IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an email to s dot adaszewski at gmail dot com. User accounts are meant only to report issues and/or generate pull requests. This is a purpose-specific Git hosting for ADARED projects. Thank you for your understanding!
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.

decagon_run.py 2.2KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162
  1. #!/usr/bin/env python3
  2. from icosagon.data import Data
  3. import os
  4. import pandas as pd
  5. from bisect import bisect_left
  6. import torch
  7. def index(a, x):
  8. i = bisect_left(a, x)
  9. if i != len(a) and a[i] == x:
  10. return i
  11. raise ValueError
  12. def main():
  13. path = '/pstore/data/data_science/ref/decagon'
  14. df_combo = pd.read_csv(os.path.join(path, 'bio-decagon-combo.csv'))
  15. df_effcat = pd.read_csv(os.path.join(path, 'bio-decagon-effectcategories.csv'))
  16. df_mono = pd.read_csv(os.path.join(path, 'bio-decagon-mono.csv'))
  17. df_ppi = pd.read_csv(os.path.join(path, 'bio-decagon-ppi.csv'))
  18. df_tgtall = pd.read_csv(os.path.join(path, 'bio-decagon-targets-all.csv'))
  19. df_tgt = pd.read_csv(os.path.join(path, 'bio-decagon-targets.csv'))
  20. lst = [ 'df_combo', 'df_effcat', 'df_mono', 'df_ppi', 'df_tgtall', 'df_tgt' ]
  21. for nam in lst:
  22. print(f'len({nam}): {len(locals()[nam])}')
  23. print(f'{nam}.columns: {locals()[nam].columns}')
  24. genes = set()
  25. genes = genes.union(df_ppi['Gene 1']).union(df_ppi['Gene 2']) \
  26. .union(df_tgtall['Gene']).union(df_tgt['Gene'])
  27. genes = sorted(genes)
  28. print('len(genes):', len(genes))
  29. drugs = set()
  30. drugs = drugs.union(df_combo['STITCH 1']).union(df_combo['STITCH 2']) \
  31. .union(df_mono['STITCH']).union(df_tgtall['STITCH']).union(df_tgt['STITCH'])
  32. drugs = sorted(drugs)
  33. print('len(drugs):', len(drugs))
  34. data = Data()
  35. data.add_node_type('Gene', len(genes))
  36. data.add_node_type('Drug', len(drugs))
  37. print('Indexing rows...')
  38. rows = [index(genes, g) for g in df_ppi['Gene 1']]
  39. print('Indexing cols...')
  40. cols = [index(genes, g) for g in df_ppi['Gene 2']]
  41. indices = list(zip(rows, cols))
  42. indices = torch.tensor(indices).transpose(0, 1)
  43. values = torch.ones(len(rows))
  44. print('indices.shape:', indices.shape, 'values.shape:', values.shape)
  45. adj_mat = torch.sparse_coo_tensor(indices, values, size=(len(genes),) * 2)
  46. adj_mat = (adj_mat + adj_mat.transpose(0, 1)) / 2
  47. print('adj_mat created')
  48. fam = data.add_relation_family('PPI', 0, 0, True)
  49. rel = fam.add_relation_type('PPI', adj_mat)
  50. if __name__ == '__main__':
  51. main()