def make_fasta_from_list(querylist, queryfasta, gaplen, seqoutname,
outfilename):
### Query list element format
# Gap: [61252 , (0:61252) , gap , 61252 , 0]
# [length , (T_start:Tstop) , "gap" , length , 0]
# Object: [b40-14.HS_iter4_seq3733|+ , (61252:6463804) , 93612:7595148 , -6402552 , 4526208]
# [ID|strand , (T_start:Tstop) , Q_start:Q_stop , -(alignment length) , matches]
gaplen = int(gaplen)
seq = Seq("")
seq.id = seqoutname
for CompntId in querylist:
Id, T_range, Q_range, alignment, matches = CompntId
if not Q_range == "gap":
CompntId_name = Id[:-2]
Orientation = Id[-1]
# Add gap between Components
if str(seq) != "":
seq = seq + "N" * gaplen
if Orientation == "-":
my_sub_seq = queryfasta[CompntId_name].reverse_complement()
else:
my_sub_seq = queryfasta[CompntId_name]
seq = seq + my_sub_seq
# Print the entire sequence
seq.id = seqoutname
seq.description = ""
print >> outfilename, seq.format('fasta')
def write_unmapped_scaffold(outblocks, scaffold, stats, unmapped_output,
genome, chromosomes):
seq = Seq('')
dbblocks = []
mapped = False
scaffold_chromosomes = []
for block in outblocks:
if genome.revised_db:
dbblocks.append([
block.chromosome, block.cm, scaffold, block.start, block.end,
block.length
])
if genome.revised_fasta:
seq += genome.sequences[scaffold][block.start - 1:block.end]
if block.chromosome != '0':
scaffold_chromosomes.append(int(block.chromosome))
stats['scaffolds'] += 1
scaffold_chromosomes = set(scaffold_chromosomes)
scaffold_start, scaffold_end = outblocks[0].start, outblocks[-1].end
scaffold_length = scaffold_end - scaffold_start + 1
stats['scaffold_length'] += scaffold_length
if seq.features or len(scaffold_chromosomes) > 0 and len(dbblocks) > 1:
unmapped_output.append(
[gd.Block(scaffold, scaffold_start, scaffold_end)])
scaffold_name = genome.revised + "{:05d}".format(genome.revised_count)
genome.revised_count += 1
genome.revised_names["{}_{}_{}".format(scaffold, scaffold_start,
scaffold_end)] = scaffold_name
stats['written_scaffolds'] += 1
stats['written_length'] += scaffold_length
if genome.revised_db:
for block in dbblocks:
genome.revised_db.execute(
"insert into scaffold_map values (?,?,?,?,?,?)", block)
if genome.revised_fasta:
seq.description = "length={}".format(len(seq))
seq.id = scaffold_name
SeqIO.write(seq, genome.revised_fasta, "fasta")
if len(scaffold_chromosomes) > 0:
chrom = next(iter(scaffold_chromosomes))
chr_unmapped_end = chromosomes[
chrom].unmapped_start + scaffold_length - 1
chromosomes[chrom].agp.append(
"{}\t{}\t{}\t{}\tD\t{}\t1\t{}\t+\n".format(
"chr{}_unmapped".format(chrom),
chromosomes[chrom].unmapped_start, chr_unmapped_end,
chromosomes[chrom].unmapped_part, scaffold_name,
scaffold_length))
chromosomes[chrom].unmapped_part += 1
chromosomes[chrom].agp.append(
"{}\t{}\t{}\t{}\tN\t100\tfragment\tno\n".format(
"chr{}_unmapped".format(chrom), chr_unmapped_end + 1,
chr_unmapped_end + 100, chromosomes[chrom].unmapped_part))
chromosomes[chrom].unmapped_part += 1
chromosomes[chrom].unmapped_start = chr_unmapped_end + 101
else:
stats['discard_scaffolds'] += 1
stats['discard_length'] += scaffold_length
for dbblock in dbblocks:
dblength = dbblock[5]
partslength = 0
for newpart in genome.newparts[scaffold]:
for origpart in genome.origparts[newpart.oldname]:
if dbblock[2] == origpart.newname and (
dbblock[3] <= origpart.newstart <= dbblock[4]
or dbblock[3] <= origpart.newend <= dbblock[4]):
if origpart.parttype in ['active', 'retained']:
partslength += origpart.newend - origpart.newstart + 1
origpart.parttype = 'removed'
if dblength != partslength:
print(scaffold, dblength, partslength, dbblock)
def write_unmapped_scaffold(outblocks, scaffold, stats, unmapped_output, genome, chromosomes):
seq = Seq('')
dbblocks = []
mapped = False
scaffold_chromosomes = []
for block in outblocks:
if genome.revised_db:
dbblocks.append([block.chromosome, block.cm, scaffold, block.start, block.end, block.length])
if genome.revised_fasta:
seq += genome.sequences[scaffold][block.start-1:block.end]
if block.chromosome != '0':
scaffold_chromosomes.append(int(block.chromosome))
stats['scaffolds'] += 1
scaffold_chromosomes = set(scaffold_chromosomes)
scaffold_start, scaffold_end = outblocks[0].start, outblocks[-1].end
scaffold_length = scaffold_end - scaffold_start + 1
stats['scaffold_length'] += scaffold_length
if seq.features or len(scaffold_chromosomes) > 0 and len(dbblocks) > 1:
unmapped_output.append([gd.Block(scaffold, scaffold_start, scaffold_end)])
scaffold_name = genome.revised + "{:05d}".format(genome.revised_count)
genome.revised_count += 1
genome.revised_names["{}_{}_{}".format(scaffold, scaffold_start, scaffold_end)] = scaffold_name
stats['written_scaffolds'] += 1
stats['written_length'] += scaffold_length
if genome.revised_db:
for block in dbblocks:
genome.revised_db.execute("insert into scaffold_map values (?,?,?,?,?,?)", block)
if genome.revised_fasta:
seq.description = "length={}".format(len(seq))
seq.id = scaffold_name
SeqIO.write(seq, genome.revised_fasta, "fasta")
if len(scaffold_chromosomes) > 0:
chrom = next(iter(scaffold_chromosomes))
chr_unmapped_end = chromosomes[chrom].unmapped_start + scaffold_length - 1
chromosomes[chrom].agp.append("{}\t{}\t{}\t{}\tD\t{}\t1\t{}\t+\n".format("chr{}_unmapped".format(chrom), chromosomes[chrom].unmapped_start, chr_unmapped_end, chromosomes[chrom].unmapped_part, scaffold_name, scaffold_length))
chromosomes[chrom].unmapped_part += 1
chromosomes[chrom].agp.append("{}\t{}\t{}\t{}\tN\t100\tfragment\tno\n".format("chr{}_unmapped".format(chrom), chr_unmapped_end+1, chr_unmapped_end+100, chromosomes[chrom].unmapped_part))
chromosomes[chrom].unmapped_part += 1
chromosomes[chrom].unmapped_start = chr_unmapped_end + 101
else:
stats['discard_scaffolds'] += 1
stats['discard_length'] += scaffold_length
for dbblock in dbblocks:
dblength = dbblock[5]
partslength = 0
for newpart in genome.newparts[scaffold]:
for origpart in genome.origparts[newpart.oldname]:
if dbblock[2] == origpart.newname and (dbblock[3] <= origpart.newstart <= dbblock[4] or dbblock[3] <= origpart.newend <= dbblock[4]):
if origpart.parttype in ['active', 'retained']:
partslength += origpart.newend - origpart.newstart + 1
origpart.parttype = 'removed'
if dblength != partslength:
print(scaffold, dblength, partslength, dbblock)
