Dose-Response Estimation

Follow this topic Ask about this topic

Latest papers

12 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Transformer-Based Reinforcement Learning for Phase I Dose Allocation
Oct 30, 2026Shijie YuanTransformer-Based RL Dose-Response Estimation
The University of Texas at Austin
D2ML: Models for Direct-to-Biology Small Molecule Screening
Oct 29, 2026AkshatKumar Nigam, Neri Amara, Hillary Dequina +7Drug Discovery Molecular Property Prediction
Kimia Therapeutics, Berkeley, CA 94710
Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
Oct 12, 2026Changjian Liu, Tianyu Wang, Yuwei Xu +6Dose-Response Estimation Causal Effect Estimation
Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, China · Beijing Key Laboratory of Spatio-temporal Perception and Urban Resilience · Taobao & Tmall Group of Alibaba, Beijing, China +2
Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects
Sep 27, 2026Shucheng Liu, Chan Park, Guanhua ChenCausal Effect Estimation Doubly Robust Estimation
University of North Carolina at Chapel Hill · University of Illinois Urbana-Champaign · University of Wisconsin–Madison
Predicting Dose-Response Success from Primary Screening Data
Aug 27, 2026Sean LimDose-Response Estimation Drug Discovery
Department of Natural Science, Rice University, Houston, TX, USA
Joint Flow Matching Enables Continuous Dose-Conditioned Cell Morphing
Aug 17, 2026Lea Bogensperger, Manuela Merlo, Martin Baumgartner +2Dose-Response Estimation Single-Cell Perturbation Modeling
University of Zurich · University Children’s Hospital Zurich
Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization
Jun 28, 2026Amirreza Dolatpour Fathkouhi, Justin Lee, Heman ShakeriFlow Matching Type 1 Diabetes
Department of Computer Science · School of Data Science
Attention-Based Estimation of the Individual Treatment Benefit Probability under Dose Variation
Jun 11, 2026Lev V. Utkin, Andrei V. Konstantinov, Stanislav K. Kogan +2Causal Effect Estimation Clinical Decision-Making
Peter the Great St.Petersburg Polytechnic University Higher School of Artificial Intelligence Technologies St.Petersburg, Russia
Doubly Robust Proxy Causal Learning with Neural Mean Embeddings
May 10, 2026Bariscan Bozkurt, Alexandre Galashov, Dimitri Meunier +3Causal Effect Estimation Causal Inference
University College London
VIANA: character Value-enhanced Intensity Assessment via domain-informed Neural Architecture
Apr 1, 2026Luana P. Queiroz, Icaro S. C. Bernardes, Ana M. Ribeiro +2Dose-Response Estimation Molecular Representation Learning
LSRE-LCM, ALiCE, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal · Department of Chemical Engineering, Norwegian University of Science and Technology, Sem Sælands vei 4, NO-7491 Trondheim, Norway · Corporate Fragrance R&D, The Procter & Gamble Company, Ivorydale Innovation Center, 5299 Spring Grove Ave., Cincinnati, OH 45140, USA +1
scTREAT: Latent Diffusion for Single-Cell Drug-Response Prediction
Oct 8, 2025Zhaokang Liang, Shuyang Zhuang, Xiaoran Jiao +3Single-Cell Perturbation Modeling Cancer Drug Response Prediction
Zhejiang University, China · Massachusetts Institute of Technology, USA
Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights
Jun 27, 2024Zeqin Yang, Weilin Chen, Ruichu Cai +7Dose-Response Estimation Causal Inference with Unobserved Confounding
School of Computer Science, Guangdong University of Technology · Didi Chuxing · Pazhou Laboratory (Huangpu) +1

Oct 30, 2026J/K move · Enter open · S save

Transformer-Based Reinforcement Learning for Phase I Dose Allocation

Shijie Yuan

The University of Texas at Austin

Transformer-Based RL Dose-Response Estimation

Open paper AskPDF arXiv

Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels. Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator. A Transformer encoder summarizes the dose tokens, trial-conditioned cross-attention produces a fixed-dimensional trial representation, and a three-action policy chooses de-escalation, staying, or escalation. The final maximum tolerated dose (MTD) decision is deliberately kept outside the learned policy: after the planned sample size, weighted isotonic regression and a prespecified safety cap select the dose closest to the target toxicity probability. In the simulations, toxicity-penalized policies reduce DLT burden while unpenalized policies improve selection accuracy at the cost of greater toxicity. These results demonstrate a controllable safety--accuracy trade-off but do not establish superiority over conventional dose-finding designs.