pima_report: pima_report.py comparison

comparison pima_report.py @ 18:e948214a9e3c draft

Uploaded

author	greg
date	Wed, 22 Mar 2023 13:07:22 +0000
parents	b4ed9f55de13
children	c509e6819795

comparison

equal deleted inserted replaced

-:b4ed9f55de13
+:e948214a9e3c
 class PimaReport:
 def __init__(self, analysis_name=None, amr_deletions_file=None, amr_matrix_files=None, assembly_fasta_file=None,
 assembly_name=None, bedtools_version=None, blastn_version=None, circos_files=None,
 compute_sequence_length_file=None, contig_coverage_file=None, dbkey=None, dnadiff_snps_file=None,
-dnadiff_version=None, feature_bed_files=None, feature_png_files=None, flye_assembly_info_file=None,
+dnadiff_version=None, errors_file=None, feature_bed_files=None, feature_png_files=None,
-flye_version=None, genome_insertions_file=None, gzipped=None, kraken2_report_file=None,
+flye_assembly_info_file=None, flye_version=None, genome_insertions_file=None, gzipped=None,
-kraken2_version=None, minimap2_version=None, mutation_regions_bed_file=None, mutation_regions_tsv_files=None,
+kraken2_report_file=None, kraken2_version=None, minimap2_version=None, mutation_regions_bed_file=None,
-ont_fastq_file=None, pima_css=None, plasmids_file=None, quast_report_file=None, reference_insertions_file=None,
+mutation_regions_tsv_files=None, ont_fastq_file=None, pima_css=None, plasmids_file=None,
-samtools_version=None, varscan_version=None):
+quast_report_file=None, read_type=None, reference_insertions_file=None, samtools_version=None,
+varscan_version=None):
 self.ofh = open("process_log.txt", "w")
 self.ofh.write("amr_deletions_file: %s\n" % str(amr_deletions_file))
 self.ofh.write("amr_matrix_files: %s\n" % str(amr_matrix_files))
 self.ofh.write("analysis_name: %s\n" % str(analysis_name))
 self.ofh.write("compute_sequence_length_file: %s\n" % str(compute_sequence_length_file))
 self.ofh.write("contig_coverage_file: %s\n" % str(contig_coverage_file))
 self.ofh.write("dbkey: %s\n" % str(dbkey))
 self.ofh.write("dnadiff_snps_file: %s\n" % str(dnadiff_snps_file))
 self.ofh.write("dnadiff_version: %s\n" % str(dnadiff_version))
+self.ofh.write("errors_file: %s\n" % str(errors_file))
 self.ofh.write("feature_bed_files: %s\n" % str(feature_bed_files))
 self.ofh.write("feature_png_files: %s\n" % str(feature_png_files))
 self.ofh.write("flye_assembly_info_file: %s\n" % str(flye_assembly_info_file))
 self.ofh.write("flye_version: %s\n" % str(flye_version))
 self.ofh.write("gzipped: %s\n" % str(gzipped))
 self.ofh.write("mutation_regions_tsv_files: %s\n" % str(mutation_regions_tsv_files))
 self.ofh.write("ont_fastq_file: %s\n" % str(ont_fastq_file))
 self.ofh.write("pima_css: %s\n" % str(pima_css))
 self.ofh.write("plasmids_file: %s\n" % str(plasmids_file))
 self.ofh.write("quast_report_file: %s\n" % str(quast_report_file))
+self.ofh.write("read_type: %s\n" % str(read_type))
 self.ofh.write("reference_insertions_file: %s\n" % str(reference_insertions_file))
 self.ofh.write("samtools_version: %s\n" % str(samtools_version))
 self.ofh.write("varscan_version: %s\n" % str(varscan_version))
 # General
 self.dnadiff_snps_file = dnadiff_snps_file
 if dnadiff_version is None:
 self.dnadiff_version = 'dnadiff (version unknown)'
 else:
 self.dnadiff_version = re.sub('_', '.', dnadiff_version.rstrip(' _snps_'))
+self.errors_file = errors_file
 self.feature_bed_files = feature_bed_files
 self.feature_png_files = feature_png_files
 self.flye_assembly_info_file = flye_assembly_info_file
 if flye_version is None:
 self.flye_version = 'flye (version unknown)'
 self.mutation_regions_bed_file = mutation_regions_bed_file
 self.mutation_regions_tsv_files = mutation_regions_tsv_files
 self.pima_css = pima_css
 self.plasmids_file = plasmids_file
 self.quast_report_file = quast_report_file
-self.read_type = 'ONT'
+self.read_type = read_type.upper()
 self.reference_insertions_file = reference_insertions_file
 self.reference_insertions_file = reference_insertions_file
 if samtools_version is None:
 self.samtools_version = 'samtools (version unknown)'
 else:
 self.feature_title = 'Features found in the assembly'
 self.feature_methods_title = 'Feature annotation'
 self.feature_plot_title = 'Feature annotation plots'
 self.large_indel_title = 'Large insertions & deletions'
 self.methods_title = 'Methods'
+self.mutation_errors_title = 'Errors finding mutations in the sample'
 self.mutation_title = 'Mutations found in the sample'
 self.mutation_methods_title = 'Mutation screening'
 self.plasmid_methods_title = 'Plasmid annotation'
 self.plasmid_title = 'Plasmid annotation'
 self.reference_methods_title = 'Reference comparison'
 try:
 mutation_regions = pandas.read_csv(self.mutation_regions_bed_file, sep='\t', header=0, index_col=False)
 except Exception:
 # Likely an empty file.
 return
-# TODO: this is the only place where reference_genome is used,
-# so I'm commenting it out for now.  We need to confirm if these
-# errors that require the reference genmoe being passed are necessary.
-# If so, we'll need to implement data tables in this tool.
-# Make sure that the positions in the BED file fall within
-# the chromosomes provided in the reference sequence.
-"""
-for mutation_region in range(mutation_regions.shape[0]):
-mutation_region = mutation_regions.iloc[mutation_region, :]
-if not (mutation_region[0] in self.reference_genome):
-self.ofh.write("\nMutation region: %s not found in reference genome.\n" % ' '.join(mutation_region.astype(str)))
-continue
-if not isinstance(mutation_region[1], int):
-self.ofh.write("\nNon-integer found in mutation region start (column 2): %s.\n" % str(mutation_region[1]))
-break
-elif not isinstance(mutation_region[2], int):
-self.ofh.write("\nNon-integer found in mutation region start (column 3): %s.\n" % str(mutation_region[2]))
-break
-if mutation_region[1] <= 0 or mutation_region[2] <= 0:
-self.ofh.write("\nMutation region %s starts before the reference sequence.\n" % ' '.join(mutation_region.astype(str)))
-if mutation_region[1] > len(self.reference_genome[mutation_region[0]].seq) or mutation_region[2] > len(self.reference_genome[mutation_region[0]].seq):
-self.ofh.write("\nMutation region %s ends after the reference sequence.\n" % ' '.join(mutation_region.astype(str)))
-"""
 amr_mutations = pandas.Series(dtype=object)
 for region_i in range(mutation_regions.shape[0]):
 region = mutation_regions.iloc[region_i, :]
 region_name = str(region['name'])
 self.ofh.write("Processing mutations for region %s\n" % region_name)
 Table_List = ['Reference contig', 'Position', 'Reference', 'Alternate', 'Drug', 'Note']
 for i in range(region_mutations.shape[0]):
 Table_List = Table_List + region_mutations.iloc[i, [0, 1, 3, 4, 5, 6]].values.tolist()
 row_count = int(len(Table_List) / 6)
 self.doc.new_table(columns=6, rows=row_count, text=Table_List, text_align='left')
+if os.path.getsize(self.errors_file) > 0:
+# Report the errors encountered when attempting
+# to find mutations in the sample.
+self.doc.new_line()
+self.doc.new_header(level=2, title=self.mutation_errors_title)
+with open(self.errors_file, 'r') as efh:
+for i, line in enumerate(efh):
+line = line.strip()
+if line:
+self.doc.new_line('* %s' % line)
 method = '%s reads were mapped to the reference sequence using %s.' % (self.read_type, self.minimap2_version)
 self.methods[self.mutation_methods_title] = self.methods[self.mutation_methods_title].append(pandas.Series(method))
 method = 'Mutations were identified using %s and %s.' % (self.samtools_version, self.varscan_version)
 self.methods[self.mutation_methods_title] = self.methods[self.mutation_methods_title].append(pandas.Series(method))
 if amr_deletions.shape[0] > 0:
 amr_deletions.columns = ['contig', 'start', 'stop', 'name', 'type', 'drug', 'note']
 amr_deletions = amr_deletions.loc[amr_deletions['type'].isin(['large-deletion', 'any']), :]
 self.doc.new_line()
 self.doc.new_header(level=2, title=self.large_indel_title)
+self.doc.new_line('This section is informative only when your idolates were identified as *Bacillus anthracis* strains')
 for genome in ['Reference insertions', 'Query insertions']:
 genome_indels = large_indels[genome].copy()
 self.doc.new_line()
 self.doc.new_header(level=3, title=genome)
 if (genome_indels.shape[0] == 0):
 parser.add_argument('--compute_sequence_length_file', action='store', dest='compute_sequence_length_file', help='Comnpute sequence length tabular file')
 parser.add_argument('--contig_coverage_file', action='store', dest='contig_coverage_file', help='Contig coverage TSV file')
 parser.add_argument('--dbkey', action='store', dest='dbkey', help='Reference genome identifier')
 parser.add_argument('--dnadiff_snps_file', action='store', dest='dnadiff_snps_file', help='DNAdiff snps tabular file')
 parser.add_argument('--dnadiff_version', action='store', dest='dnadiff_version', default=None, help='DNAdiff version string')
+parser.add_argument('--errors_file', action='store', dest='errors_file', default=None, help='AMR mutations errors encountered txt file')
 parser.add_argument('--feature_bed_dir', action='store', dest='feature_bed_dir', help='Directory of best feature hits bed files')
 parser.add_argument('--feature_png_dir', action='store', dest='feature_png_dir', help='Directory of best feature hits png files')
 parser.add_argument('--flye_assembly_info_file', action='store', dest='flye_assembly_info_file', default=None, help='Flye assembly info tabular file')
 parser.add_argument('--flye_version', action='store', dest='flye_version', default=None, help='Flye version string')
 parser.add_argument('--genome_insertions_file', action='store', dest='genome_insertions_file', help='Genome insertions BED file')
 parser.add_argument('--mutation_regions_bed_file', action='store', dest='mutation_regions_bed_file', help='AMR mutation regions BRD file')
 parser.add_argument('--mutation_regions_dir', action='store', dest='mutation_regions_dir', help='Directory of mutation regions TSV files')
 parser.add_argument('--pima_css', action='store', dest='pima_css', help='PIMA css stypesheet')
 parser.add_argument('--plasmids_file', action='store', dest='plasmids_file', help='pChunks plasmids TSV file')
 parser.add_argument('--quast_report_file', action='store', dest='quast_report_file', help='Quast report tabular file')
+parser.add_argument('--read_type', action='store', dest='read_type', help='Sample read type (ONT or Illumina)')
 parser.add_argument('--reference_insertions_file', action='store', dest='reference_insertions_file', help='Reference insertions BED file')
 parser.add_argument('--samtools_version', action='store', dest='samtools_version', default=None, help='Samtools version string')
 parser.add_argument('--varscan_version', action='store', dest='varscan_version', default=None, help='Varscan version string')
 args = parser.parse_args()
 args.compute_sequence_length_file,
 args.contig_coverage_file,
 args.dbkey,
 args.dnadiff_snps_file,
 args.dnadiff_version,
+args.errors_file,
 feature_bed_files,
 feature_png_files,
 args.flye_assembly_info_file,
 args.flye_version,
 args.genome_insertions_file,
 mutation_regions_files,
 args.ont_fastq_file,
 args.pima_css,
 args.plasmids_file,
 args.quast_report_file,
+args.read_type,
 args.reference_insertions_file,
 args.samtools_version,
 args.varscan_version)
 markdown_report.make_report()

Mercurial > repos > greg > pima_report

comparison pima_report.py @ 18:e948214a9e3c draft