def seq_msp(fafile,seqfile,genome='mm9',convert=True,bedFrag=False):
start=-3
hang='NNN'
match=[]
#find CCGG positions using Fasta file
fa=open(fafile)
for line in fa:
l=line.strip('\n')
if l[0]=='>':
ch=l[1:]
continue
if l=='NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN':
start+=len(l)
hang=l[-3:]
continue
else:
seq=hang+l
mers=[seq[x:(x+4)] for x in range(len(seq)-4)]
for i,m in enumerate(mers):
if m=='ccgg': match.append(start+i)
hang=seq[-3:]
start+=len(l)
print len(match)
fa.close()
FRAG=[]
#find cut sites 40-220bp and save as tuple
for x,y in zip(match[:-1],match[1:]):
d=y-x
if d>40 and d<250: FRAG.append((x,y))
print len(FRAG)
#nibDB the cut sites 40bp 5'-3' and
#save each as a pair of Fasta items with keys chr:position(strand)
seq_dict={}
ids,loci=[],[]
BF=[]
for x,y in FRAG:
if bedFrag: BF.append([ch,str(x+1),str(y+3)])
#for x
start=x+1
stop=x+41
key=ch+':'+str(start)+'+'
loc=(ch,start,stop,'+')
ids.append(key)
loci.append(loc)
#for y
start=y-37
stop=y+3
key=ch+':'+str(stop)+'-'
loc=(ch,start,stop,'-')
ids.append(key)
loci.append(loc)
if bedFrag: np.savetxt(seqfile.replace('.fa','_frag.bed'),BF,fmt='%s',delimiter='\t')
if genome=='hg18': DB=NibDB(nib_dirs='/nfs/genomes/human_gp_mar_06/')
else: DB=NibDB(nib_dirs=chipsequtil.get_org_settings('mm9')['genome_dir'])
fa_ids,seqs=DB.get_fasta_batch(loci)
for id,seq in zip(ids,seqs):
if convert: biseq=seq.replace('c','t')
else: biseq=seq
if id[-1]=='+':
seq_dict[id]=biseq
else:
#seq_dict[id]=seq[::-1]
seq_dict[id]=biseq
Fasta.write(seq_dict,seqfile)
if opts.gene_list :
gene_list = [x.strip() for x in open(opts.gene_list).readlines()]
id_index = 'bin'
if opts.gene_type != gene_type_choices[0] :
if opts.gene_type == 'refgene' :
id_index = 'name'
seq_recs = []
gene_map = defaultdict(list)
for rec in refgene_f :
if gene_list and rec[id_index] not in gene_list : continue # skip this one
st, end = max(0,int(rec['txStart'])-opts.upstream), min(int(rec['txStart'])+opts.downstream,nib_db.db_info[rec['chrom']]['nbases'])
key = (rec['chrom'],st,end,rec['strand'])
seq_recs.append(key)
gene_map[key[:-1]].append(rec['bin']+'/'+rec['name'])
fasta_recs = nib_db.get_fasta_batch(seq_recs)
out_f = open(opts.output,'w') if opts.output else sys.stdout
header_regex = re.compile('^.*(chr[0-9MXY]+).*:([0-9]+)-([0-9]+).*$')
for header, seq in zip(*fasta_recs) :
# map sequences back to gene names using the header
reg_obj = header_regex.search(header)
if reg_obj is not None :
chrm,st,end = reg_obj.groups()
gene_names = gene_map.get((chrm,int(st),int(end)))
if gene_names is not None :
header = header.strip()+':'+','.join(gene_names)+'\n'
out_f.write(header+seq+'\n')
num_to_sample = int(sample_percent*(end_i-st_i))
inds_to_sample = random.sample(xrange(st_i,end_i),num_to_sample)
# we memoize the sequences we've seen before so we don't fetch seqs
# unnecessarily
unmemoed_inds_to_sample = set(inds_to_sample).difference(set(pval_bin_memo.keys()))
bin_fasta_batch = []
for peak_i in unmemoed_inds_to_sample :
bin_fasta_batch.append((str(all_peaks[peak_i]['chr']),
int(all_peaks[peak_i]['start']),
int(all_peaks[peak_i]['end']),
'+'))
if len(bin_fasta_batch) != 0 :
bin_headers, bin_seq = nibDb.get_fasta_batch(bin_fasta_batch)
for i, ind in enumerate(unmemoed_inds_to_sample) :
pval_bin_memo[ind] = bin_seq[i].upper()
# score the sequences
pval_bin_pvals.append([])
for ind in inds_to_sample :
max_score = m.bestscan(pval_bin_memo[ind])
max_score = (max_score-m.minscore)/(m.maxscore-m.minscore)
pval_bin_pvals[-1].append(max_score)
pval_bin_pvals[-1] = np.array(pval_bin_pvals[-1])
mp.figure(figsize=(4,4))
font = {'size':'9'}
