comparison utils.py @ 31:d8049deb0c97 draft

planemo upload for repository https://github.com/Yating-L/jbrowse_hub commit faeedda55e23f1197bc454d3db2d52af29d786e8-dirty

30:daf6a1122200

#!/usr/bin/env python

'''
This file include common used functions for converting file format to gff3
'''
from collections import OrderedDict
import json
import subprocess
import os
import tempfile


def write_features(field, attribute, gff3):
    '''
    The function write the features to gff3 format (defined in https://github.com/The-Sequence-Ontology/Specifications/blob/master/gff3.md)
    field, attribute are ordered dictionary 
    gff3 is the file handler
    '''
    attr = []
    for v in field.values():
        gff3.write(str(v) + '\t')
    for k, v in attribute.items():
        s = str(k) + '=' + str(v)

    except OSError as err:
        print "Cannot generate chrom_sizes from twoBitInfo err({0}): {1}".format(err.errno, err.strerror)
    return chrom_sizes

def sequence_region(chrom_sizes):
    '''
    This function read from a chromatin size file generated by twoBitInfo and write the information to dict
    return a dict
    '''
    f = open(chrom_sizes, 'r')
    sizes = f.readlines()
    sizes_dict = {}
    for line in sizes:
        chrom_info = line.rstrip().split('\t')

        child_attr['Parent'] = parent_attr['ID']
        write_features(child_field, child_attr, gff3)
        num = num + 1

def add_tracks_to_json(trackList_json, new_tracks, modify_type):
    '''
    Add to track configuration (trackList.json)
    # modify_type =  'add_tracks': add a new track like bam or bigwig, new_track = dict()
    # modify_type = 'add_attr': add configuration to the existing track, new_track = dict(track_name: dict())
    '''
    with open(trackList_json, 'r+') as f:
        data = json.load(f)
        if modify_type == 'add_tracks':
            data['tracks'].append(new_tracks)
        elif modify_type == 'add_attr':

        f.write(json.dumps(data, separators=(',' , ':'), indent=4))
        f.truncate()
        f.close()

def gtfToGff3(gtf_file, gff3_file, chrom_sizes):
    '''
    Covert gtf file output from StringTie to gff3 format
    '''
    gff3 = open(gff3_file, 'w')
    gff3.write("##gff-version 3\n")
    sizes_dict = sequence_region(chrom_sizes)
    seq_regions = dict()
    parents = dict()

                attribute['transcript_id'] = attr_li[1].split()[1].strip('"')
                attribute['coverage'] = attr_li[3].split()[1].strip('"')
            write_features(field, attribute, gff3)
    gff3.close()

def sanitize_name_path(input_path):
    '''
    Galaxy will name all the files and dirs as *.dat, 
    the function is simply replacing '.' to '_' for the dirs
    '''
    return input_path.replace('.', '_')

def createBamIndex(bamfile):
    p = subprocess.Popen(['samtools', 'index', bamfile])
    p.communicate()
    filename = bamfile + '.bai'

31:d8049deb0c97

#!/usr/bin/env python

"""
This file include common used functions for converting file format to gff3
"""
from collections import OrderedDict
import json
import subprocess
import os
import tempfile
import string

def write_features(field, attribute, gff3):
    """
    The function write the features to gff3 format (defined in https://github.com/The-Sequence-Ontology/Specifications/blob/master/gff3.md)
    field, attribute are ordered dictionary 
    gff3 is the file handler
    """
    attr = []
    for v in field.values():
        gff3.write(str(v) + '\t')
    for k, v in attribute.items():
        s = str(k) + '=' + str(v)

    except OSError as err:
        print "Cannot generate chrom_sizes from twoBitInfo err({0}): {1}".format(err.errno, err.strerror)
    return chrom_sizes

def sequence_region(chrom_sizes):
    """
    This function read from a chromatin size file generated by twoBitInfo and write the information to dict
    return a dict
    """
    f = open(chrom_sizes, 'r')
    sizes = f.readlines()
    sizes_dict = {}
    for line in sizes:
        chrom_info = line.rstrip().split('\t')

        child_attr['Parent'] = parent_attr['ID']
        write_features(child_field, child_attr, gff3)
        num = num + 1

def add_tracks_to_json(trackList_json, new_tracks, modify_type):
    """
    Add to track configuration (trackList.json)
    # modify_type =  'add_tracks': add a new track like bam or bigwig, new_track = dict()
    # modify_type = 'add_attr': add configuration to the existing track, new_track = dict(track_name: dict())
    """
    with open(trackList_json, 'r+') as f:
        data = json.load(f)
        if modify_type == 'add_tracks':
            data['tracks'].append(new_tracks)
        elif modify_type == 'add_attr':

        f.write(json.dumps(data, separators=(',' , ':'), indent=4))
        f.truncate()
        f.close()

def gtfToGff3(gtf_file, gff3_file, chrom_sizes):
    """
    Covert gtf file output from StringTie to gff3 format
    """
    gff3 = open(gff3_file, 'w')
    gff3.write("##gff-version 3\n")
    sizes_dict = sequence_region(chrom_sizes)
    seq_regions = dict()
    parents = dict()

                attribute['transcript_id'] = attr_li[1].split()[1].strip('"')
                attribute['coverage'] = attr_li[3].split()[1].strip('"')
            write_features(field, attribute, gff3)
    gff3.close()


def sanitize_name(input_name):
    """
    Galaxy will name all the files and dirs as *.dat, 
    the function can replace '.' to '_' for the dirs
    """
    validChars = "_-%s%s" % (string.ascii_letters, string.digits)
    sanitized_name = ''.join([c if c in validChars else '_' for c in input_name])
    return "gonramp_" + sanitized_name

def createBamIndex(bamfile):
    p = subprocess.Popen(['samtools', 'index', bamfile])
    p.communicate()
    filename = bamfile + '.bai'