Molecular Fragment

Molecular fragment-based approaches are revolutionizing molecule design and structure elucidation by focusing on assembling pre-defined building blocks rather than atom-by-atom construction. Current research heavily utilizes machine learning, particularly deep generative models like diffusion models and graph neural networks, to predict molecular structures from spectral data or design novel molecules with desired properties, often incorporating techniques like autoregressive generation and symmetry-equivariant representations for improved efficiency and accuracy. This focus on fragments offers advantages in predicting synthesizability and controlling specific molecular properties, impacting drug discovery, materials science, and other fields requiring the design of molecules with tailored characteristics.

Papers

November 3, 2024

Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces
Siqi Chen, Zhiqiang Wang, Xianqi Deng, Yili Shen, Cheng-Wei Ju, Jun Yi, Lin Xiong, Guo Ling, Dieaa Alhmoud, Hui Guan, Zhou Lin
Many Body Potential Energy Surface Molecular Fragment

October 16, 2024

FragNet: A Graph Neural Network for Molecular Property Prediction with Four Layers of Interpretability
Gihan Panapitiya, Peiyuan Gao, C Mark Maupin, Emily G Saldanha
Graph Neural Network Inherent Interpretability Multi Layer Molecular Property Prediction Molecular Property Molecular Structure Molecular Fragment IARS Segnet

August 15, 2024

Accurate and efficient structure elucidation from routine one-dimensional NMR spectra using multitask machine learning
Frank Hu, Michael S. Chen, Grant M. Rotskoff, Matthew W. Kanan, Thomas E. Markland
Known Molecule Magnetic Resonance Molecular Structure Molecular Fragment Multitask ML System

May 8, 2024

A Review on Fragment-based De Novo 2D Molecule Generation
Sergei Voloboev
Molecule Generation Molecular Property Part Based Molecular Fragment

March 15, 2024

Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation
Odin Zhang, Yufei Huang, Shichen Cheng, Mengyao Yu, Xujun Zhang, Haitao Lin, Yundian Zeng, Mingyang Wang, Zhenxing Wu, Huifeng Zhao, Zaixi Zhang, Chenqing Hua, Yu Kang, Sunliang Cui, Peichen Pan, Chang-Yu Hsieh, Tingjun Hou
Molecular Graph Molecular Generation Geometric Learning Atomic Knowledge Non Verbal Fragment Hierarchical Generation Molecular Fragment

December 15, 2023

Autoregressive fragment-based diffusion for pocket-aware ligand design
Mahdi Ghorbani, Leo Gendelev, Paul Beroza, Michael J. Keiser
Protein Ligand 3D Molecule Molecular Scaffold AutoRegressive Diffusion Molecular Fragment

November 27, 2023

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
Ameya Daigavane, Song Kim, Mario Geiger, Tess Smidt
Known Molecule Molecule Generation Spherical Harmonic Equivariant Generative Molecular Geometry Molecular Fragment

October 5, 2023

Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Properties
Siyuan Guo, Jihong Guan, Shuigeng Zhou
Molecule Generation Molecular Property Many Property Efficient Optimization Drug Design Intriguing Property Molecular Fragment

July 26, 2023

Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength
Tongya Zheng, Tianli Zhang, Qingzheng Guan, Wenjie Huang, Zunlei Feng, Mingli Song, Chun Chen
Graph Neural Network Estimated Team Strength Artefact PARTICLE Granular Material Molecular Fragment

October 25, 2022

A Database of Ultrastable MOFs Reassembled from Stable Fragments with Machine Learning Models
Aditya Nandy, Shuwen Yue, Changhwan Oh, Chenru Duan, Gianmarco G. Terrones, Yongchul G. Chung, Heather J. Kulik
Machine Learning Model New Database Material Synthesis Metal Organic Framework Molecular Fragment MOF Structure

October 11, 2022

Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
Ilia Igashov, Hannes Stärk, Clément Vignac, Victor Garcia Satorras, Pascal Frossard, Max Welling, Michael Bronstein, Bruno Correia
Equivariant Diffusion Molecular Fragment

November 25, 2021

Fragment-based molecular generative model with high generalization ability and synthetic accessibility
Seonghwan Seo, Jaechang Lim, Woo Youn Kim
Known Molecule Molecular Design Novel Molecule Generalization Capability Molecular Generative Synthetic Multi Modal Dataset Molecular Fragment

Molecular Fragment

Papers

Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces

FragNet: A Graph Neural Network for Molecular Property Prediction with Four Layers of Interpretability

Accurate and efficient structure elucidation from routine one-dimensional NMR spectra using multitask machine learning

A Review on Fragment-based De Novo 2D Molecule Generation

Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation

Autoregressive fragment-based diffusion for pocket-aware ligand design

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Properties

Graph Neural Networks-based Hybrid Framework For Predicting Particle Crushing Strength

A Database of Ultrastable MOFs Reassembled from Stable Fragments with Machine Learning Models

Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design

Fragment-based molecular generative model with high generalization ability and synthetic accessibility