Python SeqFeature.qualifiers["cluster_id"]方法代码示例

# 需要导入模块: from Bio.SeqFeature import SeqFeature [as 别名]
# 或者: from Bio.SeqFeature.SeqFeature import qualifiers["cluster_id"] [as 别名]
def makeSeqObjectsForTblastnNeighbors(tblastn_id, clusterrunid, cur, N=200000):
    """
    Given a tBBLSATn ID and a dictionary from sanitized contig IDs (which is what will be
    present in the TBLASTN id) to non-sanitized IDs (which are what is in the database),
    returns a list of seq objects INCLUDING the TBLASTN hit itself (so that we can show that
    on the region drawing).

    We pick an N large enough to get at least one gene and then pick the closest one and get
    all of its neighbors with a call to makeSeqFeaturesForGeneNeighbors() and just tack the TBLASTN
    onto it.
    """
    # Lets first get the contig and start/stop locations (which tell us teh strand) out of
    # the TBLASTN id. This returns a ValueError if it fails which the calling function can catch if needed.
    sanitizedToNot = getSanitizedContigList(cur)

    contig, start, stop = splitTblastn(tblastn_id)
    if contig in sanitizedToNot:
        contig = sanitizedToNot[contig]

    start = int(start)
    stop = int(stop)

    # Create a seq object for the TBLASTN hit itself
    if start < stop:
        strand = +1
    else:
        strand = -1
    tblastn_feature = SeqFeature(FeatureLocation(start, stop), strand=strand, id=tblastn_id)
    tblastn_feature.qualifiers["cluster_id"] = -1

    # Find the neighboring genes.
    neighboring_genes = getGenesInRegion(contig, start - N, stop + N, cur)
    if len(neighboring_genes) == 0:
        sys.stderr.write(
            "WARNING: No neighboring genes found for TBLASTN hit %s within %d nucleotides in contig %s\n"
            % (tblastn_id, N, contig)
        )
        return [tblastn_feature]
    else:
        neighboring_geneinfo = getGeneInfo(neighboring_genes, cur)

    # Find the closest gene to ours and get the clusters for those neighbors based on the specific clusterrunid
    minlen = N
    mingene = None
    minstrand = None
    for geneinfo in neighboring_geneinfo:
        genestart = int(geneinfo[5])
        geneend = int(geneinfo[6])
        distance = min(abs(genestart - start), abs(geneend - start), abs(genestart - stop), abs(geneend - stop))
        if distance < minlen:
            mingene = geneinfo[0]
            minlen = distance

    neighboring_features = makeSeqFeaturesForGeneNeighbors(mingene, clusterrunid, cur)
    # Add the TBLASTN itself and return it.
    neighboring_features.append(tblastn_feature)
    return neighboring_features

# 需要导入模块: from Bio.SeqFeature import SeqFeature [as 别名]
# 或者: from Bio.SeqFeature.SeqFeature import qualifiers["cluster_id"] [as 别名]
def makeSeqFeature(geneid, cur):
    '''
    Make a BioPython SeqFeature object for a gene with ITEP ID geneid
    '''

    geneinfo = getGeneInfo( [ geneid ], cur )
    geneinfo = geneinfo[0]
    start = int(geneinfo[5])
    stop = int(geneinfo[6])
    strand = int(geneinfo[8])
    feature = SeqFeature(FeatureLocation(start, stop), strand=strand, id=geneid)
    # This can be overwritten by other functions but we need a placeholder.
    feature.qualifiers["cluster_id"] = -1
    return feature

# 需要导入模块: from Bio.SeqFeature import SeqFeature [as 别名]
# 或者: from Bio.SeqFeature.SeqFeature import qualifiers["cluster_id"] [as 别名]
def makeSeqFeaturesForGeneNeighbors(genename, clusterrunid, cur):
    '''
    Given a gene ID, compute the neighbors of that gene and create a SeqFeature
    object for each.

    Returns a list of neigboring genes or an empty array [] if we couldn't do anything
    with the gene Id given (not found in database or similar issue)
    '''
    outdata = getGeneNeighborhoods(genename, clusterrunid, cur)    
    genelocs = []
    for neargene in outdata: 
        neargeneid = neargene[1]
        start = int(neargene[4])
        stop = int(neargene[5])
        strandsign = neargene[6]
        if strandsign =='-': 
            strand = -1
        if strandsign =='+': 
            strand = +1
        feature = SeqFeature(FeatureLocation(start, stop), strand=strand, id = neargeneid)
        feature.qualifiers["cluster_id"] = int(neargene[8])
        genelocs.append(feature)
    return genelocs