De Novo Drug Design

De novo drug design aims to create entirely new drug molecules from scratch, accelerating and improving the drug discovery process. Current research heavily utilizes generative AI models, including diffusion models, recurrent neural networks, transformers, and variational autoencoders, often coupled with reinforcement learning algorithms to optimize molecule properties and explore chemical space more efficiently. These methods are being applied to both small molecule and protein generation, focusing on improving molecular validity, target specificity, and desired pharmacological properties. The ultimate goal is to significantly reduce the time and cost associated with drug development, leading to faster and more effective treatments for various diseases.

Papers

October 14, 2024

Diversity-Aware Reinforcement Learning for de novo Drug Design
Hampus Gummesson Svensson, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani
Reward Function Drug Design De Novo Drug Design Diversity Reinforcement Learning Molecule Optimization

June 7, 2024

Diffusion Models in $\textit{De Novo}$ Drug Design
Amira Alakhdar, Barnabas Poczos, Newell Washburn
Diffusion Model Molecule Generation Molecular Generation 3D Molecule 3D Molecule Generation Molecular Geometry De Novo Drug Design

May 10, 2024

Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning
Salma J. Ahmed, Mustafa A. Elattar
Molecule Generation Language Model Fine Tuning Drug Like Drug Target Interaction Protein Target De Novo Drug Design New Drug

February 13, 2024

A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation
Xiangru Tang, Howard Dai, Elizabeth Knight, Fang Wu, Yunyang Li, Tianxiao Li, Mark Gerstein
Generative AI Drug Discovery Known Molecule New Frontier Drug Discovery Process De Novo Drug Design

December 21, 2023

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang
Reinforcement Learning Molecular Generation Drug Design De Novo Drug Design GPT 4v

December 3, 2023

NovoMol: Recurrent Neural Network for Orally Bioavailable Drug Design and Validation on PDGFR{\alpha} Receptor
Ishir Rao
Recurrent Neural Network New Method Drug Like De Novo Drug Design Drug Candidate G Protein Coupled Receptor

October 18, 2023

Conformal Drug Property Prediction with Density Estimation under Covariate Shift
Siddhartha Laghuvarapu, Zhen Lin, Jimeng Sun
Density Estimation Covariate Shift De Novo Drug Design Drug Discovery Task

October 3, 2023

De Novo Drug Design with Joint Transformers
Adam Izdebski, Ewelina Weglarz-Tomczak, Ewa Szczurek, Jakub M. Tomczak
Generative Model Novel Molecule De Novo Drug Design Joint Generative Joint Transformer

September 24, 2023

Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design
Mohamed-Amine Chadi, Hajar Mousannif, Ahmed Aamouche
Practical Method Environment Exploration Molecule Generation Chemical Space Curiosity Inducing Situation De Novo Drug Design

June 2, 2023

Balancing Exploration and Exploitation: Disentangled $\beta$-CVAE in De Novo Drug Design
Guang Jun Nicholas Ang, De Tao Irwin Chin, Bingquan Shen
Molecular Graph Real World eXploitation Exploration Performance De Novo Drug Design

March 30, 2023

Utilizing Reinforcement Learning for de novo Drug Design
Hampus Gummesson Svensson, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani
Reinforcement Learning Small Molecule Novel Molecule De Novo Drug Design Scoring Molecule

February 15, 2023

Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks
Atabey Ünlü, Elif Çevrim, Ahmet Sarıgün, Hayriye Çelikbilek, Heval Ataş Güvenilir, Altay Koyaş, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Rifaioğlu, Tunca Doğan
Graph Transformer Protein Target De Novo Drug Design Candidate Molecule

August 30, 2022

Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design
Kehan Wu, Yingce Xia, Yang Fan, Pan Deng, Haiguang Liu, Lijun Wu, Shufang Xie, Tong Wang, Tao Qin, Tie-Yan Liu
Molecular Design Structure Based Drug Design De Novo Drug Design Computer Aided Drug Discovery Drug Candidate Transformer Based Generative Protein Pocket

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

July 23, 2022

A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Song Li, Song Ke, Chenxing Yang, Jun Chen, Yi Xiong, Lirong Zheng, Hao Liu, Liang Hong
Scientific Discovery Small Molecule De Novo Drug Design G Protein Coupled Receptor Therapeutic Target

July 4, 2022

Autonomous Drug Design with Multi-Armed Bandits
Hampus Gummesson Svensson, Esben Jannik Bjerrum, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani
Multi Armed Bandit De Novo Drug Design Greedy Learning

July 2, 2022

PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generation
Huimin Zhu, Renyi Zhou, Jing Tang, Min Li
De Novo Drug Design Pharmacophore Modeling

June 6, 2022

Exploring Chemical Space with Score-based Out-of-distribution Generation
Seul Lee, Jaehyeong Jo, Sung Ju Hwang
Chemical Space Novel Molecule Molecular Generative De Novo Drug Design

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

De Novo Drug Design

Papers

Diversity-Aware Reinforcement Learning for de novo Drug Design

Diffusion Models in $\textit{De Novo}$ Drug Design

Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning

A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

NovoMol: Recurrent Neural Network for Orally Bioavailable Drug Design and Validation on PDGFR{\alpha} Receptor

Conformal Drug Property Prediction with Density Estimation under Covariate Shift

De Novo Drug Design with Joint Transformers

Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design

Balancing Exploration and Exploitation: Disentangled $\beta$-CVAE in De Novo Drug Design

Utilizing Reinforcement Learning for de novo Drug Design

Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks

Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design

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

A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases

Autonomous Drug Design with Multi-Armed Bandits

PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generation

Exploring Chemical Space with Score-based Out-of-distribution Generation

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