Carlos-Francisco Méndez-Cruz

Deep Learning Workshop

......@@ -8,23 +8,23 @@
# Each sequence as a one-hot encoding WHAT array or matrix
# Run:
# python3 get-hga-training-test-py27-v1.py
# python3 get-hga-training-test-py27-v2.py
# --inputFile hga-sequences-toy.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
# 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
# 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
# LAVIS
# qlogin
# python get-hga-training-test-py27-v1.py
# python get-hga-training-test-py27-v2.py
# --inputFile hga-sequences-1000.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
# 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
# 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
import argparse
import pandas as pd
......@@ -105,6 +105,7 @@ if __name__ == "__main__":
sequence_adjust = sequence + 'ACGTX'
'''
# One-hot-encoding of sequences
for sequence, label in zip(sequences, labels):
sequence_adjust = sequence + 'ACGTX'
......