Skip to content

[Feat] Enhanced MSA Scripts #76

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

Merged
merged 13 commits into from
Mar 3, 2025
Merged

[Feat] Enhanced MSA Scripts #76

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
7c35fa1
Update step 1 script to support argument and cif transformed from pdb
popfido Feb 28, 2025
dc18162
Provide SharedDict for memory saving under multiprocessing in Step 3/4
popfido Feb 28, 2025
5305c2d
Upgrade Step 3 script to support arguments and large scale multiproce…
popfido Feb 28, 2025
b01cf7b
Upgrade Step 4 script to support arguments and multiprocessing
popfido Feb 28, 2025
0b00448
unify argument naming and bugfix
popfido Feb 28, 2025
4eba632
Remove use of mmap. Use parallel file reading
popfido Feb 28, 2025
18a10f0
Make read_m8 core logit as close as original
popfido Feb 28, 2025
4bb96ab
Remove format check
popfido Feb 28, 2025
cde6888
Renaming to original variable name
popfido Feb 28, 2025
5610d8f
Remove redundant log & simplified logics
popfido Feb 28, 2025
68a68b5
Simplification & cleanup
popfido Feb 28, 2025
10a3d18
Remove unused import
popfido Feb 28, 2025
bff2efd
rollback a wrongly deleted line
popfido Mar 3, 2025
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
22 changes: 18 additions & 4 deletions scripts/msa/step1-get_prot_seq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
# limitations under the License.

import json
from datetime import datetime
from pathlib import Path

import biotite.structure as struc
Expand Down Expand Up @@ -57,8 +58,15 @@ def get_seqs(mmcif_file):
if "pdbx_audit_revision_history" in mmcif_parser.cif.block:
history = mmcif_parser.cif.block["pdbx_audit_revision_history"]
info_df["release_date"] = history["revision_date"].as_array()[0]
else:
# Handle non-official mmcif file which transform from pdb file
info_df["release_date"] = datetime.now().strftime("%Y-%m-%d")

info_df["release_date_retrace_obsolete"] = mmcif_parser.release_date
if mmcif_parser.release_date:
info_df["release_date_retrace_obsolete"] = mmcif_parser.release_date
else:
# Handle non-official mmcif file which transform from pdb file
info_df["release_date_retrace_obsolete"] = datetime.now().strftime("%Y-%m-%d")

entity_poly_seq = mmcif_parser.get_category_table("entity_poly_seq")

Expand Down Expand Up @@ -189,8 +197,14 @@ def mapping_seqs_to_integer_identifiers(


if __name__ == "__main__":
# It's a demo here
cif_dir = Path("./scripts/msa/data/mmcif")
import argparse

parser = argparse.ArgumentParser()
parser.add_argument("--cif_dir", type=str, default="./scripts/msa/data/mmcif")
parser.add_argument("--out_dir", type=str, default="./scripts/msa/data/pdb_seqs")
args = parser.parse_args()

cif_dir = Path(args.cif_dir)
cif_files = [x for x in cif_dir.iterdir() if x.is_file()]

info_dfs = []
Expand All @@ -208,7 +222,7 @@ def mapping_seqs_to_integer_identifiers(
out_df = pd.concat(info_dfs)
out_df = out_df.sort_values(["pdb_id", "entity_id"])

out_dir = Path("./scripts/msa/data/pdb_seqs")
out_dir = Path(args.out_dir)
if not out_dir.exists():
out_dir.mkdir(parents=True)
# 1. extract pdb sequence info
Expand Down
Loading