Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update full_seq_processor.py #23

Open
wants to merge 7 commits into
base: master
Choose a base branch
from
Open

Update full_seq_processor.py #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a85a473
Update full_seq_processor.py
jadolfbr Mar 2, 2023
414835d
add fault tolerance for multiple pdbs or fasta sequences.
May 24, 2023
bd55b65
Merge branch 'master' of github.com:jadolfbr/parapred
May 24, 2023
376fbfc
print errors to err.
May 24, 2023
c8430f5
change exception out to string.
May 24, 2023
16e8c47
flush stdout.
May 24, 2023
3356068
print full exception through traceback.
May 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion parapred/full_seq_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def get_CDR_simple(sequence ,allow=set(["H", "K", "L"]),scheme='chothia',seqname
elif num_tuple[0] in cdr3_scheme: cdr3+=res

# put in parapred formta
cdrs={'CDR1':cdr1,'CDR2':cdr2,'CDR3':cdr3}
cdrs={'CDR1':cdr1.replace('-',''),'CDR2':cdr2.replace('-',''),'CDR3':cdr3.replace('-','')}
return cdrs

class FakeSeq :
Expand Down
21 changes: 19 additions & 2 deletions parapred/parapred.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,8 @@
from pandas import read_csv
import numpy as np
import pkg_resources
import sys
import traceback

from .structure_processor import get_structure_from_pdb, extract_cdrs_from_structure, \
residue_seq_to_one, produce_annotated_ab_structure, save_structure, aa_s, \
Expand Down Expand Up @@ -163,7 +165,14 @@ def process_multiple_pdbs(pdb_descr_file, pdb_folder):
pdb_name = pdb_name + ".pdb"

pdb_file = pdb_folder + "/" + pdb_name
process_single_pdb(pdb_file, ab_h_chain_id, ab_l_chain_id)
try:
process_single_pdb(pdb_file, ab_h_chain_id, ab_l_chain_id)
except Exception as e:
sys.stderr.write('\nSkipping {pdb_name} with erorr. \n')
sys.stderr.write("Error below:\n")
traceback.print_exc(file=sys.stderr)
sys.stderr.flush()
continue


def process_sequences(seqs):
Expand Down Expand Up @@ -206,7 +215,15 @@ def process_fasta_file(fastafile) :
sequences,_ = read_fasta(fastafile)
for srec in sequences :
print("\n> %s" % (srec.name))
process_full_VH_VL_sequence( str(srec.seq) )
try:
process_full_VH_VL_sequence( str(srec.seq) )
except Exception as e:
sys.stderr.write(f'\nErorr processing {srec.name}. Skipping\n')
sys.stderr.write("Error message below: \n")
traceback.print_exc(file=sys.stderr)
sys.stderr.flush()
continue



def main():
Expand Down
2 changes: 0 additions & 2 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ cycler==0.10.0
docopt==0.6.2
h5py==2.6.0
Keras==2.0.6
matplotlib==2.0.0
nltk==3.2.2
numpy==1.13.1
packaging==16.8
Expand All @@ -20,7 +19,6 @@ scikit-learn==0.18.1
scipy==0.19.1
six==1.10.0
sklearn==0.0
tensorflow==1.2.1
Theano==0.9.0
docopt==0.6.2
setuptools-scm==1.15.6
Expand Down