Mercurial > repos > greg > pima_report

comparison pima_report.py @ 21:667b253329c6 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Thu, 13 Apr 2023 17:13:40 +0000
parents 4fe8c35cd176
children 13a9c8ecd30e
comparison
equal deleted inserted replaced
20:4fe8c35cd176 21:667b253329c6
15 CDC_ADVISORY = 'The analysis and report presented here should be treated as preliminary. Please contact the CDC/BDRD with any results regarding _Bacillus anthracis_.' 15 CDC_ADVISORY = 'The analysis and report presented here should be treated as preliminary. Please contact the CDC/BDRD with any results regarding _Bacillus anthracis_.'
16 16
17 17
18 class PimaReport: 18 class PimaReport:
19 19
20 def __init__(self, analysis_name=None, amr_deletions_file=None, amr_matrix_files=None, assembly_fasta_file=None, 20 def __init__(self, analysis_name=None, amr_deletions_file=None, amr_matrix_files=None, assembler_version=None,
21 assembly_name=None, bedtools_version=None, blastn_version=None, circos_files=None, 21 assembly_fasta_file=None, assembly_name=None, bedtools_version=None, blastn_version=None,
22 compute_sequence_length_file=None, contig_coverage_file=None, dbkey=None, dnadiff_snps_file=None, 22 circos_files=None, compute_sequence_length_file=None, contig_coverage_file=None, dbkey=None,
23 dnadiff_version=None, errors_file=None, feature_bed_files=None, feature_png_files=None, 23 dnadiff_snps_file=None, dnadiff_version=None, errors_file=None, fastq_file=None, feature_bed_files=None,
24 flye_assembly_info_file=None, flye_version=None, genome_insertions_file=None, gzipped=None, 24 feature_png_files=None, flye_assembly_info_file=None, genome_insertions_file=None, gzipped=None,
25 kraken2_report_file=None, kraken2_version=None, minimap2_version=None, mutation_regions_bed_file=None, 25 kraken2_report_file=None, kraken2_version=None, minimap2_version=None, mutation_regions_bed_file=None,
26 mutation_regions_tsv_files=None, ont_fastq_file=None, pima_css=None, plasmids_file=None, 26 mutation_regions_tsv_files=None, pima_css=None, plasmids_file=None, quast_report_file=None,
27 quast_report_file=None, read_type=None, reference_insertions_file=None, samtools_version=None, 27 read_type=None, reference_insertions_file=None, samtools_version=None, varscan_version=None):
28 varscan_version=None):
29 self.ofh = open("process_log.txt", "w") 28 self.ofh = open("process_log.txt", "w")
30 29
31 self.ofh.write("amr_deletions_file: %s\n" % str(amr_deletions_file)) 30 self.ofh.write("amr_deletions_file: %s\n" % str(amr_deletions_file))
32 self.ofh.write("amr_matrix_files: %s\n" % str(amr_matrix_files)) 31 self.ofh.write("amr_matrix_files: %s\n" % str(amr_matrix_files))
33 self.ofh.write("analysis_name: %s\n" % str(analysis_name)) 32 self.ofh.write("analysis_name: %s\n" % str(analysis_name))
33 self.ofh.write("assembler_version: %s\n" % str(assembler_version))
34 self.ofh.write("assembly_fasta_file: %s\n" % str(assembly_fasta_file)) 34 self.ofh.write("assembly_fasta_file: %s\n" % str(assembly_fasta_file))
35 self.ofh.write("assembly_name: %s\n" % str(assembly_name)) 35 self.ofh.write("assembly_name: %s\n" % str(assembly_name))
36 self.ofh.write("bedtools_version: %s\n" % str(bedtools_version)) 36 self.ofh.write("bedtools_version: %s\n" % str(bedtools_version))
37 self.ofh.write("blastn_version: %s\n" % str(blastn_version)) 37 self.ofh.write("blastn_version: %s\n" % str(blastn_version))
38 self.ofh.write("circos_files: %s\n" % str(circos_files)) 38 self.ofh.write("circos_files: %s\n" % str(circos_files))
40 self.ofh.write("contig_coverage_file: %s\n" % str(contig_coverage_file)) 40 self.ofh.write("contig_coverage_file: %s\n" % str(contig_coverage_file))
41 self.ofh.write("dbkey: %s\n" % str(dbkey)) 41 self.ofh.write("dbkey: %s\n" % str(dbkey))
42 self.ofh.write("dnadiff_snps_file: %s\n" % str(dnadiff_snps_file)) 42 self.ofh.write("dnadiff_snps_file: %s\n" % str(dnadiff_snps_file))
43 self.ofh.write("dnadiff_version: %s\n" % str(dnadiff_version)) 43 self.ofh.write("dnadiff_version: %s\n" % str(dnadiff_version))
44 self.ofh.write("errors_file: %s\n" % str(errors_file)) 44 self.ofh.write("errors_file: %s\n" % str(errors_file))
45 self.ofh.write("fastq_file: %s\n" % str(fastq_file))
45 self.ofh.write("feature_bed_files: %s\n" % str(feature_bed_files)) 46 self.ofh.write("feature_bed_files: %s\n" % str(feature_bed_files))
46 self.ofh.write("feature_png_files: %s\n" % str(feature_png_files)) 47 self.ofh.write("feature_png_files: %s\n" % str(feature_png_files))
47 self.ofh.write("flye_assembly_info_file: %s\n" % str(flye_assembly_info_file)) 48 self.ofh.write("flye_assembly_info_file: %s\n" % str(flye_assembly_info_file))
48 self.ofh.write("flye_version: %s\n" % str(flye_version))
49 self.ofh.write("gzipped: %s\n" % str(gzipped)) 49 self.ofh.write("gzipped: %s\n" % str(gzipped))
50 self.ofh.write("genome_insertions_file: %s\n" % str(genome_insertions_file)) 50 self.ofh.write("genome_insertions_file: %s\n" % str(genome_insertions_file))
51 self.ofh.write("kraken2_report_file: %s\n" % str(kraken2_report_file)) 51 self.ofh.write("kraken2_report_file: %s\n" % str(kraken2_report_file))
52 self.ofh.write("kraken2_version: %s\n" % str(kraken2_version)) 52 self.ofh.write("kraken2_version: %s\n" % str(kraken2_version))
53 self.ofh.write("minimap2_version: %s\n" % str(minimap2_version)) 53 self.ofh.write("minimap2_version: %s\n" % str(minimap2_version))
54 self.ofh.write("mutation_regions_bed_file: %s\n" % str(mutation_regions_bed_file)) 54 self.ofh.write("mutation_regions_bed_file: %s\n" % str(mutation_regions_bed_file))
55 self.ofh.write("mutation_regions_tsv_files: %s\n" % str(mutation_regions_tsv_files)) 55 self.ofh.write("mutation_regions_tsv_files: %s\n" % str(mutation_regions_tsv_files))
56 self.ofh.write("ont_fastq_file: %s\n" % str(ont_fastq_file))
57 self.ofh.write("pima_css: %s\n" % str(pima_css)) 56 self.ofh.write("pima_css: %s\n" % str(pima_css))
58 self.ofh.write("plasmids_file: %s\n" % str(plasmids_file)) 57 self.ofh.write("plasmids_file: %s\n" % str(plasmids_file))
59 self.ofh.write("quast_report_file: %s\n" % str(quast_report_file)) 58 self.ofh.write("quast_report_file: %s\n" % str(quast_report_file))
60 self.ofh.write("read_type: %s\n" % str(read_type)) 59 self.ofh.write("read_type: %s\n" % str(read_type))
61 self.ofh.write("reference_insertions_file: %s\n" % str(reference_insertions_file)) 60 self.ofh.write("reference_insertions_file: %s\n" % str(reference_insertions_file))
69 # Inputs 68 # Inputs
70 self.amr_deletions_file = amr_deletions_file 69 self.amr_deletions_file = amr_deletions_file
71 self.amr_matrix_files = amr_matrix_files 70 self.amr_matrix_files = amr_matrix_files
72 self.analysis_name = analysis_name.split('_')[0] 71 self.analysis_name = analysis_name.split('_')[0]
73 self.ofh.write("self.analysis_name: %s\n" % str(self.analysis_name)) 72 self.ofh.write("self.analysis_name: %s\n" % str(self.analysis_name))
73 if assembler_version is None:
74 self.assembler_version = 'assembler (version unknown)'
75 else:
76 if read_type == 'ont':
77 # Assembler is flye.
78 assembler_version = assembler_version.rstrip(' _assembly info_')
79 else:
80 # Assembler is spades.
81 assembler_version = assembler_version.rstrip(' _contigs')
82 self.assembler_version = re.sub('_', '.', assembler_version)
74 self.assembly_fasta_file = assembly_fasta_file 83 self.assembly_fasta_file = assembly_fasta_file
75 self.assembly_name = re.sub('_', '.', assembly_name.rstrip(' _consensus_')) 84 self.assembly_name = re.sub('_', '.', assembly_name.rstrip(' _consensus_'))
76 if bedtools_version is None: 85 if bedtools_version is None:
77 self.bedtools_version = 'bedtools (version unknown)' 86 self.bedtools_version = 'bedtools (version unknown)'
78 else: 87 else:
92 self.dnadiff_version = re.sub('_', '.', dnadiff_version.rstrip(' _snps_')) 101 self.dnadiff_version = re.sub('_', '.', dnadiff_version.rstrip(' _snps_'))
93 self.errors_file = errors_file 102 self.errors_file = errors_file
94 self.feature_bed_files = feature_bed_files 103 self.feature_bed_files = feature_bed_files
95 self.feature_png_files = feature_png_files 104 self.feature_png_files = feature_png_files
96 self.flye_assembly_info_file = flye_assembly_info_file 105 self.flye_assembly_info_file = flye_assembly_info_file
97 if flye_version is None:
98 self.flye_version = 'flye (version unknown)'
99 else:
100 self.flye_version = re.sub('_', '.', flye_version.rstrip(' _assembly info_'))
101 self.gzipped = gzipped 106 self.gzipped = gzipped
102 self.genome_insertions_file = genome_insertions_file 107 self.genome_insertions_file = genome_insertions_file
103 self.kraken2_report_file = kraken2_report_file 108 self.kraken2_report_file = kraken2_report_file
104 if kraken2_version is None: 109 if kraken2_version is None:
105 self.kraken2_version = 'kraken2 (version unknown)' 110 self.kraken2_version = 'kraken2 (version unknown)'
144 self.mutation_errors_title = 'Errors finding mutations in the sample' 149 self.mutation_errors_title = 'Errors finding mutations in the sample'
145 self.mutation_title = 'Mutations found in the sample' 150 self.mutation_title = 'Mutations found in the sample'
146 self.mutation_methods_title = 'Mutation screening' 151 self.mutation_methods_title = 'Mutation screening'
147 self.plasmid_methods_title = 'Plasmid annotation' 152 self.plasmid_methods_title = 'Plasmid annotation'
148 self.plasmid_title = 'Plasmid annotation' 153 self.plasmid_title = 'Plasmid annotation'
154 self.reference_genome_title = 'Reference genome'
149 self.reference_methods_title = 'Reference comparison' 155 self.reference_methods_title = 'Reference comparison'
150 self.snp_indel_title = 'SNPs and small indels' 156 self.snp_indel_title = 'SNPs and small indels'
151 self.summary_title = 'Summary' 157 self.summary_title = 'Summary'
152 158
153 # Methods 159 # Methods
154 self.methods = pandas.Series(dtype='float64') 160 self.methods = pandas.Series(dtype='float64')
155 self.methods[self.contamination_methods_title] = pandas.Series(dtype='float64') 161 self.methods[self.contamination_methods_title] = pandas.Series(dtype='float64')
156 self.methods[self.assembly_methods_title] = pandas.Series(dtype='float64') 162 self.methods[self.assembly_methods_title] = pandas.Series(dtype='float64')
163 self.methods[self.reference_genome_title] = pandas.Series(dtype='float64')
157 self.methods[self.reference_methods_title] = pandas.Series(dtype='float64') 164 self.methods[self.reference_methods_title] = pandas.Series(dtype='float64')
158 self.methods[self.mutation_methods_title] = pandas.Series(dtype='float64') 165 self.methods[self.mutation_methods_title] = pandas.Series(dtype='float64')
159 self.methods[self.feature_methods_title] = pandas.Series(dtype='float64') 166 self.methods[self.feature_methods_title] = pandas.Series(dtype='float64')
160 self.methods[self.plasmid_methods_title] = pandas.Series(dtype='float64') 167 self.methods[self.plasmid_methods_title] = pandas.Series(dtype='float64')
161 168
167 # Values 174 # Values
168 self.assembly_size = 0 175 self.assembly_size = 0
169 self.contig_info = None 176 self.contig_info = None
170 self.did_medaka_ont_assembly = False 177 self.did_medaka_ont_assembly = False
171 self.feature_hits = pandas.Series(dtype='float64') 178 self.feature_hits = pandas.Series(dtype='float64')
172 self.illumina_fastq_file = None
173 self.illumina_length_mean = None 179 self.illumina_length_mean = None
174 self.illumina_read_count = None 180 self.illumina_read_count = None
175 self.illumina_bases = None 181 self.illumina_bases = None
176 self.ont_bases = None 182 self.ont_bases = None
177 # TODO: should the following be passed as a parameter? 183 # TODO: should the following be passed as a parameter?
178 self.ont_coverage_min = 30 184 self.ont_coverage_min = 30
179 self.ont_fast5 = None 185 self.ont_fast5 = None
180 self.ont_fastq_file = ont_fastq_file 186 self.fastq_file = fastq_file
181 self.ont_n50 = None 187 self.ont_n50 = None
182 # TODO: should the following be passed as a parameter? 188 # TODO: should the following be passed as a parameter?
183 self.ont_n50_min = 2500 189 self.ont_n50_min = 2500
184 self.ont_raw_fastq = self.analysis_name 190 if self.read_type == 'ONT':
191 self.ont_raw_fastq = self.analysis_name
192 self.illumina_fastq = None
193 else:
194 self.ont_raw_fastq = None
195 self.illumina_fastq = self.analysis_name
185 self.ont_read_count = None 196 self.ont_read_count = None
186 197
187 # Actions 198 # Actions
188 self.did_guppy_ont_fast5 = False 199 self.did_guppy_ont_fast5 = False
189 self.did_qcat_ont_fastq = False 200 self.did_qcat_ont_fastq = False
190 self.info_ont_fastq(self.ont_fastq_file) 201 self.ofh.write("self.read_type: %s\n" % str(self.read_type))
191 self.info_illumina_fastq() 202 if self.read_type == 'ONT':
203 self.info_ont_fastq(self.fastq_file)
204 else:
205 self.info_illumina_fastq(self.fastq_file)
192 self.load_contig_info() 206 self.load_contig_info()
193 207
194 def run_command(self, command): 208 def run_command(self, command):
195 self.ofh.write("\nXXXXXX In run_command, command:\n%s\n\n" % str(command)) 209 self.ofh.write("\nXXXXXX In run_command, command:\n%s\n\n" % str(command))
196 try: 210 try:
245 self.num_assembly_contigs = len(self.assembly) 259 self.num_assembly_contigs = len(self.assembly)
246 for i in self.assembly: 260 for i in self.assembly:
247 self.assembly_size += len(i.seq) 261 self.assembly_size += len(i.seq)
248 self.assembly_size = self.format_kmg(self.assembly_size, decimals=1) 262 self.assembly_size = self.format_kmg(self.assembly_size, decimals=1)
249 263
250 def info_illumina_fastq(self): 264 def info_illumina_fastq(self, fastq_file):
251 self.ofh.write("\nXXXXXX In info_illumina_fastq\n\n") 265 self.ofh.write("\nXXXXXX In info_illumina_fastq\n\n")
252 if self.illumina_length_mean is None: 266 if self.illumina_length_mean is None:
253 return 267 return
254 if self.gzipped: 268 if self.gzipped:
255 opener = 'gunzip -c' 269 opener = 'gunzip -c'
256 else: 270 else:
257 opener = 'cat' 271 opener = 'cat'
258 command = ' '.join([opener, 272 command = ' '.join([opener,
259 self.ont_fastq_file, 273 fastq_file,
260 '| awk \'{getline;s += length($1);getline;getline;}END{print s/(NR/4)"\t"(NR/4)"\t"s}\'']) 274 '| awk \'{getline;s += length($1);getline;getline;}END{print s/(NR/4)"\t"(NR/4)"\t"s}\''])
261 output = self.run_command(command) 275 output = self.run_command(command)
262 self.ofh.write("output:\n%s\n" % str(output)) 276 self.ofh.write("output:\n%s\n" % str(output))
263 self.ofh.write("re.split('\\t', self.run_command(command)[0]:\n%s\n" % str(re.split('\\t', self.run_command(command)[0]))) 277 self.ofh.write("re.split('\\t', self.run_command(command)[0]:\n%s\n" % str(re.split('\\t', self.run_command(command)[0])))
264 values = [] 278 values = []
272 self.illumina_length_mean += values[0] 286 self.illumina_length_mean += values[0]
273 self.ofh.write("values[1]:\n%s\n" % str(values[1])) 287 self.ofh.write("values[1]:\n%s\n" % str(values[1]))
274 self.illumina_read_count += int(values[1]) 288 self.illumina_read_count += int(values[1])
275 self.ofh.write("values[2]:\n%s\n" % str(values[2])) 289 self.ofh.write("values[2]:\n%s\n" % str(values[2]))
276 self.illumina_bases += int(values[2]) 290 self.illumina_bases += int(values[2])
277 # The original PIMA code inserts self.illumina_fastq_file into
278 # a list for no apparent reason. We don't do that here.
279 # self.illumina_length_mean /= len(self.illumina_fastq_file)
280 self.illumina_length_mean /= 1 291 self.illumina_length_mean /= 1
281 self.illumina_bases = self.format_kmg(self.illumina_bases, decimals=1) 292 self.illumina_bases = self.format_kmg(self.illumina_bases, decimals=1)
282 293
283 def start_doc(self): 294 def start_doc(self):
284 header_text = 'Analysis of ' + self.analysis_name 295 header_text = 'Analysis of ' + self.analysis_name
303 "ONT FAST5", 314 "ONT FAST5",
304 self.wordwrap_markdown(self.ont_fast5), 315 self.wordwrap_markdown(self.ont_fast5),
305 "ONT FASTQ", 316 "ONT FASTQ",
306 self.wordwrap_markdown(self.ont_raw_fastq), 317 self.wordwrap_markdown(self.ont_raw_fastq),
307 "Illumina FASTQ", 318 "Illumina FASTQ",
308 "N/A", 319 self.wordwrap_markdown(self.illumina_fastq),
309 "Assembly", 320 "Assembly",
310 self.wordwrap_markdown(self.assembly_name), 321 self.wordwrap_markdown(self.assembly_name),
311 "Reference", 322 "Reference",
312 self.wordwrap_markdown(self.dbkey), 323 self.wordwrap_markdown(self.dbkey),
313 ] 324 ]
405 '| awk \'BEGIN{bp = 0;f = 0}', 416 '| awk \'BEGIN{bp = 0;f = 0}',
406 '{if(NR == 1){sub(/+/, "", $1);s=$1}else{bp += $1;if(bp > s / 2 && f == 0){n50 = $1;f = 1}}}', 417 '{if(NR == 1){sub(/+/, "", $1);s=$1}else{bp += $1;if(bp > s / 2 && f == 0){n50 = $1;f = 1}}}',
407 'END{printf "%d\\t%d\\t%d\\n", n50, (NR - 1), s;exit}\'']) 418 'END{printf "%d\\t%d\\t%d\\n", n50, (NR - 1), s;exit}\''])
408 result = list(re.split('\\t', self.run_command(command)[0])) 419 result = list(re.split('\\t', self.run_command(command)[0]))
409 if result[1] == '0': 420 if result[1] == '0':
410 self.error_out('No ONT reads found') 421 warning = 'No ONT reads found'
422 self.assembly_notes = self.assembly_notes.append(pandas.Series(warning))
411 self.ont_n50, self.ont_read_count, ont_raw_bases = [int(i) for i in result] 423 self.ont_n50, self.ont_read_count, ont_raw_bases = [int(i) for i in result]
412 command = ' '.join([opener, 424 command = ' '.join([opener,
413 fastq_file, 425 fastq_file,
414 '| awk \'{getline;print length($0);getline;getline;}\'']) 426 '| awk \'{getline;print length($0);getline;getline;}\''])
415 result = self.run_command(command) 427 result = self.run_command(command)
528 for circos_file in self.circos_files: 540 for circos_file in self.circos_files:
529 contig = os.path.basename(circos_file) 541 contig = os.path.basename(circos_file)
530 contig_title = 'Alignment to %s' % contig 542 contig_title = 'Alignment to %s' % contig
531 self.doc.new_line() 543 self.doc.new_line()
532 self.doc.new_header(level=3, title=contig_title) 544 self.doc.new_header(level=3, title=contig_title)
533 self.doc.new_line('Blue indicates aligned sequences (to the reference) and yellow indicates missing sequences')
534 self.doc.new_line(self.doc.new_inline_image(text='contig_title', path=os.path.abspath(circos_file))) 545 self.doc.new_line(self.doc.new_inline_image(text='contig_title', path=os.path.abspath(circos_file)))
535 self.doc.new_line('<div style="page-break-after: always;"></div>') 546 self.doc.new_line('<div style="page-break-after: always;"></div>')
536 self.doc.new_line() 547 self.doc.new_line()
537 method = 'The genome assembly was aligned against the reference sequencing using dnadiff version %s.' % self.dnadiff_version 548 if self.dbkey == 'ref_genome':
549 headers = ["* Chromosome - NC_007530.2 Bacillus anthracis str. 'Ames Ancestor', complete sequence",
550 "* pXO1 - NC_007322.2 Bacillus anthracis str. 'Ames Ancestor' plasmid pXO1, complete sequence",
551 "* pXO2 - NC_007323.3 Bacillus anthracis str. 'Ames Ancestor' plasmid pXO2, complete sequence"]
552 method = '\n'.join(headers)
553 self.methods[self.reference_genome_title] = self.methods[self.reference_genome_title].append(pandas.Series(method))
554 method = 'The genome assembly was aligned against the reference sequence using %s.' % self.dnadiff_version
538 self.methods[self.reference_methods_title] = self.methods[self.reference_methods_title].append(pandas.Series(method)) 555 self.methods[self.reference_methods_title] = self.methods[self.reference_methods_title].append(pandas.Series(method))
539 556
540 def add_features(self): 557 def add_features(self):
541 self.ofh.write("\nXXXXXX In add_features\n\n") 558 self.ofh.write("\nXXXXXX In add_features\n\n")
542 if len(self.feature_bed_files) == 0: 559 if len(self.feature_bed_files) == 0:
778 self.methods[self.basecalling_methods_title] = pandas.Series(methods) 795 self.methods[self.basecalling_methods_title] = pandas.Series(methods)
779 # self.add_illumina_library_information() 796 # self.add_illumina_library_information()
780 self.add_contig_info() 797 self.add_contig_info()
781 self.evaluate_assembly() 798 self.evaluate_assembly()
782 self.add_assembly_information() 799 self.add_assembly_information()
783 if self.flye_assembly_info_file is not None: 800 if self.assembler_version is not None:
784 method = 'ONT reads were assembled using %s' % self.flye_version.rstrip('assembly info') 801 if self.read_type == 'ONT':
785 self.methods[self.assembly_methods_title] = self.methods[self.assembly_methods_title].append(pandas.Series(method)) 802 method = 'ONT reads were assembled using %s' % self.assembler_version
786 # Pull in the assembly summary and look at the coverage. 803 self.methods[self.assembly_methods_title] = self.methods[self.assembly_methods_title].append(pandas.Series(method))
787 assembly_info = pandas.read_csv(self.flye_assembly_info_file, header=0, index_col=0, sep='\t') 804 # Pull in the assembly summary and look at the coverage.
788 # Look for non-circular contigs. 805 assembly_info = pandas.read_csv(self.flye_assembly_info_file, header=0, index_col=0, sep='\t')
789 open_contigs = assembly_info.loc[assembly_info['circ.'] == 'N', :] 806 # Look for non-circular contigs.
790 if open_contigs.shape[0] > 0: 807 open_contigs = assembly_info.loc[assembly_info['circ.'] == 'N', :]
791 open_contig_ids = open_contigs.index.values 808 if open_contigs.shape[0] > 0:
792 warning = 'Flye reported {:d} open contigs ({:s}); assembly may be incomplete.'.format(open_contigs.shape[0], ', '.join(open_contig_ids)) 809 open_contig_ids = open_contigs.index.values
793 self.assembly_notes = self.assembly_notes.append(pandas.Series(warning)) 810 warning = 'Flye reported {:d} open contigs ({:s}); assembly may be incomplete.'.format(open_contigs.shape[0], ', '.join(open_contig_ids))
811 self.assembly_notes = self.assembly_notes.append(pandas.Series(warning))
812 else:
813 method = 'Illumina reads were assembled using %s' % self.assembler_version
794 if self.did_medaka_ont_assembly: 814 if self.did_medaka_ont_assembly:
795 method = 'the genome assembly was polished using ont reads and medaka.' 815 method = 'the genome assembly was polished using ont reads and medaka.'
796 self.methods[self.assembly_methods_title] = self.methods[self.assembly_methods_title].append(pandas.series(method)) 816 self.methods[self.assembly_methods_title] = self.methods[self.assembly_methods_title].append(pandas.series(method))
797 self.add_assembly_notes() 817 self.add_assembly_notes()
798 818
834 parser = argparse.ArgumentParser() 854 parser = argparse.ArgumentParser()
835 855
836 parser.add_argument('--amr_deletions_file', action='store', dest='amr_deletions_file', help='AMR deletions BED file') 856 parser.add_argument('--amr_deletions_file', action='store', dest='amr_deletions_file', help='AMR deletions BED file')
837 parser.add_argument('--amr_matrix_png_dir', action='store', dest='amr_matrix_png_dir', help='Directory of AMR matrix PNG files') 857 parser.add_argument('--amr_matrix_png_dir', action='store', dest='amr_matrix_png_dir', help='Directory of AMR matrix PNG files')
838 parser.add_argument('--analysis_name', action='store', dest='analysis_name', help='Sample identifier') 858 parser.add_argument('--analysis_name', action='store', dest='analysis_name', help='Sample identifier')
859 parser.add_argument('--assembler_version', action='store', dest='assembler_version', default=None, help='Assembler version string')
839 parser.add_argument('--assembly_fasta_file', action='store', dest='assembly_fasta_file', help='Assembly fasta file') 860 parser.add_argument('--assembly_fasta_file', action='store', dest='assembly_fasta_file', help='Assembly fasta file')
840 parser.add_argument('--assembly_name', action='store', dest='assembly_name', help='Assembly identifier') 861 parser.add_argument('--assembly_name', action='store', dest='assembly_name', help='Assembly identifier')
841 parser.add_argument('--bedtools_version', action='store', dest='bedtools_version', default=None, help='Bedtools version string') 862 parser.add_argument('--bedtools_version', action='store', dest='bedtools_version', default=None, help='Bedtools version string')
842 parser.add_argument('--blastn_version', action='store', dest='blastn_version', default=None, help='Blastn version string') 863 parser.add_argument('--blastn_version', action='store', dest='blastn_version', default=None, help='Blastn version string')
843 parser.add_argument('--circos_png_dir', action='store', dest='circos_png_dir', help='Directory of circos PNG files') 864 parser.add_argument('--circos_png_dir', action='store', dest='circos_png_dir', help='Directory of circos PNG files')
845 parser.add_argument('--contig_coverage_file', action='store', dest='contig_coverage_file', help='Contig coverage TSV file') 866 parser.add_argument('--contig_coverage_file', action='store', dest='contig_coverage_file', help='Contig coverage TSV file')
846 parser.add_argument('--dbkey', action='store', dest='dbkey', help='Reference genome identifier') 867 parser.add_argument('--dbkey', action='store', dest='dbkey', help='Reference genome identifier')
847 parser.add_argument('--dnadiff_snps_file', action='store', dest='dnadiff_snps_file', help='DNAdiff snps tabular file') 868 parser.add_argument('--dnadiff_snps_file', action='store', dest='dnadiff_snps_file', help='DNAdiff snps tabular file')
848 parser.add_argument('--dnadiff_version', action='store', dest='dnadiff_version', default=None, help='DNAdiff version string') 869 parser.add_argument('--dnadiff_version', action='store', dest='dnadiff_version', default=None, help='DNAdiff version string')
849 parser.add_argument('--errors_file', action='store', dest='errors_file', default=None, help='AMR mutations errors encountered txt file') 870 parser.add_argument('--errors_file', action='store', dest='errors_file', default=None, help='AMR mutations errors encountered txt file')
871 parser.add_argument('--fastq_file', action='store', dest='fastq_file', help='Input sample')
850 parser.add_argument('--feature_bed_dir', action='store', dest='feature_bed_dir', help='Directory of best feature hits bed files') 872 parser.add_argument('--feature_bed_dir', action='store', dest='feature_bed_dir', help='Directory of best feature hits bed files')
851 parser.add_argument('--feature_png_dir', action='store', dest='feature_png_dir', help='Directory of best feature hits png files') 873 parser.add_argument('--feature_png_dir', action='store', dest='feature_png_dir', help='Directory of best feature hits png files')
852 parser.add_argument('--flye_assembly_info_file', action='store', dest='flye_assembly_info_file', default=None, help='Flye assembly info tabular file') 874 parser.add_argument('--flye_assembly_info_file', action='store', dest='flye_assembly_info_file', default=None, help='Flye assembly info tabular file')
853 parser.add_argument('--flye_version', action='store', dest='flye_version', default=None, help='Flye version string')
854 parser.add_argument('--genome_insertions_file', action='store', dest='genome_insertions_file', help='Genome insertions BED file') 875 parser.add_argument('--genome_insertions_file', action='store', dest='genome_insertions_file', help='Genome insertions BED file')
855 parser.add_argument('--gzipped', action='store_true', dest='gzipped', default=False, help='Input sample is gzipped') 876 parser.add_argument('--gzipped', action='store_true', dest='gzipped', default=False, help='Input sample is gzipped')
856 parser.add_argument('--ont_fastq_file', action='store', dest='ont_fastq_file', help='Input sample')
857 parser.add_argument('--kraken2_report_file', action='store', dest='kraken2_report_file', default=None, help='kraken2 report file') 877 parser.add_argument('--kraken2_report_file', action='store', dest='kraken2_report_file', default=None, help='kraken2 report file')
858 parser.add_argument('--kraken2_version', action='store', dest='kraken2_version', default=None, help='kraken2 version string') 878 parser.add_argument('--kraken2_version', action='store', dest='kraken2_version', default=None, help='kraken2 version string')
859 parser.add_argument('--minimap2_version', action='store', dest='minimap2_version', default=None, help='minimap2 version string') 879 parser.add_argument('--minimap2_version', action='store', dest='minimap2_version', default=None, help='minimap2 version string')
860 parser.add_argument('--mutation_regions_bed_file', action='store', dest='mutation_regions_bed_file', help='AMR mutation regions BRD file') 880 parser.add_argument('--mutation_regions_bed_file', action='store', dest='mutation_regions_bed_file', help='AMR mutation regions BRD file')
861 parser.add_argument('--mutation_regions_dir', action='store', dest='mutation_regions_dir', help='Directory of mutation regions TSV files') 881 parser.add_argument('--mutation_regions_dir', action='store', dest='mutation_regions_dir', help='Directory of mutation regions TSV files')
896 mutation_regions_files.append(file_path) 916 mutation_regions_files.append(file_path)
897 917
898 markdown_report = PimaReport(args.analysis_name, 918 markdown_report = PimaReport(args.analysis_name,
899 args.amr_deletions_file, 919 args.amr_deletions_file,
900 amr_matrix_files, 920 amr_matrix_files,
921 args.assembler_version,
901 args.assembly_fasta_file, 922 args.assembly_fasta_file,
902 args.assembly_name, 923 args.assembly_name,
903 args.bedtools_version, 924 args.bedtools_version,
904 args.blastn_version, 925 args.blastn_version,
905 circos_files, 926 circos_files,
907 args.contig_coverage_file, 928 args.contig_coverage_file,
908 args.dbkey, 929 args.dbkey,
909 args.dnadiff_snps_file, 930 args.dnadiff_snps_file,
910 args.dnadiff_version, 931 args.dnadiff_version,
911 args.errors_file, 932 args.errors_file,
933 args.fastq_file,
912 feature_bed_files, 934 feature_bed_files,
913 feature_png_files, 935 feature_png_files,
914 args.flye_assembly_info_file, 936 args.flye_assembly_info_file,
915 args.flye_version,
916 args.genome_insertions_file, 937 args.genome_insertions_file,
917 args.gzipped, 938 args.gzipped,
918 args.kraken2_report_file, 939 args.kraken2_report_file,
919 args.kraken2_version, 940 args.kraken2_version,
920 args.minimap2_version, 941 args.minimap2_version,
921 args.mutation_regions_bed_file, 942 args.mutation_regions_bed_file,
922 mutation_regions_files, 943 mutation_regions_files,
923 args.ont_fastq_file,
924 args.pima_css, 944 args.pima_css,
925 args.plasmids_file, 945 args.plasmids_file,
926 args.quast_report_file, 946 args.quast_report_file,
927 args.read_type, 947 args.read_type,
928 args.reference_insertions_file, 948 args.reference_insertions_file,