def run_align(*data): """ Prepare data to run alignment step, only once for each project """ work_dir = dd.get_work_dir(data[0][0]) out_dir = op.join(work_dir, "seqcluster", "prepare") seq_out = op.join(out_dir, "seqs.fastq") bam_dir = op.join(work_dir, "align") new_bam_file = op.join(bam_dir, "seqs.bam") if not file_exists(new_bam_file): sample = process_alignment(data[0][0], [seq_out, None]) bam_file = dd.get_work_bam(sample[0][0]) shutil.move(bam_file, new_bam_file) shutil.move(bam_file + ".bai", new_bam_file + ".bai") shutil.rmtree(op.join(bam_dir, sample[0][0]["rgnames"]['sample'])) return data
def run_align(*data): """ Prepare data to run alignment step, only once for each project """ work_dir = dd.get_work_dir(data[0][0]) out_dir = op.join(work_dir, "seqcluster", "prepare") seq_out = op.join(out_dir, "seqs.fastq") bam_dir = op.join(work_dir, "align") new_bam_file = op.join(bam_dir, "seqs.bam") tools = dd.get_expression_caller(data[0][0]) if not file_exists(new_bam_file): sample = process_alignment(data[0][0], [seq_out, None]) bam_file = dd.get_work_bam(sample[0][0]) shutil.move(bam_file, new_bam_file) shutil.move(bam_file + ".bai", new_bam_file + ".bai") shutil.rmtree(op.join(bam_dir, sample[0][0]["rgnames"]['sample'])) for sample in data: sample[0]["align_bam"] = sample[0]["clean_fastq"] if "mirdeep2" in tools: novel_db = mirdeep.run(data) return data
def run_align(*data): """ Prepare data to run alignment step, only once for each project """ work_dir = dd.get_work_dir(data[0][0]) out_dir = op.join(work_dir, "seqcluster", "prepare") seq_out = op.join(out_dir, "seqs.fastq") bam_dir = op.join(work_dir, "align") new_bam_file = op.join(bam_dir, "seqs.bam") tools = dd.get_expression_caller(data[0][0]) if not file_exists(new_bam_file): sample = process_alignment(data[0][0], [seq_out, None]) bam_file = dd.get_work_bam(sample[0][0]) shutil.move(bam_file, new_bam_file) shutil.move(bam_file + ".bai", new_bam_file + ".bai") shutil.rmtree(op.join(bam_dir, sample[0][0]["rgnames"]['sample'])) for sample in data: # sample[0]["align_bam"] = sample[0]["clean_fastq"] sample[0]["cluster_bam"] = new_bam_file if "mirdeep2" in tools: novel_db = mirdeep.run(data) return data
def process_alignment(*args): return sample.process_alignment(*args)