A survey of generative AI for de novo drug design: new frontiers in molecule...

Paper

Abstract

Artificial intelligence (AI)-driven methods can vastly improve the historically costly drug design process, with various generative models already in widespread use. Generative models for de novo drug design, in particular, focus on the creation of novel biological compounds entirely from scratch, representing a promising future direction. Rapid development in the field, combined with the inherent complexity of the drug design process, creates a difficult landscape for new researchers to enter. In this survey, we organize de novo drug design into two overarching themes: small molecule and protein generation. Within each theme, we identify a variety of subtasks and applications, highlighting important datasets, benchmarks, and model architectures and comparing the performance of top models. We take a broad approach to AI-driven drug design, allowing for both micro-level comparisons of various methods within each subtask and macro-level observations across different fields. We discuss parallel challenges and approaches between the two applications and highlight future directions for AI-driven de novo drug design as a whole. An organized repository of all covered sources is available at https://github.com/gersteinlab/GenAI4Drug.

Analysis

Paper intelligence

Summary

This survey provides a comprehensive overview of generative AI models for de novo drug design, categorizing approaches for both small molecule and protein generation.

Key findings

Generative models are crucial for creating novel biological compounds from scratch.
The field is rapidly developing, posing challenges for new researchers.
Both small molecule and protein generation share parallel challenges and approaches.
AI-driven drug design offers significant improvements over traditional methods.

Methods

Survey of generative AI models for de novo drug design.
Organization of de novo drug design into small molecule and protein generation.
Identification of subtasks, applications, datasets, benchmarks, and model architectures.
Comparison of model performance and discussion of parallel challenges.

Limitations

The complexity of drug design makes entry difficult for new researchers.
The rapid development of the field requires continuous updates.

Applications

Small molecule generation for drug design.
Protein generation for drug design.
Biocatalysis.
Therapeutics.
Materials science.

Confidence100%

Discovery

Related papers

2026Crossref2 citations

AI Guided Protein Design for Next‐Generation Autogenic Engineered Living Materials

Hoda M. Hammad; Anna M. Duraj‐Thatte

Apr 1, 2026Advanced Intelligent Systems

2026Crossref2 citations

<i>De novo</i> protein–ligand design including protein flexibility and conformational adaptation

Jakob Agamia; Martin Zacharias

Feb 3, 2026Bioinformatics

2026PubMed

ScrambleBench: a workflow for comparative assessment of structure-based de novo generative models.

Yap V; Xu P; Mak FS; Foo K; Kang C; Anbazhagan P; Xu W

Jan 1, 2026Journal of cheminformatics

2025Crossref3 citations

AI and Quantum Computing for Advanced Materials Design

Hun Hee Cho; Tae Hyung Kim; Seung Gyu Hwang; Hongchul Shin

Oct 21, 2025Journal of AI-Driven Communication Engineering

2025OpenAlex36 citations

Strengthening nucleic acid biosecurity screening against generative protein design tools

Bruce J. Wittmann; Tessa Alexanian; Craig Bartling; Jacob Beal; Adam Clore; James Diggans; Kevin Flyangolts; Bryan T. Gemler; Tom Mitchell; Steven T. Murphy; Nicole E. Wheeler; Eric Horvitz

Oct 2, 2025Science

2025Crossref14 citations

The Role of AI-Driven De Novo Protein Design in the Exploration of the Protein Functional Universe

Guohao Zhang; Chuanyang Liu; Jiajie Lu; Shaowei Zhang; Lingyun Zhu

Sep 15, 2025Biology

Source record

Publication metadata

Authors: Xiangru Tang; Howard Dai; Elizabeth Knight; Fang Wu; Yunyang Li; Tianxiao Li; Mark Gerstein
Published: May 23, 2024
Journal or venue: Briefings in Bioinformatics
DOI: 10.1093/bib/bbae338
Paper type: journal article
Source: Openalex

DOI OpenAlex