def get_dataset(fname,k): labels = [] features = [] for prot_id,seq in seq2feature.parse_fasta(fname): labels.append(prot_id) features.append(k_spec(seq,k)) return labels,features
def split_fasta(fname, save_dir):
for cnt, (idch, seq) in enumerate(seq2feature.parse_fasta(fname)):
if cnt > MAX:
#break
pass
wfname = base64.b64encode(idch.strip().replace("\t", ""))
with open("%s/%s.fasta" % (save_dir, wfname), "w") as fout:
fout.write(">%s\n" % (idch.strip()))
fout.write(seq + "\n")
def split_fasta(fname,save_dir):
for cnt,(idch,seq) in enumerate(seq2feature.parse_fasta(fname)):
if cnt > MAX:
#break
pass
wfname = base64.b64encode(idch.strip().replace("\t",""))
with open("%s/%s.fasta" % (save_dir,wfname),"w") as fout:
fout.write(">%s\n" % (idch.strip()))
fout.write(seq + "\n")
def get_dataset(fname,k):
labels = []
features = []
for prot_id,seq in seq2feature.parse_fasta(fname):
labels.append(prot_id)
features.append(k_spec(seq,k))
return labels,features
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Predict X binding proteins.')
parser.add_argument('-model',action="store",dest="model")
parser.add_argument('-thr',action="store",dest="thr",type = float)
parser.add_argument('-fname',action="store",dest="fname")
model = parser.parse_args().model
fname = parser.parse_args().fname
thr = parser.parse_args().thr
labels,features = get_dataset(fname,2)
model = svmutil.svm_load_model(model)
plbl, pacc, pvals = svmutil.svm_predict([0]*len(features),features,model,"")
for cnt,(prot_id,seq) in enumerate(seq2feature.parse_fasta(fname)):
pval = pvals[cnt][0]
if pval >= thr:
print "> %s:%f" % (prot_id,pval)
print seq
