diff --git a/cnvpipelines.py b/cnvpipelines.py index 022472450405e095498c250908e984eb91e8945a..ca3317293457acbc46c21a6c06d181772d336ae2 100755 --- a/cnvpipelines.py +++ b/cnvpipelines.py @@ -118,13 +118,13 @@ class CnvPipeline: # Some checks: if not os.path.isfile(sample): - raise ValueError("Sample file '%s' does not exists" % sample) + raise ValueError("Sample bam file '%s' does not exists" % sample) bam = pysam.AlignmentFile(sample) if "RG" not in bam.header: - raise ValueError("Sample file '%s' has no RG tag in headers" % sample) + raise ValueError("Sample bam file '%s' has no RG tag in headers" % sample) samples_list = bam.header['RG'] if len(samples_list) == 0: - raise ValueError("Sample file '%s' has none sample" % sample) + raise ValueError("Sample bam file '%s' empty read group (RG) list" % sample) # Get sample name: if len(samples_list) > 1: @@ -171,10 +171,10 @@ class CnvPipeline: if len(samples_name) > 0: ## Sample names for the batch self._write_samples(samples_name, smple_file + "." + str(n_block)) - + if len(all_samples_name) > 0: ## All samples names - self._write_samples(all_samples_name, smple_file) - + self._write_samples(all_samples_name, smple_file) + @staticmethod def _fail(message): @@ -649,7 +649,7 @@ class CnvPipeline: def run_detection(self, reference, tools, samples, variant_types, chromosomes="all", force_wdir=False, batches=-1, batches_parallel=5, refbundle=None, force_all_chr=False, **kwargs): - + print("rundetection",self, reference, tools, samples, variant_types, chromosomes="all", force_wdir=False, batches=-1,batches_parallel=5, refbundle=None, force_all_chr=False, **kwargs) """ Run a detection workflow @@ -1128,7 +1128,7 @@ class CnvPipeline: # Create sample file for fastq files: samples_file_fq = os.path.join(self.wdir, "samples.yml") samples_file_d = os.path.join(self.wdir, "samples.list") - + self._create_samples_fastq_simulaton(nb_inds, samples_file_fq) self._create_samples_detection_simulation(nb_inds, samples_file_d) @@ -1533,7 +1533,7 @@ if __name__ == "__main__": test_parser.set_defaults(func="run_test") args = parser.parse_args() - + if args.func == "run_detection" and args.refbundle is None and "genomestrip" in args.tools: diff --git a/snakecnv/align.snk b/snakecnv/align.snk index d8067cc7b08c64257b3172d2a7698540586f6a5e..f634d623a0fe070da9e9d7b34ca54939c64b369a 100644 --- a/snakecnv/align.snk +++ b/snakecnv/align.snk @@ -48,7 +48,7 @@ rule bwamap: output: bam = temp("bwa/{sample}.bam") threads: - get_threads("bwamap", 4) + get_threads("bwamap", 8) log: stdout = "logs/map_{sample}.o", stderr = "logs/map_{sample}.e" @@ -91,4 +91,4 @@ rule markduplicate: """ picard MarkDuplicates I={input.bam} O={output.bam} M={output.metrics} REMOVE_DUPLICATES=true 1> {log.stdout} \ 2> {log.stderr}; - """ \ No newline at end of file + """ diff --git a/snakecnv/bin/findNstretches.py b/snakecnv/bin/findNstretches.py index 7a5b7a36c2b405f383354d81a980be74bfddb44c..b18025168b105a846df411d2a8c61813ab49430a 100755 --- a/snakecnv/bin/findNstretches.py +++ b/snakecnv/bin/findNstretches.py @@ -24,7 +24,7 @@ def find_chrom_Nstretches(chrom, fastafile, cutoff): p = re.compile("N{%s,}" % cutoff) with FastaFile(fastafile) as fasta: sequence = fasta.fetch(chrom) - gaps = [(chrom, m.start(), m.end() + 1) for m in re.finditer(p, sequence)] + gaps = [(chrom, m.start(), m.end()) for m in re.finditer(p, sequence)] return gaps