paper-with-me

Papers

Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity

2025-09-25 · Mohammadsaleh Refahi, Bahrad A. Sokhansanj, James R. Brown, Gail Rosen arxiv

Accurate prediction of drug-target binding affinity can accelerate drug discovery by prioritizing promising compounds before costly wet-lab screening. While deep learning has advanced this task, most models fuse ligand and protein representations via simple concatenation and lack explicit geometric regularization, resulting in poor generalization across chemical space and time. We introduce FIRM-DTI, a lightweight framework that conditions molecular embeddings on protein embeddings through a feature-wise linear modulation (FiLM) layer and enforces metric structure with a triplet loss. An RBF regression head operating on embedding distances yields smooth, interpretable affinity predictions. Despite its modest size, FIRM-DTI achieves state-of-the-art performance on the Therapeutics Data Commons DTI-DG benchmark, as demonstrated by an extensive ablation study and out-of-domain evaluation. Our results underscore the value of conditioning and metric learning for robust drug-target affinity prediction.

📄 PDF Abstract BibTeX arXiv:2509.20693

Code (0)

등록된 구현이 없습니다.

Tasks

Metric LearningDrug Discovery

Similar Papers 제목 키워드 기반

GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow

2023-02-23 · Fang Sun, Zhihao Zhan, Hongyu Guo, Ming Zhang 외

Designing molecules that bind to specific target proteins is a fundamental task in drug discovery. Recent models leverage geometric constraints to generate ligand molecules that bind cohesively with specific protein pock…

3D geometry3D Molecule GenerationDrug Discovery

Generating 3D Molecules for Target Protein Binding

2022-04-19 · Meng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi 외

A fundamental problem in drug discovery is to design molecules that bind to specific proteins. To tackle this problem using machine learning methods, here we propose a novel and effective framework, known as GraphBP, to …

Drug DiscoveryGraph Neural Network

Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number

2025-09-01 · Jingyuan Zhou, Hao Qian, Shikui Tu, Lei Xu arxiv

Structure-based drug design (SBDD), aiming to generate 3D molecules with high binding affinity toward target proteins, is a vital approach in novel drug discovery. Although recent generative models have shown great poten…

Drug Discovery

Fragment and Geometry Aware Tokenization of Molecules for Structure-Based Drug Design Using Language Models

2024-08-19 · Cong Fu, Xiner Li, Blake Olson, Heng Ji 외

Structure-based drug design (SBDD) is crucial for developing specific and effective therapeutics against protein targets but remains challenging due to complex protein-ligand interactions and vast chemical space. Althoug…

Drug Design

Design of Ligand-Binding Proteins with Atomic Flow Matching

2024-09-18 · Junqi Liu, Shaoning Li, Chence Shi, Zhi Yang 외

Designing novel proteins that bind to small molecules is a long-standing challenge in computational biology, with applications in developing catalysts, biosensors, and more. Current computational methods rely on the assu…