IBM / fold2seq

Code for Fold2Seq paper from ICML 2021
Apache License 2.0
49 stars 8 forks source link

Error running fold_feat_gen.py (2nd) #8

Open kimdn opened 1 year ago

kimdn commented 1 year ago

I'm not sure whether https://github.com/IBM/fold2seq/issues/1 is fixed.

With example data

WE46901:run_example kimd999$ cat domain_list.txt
/Users/kimd999/research/projects/Margaret/code/fold2seq/data/example/1aj4A00-2-161   1aj4  A  2   161
/Users/kimd999/research/projects/Margaret/code/fold2seq/data/example/1bzqK00-801-924 1bzq  K  801 924
/Users/kimd999/research/projects/Margaret/code/fold2seq/data/example/1ge0A00-1-130   1ge0  A  1   130

I see


total number of seqs: 470679
removed # seqs in ss.txt: 9337
Traceback (most recent call last):
  File "/Users/kimd999/research/projects/Margaret/code/fold2seq/data/fold_feat_gen.py", line 152, in <module>
    x1,x2 = selection(line[0] ,  line[2], int(line[3]), int(line[4]), seq_ss)
  File "/Users/kimd999/research/projects/Margaret/code/fold2seq/data/fold_feat_gen.py", line 42, in selection
    start = start.replace(')','')
AttributeError: 'int' object has no attribute 'replace'
kimdn commented 1 year ago

Even after I commented out these replace lines, still I see

(fold2seq) [kimd999@tlogin3 data]$ ./run_this.sh
total number of seqs: 470679
removed # seqs in ss.txt: 9337
Traceback (most recent call last):
  File "fold_feat_gen.py", line 152, in <module>
    x1,x2 = selection(line[0] ,  line[2], int(line[3]), int(line[4]), seq_ss)
  File "fold_feat_gen.py", line 79, in selection
    raise ValueError("encounter inconsistent pdb structure:"+pdb_path+chain+" "+str(start)+','+str(end))
ValueError: encounter inconsistent pdb structure:example/1aj4A00-2-161A 2,161

both at my mac and linux