UniIF: Unified Molecule Inverse Folding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Zhangyang, Wang, Jue, Tan, Cheng, Wu, Lirong, Huang, Yufei, Li, Siyuan, Ye, Zhirui, Li, Stan Z.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910462433558528
author Gao, Zhangyang
Wang, Jue
Tan, Cheng
Wu, Lirong
Huang, Yufei
Li, Siyuan
Ye, Zhirui
Li, Stan Z.
author_facet Gao, Zhangyang
Wang, Jue
Tan, Cheng
Wu, Lirong
Huang, Yufei
Li, Siyuan
Ye, Zhirui
Li, Stan Z.
contents Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified models have been proposed for different small- or macro-molecules, few have attempted to unify the learning process, resulting in redundant efforts. Complementary to recent advancements in molecular structure prediction, such as RoseTTAFold All-Atom and AlphaFold3, we propose the unified model UniIF for the inverse folding of all molecules. We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization. 2) Model-Level: We introduce a geometric block attention network, comprising a geometric interaction, interactive attention and virtual long-term dependency modules, to capture the 3D interactions of all molecules. Through comprehensive evaluations across various tasks such as protein design, RNA design, and material design, we demonstrate that our proposed method surpasses state-of-the-art methods on all tasks. UniIF offers a versatile and effective solution for general molecule inverse folding.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18968
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UniIF: Unified Molecule Inverse Folding
Gao, Zhangyang
Wang, Jue
Tan, Cheng
Wu, Lirong
Huang, Yufei
Li, Siyuan
Ye, Zhirui
Li, Stan Z.
Artificial Intelligence
Machine Learning
Quantitative Methods
Molecule inverse folding has been a long-standing challenge in chemistry and biology, with the potential to revolutionize drug discovery and material science. Despite specified models have been proposed for different small- or macro-molecules, few have attempted to unify the learning process, resulting in redundant efforts. Complementary to recent advancements in molecular structure prediction, such as RoseTTAFold All-Atom and AlphaFold3, we propose the unified model UniIF for the inverse folding of all molecules. We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization. 2) Model-Level: We introduce a geometric block attention network, comprising a geometric interaction, interactive attention and virtual long-term dependency modules, to capture the 3D interactions of all molecules. Through comprehensive evaluations across various tasks such as protein design, RNA design, and material design, we demonstrate that our proposed method surpasses state-of-the-art methods on all tasks. UniIF offers a versatile and effective solution for general molecule inverse folding.
title UniIF: Unified Molecule Inverse Folding
topic Artificial Intelligence
Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2405.18968