Annealed fractional Lévy–Itō diffusion models for protein generation
Protein generation has numerous applications in designing therapeutic antibodies and creating new drugs. Still, it is a demanding task due to the inherent complexities of protein structures and the limitations of current generative models. Proteins possess intricate geometry, and sampling their conf...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037024000928 |
| _version_ | 1797200838631882752 |
|---|---|
| author | Eric Paquet Farzan Soleymani Herna Lydia Viktor Wojtek Michalowski |
| author_facet | Eric Paquet Farzan Soleymani Herna Lydia Viktor Wojtek Michalowski |
| author_sort | Eric Paquet |
| collection | DOAJ |
| description | Protein generation has numerous applications in designing therapeutic antibodies and creating new drugs. Still, it is a demanding task due to the inherent complexities of protein structures and the limitations of current generative models. Proteins possess intricate geometry, and sampling their conformational space is challenging due to its high dimensionality. This paper introduces novel Markovian and non-Markovian generative diffusion models based on fractional stochastic differential equations and the Lévy distribution, allowing for a more effective exploration of the conformational space. The approach is applied to a dataset of 40,000 proteins and evaluated in terms of Fréchet distance, fidelity, and diversity, outperforming the state-of-the-art by 25.4%, 35.8%, and 11.8%, respectively. |
| first_indexed | 2024-04-24T07:38:01Z |
| format | Article |
| id | doaj.art-01c4b28fa2e14dcabbbda16e97deee68 |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-04-24T07:38:01Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-01c4b28fa2e14dcabbbda16e97deee682024-04-20T04:17:19ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-012316411653Annealed fractional Lévy–Itō diffusion models for protein generationEric Paquet0Farzan Soleymani1Herna Lydia Viktor2Wojtek Michalowski3National Research Council, 1200 Montreal Road, Ottawa, ON, K1A 0R6, Canada; School of Electrical Engineering and Computer Science, University of Ottawa, ON, K1N 6N5, Canada; Corresponding author at: National Research Council, 1200 Montreal Road, Ottawa, ON, K1A 0R6, Canada.Telfer School of Management, University of Ottawa, ON, K1N 6N5, CanadaSchool of Electrical Engineering and Computer Science, University of Ottawa, ON, K1N 6N5, CanadaTelfer School of Management, University of Ottawa, ON, K1N 6N5, CanadaProtein generation has numerous applications in designing therapeutic antibodies and creating new drugs. Still, it is a demanding task due to the inherent complexities of protein structures and the limitations of current generative models. Proteins possess intricate geometry, and sampling their conformational space is challenging due to its high dimensionality. This paper introduces novel Markovian and non-Markovian generative diffusion models based on fractional stochastic differential equations and the Lévy distribution, allowing for a more effective exploration of the conformational space. The approach is applied to a dataset of 40,000 proteins and evaluated in terms of Fréchet distance, fidelity, and diversity, outperforming the state-of-the-art by 25.4%, 35.8%, and 11.8%, respectively.http://www.sciencedirect.com/science/article/pii/S2001037024000928DiffusionFractionalGenerative modelLévy–ItōNoisingProtein |
| spellingShingle | Eric Paquet Farzan Soleymani Herna Lydia Viktor Wojtek Michalowski Annealed fractional Lévy–Itō diffusion models for protein generation Computational and Structural Biotechnology Journal Diffusion Fractional Generative model Lévy–Itō Noising Protein |
| title | Annealed fractional Lévy–Itō diffusion models for protein generation |
| title_full | Annealed fractional Lévy–Itō diffusion models for protein generation |
| title_fullStr | Annealed fractional Lévy–Itō diffusion models for protein generation |
| title_full_unstemmed | Annealed fractional Lévy–Itō diffusion models for protein generation |
| title_short | Annealed fractional Lévy–Itō diffusion models for protein generation |
| title_sort | annealed fractional levy ito diffusion models for protein generation |
| topic | Diffusion Fractional Generative model Lévy–Itō Noising Protein |
| url | http://www.sciencedirect.com/science/article/pii/S2001037024000928 |
| work_keys_str_mv | AT ericpaquet annealedfractionallevyitodiffusionmodelsforproteingeneration AT farzansoleymani annealedfractionallevyitodiffusionmodelsforproteingeneration AT hernalydiaviktor annealedfractionallevyitodiffusionmodelsforproteingeneration AT wojtekmichalowski annealedfractionallevyitodiffusionmodelsforproteingeneration |