De Novo

De novo design focuses on computationally generating novel molecules or sequences with desired properties, primarily for drug discovery and materials science. Current research emphasizes the use of advanced generative models, including transformers, graph neural networks, and normalizing flows, often coupled with reinforcement learning to optimize for specific objectives like binding affinity or degradation potential. This approach accelerates the traditionally slow and expensive process of molecular discovery, offering significant potential for improving drug development and materials design by enabling the exploration of vast chemical spaces. The field is also actively addressing challenges such as sample efficiency and the handling of complex molecular structures, including proteins and PROTACs.

Papers

October 22, 2024

Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability
Nina Gubina, Andrei Dmitrenko, Gleb Solovev, Lyubov Yamshchikova, Oleg Petrov, Ivan Lebedev, Nikita Serov, Grigorii Kirgizov, Nikolay Nikitin, Vladimir Vinogradov
Crystalline Material De Novo Graphic Tablet De Novo Crystal

October 11, 2024

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
Zheng Yi Ho, Siyuan Liang, Sen Zhang, Yibing Zhan, Dacheng Tao
Language Model Attention Head Textual Adversarial Attack De Novo Path Norm

August 19, 2024

Rethinking Molecular Design: Integrating Latent Variable and Auto-Regressive Models for Goal Directed Generation
Heath Arthur-Loui, Amina Mollaysa, Michael Krauthammer
Variational Autoencoders Molecular Representation Generative Approach Auto Regressive State of the Art Generative De Novo

June 24, 2024

A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design
Yossra Gharbi, Rocío Mercado
Machine Learning Product Design Novel Approach Comprehensive Review Structure Based Drug Design De Novo Protein Prediction Task Protein Degradation

March 9, 2024

AdaNovo: Adaptive \emph{De Novo} Peptide Sequencing with Conditional Mutual Information
Jun Xia, Shaorong Chen, Jingbo Zhou, Tianze Ling, Wenjie Du, Sizhe Liu, Stan Z. Li
Amino Acid Peptide Source Conditional Mutual Information De Novo Mass Spectrometry Peptide Level Identification Precision

November 24, 2023

LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Design
Niklas Dobberstein, Astrid Maass, Jan Hamaekers
Generative Model Molecule Generation Chemical Space LLaVA HD De Novo Generative Transformer Model

November 22, 2023

Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
Ian Dunn, David Ryan Koes
Scientific Inference Latent Representation Coarse Grained Structure Based Drug Design Protein Structure De Novo Molecular Diffusion Model

October 9, 2023

Molecular De Novo Design through Transformer-based Reinforcement Learning
Pengcheng Xu, Tao Feng, Tianfan Fu, Siddhartha Laghuvarapu, Jimeng Sun
Reinforcement Learning Recurrent Neural Network RNN Model De Novo Transformer Based Generative

May 15, 2023

MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation
Yiheng Zhu, Zhenqiu Ouyang, Ben Liao, Jialu Wu, Yixuan Wu, Chang-Yu Hsieh, Tingjun Hou, Jian Wu
Normalizing Flow Molecular Graph De Novo Hierarchical Generative Hierarchical Generation

May 10, 2023

Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design
Jeff Guo, Philippe Schwaller
Molecular Design Experience Replay Memory Augmentation Molecular Generative Single Sample Molecular Optimization De Novo

April 4, 2023

De-novo Identification of Small Molecules from Their GC-EI-MS Spectra
Adam Hájek, Michal Starý, Filip Jozefov, Helge Hecht, Elliott Price, Aleš Křenek
Small Molecule Chemical Space De Novo Mass Spectrum GC EI M Spectrum

November 30, 2022

xTrimoABFold: De novo Antibody Structure Prediction without MSA
Yining Wang, Xumeng Gong, Shaochuan Li, Bing Yang, YiWu Sun, Chuan Shi, Yangang Wang, Cheng Yang, Hui Li, Le Song
De Novo Antibody Structure Prediction

November 4, 2022

De novo PROTAC design using graph-based deep generative models
Divya Nori, Connor W. Coley, Rocío Mercado
Generative Model Product Design De Novo Protein Degradation

October 22, 2022

Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES
Esben Jannik Bjerrum, Christian Margreitter, Thomas Blaschke, Raquel López-Ríos de Castro
Drug Discovery Novel Molecule Molecular Optimization De Novo Scoring Molecule Molecular Input Line Entry System

October 17, 2022

A Transformer-based Generative Model for De Novo Molecular Design
Wenlu Wang, Ye Wang, Honggang Zhao, Simone Sciabola
Molecular Design Drug Like Drug Target Transformer Based Generative De Novo

October 13, 2022

Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
Jenna C. Fromer, Connor W. Coley
Multi Objective Optimization Multi Objective Small Molecule De Novo Molecular Discovery

May 21, 2022

De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learning
Andrew D. McNaughton, Mridula S. Bontha, Carter R. Knutson, Jenna A. Pope, Neeraj Kumar
Reinforcement Learning Drug Discovery Molecular Design Protein Target De Novo Molecular Scaffold

March 16, 2022

DePS: An improved deep learning model for de novo peptide sequencing
Cheng Ge, Yi Lu, Jia Qu, Liangxu Xie, Feng Wang, Hong Zhang, Ren Kong, Shan Chang
Deep Learning Model Protein Sequence Amino Acid Mass Spectrometry De Novo

December 2, 2021

Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model
Samuel C. Hoffman, Vijil Chenthamarakshan, Dmitry Yu. Zubarev, Daniel P. Sanders, Payel Das
Deep Generative Model Efficient Generation De Novo Extreme Ultraviolet Lithography

De Novo

Papers

Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

Rethinking Molecular Design: Integrating Latent Variable and Auto-Regressive Models for Goal Directed Generation

A Comprehensive Review of Emerging Approaches in Machine Learning for De Novo PROTAC Design

AdaNovo: Adaptive \emph{De Novo} Peptide Sequencing with Conditional Mutual Information

LLamol: A Dynamic Multi-Conditional Generative Transformer for De Novo Molecular Design

Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure

Molecular De Novo Design through Transformer-based Reinforcement Learning

MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generation

Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design

De-novo Identification of Small Molecules from Their GC-EI-MS Spectra

xTrimoABFold: De novo Antibody Structure Prediction without MSA

De novo PROTAC design using graph-based deep generative models

Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES

A Transformer-based Generative Model for De Novo Molecular Design

Computer-Aided Multi-Objective Optimization in Small Molecule Discovery

De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learning

DePS: An improved deep learning model for de novo peptide sequencing

Sample-Efficient Generation of Novel Photo-acid Generator Molecules using a Deep Generative Model