NVIDIA-BioNeMo / NVIDIA-BioNeMo/KERMT

make cuik-molmaker optional

Open
#2 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
99
Forks
18
Avg merge
5d 14h
Merged PRs (30d)
1

Description

Hello,
cuik-molmaker is currently required for fine-tuning KERMT. However, cuik-molmaker may not be compatible with many supercomputing environments, since it requires >= GLIBC_2.32. For example, NERSC perlmutter is compiled with GLIBC_2.31, so KERMT cannot be used on NERSC. Since cuik-molmaker mol graphs are equivalent to RDKit mol graphs, using cuik-molmaker should be made optional in molgraph.py.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading molgraph.py and tracing where cuik-molmaker is imported or required during KERMT fine-tuning. Compare the existing cuik-molmaker and RDKit molecular graph paths described in the issue. Done means cuik-molmaker is optional and KERMT can be used in environments with GLIBC_2.31.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Refactor
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.