def peak_to_seq_pipeline(untagged_peak_file, tagged1_peak_file, tagged2_peak_file, gff3, fasta, junction_df=None, branch_df=None, cutoff=5, name='CP_peaks'):
if 'pombe' in gff3: organism = 'pombe'
else: organism = None
transcript_dict = SP.build_transcript_dict(gff3, organism=organism)
print "Finding peaks in transcripts..."
print untagged_peak_file
untagged = CP_peaks_by_gene(untagged_peak_file, transcript_dict, cutoff=cutoff)
print tagged1_peak_file
tagged1 = CP_peaks_by_gene(tagged1_peak_file, transcript_dict, cutoff=cutoff)
print tagged2_peak_file
tagged2 = CP_peaks_by_gene(tagged2_peak_file, transcript_dict, cutoff=cutoff)
print "Comparing peaks between replicates..."
peaks = CP_compare_reps(untagged, tagged1, tagged2)
print "Checking peaks against annotation..."
ss_dict, flag = SP.list_splice_sites(gff3, organism=organism)
peak_df = CP_compare_to_annotation(peaks, ss_dict, transcript_dict)
peak_df = collapse_unpredicted_peaks(peak_df)
peak_df['genome coord'] = peak_df['chromosome'].str.cat(peak_df['position'].apply(int).apply(str), sep=':')
if type(fasta) == str:
fasta = SP.make_fasta_dict(fasta)
print "Adding sequences..."
peak_seq_df = add_sequence_to_df(peak_df, fasta, flag=flag)
print "Writing bedgraph..."
with open(name+'.bedgraph', 'w') as fout:
for ix, r in peak_seq_df.iterrows():
if r['strand'] == '+':
position2 = r['position']+1
height = r['height']
elif r['strand'] == '-':
position2 = r['position']-1
height = r['height']*-1
line_list = [r['chromosome'], r['position'], position2, height, '\n']
line_list = [str(x) for x in line_list]
line = '\t'.join(line_list)
fout.write(line)
print "Completed"
return peak_seq_df
'''Usage: python process_juncbase.py juncbase_output gff3_file fasta_file prefix
Please note: uses chr# format for chromosome names.'''
import sys
sys.path.insert(0, '/Users/jordanburke/RNA-is-awesome/')
sys.path.insert(0, '/home/jordan/RNA-is-awesome/')
sys.path.insert(0, '/home/jordan/CodeBase/RNA-is-awesome')
import SPTools as SP
juncbase_output = sys.argv[1]
gff3_file = sys.argv[2]
print gff3_file
fasta_file = sys.argv[3]
print fasta_file
prefix = sys.argv[4]
fasta_dict = SP.make_fasta_dict(fasta_file)
junc_df, sample_list = SP.read_juncbase_output(juncbase_output)
seq_df = SP.get_junction_sequence(junc_df, gff3_file, fasta_dict)
pos_matrix_5prime, pos_matrix_3prime = SP.generate_consensus_matrix(gff3_file, fasta_dict, PSSM=True)
scored_df = SP.score_new_sites(seq_df, pos_matrix_5prime, pos_matrix_3prime, PSSM=True)
filt_df1, filt_df2 = SP.reformat_df(scored_df, sample_list)
#intron_ret_df = filt_df[filt_df['as_event_type'] == 'intron_retention']
#intron_ret_df = intron_ret_df.reset_index(drop=True)
#alt_donor = filt_df[filt_df['as_event_type'] == 'alternative_donor']
#alt_acceptor = filt_df[filt_df['as_event_type'] == 'alternative_acceptor']
filt_df1.to_csv('{0}_seq_score.tsv'.format(prefix), sep='\t', float_format='%.2f')
filt_df2.to_csv('{0}_PSI.tsv'.format(prefix), sep='\t', float_format='%.2f')
def get_peak_sequence3(input_file, fasta_file, gff3_file, gene_list,window=1000):
'''Makes a fasta file of peak sequences based on an input file.
Input file columns - 1: transcript, 2: chromosome, 3: peak center
Remember to save the input file as an MS-DOS CSV file if exporting from Excel
Note: retrieves sequence
Parameters
----------
input_file : str
CSV file - see above
fasta_file : str
.json dictionary of chromosome sequences or fasta file (.json will load faster)
gff3_file : str
gff3 file for your organism
gene_list: str
CSV file
window : int, default 1000
Size of sequence to retrieve (peak boundaries are window/2 on either side of peak summit)
Outputs
------
peak_fasta : fasta file with all peak sequences
'''
tx_dict = SP.build_transcript_dict(gff3_file)
if type(fasta_file) == dict:
fa_dict = fasta_file
else:
if fasta_file.endswith('json'):
with open(fasta_file) as f:
fa_dict = json.load(f)
else:
fa_dict = SP.make_fasta_dict(fasta_file)
seq_list = []
no_tx_n = 1
with open(input_file,'r') as csv_file:
f = csv.reader(csv_file, dialect=csv.excel)
for row in f:
tx_list = row[0].split(',')
for tx in tx_list:
tx = tx+'T0'
if tx.startswith('3P'): tx = tx.split('3P')[1]
chrom = row[1]
if not chrom.startswith('chr'):
chrom = 'chr'+str(chrom)
try:
center = int(row[2])
start = center-window/2
end = center+window/2
if tx in tx_dict:
strand = tx_dict[tx][2]
else:
print tx+" not in GFF3 file"
strand = '+'
tx = chrom+':'+str(center)
seq = seq_simple(chrom, start, end, strand, fa_dict)
seq_list.append((tx,seq))
except ValueError:
pass
genes_of_interest=gene_list.split("\n")
with open('{0}_peak_sequences.fa'.format(input_file.split('/')[-1].split('.')[0]),'w') as fout:
for tx, seq in seq_list:
if tx in genes_of_interest:
fout.write('>'+tx+'\n')
fout.write(seq+'\n')
return seq_list
def get_peak_sequence3(input_file,
fasta_file,
gff3_file,
gene_list,
window=1000):
'''Makes a fasta file of peak sequences based on an input file.
Input file columns - 1: transcript, 2: chromosome, 3: peak center
Remember to save the input file as an MS-DOS CSV file if exporting from Excel
Note: retrieves sequence
Parameters
----------
input_file : str
CSV file - see above
fasta_file : str
.json dictionary of chromosome sequences or fasta file (.json will load faster)
gff3_file : str
gff3 file for your organism
gene_list: str
CSV file
window : int, default 1000
Size of sequence to retrieve (peak boundaries are window/2 on either side of peak summit)
Outputs
------
peak_fasta : fasta file with all peak sequences
'''
tx_dict = SP.build_transcript_dict(gff3_file)
if type(fasta_file) == dict:
fa_dict = fasta_file
else:
if fasta_file.endswith('json'):
with open(fasta_file) as f:
fa_dict = json.load(f)
else:
fa_dict = SP.make_fasta_dict(fasta_file)
seq_list = []
no_tx_n = 1
with open(input_file, 'r') as csv_file:
f = csv.reader(csv_file, dialect=csv.excel)
for row in f:
tx_list = row[0].split(',')
for tx in tx_list:
tx = tx + 'T0'
if tx.startswith('3P'): tx = tx.split('3P')[1]
chrom = row[1]
if not chrom.startswith('chr'):
chrom = 'chr' + str(chrom)
try:
center = int(row[2])
start = center - window / 2
end = center + window / 2
if tx in tx_dict:
strand = tx_dict[tx][2]
else:
print tx + " not in GFF3 file"
strand = '+'
tx = chrom + ':' + str(center)
seq = seq_simple(chrom, start, end, strand, fa_dict)
seq_list.append((tx, seq))
except ValueError:
pass
genes_of_interest = gene_list.split("\n")
with open(
'{0}_peak_sequences.fa'.format(
input_file.split('/')[-1].split('.')[0]), 'w') as fout:
for tx, seq in seq_list:
if tx in genes_of_interest:
fout.write('>' + tx + '\n')
fout.write(seq + '\n')
return seq_list
def build_junction_df(junction_bed, gff3_file, fasta, organism=None):
transcript_dict = SP.build_transcript_dict(gff3_file, organism=organism)
if type(fasta) == str:
fasta = SP.make_fasta_dict(fasta)
junction_dict = build_junction_dict(junction_bed,
gff3_file,
transcript_dict,
organism=organism)
junction_count = 0
for tx, junctions in junction_dict.iteritems():
junction_count += len(junctions)
junction_df = pd.DataFrame(index=range(junction_count),
columns=[
'intron tuple', 'chromosome', 'start',
'end', 'strand', 'depth', 'type', 'size',
'annotated intron size',
'annotated intron start',
'annotated intron end'
])
n = 0
for tx, junctions in junction_dict.iteritems():
for junction in junctions:
junction_df.ix[n] = [tx] + junction
n += 1
sequence1 = []
sequence2 = []
ann_seq1 = []
ann_seq2 = []
seq_type1 = []
seq_type2 = []
df_tx = []
for index, row in junction_df.iterrows():
df_tx.append(row['intron tuple'][0])
chrom = convert_chrom(row['chromosome'])
if row['strand'] == '+':
curr1 = fasta[chrom][(row['start'] - 1):(row['start'] + 7)]
sequence1.append(curr1)
curr2 = fasta[chrom][(row['end'] - 5):(row['end'] + 3)]
sequence2.append(curr2)
if row['annotated intron start'] is None:
ann_seq1.append(None)
ann_seq2.append(None)
else:
ann_seq1.append(
fasta[chrom][(row['annotated intron start'] -
1):(row['annotated intron start'] + 7)])
ann_seq2.append(fasta[chrom][(row['annotated intron end'] -
5):(row['annotated intron end'] +
3)])
elif row['strand'] == '-':
curr1 = SP.reverse_complement(fasta[chrom][(row['start'] -
6):(row['start'] + 2)])
sequence1.append(curr1)
curr2 = SP.reverse_complement(fasta[chrom][(row['end'] -
2):(row['end'] + 6)])
sequence2.append(curr2)
if row['annotated intron start'] is None:
ann_seq1.append(None)
ann_seq2.append(None)
else:
ann_seq1.append(
SP.reverse_complement(
fasta[chrom][row['annotated intron start'] -
6:row['annotated intron start'] + 2]))
ann_seq2.append(
SP.reverse_complement(
fasta[chrom][row['annotated intron end'] -
2:row['annotated intron end'] + 6]))
else:
sequence1.append('NNNNNNNN')
sequence2.append('NNNNNNNN')
ann_seq1.append('NNNNNNNN')
ann_seq2.append('NNNNNNNN')
if row['type'] == 'Annotated':
seq_type1.append('5p annotated')
seq_type2.append('3p annotated')
elif row['type'] == '5p tethered':
seq_type1.append('5p annotated')
seq_type2.append(curr2[4:6])
else:
seq_type1.append(curr1[2:4])
seq_type2.append(curr2[4:6])
junc_seq_df = junction_df
junc_seq_df['sequence1'] = sequence1
junc_seq_df['sequence2'] = sequence2
junc_seq_df['seq type1'] = seq_type1
junc_seq_df['seq type2'] = seq_type2
junc_seq_df['annotated sequence1'] = ann_seq1
junc_seq_df['annotated sequence2'] = ann_seq2
junc_seq_df['transcript'] = df_tx
return junc_seq_df
def peak_to_seq_pipeline(untagged_peak_file,
tagged1_peak_file,
tagged2_peak_file,
gff3,
fasta,
junction_df=None,
branch_df=None,
cutoff=5,
name='CP_peaks'):
if 'pombe' in gff3: organism = 'pombe'
else: organism = None
transcript_dict = SP.build_transcript_dict(gff3, organism=organism)
print "Finding peaks in transcripts..."
print untagged_peak_file
untagged = CP_peaks_by_gene(untagged_peak_file,
transcript_dict,
cutoff=cutoff)
print tagged1_peak_file
tagged1 = CP_peaks_by_gene(tagged1_peak_file,
transcript_dict,
cutoff=cutoff)
print tagged2_peak_file
tagged2 = CP_peaks_by_gene(tagged2_peak_file,
transcript_dict,
cutoff=cutoff)
print "Comparing peaks between replicates..."
peaks = CP_compare_reps(untagged, tagged1, tagged2)
print "Checking peaks against annotation..."
ss_dict, flag = SP.list_splice_sites(gff3, organism=organism)
peak_df = CP_compare_to_annotation(peaks, ss_dict, transcript_dict)
peak_df = collapse_unpredicted_peaks(peak_df)
peak_df['genome coord'] = peak_df['chromosome'].str.cat(
peak_df['position'].apply(int).apply(str), sep=':')
if type(fasta) == str:
fasta = SP.make_fasta_dict(fasta)
print "Adding sequences..."
peak_seq_df = add_sequence_to_df(peak_df, fasta, flag=flag)
print "Writing bedgraph..."
with open(name + '.bedgraph', 'w') as fout:
for ix, r in peak_seq_df.iterrows():
if r['strand'] == '+':
position2 = r['position'] + 1
height = r['height']
elif r['strand'] == '-':
position2 = r['position'] - 1
height = r['height'] * -1
line_list = [
r['chromosome'], r['position'], position2, height, '\n'
]
line_list = [str(x) for x in line_list]
line = '\t'.join(line_list)
fout.write(line)
print "Completed"
return peak_seq_df
def build_junction_df(junction_bed, gff3_file, fasta, organism=None):
transcript_dict = SP.build_transcript_dict(gff3_file, organism=organism)
if type(fasta) == str:
fasta=SP.make_fasta_dict(fasta)
junction_dict = build_junction_dict(junction_bed, gff3_file, transcript_dict, organism=organism)
junction_count = 0
for tx, junctions in junction_dict.iteritems():
junction_count += len(junctions)
junction_df = pd.DataFrame(index=range(junction_count), columns=['intron tuple','chromosome','start','end','strand','depth','type','size','annotated intron size','annotated intron start','annotated intron end'])
n=0
for tx, junctions in junction_dict.iteritems():
for junction in junctions:
junction_df.ix[n] = [tx]+junction
n+=1
sequence1 = []
sequence2 = []
ann_seq1 = []
ann_seq2 = []
seq_type1 = []
seq_type2 = []
df_tx = []
for index, row in junction_df.iterrows():
df_tx.append(row['intron tuple'][0])
chrom = convert_chrom(row['chromosome'])
if row['strand'] == '+':
curr1 = fasta[chrom][(row['start']-1):(row['start']+7)]
sequence1.append(curr1)
curr2 = fasta[chrom][(row['end']-5):(row['end']+3)]
sequence2.append(curr2)
if row['annotated intron start'] is None:
ann_seq1.append(None)
ann_seq2.append(None)
else:
ann_seq1.append(fasta[chrom][(row['annotated intron start']-1):(row['annotated intron start']+7)])
ann_seq2.append(fasta[chrom][(row['annotated intron end']-5):(row['annotated intron end']+3)])
elif row['strand'] == '-':
curr1 = SP.reverse_complement(fasta[chrom][(row['start']-6):(row['start']+2)])
sequence1.append(curr1)
curr2 = SP.reverse_complement(fasta[chrom][(row['end']-2):(row['end']+6)])
sequence2.append(curr2)
if row['annotated intron start'] is None:
ann_seq1.append(None)
ann_seq2.append(None)
else:
ann_seq1.append(SP.reverse_complement(fasta[chrom][row['annotated intron start']-6:row['annotated intron start']+2]))
ann_seq2.append(SP.reverse_complement(fasta[chrom][row['annotated intron end']-2:row['annotated intron end']+6]))
else:
sequence1.append('NNNNNNNN')
sequence2.append('NNNNNNNN')
ann_seq1.append('NNNNNNNN')
ann_seq2.append('NNNNNNNN')
if row['type'] == 'Annotated':
seq_type1.append('5p annotated')
seq_type2.append('3p annotated')
elif row['type'] == '5p tethered':
seq_type1.append('5p annotated')
seq_type2.append(curr2[4:6])
else:
seq_type1.append(curr1[2:4])
seq_type2.append(curr2[4:6])
junc_seq_df = junction_df
junc_seq_df['sequence1'] = sequence1
junc_seq_df['sequence2'] = sequence2
junc_seq_df['seq type1'] = seq_type1
junc_seq_df['seq type2'] = seq_type2
junc_seq_df['annotated sequence1'] = ann_seq1
junc_seq_df['annotated sequence2'] = ann_seq2
junc_seq_df['transcript'] = df_tx
return junc_seq_df
