Improved motif-scaffolding with SE(3) flow matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909261927284736 |
|---|---|
| author | Yim, Jason Campbell, Andrew Mathieu, Emile Foong, Andrew Y. K. Gastegger, Michael Jiménez-Luna, José Lewis, Sarah Satorras, Victor Garcia Veeling, Bastiaan S. Noé, Frank Barzilay, Regina Jaakkola, Tommi S. |
| author_facet | Yim, Jason Campbell, Andrew Mathieu, Emile Foong, Andrew Y. K. Gastegger, Michael Jiménez-Luna, José Lewis, Sarah Satorras, Victor Garcia Veeling, Bastiaan S. Noé, Frank Barzilay, Regina Jaakkola, Tommi S. |
| contents | Protein design often begins with the 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 range of motifs. However, 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 without additional training. On a benchmark of 24 biologically meaningful motifs, we show our method achieves 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art. Code: https://github.com/microsoft/protein-frame-flow |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04082 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved motif-scaffolding with SE(3) flow matching Yim, Jason Campbell, Andrew Mathieu, Emile Foong, Andrew Y. K. Gastegger, Michael Jiménez-Luna, José Lewis, Sarah Satorras, Victor Garcia Veeling, Bastiaan S. Noé, Frank Barzilay, Regina Jaakkola, Tommi S. Quantitative Methods Machine Learning Protein design often begins with the 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 range of motifs. However, 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 without additional training. On a benchmark of 24 biologically meaningful motifs, we show our method achieves 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art. Code: https://github.com/microsoft/protein-frame-flow |
| title | Improved motif-scaffolding with SE(3) flow matching |
| topic | Quantitative Methods Machine Learning |
| url | https://arxiv.org/abs/2401.04082 |