Saved in:
Bibliographic Details
Main Authors: Navarro, Carles, Tholke, Philipp, de Fabritiis, Gianni
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.19562
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Structure-based drug discovery faces the dual challenge of accurately capturing 3D protein-ligand interactions while navigating ultra-large chemical spaces to identify synthetically accessible candidates. In this work, we present a unified framework that addresses these challenges by combining contrastive 3D structure encoding with autoregressive molecular generation conditioned on commercial compound spaces. First, we introduce an SE(3)-equivariant transformer that encodes ligand and pocket structures into a shared embedding space via contrastive learning, achieving competitive results in zero-shot virtual screening. Second, we integrate these embeddings into a multimodal Chemical Language Model (MCLM). The model generates target-specific molecules conditioned on either pocket or ligand structures, with a learned dataset token that steers the output toward targeted chemical spaces, yielding candidates with favorable predicted binding properties across diverse targets.