Merck / Merck/compoundcomplexity

Can't reproduce results

Open
#1 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Perl
Stars
4
Forks
3
PR merge metrics
No merged PRs in 30d

Description

Hello,

I am trying to reproduce your results from the SMART-PMI paper. However, I am unable to determine the same compound complexity that was reported in the paper.

For example, the following SMILES (ClC1=CC=C2C(N=C(/C=C/C3=CC=CC([C@H](SCC4(CC4)CC(O)=O)CCC5=CC=CC=C5C(C)(C)O)=C3)C=C2)=C1) (MK-0476) was reported to have a complexity of 3.1, however, when I run this code I get output that looks like this:

MOLECULE PREDICTED OBSERVED
mol 1.71903 NA

I am using the latest version of MOE (2022) and Perl 5.3 in Linux. The terminal output of the command does not throw any obvious errors. However it looks like I may be missing an activity file of some sort, but I cannot figure out what that is referring to. Console outputs linked below

Is there anything I may be missing to get this code to work?

Thank you so much

[console.txt](https://github.com/Merck/compoundcomplexity/files/9104853/console.txt)
[std_err.txt](https://github.com/Merck/compoundcomplexity/files/9104860/std_err.txt)

[test_smi.txt](https://github.com/Merck/compoundcomplexity/files/9104855/test_smi.txt)

Contributor guide

No contributing guide indexed for this repository

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 reviewing the attached console.txt and std_err.txt alongside test_smi.txt and the reported command context. Check how the Perl implementation consumes the supplied SMILES and whether an activity file is required. Done means identifying the cause of the differing complexity and documenting or fixing the steps needed to reproduce the paper's result.

Written by the indexing model from the issue text.

Assessment

Tech stack
linux, perl
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.