def run(self):
tmp = run_cmd([
'Rscript', RQ_PLOT, '{}/reads_quality_plot/'.format(OutDir),
SampleInf
])
with self.output().open('w') as reads_quality_plot_log:
reads_quality_plot_log.write(tmp)
def run(self):
download_biomart_go_cmd = [
'Rscript', BIOMART_DOWNLOAD, '--gene_tr_file',
'{0}/{1}.gene_trans_map.txt'.format(annotation_dir, species_latin),
'--output', '{0}/{1}'.format(annotation_dir, species_latin),
'--species', '{}'.format(species_ensembl)
]
get_topgo_go_cmd = [
'python', TOPGO_FORMAT, '--biomart_go',
'{0}/{1}.go.txt'.format(annotation_dir, species_latin),
'--out_dir', '{}'.format(annotation_dir)
]
gene_go_anno_cmd = [
'python', GO_ANNO, '{0}/{1}.go.txt'.format(annotation_dir,
species_latin),
'{0}/{1}.go_detail.txt'.format(annotation_dir, species_latin),
'{0}/{1}.go_anno.txt'.format(annotation_dir, species_latin)
]
go_cmd_list = [
download_biomart_go_cmd, get_topgo_go_cmd, gene_go_anno_cmd
]
go_annotation_log_inf = run_cmd(go_cmd_list)
with self.output().open('w') as go_annotation_log:
go_annotation_log.write(go_annotation_log_inf)
def run(self):
log_dir = path.join(OutDir, 'logs')
kallisto_dir = path.join(OutDir, 'kallisto')
tmp = run_cmd(['mkdir', '-p', log_dir, kallisto_dir])
with self.output().open('w') as prepare_logs:
prepare_logs.write(tmp)
def run(self):
tmp = run_cmd([
'python', FASTQC_SUMMERY, '{}'.format(SampleInf),
'{}'.format(OutDir), '{}/fastqc_general_stats'.format(OutDir)
])
with self.output().open('w') as qc_summary:
qc_summary.write(tmp)
def run(self):
fasta_file_name = path.basename(self.fasta_file)
# orf_pred_cmd = ['TransDecoder.LongOrfs',
# '-t',
# '{}/stringtie_merge.fa'.format(OutDir),
# '--gene_trans_map',
# SampleInf]
# link_orf_cmd = ['ln',
# '-s',
# '{}/stringtie_merge.fa.transdecoder_dir/longest_orfs.pep'.format(
# OutDir),
# '{}/annotation']
blast_cmd = [
'blastp', '-query', self.fasta_file, '-db', self.database,
'-evalue', '1e-5', '-outfmt',
'6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore stitle',
'-max_target_seqs', '1', '-num_threads', BLAST_THREAD, '-out',
'{0}/{1}.blasttab'.format(self.blast_out_dir, fasta_file_name)
]
blast_log_inf = run_cmd(blast_cmd)
with self.output().open('w') as blast_log:
blast_log.write(blast_log_inf)
def run(self):
group1, group2 = self.compare
group1_bam_list = [
'{0}/{1}.bam'.format(BamDir, each_sample)
for each_sample in group_sample_df.loc[group1][1]
]
group2_bam_list = [
'{0}/{1}.bam'.format(BamDir, each_sample)
for each_sample in group_sample_df.loc[group2][1]
]
out_dir = path.join(OutDir, 'rmats',
'{0}_vs_{1}'.format(group1, group2))
tmp = run_cmd([
'RNASeq-MATS.py', '-b1', '{}'.format(','.join(group1_bam_list)),
'-b2', '{}'.format(','.join(group2_bam_list)), '-t', 'paired',
'-len', '150', '-gtf', '{}'.format(Gtf), '-o',
'{}'.format(out_dir), '-c',
'{}'.format(splicing_difference_cutoff), '-analysis',
'{}'.format(analysis_type), '-libType', '{}'.format(library_type),
'-novelSS', '{0}'.format(novel_splice)
])
with self.output().open('w') as run_rmats_log:
run_rmats_log.write(tmp)
def run(self):
log_dir = path.join(self.OutDir, 'logs')
qc_data_dir = path.join(self.OutDir, 'qc_data')
prepare_inf = run_cmd(['mkdir', '-p', log_dir, qc_data_dir])
with self.output().open('w') as prepare_logs:
prepare_logs.write(prepare_inf)
def run(self):
tmp = run_cmd([
'read_distribution.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-r', BedFile
])
with self.output().open('w') as read_distribution_inf:
read_distribution_inf.write(tmp)
def run(self):
log_dir = path.join(OutDir, 'logs')
mapping_dir = path.join(OutDir, 'mapping_dir')
bam_dir = path.join(OutDir, 'bam_dir')
tmp = run_cmd(['mkdir', '-p', log_dir, mapping_dir, bam_dir])
with self.output().open('w') as prepare_logs:
prepare_logs.write(tmp)
def run(self):
diff_cmd = []
diff_cmd.append(['Rscript',
DIFF_ANALYSIS,
'--kallisto_dir',
'{}/kallisto'.format(OutDir),
'--tpm_table',
'{}/expression_summary/Gene.tpm.txt'.format(OutDir),
'--compare',
self.compare,
'--sample_inf',
SampleInf,
'--gene2tr',
Gene2Tr,
'--out_dir',
'{0}/differential_analysis/{1}'.format(
OutDir, self.compare),
'--qvalue',
str(Qvalue),
'--logfc',
str(LogFC)])
if Anno:
diff_cmd.append(['python',
QUANT_ANNO,
'-a',
Anno,
'-q',
'{0}/differential_analysis/{1}'.format(
OutDir, self.compare)])
diff_inf = run_cmd(diff_cmd)
with self.output().open('w') as diff_log:
diff_log.write(diff_inf)
def run(self):
tmp = run_cmd([
'infer_experiment.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-r', BedFile
])
with self.output().open('w') as infer_experiment_log:
infer_experiment_log.write(tmp)
def run(self):
tmp = run_cmd([
'junction_saturation.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-r', BedFile, '-o',
'{0}/junction_saturation/{1}'.format(OutDir, self.sample)
])
with self.output().open('w') as junction_saturation_log:
junction_saturation_log.write(tmp)
def run(self):
log_dir = path.join(OutDir, 'logs')
rmats_dir = path.join(OutDir, 'rmats')
tmp = run_cmd(['mkdir', '-p', log_dir, rmats_dir])
with self.output().open('w') as prepare_log:
prepare_log.write(tmp)
def run(self):
tmp = run_cmd([
'geneBody_coverage.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-r', BedFile, '-o',
'{0}/genebody_coverage/{1}'.format(OutDir, self.sample)
])
with self.output().open('w') as genebody_coverage_log:
genebody_coverage_log.write(tmp)
def run(self):
tmp = run_cmd([
'python', READ_DISTRIBUTION_PLOT_PREPARE, SampleInf,
'{0}/read_distribution/'.format(OutDir)
])
with self.output().open('w') as read_distribution_plot_prepare_logs:
read_distribution_plot_prepare_logs.write(tmp)
def run(self):
tmp = run_cmd([
FASTQC, '{0}/{1}_1.clean.fq.gz'.format(CleanDir, self.sample),
'{0}/{1}_2.clean.fq.gz'.format(CleanDir, self.sample), '--extract',
'-o', '{}/fastqc_results'.format(OutDir)
])
with self.output().open('w') as qc_logs:
qc_logs.write(tmp)
def run(self):
tmp = run_cmd([
'inner_distance.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-r', BedFile, '-o',
'{0}/inner_distance/{1}'.format(OutDir, self.sample)
])
with self.output().open('w') as inner_distance_log:
inner_distance_log.write(tmp)
def run(self):
gc_dir = path.join(OutDir, 'gc_plot')
tmp = run_cmd([
'Rscript', GC_PLOT_R, '--gc_dir', gc_dir, '--out_dir', gc_dir,
'--sample_inf', SampleInf
])
with self.output().open('w') as gc_plot_log:
gc_plot_log.write(tmp)
def run(self):
tmp = run_cmd([
'read_duplication.py', '-i',
'{0}/{1}.bam'.format(BamDir, self.sample), '-o',
'{0}/read_duplication/{1}'.format(OutDir, self.sample)
])
with self.output().open('w') as read_duplication_log:
read_duplication_log.write(tmp)
def run(self):
log_dir = path.join(self.OutDir, 'logs')
bam_process = path.join(self.OutDir, 'bam')
tmp = run_cmd(['mkdir', '-p', log_dir, bam_process])
with self.output().open('w') as prepare_log:
prepare_log.write(tmp)
def run(self):
tmp = run_cmd([
'Rscript', GO_ANALYSIS_R, '--quant_dir', QuantDir, '--go_anno',
GoseqAnno, '--gene_length', GeneLen, '--topgo_anno', TopgoAnno,
'--out_dir', OutDir
])
with self.output().open('w') as go_logs_inf:
go_logs_inf.write(tmp)
def run(self):
log_dir = path.join(OutDir, 'logs')
assembly_dir = path.join(OutDir, 'assembly_dir')
annotation_dir = path.join(OutDir, 'annotation')
tmp = run_cmd(['mkdir', '-p', log_dir, assembly_dir, annotation_dir])
with self.output().open('w') as prepare_logs:
prepare_logs.write(tmp)
def run(self):
tmp = run_cmd([
'Rscript', KALLISTO_TO_DIFF, '--quant_dir',
'{}/kallisto'.format(OutDir), '--sample_inf', SampleInf,
'--gene2tr', Gene2Tr, '--out_dir', OutDir
])
with self.output().open('w') as run_diff_logs:
run_diff_logs.write(tmp)
def run(self):
transcript_feature_cmd = [
'python', TRANSCRIPT_FEATURE, '--gtf', ref_gtf, '--species',
species_latin, '--out_dir', annotation_dir
]
transcript_inf_table_log_inf = run_cmd(transcript_feature_cmd)
with self.output().open('w') as transcript_inf_table_log:
transcript_inf_table_log.write(transcript_inf_table_log_inf)
def run(self):
tmp = run_cmd([
'Rscript', ENRICH_BARPLOT_R, '--anno', GoseqAnno, '--table',
'{0}/go/{1}'.format(OutDir, self.compare), '--diff',
'{0}/differential_analysis/{1}'.format(QuantDir, self.compare),
'--type', 'go', '--out', '{0}/go/{1}'.format(OutDir, self.compare)
])
with self.output().open('w') as go_plot_logs:
go_plot_logs.write(tmp)
def run(self):
tmp = run_cmd([
'python', KEGG_ANALYSIS_PYTHON, '--blast_out', KEGGBlast,
'--species', KEGGAbbr, '--background', KEGGBackground,
'--diff_dir', '{}/differential_analysis/'.format(QuantDir),
'--out_dir', '{}/kegg'.format(OutDir)
])
with self.output().open('w') as kegg_log_inf:
kegg_log_inf.write(tmp)
def run(self):
tin_dir = path.join(OutDir, 'tin')
chdir(tin_dir)
tin_inf = run_cmd([
'tin.py', '-i', '{0}/{1}.bam'.format(BamDir, self.sample), '-r',
BedFile
])
with self.output().open('w') as tin_log:
tin_log.write(tin_inf)
def run(self):
tmp = run_cmd([
'Rscript', ENRICH_BARPLOT_R, '--anno', KEGGBlast, '--table',
'{0}/kegg/{1}'.format(OutDir, self.compare), '--diff',
'{0}/differential_analysis/{1}'.format(QuantDir,
self.compare), '--type',
'kegg', '--out', '{0}/kegg/{1}'.format(OutDir, self.compare)
])
with self.output().open('w') as kegg_plog_logs:
kegg_plog_logs.write(tmp)
def run(self):
tmp = run_cmd([
'java', '-jar', '{}'.format(GATK_PATH), '-T', 'VariantFiltration',
'-window', '35', '-cluster', '3', '-filterName', 'FS', '-filter',
'FS > 30.0', '-filterName', 'QD', '-filter', 'QD < 2.0', '-R',
'{}'.format(Ref), '-V', '{}/snp.raw.vcf'.format(OutDir), '-o',
'{}/snp.filter.vcf'.format(OutDir)
])
with self.output().open('w') as snp_filter_log:
snp_filter_log.write(tmp)
def run(self):
report_tb_cmd = ['Rscript',
QUANT_REPORT,
'--quant_dir',
OutDir,
'--sample_inf',
SampleInf]
report_tb_inf = run_cmd(report_tb_cmd)
with self.output().open('w') as report_log:
report_log.write(report_tb_inf)