Carlos-Francisco Méndez-Cruz

Deep Learning Workshop

...@@ -8,23 +8,23 @@ ...@@ -8,23 +8,23 @@
8 # Each sequence as a one-hot encoding WHAT array or matrix 8 # Each sequence as a one-hot encoding WHAT array or matrix
9 9
10 # Run: 10 # Run:
11 -# python3 get-hga-training-test-py27-v1.py 11 +# python3 get-hga-training-test-py27-v2.py
12 # --inputFile hga-sequences-toy.txt 12 # --inputFile hga-sequences-toy.txt
13 # --inputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 13 # --inputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
14 # --outputTraining hga-sequences-training.txt 14 # --outputTraining hga-sequences-training.txt
15 # --outputTest hga-sequences-test.txt 15 # --outputTest hga-sequences-test.txt
16 # --outputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 16 # --outputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
17 -# python get-hga-training-test-py3.py --inputFile hga-sequences-1000.txt --inputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation --outputTraining hga-sequences-training.txt --outputTest hga-sequences-test.txt --outputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 17 +# python get-hga-training-test-py27-v2.py --inputFile hga-sequences-1000.txt --inputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation --outputTraining hga-sequences-training.txt --outputTest hga-sequences-test.txt --outputPath /home/cmendezc/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
18 18
19 # LAVIS 19 # LAVIS
20 # qlogin 20 # qlogin
21 -# python get-hga-training-test-py27-v1.py 21 +# python get-hga-training-test-py27-v2.py
22 # --inputFile hga-sequences-1000.txt 22 # --inputFile hga-sequences-1000.txt
23 # --inputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 23 # --inputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
24 # --outputTraining hga-sequences-training.txt 24 # --outputTraining hga-sequences-training.txt
25 # --outputTest hga-sequences-test.txt 25 # --outputTest hga-sequences-test.txt
26 # --outputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 26 # --outputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
27 -# python get-hga-training-test-py27-v1.py --inputFile hga-sequences-toy.txt --inputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation --outputTraining hga-sequences-training.txt --outputTest hga-sequences-test.txt --outputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation 27 +# python get-hga-training-test-py27-v2.py --inputFile hga-sequences-toy.txt --inputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation --outputTraining hga-sequences-training.txt --outputTest hga-sequences-test.txt --outputPath /mnt/Genoma/amedina/cmendez/gitlab-deep-learning-workshop/data-sets/human-genome-annotation
28 28
29 import argparse 29 import argparse
30 import pandas as pd 30 import pandas as pd
...@@ -105,6 +105,7 @@ if __name__ == "__main__": ...@@ -105,6 +105,7 @@ if __name__ == "__main__":
105 sequence_adjust = sequence + 'ACGTX' 105 sequence_adjust = sequence + 'ACGTX'
106 106
107 ''' 107 '''
108 +
108 # One-hot-encoding of sequences 109 # One-hot-encoding of sequences
109 for sequence, label in zip(sequences, labels): 110 for sequence, label in zip(sequences, labels):
110 sequence_adjust = sequence + 'ACGTX' 111 sequence_adjust = sequence + 'ACGTX'
......