Hybrid Mechanistic-Neural Modeling of Concentration-Time Dynamics Generalizes Human Pharmacokinetics Prediction Across Unseen Chemical Space
Badkul, A.; Cai, L.; Kim, M.; Wang, J.; Xie, L.
Show abstract
The pharmacokinetics concentration-time profile encodes ADME dynamics. Its optimization in drug discovery curbs late-stage attrition, yet forecasting human pharmacokinetics from chemical structure remains difficult. Machine learning models ignore continuous ADME dynamics, whereas physiologically based pharmacokinetics (PBPK) models demand unavailable parameters and impose rigid, misspecified compartmental structures. We present PK-MUSE (PharmacoKinetic hybrid Mechanistic Universal System Equation), augmenting a two-compartment model with bounded, state- and time-dependent neural corrections to elimination and intercompartmental distribution. Molecular structure parameterizes compound-specific behavior, while learned corrections refine dynamic equations. Across scaffold and temporal out-of-distribution evaluations, PK-MUSE achieved the lowest mean exposure-endpoint MdFE, reducing MdFE by 7.2%, 45.2%, and 26.2% versus state-of-the-art machine learning (HML- RF), deep learning compartmental (DeepCt), and PBPK (PK-Sim) models. Interrogating the corrections localized misspecification to distribution rather than elimination. By extending mechanistic simulators with data-driven constrained neural dynamics that preserve interpretability and generalize to unseen chemotypes, PK-MUSE advances digital twins for drug discovery.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- TrustAffinity: accurate, reliable and scalable out-of-distribution protein-ligand binding affinity prediction using trustworthy deep learning 96%
- Sagittarius: Extrapolating Heterogeneous Time-Series Gene Expression Data 92%
- An interpretable deep learning framework for genome-informed precision oncology 92%
Similar papers in this journal
- Informing Pharmacokinetic Models with Physiological Data: Oral Population Modeling of L-Serine in Humans 90%
- Machine learning enables accurate and rapid prediction of active molecules against breast cancer cells 90%
- Physiologically based pharmacokinetic (PBPK) modeling of the role of CYP2D6 polymorphism for metabolic phenotyping with dextromethorphan 89%
Similar papers in this journal
- AnimalGAN: A Generative Adversarial Network Model Alternative to Animal Studies for Clinical Pathology Assessment 94%
- First fully-automated AI/ML virtual screening cascade implemented at a drug discovery centre in Africa 94%
- Community assessment of cancer drug combination screens identifies strategies for synergy prediction 93%
Similar papers in this journal
- Rational Discovery of Dual-Action Multi-Target Kinase Inhibitor for Precision Anti-Cancer Therapy Using Structural Systems Pharmacology 94%
- Monotherapy cancer drug-blind response prediction is limited to intraclass generalization 93%
- Optimizing clinical dosing of combination broadly neutralizing antibodies for HIV prevention 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.