@article{barghout2026kingems,
  title = {kinGEMs: A scalable framework for resource-constrained models through stochastic tuning of deep learning-predicted kinetic parameters},
  author = {Barghout, Rana A. and Serrano, Lya Chinas and Sanchez-Lengeling, Benjamin and Mahadevan, Radhakrishnan},
  journal = {PLOS Computational Biology},
  year = {2026},
  month = oct,
  doi = {10.64898/2026.03.14.711833},
  url = {https://doi.org/10.64898/2026.03.14.711833},
  preprint = {https://www.biorxiv.org/content/10.64898/2026.03.14.711833v1},
  github = {https://github.com/LMSE/kinGEMs},
  keywords = {proteins, datacentric-ai, graphs, ai},
  abstract = {Couples deep learning turnover number predictions with stochastic simulated annealing to parameterize enzyme-constrained genome-scale models across 93 organisms, resolving long-standing biocatalytic data sparsity.},
}