Token-Mol is presented, a token-only 3D drug design model that encodes both 2D and 3D structural information, along with molecular properties, into discrete tokens, which introduces a Gaussian cross-entropy loss function tailored for regression tasks, enabling superior performance across multiple downstream application...
Ji-Ke Wang, Rui Qin, Mingyang Wang et al.· Nature Communications· 30 citations· ⚡1
It is demonstrated that linker-free PROTACs can outperform traditional designs, marking a paradigm shift in PROTAC development for targeted protein degradation.
A deep learning framework that integrates knowledge graph embedding and pre-training strategies to overcome the intractable cold start issue, achieving superior performance and interpretability in drug repurposing is introduced.
Kun Li, Jiacai Yi, Qing Ye et al.· Communications Chemistry· 1 citation
HiCLR is the first foundation model that can be broadly applied to various synthesis-related tasks, and it achieves state-of-the-art performance in reaction classification, reaction condition recommendation, reaction yield prediction, synthesis planning, and even molecular property prediction.
Jialu Wu, Yiheng Zhu, Xiaorui Wang et al.· JACS Au· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
RSGPT, a generative model pre-trained on ten billion data points, achieving state-of-the-art performance for synthesis planning, and introduces reinforcement learning to capture the relationships among products, reactants, and templates more accurately.
Yafeng Deng, Xinda Zhao, Hanyu Sun et al.· Nature Communications· 18 citations· ⚡2
The AI-guided development of a first-in-class proteolysis-targeting chimera (PROTAC) designed to selectively degrade the CLIP1-LTK fusion protein is reported, providing a promising therapeutic strategy for overcoming acquired resistance in kinase-driven cancers.
Shi-Cheng Chen, Hai-Ting Duan, S. Zhong et al.· Proceedings of the National...· 0 citations
ERAM aligns pre-trained molecular representations from Protein Language Model with the knowledge of enzyme catalysis by modeling enzymatic reactions as multi-relational data, and demonstrates its potential as a versatile and effective tool for enzyme catalysis research.
This study introduces LaMGen, an LLM-powered framework that leverages large-scale protein-ligand data and rotation-aware molecular encoding to rapidly produce chemically plausible multi-target candidates, achieving strong zero-shot generalization, superior molecular quality, and robust performance across dual- and trip...
Qun Su, Qiaolin Gou, Hui Zhang et al.· Nature Communications· 1 citation
The Biotoxins Database (BioTD) is the largest open-source database for toxins, offering open access to 14,607 data records (8,185 activity records), covering 8,975 toxins sourced from 5,220 references and patents across over 900 species.
Gaoang Wang, Hang Wu, Yang Liao et al.· Journal of Chemical Informat...· 0 citations
BBBP-Atlas is proposed, a structure-aware BBB permeability prediction model designed for unified modeling of small molecules and peptides with the first cross-modal dataset OmniBBBP, which offers a versatile and cross-modal approach for single-compound prediction, batch screening, and dataset exploration for CNS drug d...
Xin Shen, Qun Su, Hao Luo et al.· bioRxiv· 0 citations
An integrated computational workflow that combines enhanced sampling techniques and machine learning collective variables to identify druggable conformations of the AR-NTD and elucidate the binding mechanism of its modulator, EPI-002 is introduced.
Kai Zhu, Huating Wang, Jin-Tu Zhang et al.· Nature Communications· 0 citations
ChatGPT histories should not be treated as clinical screening data but as evidence LLMs are increasingly used as informal support infrastructure, which is private, persistent, responsive, and available outside ordinary hours.
N. K. R. Sehgal, D. Folk, Lyle Ungar et al.· Proceedings of the 2026 Comp...· 0 citations
