1
|
Yim J, Campbell A, Mathieu E, Foong AYK, Gastegger M, Jiménez-Luna J, Lewis S, Satorras VG, Veeling BS, Noé F, Barzilay R, Jaakkola TS. Improved motif-scaffolding with SE(3) flow matching. ArXiv 2024:arXiv:2401.04082v1. [PMID: 38259348 PMCID: PMC10802670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
Protein design often begins with knowledge of a desired function from a motif which motif-scaffolding aims to construct a functional protein around. Recently, generative models have achieved breakthrough success in designing scaffolds for a diverse range of motifs. However, the generated scaffolds tend to lack structural diversity, which can hinder success in wet-lab validation. In this work, we extend FrameFlow, an SE(3) flow matching model for protein backbone generation, to perform motif-scaffolding with two complementary approaches. The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy. The second is motif guidance, which performs scaffolding using an estimate of the conditional score from FrameFlow, and requires no additional training. Both approaches achieve an equivalent or higher success rate than previous state-of-the-art methods, with 2.5 times more structurally diverse scaffolds. Code: https://github.com/microsoft/frame-flow.
Collapse
Affiliation(s)
- Jason Yim
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology
| | | | | | | | | | | | | | | | | | | | - Regina Barzilay
- Computer Science and Articial Intelligence Laboratory, Massachusetts Institute of Technology
| | - Tommi S Jaakkola
- Computer Science and Articial Intelligence Laboratory, Massachusetts Institute of Technology
| |
Collapse
|
2
|
Arts M, Garcia Satorras V, Huang CW, Zügner D, Federici M, Clementi C, Noé F, Pinsler R, van den Berg R. Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics. J Chem Theory Comput 2023; 19:6151-6159. [PMID: 37688551 DOI: 10.1021/acs.jctc.3c00702] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/11/2023]
Abstract
Coarse-grained (CG) molecular dynamics enables the study of biological processes at temporal and spatial scales that would be intractable at an atomistic resolution. However, accurately learning a CG force field remains a challenge. In this work, we leverage connections between score-based generative models, force fields, and molecular dynamics to learn a CG force field without requiring any force inputs during training. Specifically, we train a diffusion generative model on protein structures from molecular dynamics simulations, and we show that its score function approximates a force field that can directly be used to simulate CG molecular dynamics. While having a vastly simplified training setup compared to previous work, we demonstrate that our approach leads to improved performance across several protein simulations for systems up to 56 amino acids, reproducing the CG equilibrium distribution and preserving the dynamics of all-atom simulations such as protein folding events.
Collapse
Affiliation(s)
- Marloes Arts
- Department of Computer Science, University of Copenhagen, Universitetsparken 1, Copenhagen 2100, Denmark
| | - Victor Garcia Satorras
- AI4Science, Microsoft Research, Evert van de Beekstraat 354, Amsterdam 1118 CZ, The Netherlands
| | - Chin-Wei Huang
- AI4Science, Microsoft Research, Evert van de Beekstraat 354, Amsterdam 1118 CZ, The Netherlands
| | - Daniel Zügner
- AI4Science, Microsoft Research, Karl-Liebknecht-Straße 32, Berlin 10178, Germany
| | - Marco Federici
- Informatics Institute, University of Amsterdam, Science Park 904, Amsterdam 1098 XH, The Netherlands
| | - Cecilia Clementi
- AI4Science, Microsoft Research, Karl-Liebknecht-Straße 32, Berlin 10178, Germany
- Department of Physics, Freie Universität Berlin, Arnimalle 12, Berlin 14195, Germany
| | - Frank Noé
- AI4Science, Microsoft Research, Karl-Liebknecht-Straße 32, Berlin 10178, Germany
| | - Robert Pinsler
- AI4Science, Microsoft Research, 21 Station Road, Cambridge CB1 2FB, U.K
| | - Rianne van den Berg
- AI4Science, Microsoft Research, Evert van de Beekstraat 354, Amsterdam 1118 CZ, The Netherlands
| |
Collapse
|