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements_gene_family_classifier" /> + <expand macro="stdio" /> <command> <![CDATA[ #if str($options_type.options_type_selector) == 'advanced': @@ -295,42 +289,8 @@ </help> <citations> - <citation type="bibtex"> - @misc{None, - journal = {None}, - author = {1. Wafula EK}, - title = {Manuscript in preparation}, - year = {None}, - url = {https://github.com/dePamphilis/PlantTribes},} - </citation> - <citation type="bibtex"> - @article{Sasidharan2012, - journal = {Nucleic Acids Research}, - author = {2. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, - title = {GFam: a platform for automatic annotation of gene families}, - year = {2012}, - pages = {gks631},} - </citation> - <citation type="bibtex"> - @article{Li2003, - journal = {Genome Research} - author = {3. Li L, Stoeckert CJ, Roos DS}, - title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, - year = {2003}, - volume = {13}, - number = {9}, - pages = {2178-2189},} - </citation> - <citation type="bibtex"> - @article{Emms2015, - journal = {Genome Biology} - author = {4. Emms DM, Kelly S}, - title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, - year = {2015}, - volume = {16}, - number = {1}, - pages = {157},} - </citation> + <expand macro="citation1" /> + <expand macro="citations2to4" /> <citation type="bibtex"> @article{Altschul1990, journal = {Journal of molecular biology}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Thu Apr 06 14:21:39 2017 -0400 @@ -0,0 +1,85 @@ +<?xml version='1.0' encoding='UTF-8'?> +<macros> + <xml name="requirements_assembly_post_processor"> + <requirements> + <requirement type="package" version="0.4">plant_tribes_assembly_post_processor</requirement> + </requirements> + </xml> + <xml name="requirements_gene_family_classifier"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_classifier</requirement> + </requirements> + </xml> + <xml name="requirements_gene_family_integrator"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_integrator</requirement> + </requirements> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range="1:"/> + <exit_code range=":-1"/> + <regex match="Error:"/> + <regex match="Exception:"/> + </stdio> + </xml> + <xml name="param_scaffold"> + <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold"> + <options from_data_table="plant_tribes_scaffolds" /> + <validator type="no_options" message="No PlantTribes scaffolds are available. Use the PlantTribes Scaffolds Download Data Manager tool in Galaxy to install and populate the PlantTribes scaffolds data table." /> + </param> + </xml> + <xml name="param_method"> + <param name="method" type="select" label="Protein clustering method"> + <option value="gfam" selected="true">GFam</option> + <option value="orthofinder">OrthoFinder</option> + <option value="orthomcl">OrthoMCL</option> + </param> + </xml> + <xml name="param_orthogroup_fna"> + <param name="orthogroup_fna" type="select" display="radio" label="Process corresponding gene family classification orthogroups CDS fasta files?"> + <option value="yes" selected="true">Yes</option> + <option value="no">No</option> + </param> + </xml> + <xml name="citation1"> + <citation type="bibtex"> + @misc{None, + journal = {None}, + author = {1. Wafula EK}, + title = {Manuscript in preparation}, + year = {None}, + url = {https://github.com/dePamphilis/PlantTribes},} + </citation> + </xml> + <xml name="citations2to4"> + <citation type="bibtex"> + @article{Sasidharan2012, + journal = {Nucleic Acids Research}, + author = {2. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, + title = {GFam: a platform for automatic annotation of gene families}, + year = {2012}, + pages = {gks631},} + </citation> + <citation type="bibtex"> + @article{Li2003, + journal = {Genome Research} + author = {3. Li L, Stoeckert CJ, Roos DS}, + title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, + year = {2003}, + volume = {13}, + number = {9}, + pages = {2178-2189},} + </citation> + <citation type="bibtex"> + @article{Emms2015, + journal = {Genome Biology} + author = {4. Emms DM, Kelly S}, + title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, + year = {2015}, + volume = {16}, + number = {1}, + pages = {157},} + </citation> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/utils.py Thu Apr 06 14:21:39 2017 -0400 @@ -0,0 +1,42 @@ +import os +import shutil +import sys + + +def check_execution_errors(rc, stderr): + if rc != 0: + stop_err(stderr.read()) + + +def move_directory_files(source_dir, destination_dir): + source_directory = os.path.abspath(source_dir) + destination_directory = os.path.abspath(destination_dir) + if not os.path.isdir(destination_directory): + os.makedirs(destination_directory) + for dir_entry in os.listdir(source_directory): + source_entry = os.path.join(source_directory, dir_entry) + shutil.move(source_entry, destination_directory) + + +def stop_err(msg): + sys.stderr.write(msg) + sys.exit(1) + + +def write_html_output(output, title, dir): + with open(output, 'w') as fh: + fh.write('<html><head><h3>%s</h3></head>\n' % title) + fh.write('<body><p/><table cellpadding="2">\n') + fh.write('<tr><th>Size</th><th>Name</th></tr>\n') + for index, fname in enumerate(sorted(os.listdir(dir))): + if index % 2 == 0: + bgcolor = '#D8D8D8' + else: + bgcolor = '#FFFFFF' + try: + size = str(os.path.getsize(os.path.join(dir, fname))) + except: + size = 'unknown' + link = '<a href="%s" type="text/plain">%s</a>\n' % (fname, fname) + fh.write('<tr bgcolor="%s"><td>%s</td><td>%s</td></tr>\n' % (bgcolor, size, link)) + fh.write('</table></body></html>\n')