Ark-ADMET: endpoint-specific selection of molecular representations and hyperparameters for gradient-boosted ADMET models under the Therapeutics Data Commons benchmark protocol
- 1Eonark
Abstract
Typical submissions to the Therapeutics Data Commons (TDC) absorption, distribution, metabolism, excretion, and toxicity (ADMET) benchmark leaderboard apply a single architecture and a single feature representation across all 22 endpoints, despite substantial heterogeneity in evaluation metric, training-set size, and class balance. Rather than proposing a new architecture, we show that endpoint-specific selection of molecular representations and CatBoost hyperparameters, carried out under the official TDC ADMET benchmark protocol, is a competitive alternative to that uniform recipe. For each endpoint, a fixed CatBoost backbone was paired with configurations chosen from a common candidate set comprising published fingerprints and physicochemical descriptors, truncated three-dimensional PaDEL descriptors, frozen graph isomorphism network (GIN) and MiniMol embeddings, and a convex combination with a shallow network trained on the MiniMol embedding alone. All feature and hyperparameter choices were made on an internal scaffold validation split under a prespecified strict-improvement rule. Against a frozen snapshot of the public leaderboard, the resulting Ark-ADMET family of 22 endpoint-specific models matched or exceeded the best previously listed score on 7 of 21 rankable endpoints and strictly exceeded it on 3. All selected configurations retain the baseline fingerprint-and-descriptor block; optional components differ across endpoints. Taken together, these results show that competitive performance on this benchmark can be achieved without a new architecture or a single optional representation shared across all endpoints.
Related
- On the sensitivity to hyperparameters of a Bayesian method to infer selection signatures
- Decoding molecular heterogeneity in lupus nephritis: integrating single-cell and spatial multi-omics for endotype-driven precision therapeutics
- Goal-directed action selection relies on conjunctive representations that bind goals, actions and expected sensory outcomes
- From molecular mechanisms to clinical practice: advances in the immune microenvironment and translational therapeutics of colorectal cancer liver metastasis
- An Adaptive Optimizer without User-Specified Hyperparameters through Historical Projection and Self-Calibrated Scaling
BibTeX
@misc{shi2026arkadmet,
title = {{Ark-ADMET: endpoint-specific selection of molecular representations and hyperparameters for gradient-boosted ADMET models under the Therapeutics Data Commons benchmark protocol}},
author = {Y. Shi and H. Luo and F. Liu and S. Zhao},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.762420},
url = {https://www.biorxiv.org/content/10.64898/2026.10.28.762420v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Ark-ADMET: endpoint-specific selection of molecular representations and hyperparameters for gradient-boosted ADMET models under the Therapeutics Data Commons benchmark protocol
AU - Y. Shi
AU - H. Luo
AU - F. Liu
AU - S. Zhao
PY - 2026
DA - 2026/10/28
PB - bioRxiv
DO - 10.64898/2026.10.28.762420
UR - https://www.biorxiv.org/content/10.64898/2026.10.28.762420v1
AB - Typical submissions to the Therapeutics Data Commons (TDC) absorption, distribution, metabolism, excretion, and toxicity (ADMET) benchmark leaderboard apply a single architecture and a single feature representation across all 22 endpoints, despite substantial heterogeneity in evaluation metric, training-set size, and class balance. Rather than proposing a new architecture, we show that endpoint-specific selection of molecular representations and CatBoost hyperparameters, carried out under the official TDC ADMET benchmark protocol, is a competitive alternative to that uniform recipe. For each endpoint, a fixed CatBoost backbone was paired with configurations chosen from a common candidate set comprising published fingerprints and physicochemical descriptors, truncated three-dimensional PaDEL descriptors, frozen graph isomorphism network (GIN) and MiniMol embeddings, and a convex combination with a shallow network trained on the MiniMol embedding alone. All feature and hyperparameter choices were made on an internal scaffold validation split under a prespecified strict-improvement rule. Against a frozen snapshot of the public leaderboard, the resulting Ark-ADMET family of 22 endpoint-specific models matched or exceeded the best previously listed score on 7 of 21 rankable endpoints and strictly exceeded it on 3. All selected configurations retain the baseline fingerprint-and-descriptor block; optional components differ across endpoints. Taken together, these results show that competitive performance on this benchmark can be achieved without a new architecture or a single optional representation shared across all endpoints.
ER -