# get the sequences from the sequence names
novelseq = {}
for sequence in seqnames:
novelseq[sequence] = get_seqs(sequence)
# Get homolog data for each sequence
for record in novelseq:
qseqid =novelseq[record].seq
taxarecords = []
print('Getting homolog data for qseqid ' + record)
for taxa in taxalist:
taxainfo = {}
taxainfo['novel'] = record
taxainfo['taxa'] = taxa
taxainfo['taxid'] = ncbi.get_taxid(taxa)
taxainfo['blast_record'] = get_BLAST(taxainfo['taxid'], qseqid)
try:
taxainfo['sbjctseq'] = taxainfo['blast_record'].alignments[0].hsps[0].sbjct[:50]
print(taxainfo['sbjctseq'])
try:
taxainfo['GI'] = int(taxainfo['blast_record'].alignments[0].title.split('|')[1])
print("GI is: " + str(taxainfo['GI']))
except:
print("GI not valid for " + taxa + " : " + taxainfo['blast_record'].alignments[0].title.split('|')[1])
try:
taxainfo['seqdef'] = ncbi.get_gene_data(taxainfo['GI'])[0]['GBSeq_definition']
print('GBSeq_definition is ' + taxainfo['seqdef'])
except:
print("Unable to get GBSeq_definition")
try:
taxainfo['lineage'] = ncbi.get_lineage(taxainfo['taxid'])
sid = genus + "_" + species
name = genus + "_" + species
record_dict[novelseq1].name = name
record_dict[novelseq2].name = name
record_dict[novelseq1].id = sid
record_dict[novelseq2].id = sid
record_dict[novelseq1].description = novelseq1
record_dict[novelseq2].description = novelseq2
homologs = ()
for ataxa in list(alltaxa)[:4]:
print("lookup " + ataxa)
taxid = ncbi.get_taxid(ataxa)
print(ataxa + " tax id is " + str(taxid))
qseq1 = str(record_dict[novelseq2].seq)
blast_record = get_BLAST(taxid, qseq1)
try:
sbjctseq1 = blast_record.alignments[0].hsps[0].sbjct[:50]
sgi1 = blast_record.alignments[0].title.split('|')[1]
print("1", sbjctseq1)
seqdef1 = ncbi.get_gene_data(sgi1)[0]['GBSeq_definition']
lineage1 = ncbi.get_lineage(taxid)
sequence1 = ncbi.get_gene_seq(sgi1)
except:
print("No match")
sgi1 = 0
qseq2 = str(record_dict[novelseq1].seq)
blast_record = get_BLAST(taxid, qseq2)
try: