Drug Design

Drug design aims to create molecules with desired therapeutic properties, accelerating the often lengthy and costly drug discovery process. Current research heavily utilizes machine learning, employing various architectures like graph neural networks, transformers, variational autoencoders, and diffusion models, often integrated with reinforcement learning and evolutionary algorithms to optimize molecule generation and predict properties such as binding affinity and synthesizability. This field is crucial for advancing healthcare, enabling the development of more effective and personalized treatments for a wide range of diseases by efficiently exploring the vast chemical space of potential drug candidates.

Papers

December 15, 2023

Automating reward function configuration for drug design
Marius Urbonas, Temitope Ajileye, Paul Gainer, Douglas Pires
Reward Function Drug Discovery Drug Design Reward Function Design Generative Molecular Design

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

June 19, 2023

SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design
Carl Edwards, Aakanksha Naik, Tushar Khot, Martin Burke, Heng Ji, Tom Hope
Different Context Drug Design Drug Synergy Drug Synergy Prediction

May 4, 2023

Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks
Isaac Filella-Merce, Alexis Molina, Marek Orzechowski, Lucía Díaz, Yang Ming Zhu, Julia Vilalta Mor, Laura Malo, Ajay S Yekkirala, Soumya Ray, Victor Guallar
Generative AI Drug Discovery Chemical Space Active Learning Framework Drug Design Chemical Property Prediction

March 6, 2023

3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
Jiaqi Guan, Wesley Wei Qian, Xingang Peng, Yufeng Su, Jian Peng, Jianzhu Ma
Molecule Generation Model Free Drug Design Affinity Prediction Protein Target Equivariant Diffusion

February 14, 2023

Do Deep Learning Models Really Outperform Traditional Approaches in Molecular Docking?
Yuejiang Yu, Shuqi Lu, Zhifeng Gao, Hang Zheng, Guolin Ke
Deep Learning Deep Learning Model Molecular Docking Current Method Drug Design

January 15, 2023

Geometric Graph Learning with Extended Atom-Types Features for Protein-Ligand Binding Affinity Prediction
Md Masud Rana, Duc Duy Nguyen
Protein Ligand Drug Design Affinity Prediction Atomic Knowledge Binding Affinity Protein Ligand Binding Affinity Prediction

November 10, 2022

Probabilistic thermal stability prediction through sparsity promoting transformer representation
Yevgen Zainchkovskyy, Jesper Ferkinghoff-Borg, Anja Bennett, Thomas Egebjerg, Nikolai Lorenzen, Per Jr. Greisen, Søren Hauberg, Carsten Stahlhut
Sparsity Increase Pre Trained Transformer Protein Language Model Protein Design Drug Design Transformer Representation

October 4, 2022

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
Gabriele Corso, Hannes Stärk, Bowen Jing, Regina Barzilay, Tommi Jaakkola
Molecular Docking Drug Design Diffusion Step Ligand Pose

August 30, 2022

HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention
Weimin Zhu, Yi Zhang, DuanCheng Zhao, Jianrong Xu, Ling Wang
Graph Neural Network Molecular Graph Molecular Property Prediction Molecular Property Drug Design Feature Wise Attention

August 14, 2022

Widely Used and Fast De Novo Drug Design by a Protein Sequence-Based Reinforcement Learning Model
Yaqin Li, Lingli Li, Yongjin Xu, Yi Yu
Reinforcement Learning Drug Discovery Molecular Design Molecular Generation Drug Design Protein Data De Novo Drug Design De Novo Protein Design

February 18, 2022

Molecule Generation for Drug Design: a Graph Learning Perspective
Nianzu Yang, Huaijin Wu, Kaipeng Zeng, Yang Li, Junchi Yan
Graph Drawing Graph Learning Known Molecule Molecule Generation Molecular Design Drug Design

January 31, 2022

GENEOnet: A new machine learning paradigm based on Group Equivariant Non-Expansive Operators. An application to protein pocket detection
Giovanni Bocchi, Patrizio Frosini, Alessandra Micheletti, Alessandro Pedretti, Carmen Gratteri, Filippo Lunghini, Andrea Rosario Beccari, Carmine Talarico
New Machine Efficient Computation Hui Walter Paradigm Drug Design Computing Paradigm Protein Pocket

January 28, 2022

Insights into performance evaluation of com-pound-protein interaction prediction methods
Adiba Yaseen, Imran Amin, Naeem Akhter, Asa Ben-Hur, Fayyaz Minhas
DCU Insight AQ Performance Evaluation Protein Protein Interaction Drug Design Compound Library Compound Protein Interaction Preclinical Drug Screening

January 25, 2022

Molecule Generation from Input-Attributions over Graph Convolutional Networks
Dylan Savoia, Alessio Ragno, Roberto Capobianco
Molecule Generation Novel Molecule Drug Design Graph Convolution Network Quantitative Structure Activity Relationship Attribution Mask

January 21, 2022

Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspective
Ryan K. Tan, Yang Liu, Lei Xie
Reinforcement Learning Product Design Drug Discovery Drug Design De Novo Drug Design Personalized Medicine

Drug Design

Papers

Automating reward function configuration for drug design

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

SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design

Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks

3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction

Do Deep Learning Models Really Outperform Traditional Approaches in Molecular Docking?

Geometric Graph Learning with Extended Atom-Types Features for Protein-Ligand Binding Affinity Prediction

Probabilistic thermal stability prediction through sparsity promoting transformer representation

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention

Widely Used and Fast De Novo Drug Design by a Protein Sequence-Based Reinforcement Learning Model

Molecule Generation for Drug Design: a Graph Learning Perspective

GENEOnet: A new machine learning paradigm based on Group Equivariant Non-Expansive Operators. An application to protein pocket detection

Insights into performance evaluation of com-pound-protein interaction prediction methods

Molecule Generation from Input-Attributions over Graph Convolutional Networks

Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspective