Implementation gap report
A general model to predict small molecule substrates of enzymes based on machine and deep learning
Alexander Kroll et al. · Nature Communications · 2023. Citation count: 171 from OpenAlex cited_by_count, snapshot 2026-05-26.
Specified
3
Partial
2
Missing
2
Contract files
9
Specified
Paper metadata and citation snapshot are available from OpenAlex for 2023-05-15.
The work matches the molecular property prediction support boundary used for OpenAlgo hub triage.
Template estimate: fingerprint descriptor classification.
Partial
Dataset and metric extraction still require OpenAlgo parser review before any reproduction claim.
Generated code can expose runnable scaffolding, but paper-specific hyperparameters must be confirmed by a reviewer.
Missing
No copyrighted PDF or full-paper text is stored in the hub manifest.
Official benchmark assets, split files, and random seed policy must be attached before benchmark reproduction can be claimed.
Repository
openalgo-repro-a-general-model-to-predict-small-molecule-substrates-of-enzymes-based-on-machine
Awaiting OpenAlgo generation and GitHub publication after pilot review.
- Repository status
- Not started
- Contract status
- not_started
Repository contract
{
"schemaVersion": 1,
"generatedBy": "OpenAlgo",
"paperId": "oa-repro-047",
"title": "A general model to predict small molecule substrates of enzymes based on machine and deep learning",
"doi": "10.1038/s41467-023-38347-2",
"hubUrl": "https://openalgo.com/hub/a-general-model-to-predict-small-molecule-substrates-of-enzymes-based-on-machine",
"translateUrl": "https://openalgo.com/?utm_source=github&utm_medium=repro_repo&utm_campaign=repro_hub&utm_content=a-general-model-to-predict-small-molecule-substrates-of-enzymes-based-on-machine",
"repositoryName": "openalgo-repro-a-general-model-to-predict-small-molecule-substrates-of-enzymes-based-on-machine",
"repositoryDescription": "OpenAlgo-generated reproducibility scaffold and gap report for A general model to predict small molecule substrates of enzymes based on machine and deep learning",
"templateFamily": "fingerprint_descriptor_classification",
"modelFamily": "classical_ml",
"validationStatus": "not_published",
"validationLabel": "Not published",
"gapCounts": {
"specified": 3,
"partial": 2,
"missing": 2
},
"citationSource": "OpenAlex cited_by_count",
"citationSnapshotAt": "2026-05-26T00:00:00.000-07:00",
"requiredFiles": [
"README.md",
"REPRODUCIBILITY_GAPS.md",
"requirements.txt",
"Dockerfile",
"openalgo.json",
"CITATION.cff",
"LICENSE",
".github/workflows/ci.yml",
"src/"
],
"publicationNotice": "This repository is OpenAlgo-generated and is not an official author implementation unless explicitly stated by the paper authors.",
"source": "https://openalgo.com"
}Corpus decision
Accepted from the OpenAlex query snapshot after QSAR/molecular ML term filtering, then ranked by citation count.
Source queries: cheminformatics machine learning molecular property; SMILES representation learning property prediction.