PO.CH01.07 · 化学

基于深度学习的逆转癌症相关转录表型的新型疗法的筛选与设计

Deep learning-based screening and design of novel therapeutics that reverse cancer-associated transcriptional phenotypes

编号 975 展板 2 时间 4/19 02:00–05:00 区域 Section 38 主讲 Bin Chen, PhD

分会场 Computational, Technological, and Mechanistic Advances

该海报暂无可下载的资料 AACR 官方页面

作者与单位 Authors & Affiliations

Jing Xing¹, Mingdian Tan², Dmitry Leshchiner¹, Mengying Sun³, Shreya Paithankar¹, Rama Shankar¹, Erika Lisabeth³, Bilal Aleiwi³, Ruoqiao Chen³, Matthew Giletto³, Richard Neubig³, Samuel So², Edmund Ellsworth³, Mei-Sze Chua², Jiayu Zhou⁴, Bin Chen¹

¹Michigan State University, Grand Rapids, MI,²Stanford University, Palo Alto, CA,³Michigan State University, East Lansing, MI,⁴University of Michigan, Ann Arbor, MI

摘要 Abstract

中文摘要

鉴定能够逆转疾病相关转录组特征表达的药物，作为发现药物再利用候选物的一种策略已被广泛探索，但其在新化合物发现与优化方面的潜力在很大程度上仍未得到充分挖掘。在此，我们提出一个基于深度学习、由转录组特征引导的药物发现平台，可对大型化合物库进行筛选并对先导化合物进行优化。我们首先开发了一个仅从化学结构预测基因表达变化的模型，并将其用于推断大型筛选库中化合物所诱导的表达变化。随后，我们优化化合物评分，并采用蒙特卡洛树搜索方法进行多目标优化。通过纳入结构-基因-活性关系（Structure-Gene-Activity Relationships），我们直接从转录组数据中揭示药物机制。为展示该系统的实用性，我们针对肝细胞癌（HCC）鉴定并验证了化合物。在HCC中，我们设计出一种新型化合物，将IC50从4 μM改善至0.5 μM，同时具有更高的体外选择性、良好的药代动力学以及体内活性。

查看英文原文 English abstract

Identifying drugs that reverse expression of disease-associated transcriptomic features has been widely explored as a strategy for discovering drug repurposing candidates, but its potential for novel compound discovery and optimization remains largely underexplored. Here, we present a deep learning-based drug discovery platform, guided by transcriptomic features, that screens large compound libraries and optimizes lead compounds. We first develop a model that predicts gene expression changes solely from chemical structures and deploy it to infer the expression changes induced by compounds in large screening libraries. We then refine compound scoring and employ a Monte Carlo Tree Search method for multi-objective optimization. By incorporating Structure-Gene-Activity Relationships, we uncover drug mechanisms directly from transcriptomic data. To demonstrate the utility of the system, we identify and validate compounds for hepatocellular carcinoma (HCC). In HCC, we design a novel compound that improves the IC 50 from 4 µM to 0.5 µM, with increased in vitro selectivity, favorable pharmacokinetics and in vivo activity.

利益披露 Disclosure

J. Xing, None.. M. Tan, None.. M. Sun, None.. S. Paithankar, None.. E. Lisabeth, None.. B. Aleiwi, None.. M. Giletto, None.. R. Neubig, None.. S. So, None.. E. Ellsworth, None.. M. Chua, None.. J. Zhou, None.. B. Chen, None.

← 返回 AACR 2026 检索