comparison pima_report.py @ 28:27485e70ed2b draft

Uploaded

27:ddc056cf16bf

import argparse
import os
import pandas
import pypandoc
import re

                 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, errors_file=None, feature_bed_files=None,
                 feature_png_files=None, flye_assembly_info_file=None, genome_insertions_file=None, gzipped=None,
                 illumina_forward_read_file=None, illumina_reverse_read_file=None, kraken2_report_file=None,
                 kraken2_version=None, minimap2_version=None, mutation_regions_bed_file=None,
                 mutation_regions_tsv_files=None, ont_file=None, pima_css=None, plasmids_file=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("genome_insertions_file: %s\n" % str(genome_insertions_file))
        self.ofh.write("illumina_forward_read_file: %s\n" % str(illumina_forward_read_file))
        self.ofh.write("illumina_reverse_read_file: %s\n" % str(illumina_reverse_read_file))
        self.ofh.write("kraken2_report_file: %s\n" % str(kraken2_report_file))
        self.ofh.write("kraken2_version: %s\n" % str(kraken2_version))
        self.ofh.write("minimap2_version: %s\n" % str(minimap2_version))
        self.ofh.write("mutation_regions_bed_file: %s\n" % str(mutation_regions_bed_file))
        self.ofh.write("mutation_regions_tsv_files: %s\n" % str(mutation_regions_tsv_files))
        self.ofh.write("ont_file: %s\n" % str(ont_file))
        self.ofh.write("pima_css: %s\n" % str(pima_css))

        self.kraken2_report_file = kraken2_report_file
        if kraken2_version is None:
            self.kraken2_version = 'kraken2 (version unknown)'
        else:
            self.kraken2_version = re.sub('_', '.', kraken2_version.rstrip(' _report_'))
        if minimap2_version is None:
            self.minimap2_version = 'minimap2 (version unknown)'
        else:
            self.minimap2_version = re.sub('_', '.', minimap2_version)
        self.mutation_regions_bed_file = mutation_regions_bed_file

        self.contig_alignment_title = 'Alignment vs. reference contigs'
        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'

            row_count = int(len(Table_List) / 4)
            self.doc.new_table(columns=4, rows=row_count, text=Table_List, text_align='left')
        method = 'Large insertions or deletions were found as the complement of aligned regions using %s.' % self.bedtools_version
        self.methods[self.reference_methods_title] = self.methods[self.reference_methods_title].append(pandas.Series(method))
        self.doc.new_line()
        self.doc.new_line('<div style="page-break-after: always;"></div>')
        self.doc.new_line()

    def add_plasmids(self):
        try:

        self.add_feature_plots()
        self.add_mutations()
        self.add_large_indels()
        self.add_plasmids()
        self.add_amr_matrix()
        # self.add_snps()
        self.add_methods()
        self.make_tex()
        # It took me quite a long time to find out that the value of the -t
        # (implied) argument in the following command must be 'html' instead of

parser.add_argument('--gzipped', action='store_true', dest='gzipped', default=False, help='Sample(s) is/are gzipped')
parser.add_argument('--illumina_forward_read_file', action='store', dest='illumina_forward_read_file', help='Illumina forward read file')
parser.add_argument('--illumina_reverse_read_file', action='store', dest='illumina_reverse_read_file', help='Illumina reverse read file')
parser.add_argument('--kraken2_report_file', action='store', dest='kraken2_report_file', default=None, help='kraken2 report file')
parser.add_argument('--kraken2_version', action='store', dest='kraken2_version', default=None, help='kraken2 version string')
parser.add_argument('--minimap2_version', action='store', dest='minimap2_version', default=None, help='minimap2 version string')
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('--ont_file', action='store', dest='ont_file', help='ONT single read file')
parser.add_argument('--pima_css', action='store', dest='pima_css', help='PIMA css stypesheet')

                             args.gzipped,
                             args.illumina_forward_read_file,
                             args.illumina_reverse_read_file,
                             args.kraken2_report_file,
                             args.kraken2_version,
                             args.minimap2_version,
                             args.mutation_regions_bed_file,
                             mutation_regions_files,
                             args.ont_file,
                             args.pima_css,

28:27485e70ed2b

#!/usr/bin/env python

import argparse
import os
import pandas
import pypandoc
import re

                 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, errors_file=None, feature_bed_files=None,
                 feature_png_files=None, flye_assembly_info_file=None, genome_insertions_file=None, gzipped=None,
                 illumina_forward_read_file=None, illumina_reverse_read_file=None, kraken2_report_file=None,
                 kraken2_version=None, lrn_risk_amr_file=None, lrn_risk_blacklist_file=None, lrn_risk_vf_file=None,
                 minimap2_version=None, mutation_regions_bed_file=None, mutation_regions_tsv_files=None,
                 ont_file=None, pima_css=None, plasmids_file=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("genome_insertions_file: %s\n" % str(genome_insertions_file))
        self.ofh.write("illumina_forward_read_file: %s\n" % str(illumina_forward_read_file))
        self.ofh.write("illumina_reverse_read_file: %s\n" % str(illumina_reverse_read_file))
        self.ofh.write("kraken2_report_file: %s\n" % str(kraken2_report_file))
        self.ofh.write("kraken2_version: %s\n" % str(kraken2_version))
        self.ofh.write("lrn_risk_amr_file: %s\n" % str(lrn_risk_amr_file))
        self.ofh.write("lrn_risk_blacklist_file: %s\n" % str(lrn_risk_blacklist_file))
        self.ofh.write("lrn_risk_vf_file: %s\n" % str(lrn_risk_vf_file))
        self.ofh.write("minimap2_version: %s\n" % str(minimap2_version))
        self.ofh.write("mutation_regions_bed_file: %s\n" % str(mutation_regions_bed_file))
        self.ofh.write("mutation_regions_tsv_files: %s\n" % str(mutation_regions_tsv_files))
        self.ofh.write("ont_file: %s\n" % str(ont_file))
        self.ofh.write("pima_css: %s\n" % str(pima_css))

        self.kraken2_report_file = kraken2_report_file
        if kraken2_version is None:
            self.kraken2_version = 'kraken2 (version unknown)'
        else:
            self.kraken2_version = re.sub('_', '.', kraken2_version.rstrip(' _report_'))
        self.lrn_risk_amr_file = lrn_risk_amr_file
        self.lrn_risk_blacklist_file = lrn_risk_blacklist_file
        self.lrn_risk_vf_file = lrn_risk_vf_file
        if minimap2_version is None:
            self.minimap2_version = 'minimap2 (version unknown)'
        else:
            self.minimap2_version = re.sub('_', '.', minimap2_version)
        self.mutation_regions_bed_file = mutation_regions_bed_file

        self.contig_alignment_title = 'Alignment vs. reference contigs'
        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.lrn_risk_title = 'LRNRisk isolate classification'
        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'

            row_count = int(len(Table_List) / 4)
            self.doc.new_table(columns=4, rows=row_count, text=Table_List, text_align='left')
        method = 'Large insertions or deletions were found as the complement of aligned regions using %s.' % self.bedtools_version
        self.methods[self.reference_methods_title] = self.methods[self.reference_methods_title].append(pandas.Series(method))
        self.doc.new_line()
        self.doc.new_line('<div style="page-break-after: always;"></div>')
        self.doc.new_line()

    def add_lrn_risk_info(self):
        self.ofh.write("\nXXXXXX In add_lrn_risk_info\n\n")
        if self.lrn_risk_amr_file is None and self.lrn_risk_blacklist_file is None and self.lrn_risk_vf_file is None:
            return
        self.doc.new_line()
        self.doc.new_header(level=2, title=self.lrn_risk_title)
        # Process self.lrn_risk_amr_file.
        try:
            lrn_risk_amr = pandas.read_csv(filepath_or_buffer=self.lrn_risk_amr_file, sep='\t', header=0)
        except Exception:
            lrn_risk_amr = pandas.DataFrame()
        if lrn_risk_amr.shape[0] > 0:
            self.doc.new_line()
            self.doc.new_header(level=2, title="AMR Determinant Distribution")
            self.doc.new_line()
            Table_List = ["Gene", "Contig", "% Identity", "% Coverage", "E-Value", "Annotation", "Comparison to Publicly Available Genomes"]
            for index, row in lrn_risk_amr.iterrows():
                Table_List = Table_List + row.tolist()
            row_count = int(len(Table_List) / 7)
            self.doc.new_table(columns=7, rows=row_count, text=Table_List, text_align='left')
        # Process self.lrn_risk_blacklist_file.
        try:
            lrn_risk_blacklist = pandas.read_csv(filepath_or_buffer=self.lrn_risk_blacklist_file, sep='\t', header=0)
        except Exception:
            lrn_risk_blacklist = pandas.DataFrame()
        if lrn_risk_blacklist.shape[0] > 0:
            self.doc.new_line()
            self.doc.new_header(level=2, title="Blacklisted High-risk Virulence Factors")
            self.doc.new_line()
            Table_List = ["Blacklisted Gene", "Reason", "Risk Category"]
            for index, row in lrn_risk_blacklist.iterrows():
                Table_List = Table_List + row.tolist()
            row_count = int(len(Table_List) / 3)
            self.doc.new_table(columns=3, rows=row_count, text=Table_List, text_align='left')
        # Process self.lrn_risk_vf_file.
        try:
            lrn_risk_vf = pandas.read_csv(filepath_or_buffer=self.lrn_risk_vf_file, sep='\t', header=0)
        except Exception:
            lrn_risk_vf = pandas.DataFrame()
        if lrn_risk_vf.shape[0] > 0:
            self.doc.new_line()
            self.doc.new_header(level=2, title="Virulence Factor Distribution")
            self.doc.new_line()
            Table_List = ["Gene", "Contig", "% Identity", "% Coverage", "E-Value", "Annotation", "Comparison to Publicly Available Genomes"]
            for index, row in lrn_risk_vf.iterrows():
                Table_List = Table_List + row.tolist()
            row_count = int(len(Table_List) / 7)
            self.doc.new_table(columns=7, rows=row_count, text=Table_List, text_align='left')
        self.doc.new_line('<div style="page-break-after: always;"></div>')
        self.doc.new_line()

    def add_plasmids(self):
        try:

        self.add_feature_plots()
        self.add_mutations()
        self.add_large_indels()
        self.add_plasmids()
        self.add_amr_matrix()
        self.add_lrn_risk_info()
        # self.add_snps()
        self.add_methods()
        self.make_tex()
        # It took me quite a long time to find out that the value of the -t
        # (implied) argument in the following command must be 'html' instead of

parser.add_argument('--gzipped', action='store_true', dest='gzipped', default=False, help='Sample(s) is/are gzipped')
parser.add_argument('--illumina_forward_read_file', action='store', dest='illumina_forward_read_file', help='Illumina forward read file')
parser.add_argument('--illumina_reverse_read_file', action='store', dest='illumina_reverse_read_file', help='Illumina reverse read file')
parser.add_argument('--kraken2_report_file', action='store', dest='kraken2_report_file', default=None, help='kraken2 report file')
parser.add_argument('--kraken2_version', action='store', dest='kraken2_version', default=None, help='kraken2 version string')
parser.add_argument('--lrn_risk_amr_file', action='store', dest='lrn_risk_amr_file', default=None, help='LRN RISK AMR TSV file')
parser.add_argument('--lrn_risk_blacklist_file', action='store', dest='lrn_risk_blacklist_file', default=None, help='LRN RISK blacklist TSV file')
parser.add_argument('--lrn_risk_vf_file', action='store', dest='lrn_risk_vf_file', default=None, help='LRN RISK virulence factors TSV file')
parser.add_argument('--minimap2_version', action='store', dest='minimap2_version', default=None, help='minimap2 version string')
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('--ont_file', action='store', dest='ont_file', help='ONT single read file')
parser.add_argument('--pima_css', action='store', dest='pima_css', help='PIMA css stypesheet')

                             args.gzipped,
                             args.illumina_forward_read_file,
                             args.illumina_reverse_read_file,
                             args.kraken2_report_file,
                             args.kraken2_version,
                             args.lrn_risk_amr_file,
                             args.lrn_risk_blacklist_file,
                             args.lrn_risk_vf_file,
                             args.minimap2_version,
                             args.mutation_regions_bed_file,
                             mutation_regions_files,
                             args.ont_file,
                             args.pima_css,