Ejemplo n.º 1
0
def constructe_aln_graph_from_fasta(read_fasta_fn, 
                                    backbone_fasta_fn, 
                                    max_num_reads = None, 
                                    remove_in_del = False, 
                                    ref_group = None,
                                    min_length = None):

    import os

    os.system("blasr %s %s -m 5 -nproc 8 -out %s" % (read_fasta_fn, backbone_fasta_fn, read_fasta_fn+".aln_unsorted"))
    os.system("cat %s | sort > %s" % (read_fasta_fn+".aln_unsorted", read_fasta_fn+".aln" ))
    
    aln_hit_iterator = simple_align_hit_iterator(read_fasta_fn+".aln", ref_group = ref_group)

    alns = get_aln_array(aln_hit_iterator, 
                         max_num_reads = max_num_reads, 
                         remove_in_del = remove_in_del, 
                         min_length = min_length)
        
    backboneSeq = open(backbone_fasta_fn).read()
    backboneSeq = "".join(backboneSeq.split()[1:])

    g = AlnGraph(backboneSeq)

    i = 0
    for aln in alns:
        rId = aln[2]
        rId = rId.split("/")[0]
        aln = aln[0:2]
        g.add_alignment( aln, "%s" % rId)

    return g
Ejemplo n.º 2
0
def constructe_aln_graph_from_cmph5(cmpH5_fn, 
                                    backbone_fasta_fn, 
                                    max_num_reads = None, 
                                    remove_in_del = False, 
                                    ref_group = None,
                                    min_length = None):

    from pbcore.io import cmph5
    from pbcore.io.cmph5 import CmpH5

    cmpType = CmpH5.SFCmpH5
    cmph5f = cmph5.factory.create( cmpH5_fn, "r", cmpType=cmpType )

    aln_hit_iterator = None

    if ref_group != None:
        aln_hit_iterator = cmph5f["/%s" % ref_group].alnHitIterator()
    else:
        aln_hit_iterator = cmph5f.alnHitIterator()

    alns = get_aln_array(aln_hit_iterator, 
                         max_num_reads = max_num_reads, 
                         remove_in_del = remove_in_del, 
                         min_length = min_length)
    
    backboneSeq = open(backbone_fasta_fn).read()
    backboneSeq = "".join(backboneSeq.split()[1:])

    g = AlnGraph(backboneSeq)

    i = 0
    for aln in alns:
        rId = aln[2]
        aln = aln[0:2]
        g.add_alignment( aln, "%s" % rId)

    cmph5.factory.close(cmph5f)
    return g