Mercurial > repos > rnateam > rnacommender

comparison main.py @ 0:8918de535391 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/rna_commander/tools/rna_tools/rna_commender commit 2fc7f3c08f30e2d81dc4ad19759dfe7ba9b0a3a1
author rnateam
date Tue, 31 May 2016 05:41:03 -0400
parents
children a609d6dc8047
comparison
equal deleted inserted replaced
-1:000000000000 0:8918de535391
1 #!/usr/bin/env python
2 """Recommendation."""
3
4 import argparse
5 import sys
6 from rbpfeatures import RBPVectorizer
7 from data import PredictDataset
8 from recommend import Predictor
9
10 from theano import config
11
12 __author__ = "Gianluca Corrado"
13 __copyright__ = "Copyright 2016, Gianluca Corrado"
14 __license__ = "MIT"
15 __maintainer__ = "Gianluca Corrado"
16 __email__ = "gianluca.corrado@unitn.it"
17 __status__ = "Production"
18
19 config.floatX = 'float32'
20
21 if __name__ == '__main__':
22 parser = argparse.ArgumentParser(
23 description=__doc__,
24 formatter_class=argparse.ArgumentDefaultsHelpFormatter)
25 parser.add_argument('fasta', metavar='fasta', type=str,
26 help="""Fasta file containing the RBP \
27 sequences.""")
28
29 args = parser.parse_args()
30
31 v = RBPVectorizer(fasta=args.fasta)
32 rbp_fea = v.vectorize()
33
34 if rbp_fea is not None:
35 # Define and load dataset
36 D = PredictDataset(
37 fp=rbp_fea, fr="AURA_Human_data/RNA_features/HT_utrs.h5")
38 dataset = D.load()
39
40 model = "AURA_Human_data/model/trained_model.pkl"
41
42 # Define the Trainer and train the model
43 P = Predictor(predict_dataset=dataset,
44 trained_model=model,
45 serendipity_dic=model + '_',
46 output="output.txt")
47 P.predict()
48 else:
49 sys.exit("""The queried protein has no domain similarity with the proteins in the training dataset. It cannot be predicted.""")