def test_get_gene_annotation(self):
"Test utils.get_gene_annotation()"
feature = FakeFeature("CDS")
self.assertEqual('unannotated orf', utils.get_gene_annotation(feature))
feature.qualifiers['product'] = ['fake']
self.assertEqual('fake', utils.get_gene_annotation(feature))
def write_gene(txt, info, options):
"Write gene table to TXT"
#TXT columns: gene ID, gene start, gene end, gene strand, smCOG, locus_tag/geneID, annotation
txt.write("\t".join([
"gene ID", "gene start", "gene end", "gene strand", "smCOG",
"locus_tag", "annotation"
]) + "\n")
for BGCnr in info.clusternrs:
#Retrieve all data that will be written out
cluster_feature = utils.get_cluster_by_nr(info.seq_record, BGCnr)
cluster_gene_features = utils.get_cluster_cds_features(
cluster_feature, info.seq_record)
for cds in cluster_gene_features:
gene_id = utils.get_gene_acc(cds).partition(".")[0]
cds_start = str(cds.location.start)
cds_end = str(cds.location.end)
if cds.strand == 1:
cds_strand = "+"
else:
cds_strand = "-"
smCOG = "" ##Not used for now
locus_tag = utils.get_gene_id(cds).partition(".")[0]
annotation = utils.get_gene_annotation(cds)
txt.write("\t".join([
gene_id, cds_start, cds_end, cds_strand, smCOG, locus_tag,
annotation
]) + "\n")
def create_blast_inputs(genecluster, seq_record):
#Create input fasta files for BLAST search
queryclusterprots = utils.get_cluster_cds_features(genecluster, seq_record)
queryclusternames = []
queryclusterseqs = []
queryclusterprotsnames = []
for cds in queryclusterprots:
if cds.strand == 1:
strand = "+"
else:
strand = "-"
fullname = "|".join(["input", "c" + str(utils.get_cluster_number(genecluster)), \
str(cds.location.nofuzzy_start) + "-" + \
str(cds.location.nofuzzy_end), \
strand, utils.get_gene_acc(cds), utils.get_gene_annotation(cds)])
queryclusterseqs.append(str(utils.get_aa_sequence(cds)))
queryclusternames.append(fullname)
queryclusterprotsnames.append(utils.get_gene_acc(cds))
return queryclusternames, queryclusterseqs, queryclusterprotsnames
def create_blast_inputs(genecluster, seq_record):
options = config.get_config()
#Create input fasta files for BLAST search
if options.taxon == "plants":
queryclusterprots = filter_overlap(utils.get_cluster_cds_features(genecluster, seq_record))
else:
queryclusterprots = utils.get_cluster_cds_features(genecluster, seq_record)
queryclusternames = []
queryclusterseqs = []
queryclusterprotsnames = []
for cds in queryclusterprots:
if cds.strand == 1:
strand = "+"
else:
strand = "-"
fullname = "|".join(["input", "c" + str(utils.get_cluster_number(genecluster)), \
str(cds.location.start).replace(">","").replace("<","") + "-" + \
str(cds.location.end).replace(">","").replace("<",""), \
strand, utils.get_gene_acc(cds), utils.get_gene_annotation(cds)])
queryclusterseqs.append(str(utils.get_aa_sequence(cds)))
queryclusternames.append(fullname)
queryclusterprotsnames.append(utils.get_gene_acc(cds))
return queryclusternames, queryclusterseqs, queryclusterprotsnames
def write_clusterblast_output(options,
seq_record,
clusterblastStorage,
searchtype="general"):
clusternumber = clusterblastStorage.clusternumber
queryclusterprots = clusterblastStorage.queryclusterprots
clusters = clusterblastStorage.clusters
ranking = clusterblastStorage.ranking
proteins = clusterblastStorage.proteins
#Output for each hit: table of genes and locations of input cluster, table of genes and locations of hit cluster, table of hits between the clusters
currentdir = os.getcwd()
os.chdir(get_output_dir(options, searchtype))
out_file = open("cluster" + str(clusternumber) + ".txt", "w")
out_file.write("ClusterBlast scores for " + seq_record.id + "\n")
out_file.write(
"\nTable of genes, locations, strands and annotations of query cluster:\n"
)
feature_by_id = utils.get_feature_dict_protein_id(seq_record)
for i in queryclusterprots:
cds = feature_by_id[i]
if cds.strand == 1:
strand = "+"
else:
strand = "-"
out_file.write("\t".join([
i,
str(cds.location.nofuzzy_start),
str(cds.location.nofuzzy_end), strand,
utils.get_gene_annotation(cds)
]) + "\t\n")
out_file.write("\n\nSignificant hits: \n")
top_hits = ranking[:100]
for n, cluster_and_result in enumerate(top_hits):
cluster = cluster_and_result[0]
out_file.write("{}. {}\t{}\n".format(n + 1, cluster,
clusters[cluster][1]))
out_file.write("\n\nDetails:")
for n, cluster_and_result in enumerate(top_hits):
cluster, result = cluster_and_result
# TODO: change to just result.hits during next minor version bump
nrhits = result.hits + result.synteny_score + result.core_bonus
out_file.write("\n\n>>\n")
out_file.write("{}. {}\n".format(n + 1, cluster))
out_file.write("Source: {}\n".format(clusters[cluster][1]))
out_file.write("Type: {}\n".format(clusters[cluster][2]))
out_file.write(
"Number of proteins with BLAST hits to this cluster: %d\n" %
nrhits)
out_file.write("Cumulative BLAST score: %d\n\n" % result.blast_score)
out_file.write(
"Table of genes, locations, strands and annotations of subject cluster:\n"
)
clusterproteins = clusters[cluster][0]
for protein_name in clusterproteins:
protein = proteins.get(protein_name)
if protein:
out_file.write(str(protein))
out_file.write(
"\nTable of Blast hits (query gene, subject gene, %identity, blast score, %coverage, e-value):\n"
)
if result.scored_pairings:
for query, subject in result.scored_pairings:
# TODO : check the trailing \t is meaningful
out_file.write("{}\t{}\t\n".format(query.id,
subject.get_table_string()))
else:
out_file.write("data not found\n")
out_file.write("\n")
out_file.close()
os.chdir(currentdir)
def write_clusterblast_output(options, seq_record,clusterblastStorage, searchtype="general"):
clusternumber = clusterblastStorage.clusternumber
queryclusterprots = clusterblastStorage.queryclusterprots
clusters = clusterblastStorage.clusters
hitclusterdata = clusterblastStorage.hitclusterdata
rankedclusters = clusterblastStorage.rankedclusters
rankedclustervalues = clusterblastStorage.rankedclustervalues
proteintags = clusterblastStorage.proteintags
proteinlocations = clusterblastStorage.proteinlocations
proteinannotations = clusterblastStorage.proteinannotations
proteinstrands = clusterblastStorage.proteinstrands
#Output for each hit: table of genes and locations of input cluster, table of genes and locations of hit cluster, table of hits between the clusters
logging.info(" Writing output file...")
currentdir = os.getcwd()
if searchtype == "general":
options.clusterblast_outputfolder = options.full_outputfolder_path + os.sep + "clusterblast"
if not os.path.exists(options.clusterblast_outputfolder):
os.mkdir(options.clusterblast_outputfolder)
outputfolder = options.clusterblast_outputfolder
elif searchtype == "subclusters":
options.subclusterblast_outputfolder = options.full_outputfolder_path + os.sep + "subclusterblast"
if not os.path.exists(options.subclusterblast_outputfolder):
os.mkdir(options.subclusterblast_outputfolder)
outputfolder = options.subclusterblast_outputfolder
elif searchtype == "knownclusters":
options.knownclusterblast_outputfolder = options.full_outputfolder_path + os.sep + "knownclusterblast"
if not os.path.exists(options.knownclusterblast_outputfolder):
os.mkdir(options.knownclusterblast_outputfolder)
outputfolder = options.knownclusterblast_outputfolder
os.chdir(outputfolder)
out_file = open("cluster" + str(clusternumber) + ".txt","w")
out_file.write("ClusterBlast scores for " + seq_record.id + "\n")
out_file.write("\nTable of genes, locations, strands and annotations of query cluster:\n")
feature_by_id = utils.get_feature_dict_protein_id(seq_record)
for i in queryclusterprots:
cds = feature_by_id[i]
if cds.strand == 1:
strand = "+"
else:
strand = "-"
out_file.write("\t".join([i, str(cds.location.start).replace(">","").replace("<",""), str(cds.location.end).replace(">","").replace("<",""), strand, utils.get_gene_annotation(cds)]) + "\t\n")
out_file.write("\n\nSignificant hits: \n")
z = 0
for i in rankedclusters[:100]:
out_file.write(str(z+1) + ". " + i + "\t" + clusters[i][1] + "\n")
z += 1
z = 0
out_file.write("\n\nDetails:")
for i in rankedclusters[:100]:
value = "%.8f" % rankedclustervalues[z]
nrhits = value.split(".")[0]
if nrhits > 0:
out_file.write("\n\n>>\n")
cumblastscore = str(int(float(value.split(".")[1][2:])))
out_file.write("\n".join([str(z+1) + ". " + i, "Source: " + clusters[i][1], "Type: " + clusters[i][2], "Number of proteins with BLAST hits to this cluster: " + nrhits,"Cumulative BLAST score: " + cumblastscore + "\n", "Table of genes, locations, strands and annotations of subject cluster:\n"]))
clusterproteins = clusters[i][0]
for j in clusterproteins:
if proteinlocations.has_key(j) and proteinannotations.has_key(j) and proteinstrands.has_key(j):
if proteintags[j] == "no_locus_tag":
out_file.write(j + "\t")
else:
out_file.write(proteintags[j] + "\t")
out_file.write("\t".join([j, proteinlocations[j].split("-")[0], proteinlocations[j].split("-")[1], proteinstrands[j], proteinannotations[j]]) + "\n")
out_file.write("\nTable of Blast hits (query gene, subject gene, %identity, blast score, %coverage, e-value):\n")
if i in hitclusterdata.keys():
tabledata = hitclusterdata[i]
for x in tabledata:
w = 0
for y in x:
if w == 0:
out_file.write(str(y).split("|")[4] + "\t")
w += 1
else:
out_file.write(str(y) + "\t")
out_file.write("\n")
else:
out_file.write("data not found\n")
out_file.write("\n")
z += 1
out_file.close()
os.chdir(currentdir)
