ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model

2023/10/16 by Bo Ni, David L. Kaplan, Ni, Bo +3 · 2 voices · 2 citations
Biochemistry, Genetics and Molecular Biology · Chemistry · Computer Science · Materials Science · Physics and Astronomy · #Biochemical and Structural Characterization #Biological system #Biology #Biomolecules (q-bio.BM) #Chemistry #Computation and Language (cs.CL) #Computational biology #Computer science #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Physical sciences #Force Microscopy Techniques and Applications #Machine Learning (cs.LG) #Materials Science (cond-mat.mtrl-sci) #Materials science #Mechanical strength #Mesoscale and Nanoscale Physics (cond-mat.mes-hall) #Nanotechnology #Nonlinear system #Physics #Protein design #Protein structure #Sequence (biology) #Silk-based biomaterials and applications #Synthetic biology #cond-mat.mes-hall #cond-mat.mtrl-sci #cs.CL #cs.LG #q-bio.BM

paper · pdf · doi:10.48550/arxiv.2310.10605

published in PubMed (National Institutes of Health)

openalex publication_date 2023/10/16 · arxiv published 2023/10/16 · openalex created_date 2023/10/18 · arxiv updated 2023/12/16 · openalex updated_date 2026/08/06

Abstract

Through evolution, nature has presented a set of remarkable protein materials, including elastins, silks, keratins and collagens with superior mechanical performances that play crucial roles in mechanobiology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. Here we report a generative model that predicts protein designs to meet complex nonlinear mechanical property-design objectives. Our model leverages deep knowledge on protein sequences from a pre-trained protein language model and maps mechanical unfolding responses to create novel proteins. Via full-atom molecular simulations for direct validation, we demonstrate that the designed proteins are novel, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, as well as the detailed unfolding force-separation curves. Our model offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, using mechanical features as target to enable the discovery of protein materials with superior mechanical properties.

Citations

• Theoretical and computational hierarchical nanomechanics of protein materials: Deformation and fracture
• Denoising Diffusion Probabilistic Models
• End-to-end deep learning method to predict complete strain and stress tensors for complex hierarchical composite microstructures
• ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning
• Highly accurate protein structure prediction with AlphaFold
• КОМПЬЮТЕРНАЯ ТОМОГРАФИЯ – ОСНОВА ОПТИМИЗАЦИИ МИНИТОРАКОТОМНОГО ДОСТУПА
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• A very preliminary analysis of DALL-E 2
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Diffusion-LM Improves Controllable Text Generation
• Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models
• Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem
• Robust deep learning–based protein sequence design using ProteinMPNN
• High-Resolution Image Synthesis with Latent Diffusion Models
• Large language models generate functional protein sequences across diverse families
• DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• A Survey of Diffusion Models in Natural Language Processing
• De novo design of protein structure and function with RFdiffusion
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• MusicSwarm: Biologically Inspired Intelligence for Music Composition
• Customizing Spider Silk: Generative Models with Mechanical Property Conditioning for Protein Engineering

Discussions

• “ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model” Authors show with MD that "designed proteins are novel and fulfill [bsky, 4 points, 0 comments]
• A conditional latent space protein sequence diffusion model that generates proteins with desired mechanical properties. Bo Ni, David L. Kaplan, Markus J. Buehler arxiv.org/abs/2310.10605 [bsky, 2 points, 0 comments]

Related

• Elasticity, strength and resilience: A comparative study on mechanical signatures of α-Helix, β-sheet and tropocollagen domains
• Protein-Based Biological Materials: Molecular Design and Artificial Production
• Protein-based materials: Applications, modification and molecular design
• Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation
• Mesoscopic model for mechanical characterization of biological protein materials