NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
- URL: http://arxiv.org/abs/2502.12638v1
- Date: Tue, 18 Feb 2025 08:40:13 GMT
- Title: NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
- Authors: Zhiyuan Liu, Yanchen Luo, Han Huang, Enzhi Zhang, Sihang Li, Junfeng Fang, Yaorui Shi, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua,
- Abstract summary: We propose a foundation model -- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation.
NExT-Mol uses an extensively pretrained molecule LM for 1D molecule generation, and subsequently predicts the generated molecule's 3D conformers.
We enhance NExT-Mol's performance by scaling up the LM's model size, refining the diffusion neural architecture, and applying 1D to 3D transfer learning.
- Score: 72.22099363325145
- License:
- Abstract: 3D molecule generation is crucial for drug discovery and material design. While prior efforts focus on 3D diffusion models for their benefits in modeling continuous 3D conformers, they overlook the advantages of 1D SELFIES-based Language Models (LMs), which can generate 100% valid molecules and leverage the billion-scale 1D molecule datasets. To combine these advantages for 3D molecule generation, we propose a foundation model -- NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation. NExT-Mol uses an extensively pretrained molecule LM for 1D molecule generation, and subsequently predicts the generated molecule's 3D conformers with a 3D diffusion model. We enhance NExT-Mol's performance by scaling up the LM's model size, refining the diffusion neural architecture, and applying 1D to 3D transfer learning. Notably, our 1D molecule LM significantly outperforms baselines in distributional similarity while ensuring validity, and our 3D diffusion model achieves leading performances in conformer prediction. Given these improvements in 1D and 3D modeling, NExT-Mol achieves a 26% relative improvement in 3D FCD for de novo 3D generation on GEOM-DRUGS, and a 13% average relative gain for conditional 3D generation on QM9-2014. Our codes and pretrained checkpoints are available at https://github.com/acharkq/NExT-Mol.
Related papers
- Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation [66.75243908044538]
We introduce Zero-1-to-G, a novel approach to direct 3D generation on Gaussian splats using pretrained 2D diffusion models.
To incorporate 3D awareness, we introduce cross-view and cross-attribute attention layers, which capture complex correlations and enforce 3D consistency across generated splats.
This makes Zero-1-to-G the first direct image-to-3D generative model to effectively utilize pretrained 2D diffusion priors, enabling efficient training and improved generalization to unseen objects.
arXiv Detail & Related papers (2025-01-09T18:37:35Z) - VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models [20.084928490309313]
This paper presents a novel method for building scalable 3D generative models utilizing pre-trained video diffusion models.
By unlocking its multi-view generative capabilities through fine-tuning, we generate a large-scale synthetic multi-view dataset to train a feed-forward 3D generative model.
The proposed model, VFusion3D, trained on nearly 3M synthetic multi-view data, can generate a 3D asset from a single image in seconds.
arXiv Detail & Related papers (2024-03-18T17:59:12Z) - LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation [73.36690511083894]
This paper introduces a novel framework called LN3Diff to address a unified 3D diffusion pipeline.
Our approach harnesses a 3D-aware architecture and variational autoencoder to encode the input image into a structured, compact, and 3D latent space.
It achieves state-of-the-art performance on ShapeNet for 3D generation and demonstrates superior performance in monocular 3D reconstruction and conditional 3D generation.
arXiv Detail & Related papers (2024-03-18T17:54:34Z) - 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors [85.11117452560882]
We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors.
The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality texture generation
arXiv Detail & Related papers (2024-03-04T17:26:28Z) - GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models [102.22388340738536]
2D and 3D diffusion models can generate decent 3D objects based on prompts.
3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain.
This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation.
arXiv Detail & Related papers (2023-10-12T17:22:24Z) - Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape [46.31314488932164]
We present Sin3DM, a diffusion model that learns the internal patch distribution from a single 3D textured shape.
We show that our method outperforms prior methods in generation quality of 3D shapes.
arXiv Detail & Related papers (2023-05-24T17:57:15Z) - Geometric Latent Diffusion Models for 3D Molecule Generation [172.15028281732737]
Generative models, especially diffusion models (DMs), have achieved promising results for generating feature-rich geometries.
We propose a novel and principled method for 3D molecule generation named Geometric Latent Diffusion Models (GeoLDM)
arXiv Detail & Related papers (2023-05-02T01:07:22Z) - Geometry-Complete Diffusion for 3D Molecule Generation and Optimization [3.8366697175402225]
We introduce the Geometry-Complete Diffusion Model (GCDM) for 3D molecule generation.
GCDM outperforms existing 3D molecular diffusion models by significant margins across conditional and unconditional settings.
We also show that GCDM's geometric features can be repurposed to consistently optimize the geometry and chemical composition of existing 3D molecules.
arXiv Detail & Related papers (2023-02-08T20:01:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.