Skip to content
Log in
Sponsored Artificial Intelligence: A Modern Approach, Global Edition Artificial Intelligence: A Modern Approach, Global Edition
Open access

MG2Act: A Mechanism-Inspired Sequential Attention Framework for Molecular Glue Degradation Prediction

Zhiyao Zhuang Dan Teng Xiao-Jing Xu Senbiao Fang Yifan Wang M. Hou Ling Ge Shan-Wen Yuan Miaoyuan Yang Lei Cheng Zong-Qun Zhang Qi He Zhuo-Yue Li Ximing Xu Shumin Ma Su-Lin Zhang Xiao Wang Ming-Yue Zheng Chong Qin
Aug 2026 · bioRxiv · 0 citations · 40 references
Biology

TL;DR

This work presents MG2Act, a structure-independent framework that translates two-step logic into sequential cross-attention, using CRBN-mediated degradation as the most data-rich representative system.

DOI Semantic Scholar
Read PDF

Similar papers

Preprint Aug 2026

DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction

DegradeQuery, a context-aware prediction framework that converts label-missing records into a pretraining signal, is introduced and demonstrates that incompletely labeled PROTAC databases contain useful relational supervision and provide a practical route for learning context-aware degradation predictors from scarce ex...

Dong Xu, Zhang-Fan Yang, Jian-Tao Wu et al. · 0 citations
Aug 2026

DiConSite: A Unified Topology-Adaptive Architecture for Protein Binding Site Prediction Across Ligand Modalities.

By combining protein language model embeddings with topology-adaptive geometric reasoning, DiConSite offers a reusable framework for residue-level protein interaction analysis and achieves consistently strong and often best-performing results, while improving robustness to structural uncertainty and cross-modal variati...

Shou-Zhi Chen, Zhen-Chao Tang, Lin-Lin You et al. · 1 citation
Open access Aug 2026

De novo Design of Macrocyclic Molecular Glues

EvoBind-multimer is presented, a deep learning framework for the de novo design of molecular glues directly from protein sequences that generates small macrocyclic peptides that bridge user-defined protein pairs without requiring prior interface knowledge or existing ligands.

Andrä Brunner, Krzysztof Wierbiłowicz, Diandra Daumiller et al. · 0 citations
Open access Jul 2026

From Ternary Modeling to Predictive PROTAC Design: A Computational Perspective

A Perspective on computational PROTAC methodologies published from 2019 to the present is presented, organizing the field into two complementary streams: constraint-driven, physics-based workflows that assemble and refine ternary complex models by enforcing geometric feasibility and evaluating pose stability using dock...

Joseph M. Schulz, R. Reynolds, S. Schürer · 0 citations
Aug 2026

Beyond random splits: A hierarchical benchmark of transferability and reliability in PROTAC activity prediction.

A hierarchical benchmark designed to expose evaluation pitfalls and quantify the transferability and reliability limits of current PROTAC predictors is presented, repositioning PROTAC prediction as a problem of transferability and reliability rather than leaderboard optimization and provide practical guidelines for fut...

Ren Zhu, Guang-Hao Guo, Lu-Lu Li et al. · 0 citations
Open access Aug 2026

Proteome-wide identification of the druggable CRBN interactome.

This pipeline identified 6 known and 43 novel CRBN-pomalidomide binders, including orthogonally validated hits that provide privileged starting points for MGD development, and expects this binding-focused workflow to be applicable to other MGD-E3 ligase systems, potentially extending the scope of this emerging drug cla...

Pius Galli, Shuhao Xiao, Y. Meng et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.