def _wholegenome(reference, query, read_length, read_depth, min_alignment_quality, max_direct_repeat_length,
large_insertion_cutoff, query_id, output_prefix):
min_alignment_inner_length = max_direct_repeat_length + 1
if not bwatools.genome_is_indexed(reference):
click.echo("Indexing reference...")
bwatools.index_genome(reference)
else:
click.echo("Reference already indexed...")
if not bowtie2tools.genome_is_indexed(query):
click.echo("Indexing query...")
bowtie2tools.index_genome(query)
else:
click.echo("Query already indexed...")
click.echo("Making query reads...")
query_reads_path = output_prefix + '.query.tmp.fq'
make_reads(query, query_reads_path, read_length, read_depth)
click.echo("Aligning query reads to reference...")
out_sam = output_prefix + '.query.reference.tmp.sam'
bwatools.align_to_genome_se(query_reads_path, reference, out_sam, threads=1, verbose=False)
click.echo("Sorting and indexing alignment file...")
out_bam = output_prefix + '.query.reference.tmp.bam'
samtools.sort_coordinate(out_sam, out_bam, delete_in_bam=True)
samtools.index(out_bam)
find_file = output_prefix + '.find.tsv'
_find(out_bam, min_softclip_length=8, min_softclip_count=1, min_alignment_quality=min_alignment_quality,
min_alignment_inner_length=min_alignment_inner_length, min_distance_to_mate=max_direct_repeat_length + 2,
min_softclip_ratio=0.01, max_indel_ratio=0.0, large_insertion_cutoff=large_insertion_cutoff,
min_count_consensus=1, sample_id=query_id, output_file=find_file)
pair_file = output_prefix + '.pair.tsv'
_pair(find_file, out_bam, reference, max_direct_repeat_length=max_direct_repeat_length,
min_alignment_quality=min_alignment_quality, min_alignment_inner_length=min_alignment_inner_length,
max_junction_spanning_prop=0.01, large_insertion_cutoff=large_insertion_cutoff, output_file=pair_file)
inferseq_file = output_prefix + '.inferseq.tsv'
_inferseq_assembly(pair_file, out_bam, query, reference, min_perc_identity=0.95,
max_internal_softclip_prop=0.01, max_inferseq_size=500000,
min_inferseq_size=30, keep_intermediate=False, output_file=inferseq_file)
shell('rm %s %s %s' % (query_reads_path, out_bam, out_bam+'.bai'))
def _makedatabase(inferseqfiles, minimum_size, maximum_size, threads, memory, force, output_dir, prefix):
click.echo("Parsing inferseq files")
if len(inferseqfiles) == 1 and is_path_list(inferseqfiles[0]):
inferseqfiles = [l.strip() for l in open(inferseqfiles[0], 'r')]
click.echo("Combining the inferseq files...")
inferseq = combine_inferseq_files(inferseqfiles, minimum_size, maximum_size)
database_maker = DatabaseMaker(inferseq, threads, memory, output_dir)
try:
makedirs(output_dir)
except FileExistsError:
if force:
click.echo('Deleting old database directory...')
rmtree(output_dir)
makedirs(output_dir)
else:
click.echo('Output directory already exists. Use --force to overwrite directory.')
sys.exit()
if inferseq.shape[0] == 0:
click.echo("No termini found in the input file...")
clustered_seqs = database_maker.get_header_dataframe()
else:
cluster_fna = database_maker.run_cluster_seqs()
outfile = join(output_dir, prefix+'.fna')
rename(cluster_fna, outfile)
database_maker.remove_int_files()
click.echo("Indexing database for use with bowtie2")
index_genome(outfile)
def index_genome(inferseq_assembly):
if not bowtie2tools.genome_is_indexed(inferseq_assembly):
click.echo("Indexing inferseq assembly...")
bowtie2tools.index_genome(inferseq_assembly)
click.echo("Genome has been indexed...")
def index_database(inferseq_database):
if not bowtie2tools.genome_is_indexed(inferseq_database):
click.echo("Indexing inferseq database...")
bowtie2tools.index_genome(inferseq_database)
click.echo("Database has been indexed...")
def index_genome(inferseq_reference):
if not bowtie2tools.genome_is_indexed(inferseq_reference):
click.echo("Indexing inferseq reference genome...")
bowtie2tools.index_genome(inferseq_reference)
click.echo("Genome has been indexed...")