Activity Landscape Roughness Anticipates Machine-Learning Reliability Across Environmental Chemistry Endpoints
Environmental Science & Technology · 2026
DOI: 10.1021/acs.est.6c06820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology, 2026. Verfasst von Haoyang Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai200241, PR China. Hauptthemen laut MEDLINE: Machine Learning. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Machine learning increasingly supports chemical risk assessment under REACH, TSCA, and OECD QSAR frameworks, but random-split performance can be optimistic for structurally novel chemicals. We ask whether task difficulty can be anticipated before model training. EnvMolBench spans 45 datasets, 114,500+ end point-specific records (55,984 unique structures), and 6500+ model–dataset combinations from 13 algorithms and 6 representation categories. Training-set activity landscape roughness, quantified by nearest-neighbor disagreement rate (classification) or the Structure–Activity Landscape Index (regression), was associated with best-observed performance (Spearman ρ = −0.71, 95% CI [−0.94, −0.26], p = 0.0009 for classification; ρ = −0.47, 95% CI [−0.81, −0.04], p = 0.019 for regression), surviving family-wide FDR correction for classification (q = 0.0085) but not regression (q = 0.063). On high-roughness end points, excluding activity-cliff compounds post hoc raised AUC by a mean 0.134 and lowered standardized RMSE by 0.067, whereas removing cliffs from training did not help. The three evaluated pretrained models did not outperform well-tuned baselines on the ten roughest end points. Roughness therefore provides an empirical, representation-relative diagnostic of achievable performance rather than a fundamental ceiling, motivating a workflow linking it to method selection, applicability-domain assessment, and conformal calibration. EnvMolBench, its datasets, splits, and baselines are released openly.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Environmental Science, School of Ecological and Environmental Sciences, East China Normal University, Shanghai200241, PR China.
- College of Environmental Science and Engineering, Tongji University, Shanghai200092, China.
ORCID-Profile: Zeting Wu, Shifa Zhong
Förderung
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Li, H., Wu, Z., & Zhong, S. (2026). Activity Landscape Roughness Anticipates Machine-Learning Reliability Across Environmental Chemistry Endpoints. Environmental Science & Technology. https://doi.org/10.1021/acs.est.6c06820
Vancouver
Li H, Wu Z, Zhong S. Activity Landscape Roughness Anticipates Machine-Learning Reliability Across Environmental Chemistry Endpoints. Environmental Science & Technology. 2026. doi:10.1021/acs.est.6c06820
BibTeX
@article{Li2026,
author = {Li, Haoyang and Wu, Zeting and Zhong, Shifa},
title = {Activity Landscape Roughness Anticipates Machine-Learning Reliability Across Environmental Chemistry Endpoints},
journal = {Environmental Science & Technology},
year = {2026},
doi = {10.1021/acs.est.6c06820}
}
EUVIMED