Accessing Enzyme Kinetic Data and Prediction Methods at Scale

Abstract

Enzyme kinetic parameters inform metabolic models, yet experimental measurements are sparse. A growing body of work predicts them from protein and substrate features, but software fragmentation hinders adoption, so downstream tools lock into the most accessible method. We present OpenKinetics Predictor (at predictor.openkinetics.org), an open-source platform integrating thirteen methods in isolated environments behind one interface. The platform optionally reports similarity between query proteins and each method's training data to contextualise reliability. A common featurisation-prediction abstraction keeps it extensible, and independent parties, including original authors, contributed many methods. We pair it with a data portal (at data.openkinetics.org) that exposes CatLog, a curated kinetic dataset, with precomputed embeddings, predicted binding sites, and standardised splits. Both offer a web interface and an API, and the GECKO modelling toolbox already calls the predictor API. As a case study, we predict across an E. coli model and find inter-predictor agreement varies with metabolic context and data availability.

Going beyond labels: Semi-supervised learning for enzyme kinetic parameter prediction
A. Malli, D. Vasyutyn, A. Majumder +1
bioRxiv15 Oct 2026PreprintCC BYFull textBioinformatics & computational biologybioRxiv
The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]
Bilal Ahmad, Rajed Mehmood
arXiv7 Sep 2026PreprintarXiv licenceFull textBioinformatics & computational biologyarXiv
Octave: Scale-resolved Evaluation of Spatial Gene Expression Prediction from Histology
Q. Wang, S. Gu, Q. Lan +3
bioRxiv25 Sep 2026PreprintAll rights reservedFull textBioinformatics & computational biologybioRxiv
MSCF-DM: center-site-aware attention and gated multi-scale fusion network for cross-species DNA methylation site prediction
Xin Wei, Siqin Hu
BMC Genomics4 Nov 2026Peer-reviewedCC BY 4.0Genetics & genomicsCrossref
Pre-season bare-soil spectral proxies complement pod-filling canopy indices for field-scale soybean-yield prediction from UAV imagery
Yan Zhao, Zhiyuan Tian, Rui Ma +1
iScience25 Oct 2026Peer-reviewedCC BY-NC-ND 4.0EcologyCell PressCrossref

Cite

BibTeX RIS

BibTeX

@misc{alwer2026accessing,
  title = {{Accessing Enzyme Kinetic Data and Prediction Methods at Scale}},
  author = {S. Alwer and H. Escoffier and K. Taha and V. Boorla and H. Yu and S. Santra and Z. Wang and C. Egwu and A. Osinuga and S. Dey and V. S. Raghunath and F. Zare and J. McGoldrick and J.-N. Weder and E. Kerkhoven and X. Luo and C. D. Maranas and L. Zheng and U. Wittig and R. Chowdhury and R. Saha and N. Toepfer and T. Sauter and R. M. T. Fleming},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.25.751968},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.25.751968v1},
  note = {CC BY},
}

RIS

TY  - UNPB
TI  - Accessing Enzyme Kinetic Data and Prediction Methods at Scale
AU  - S. Alwer
AU  - H. Escoffier
AU  - K. Taha
AU  - V. Boorla
AU  - H. Yu
AU  - S. Santra
AU  - Z. Wang
AU  - C. Egwu
AU  - A. Osinuga
AU  - S. Dey
AU  - V. S. Raghunath
AU  - F. Zare
AU  - J. McGoldrick
AU  - J.-N. Weder
AU  - E. Kerkhoven
AU  - X. Luo
AU  - C. D. Maranas
AU  - L. Zheng
AU  - U. Wittig
AU  - R. Chowdhury
AU  - R. Saha
AU  - N. Toepfer
AU  - T. Sauter
AU  - R. M. T. Fleming
PY  - 2026
DA  - 2026/09/25
PB  - bioRxiv
DO  - 10.64898/2026.09.25.751968
UR  - https://www.biorxiv.org/content/10.64898/2026.09.25.751968v1
AB  - Enzyme kinetic parameters inform metabolic models, yet experimental measurements are sparse. A growing body of work predicts them from protein and substrate features, but software fragmentation hinders adoption, so downstream tools lock into the most accessible method. We present OpenKinetics Predictor (at predictor.openkinetics.org), an open-source platform integrating thirteen methods in isolated environments behind one interface. The platform optionally reports similarity between query proteins and each method's training data to contextualise reliability. A common featurisation-prediction abstraction keeps it extensible, and independent parties, including original authors, contributed many methods. We pair it with a data portal (at data.openkinetics.org) that exposes CatLog, a curated kinetic dataset, with precomputed embeddings, predicted binding sites, and standardised splits. Both offer a web interface and an API, and the GECKO modelling toolbox already calls the predictor API. As a case study, we predict across an E. coli model and find inter-predictor agreement varies with metabolic context and data availability.
ER  -

Abstract

Related

Cite