Generative AI techniques for conformational diversity and evolutionary adaptation of proteins
Brownless, Alfie Louise R. ; Yehorova, Dariia ; Welsh, Colin L. and Kamerlin, Shina Caroline Lynn LU
(2025)
In Current Opinion in Structural Biology
94.
- Abstract
The advent of AlphaFold and consumer large language models have elicited unprecedented development of artificial intelligence (AI). AI has had substantial impact in every area of research, including in molecular biology. This is principally in thanks to contributions to the Protein Data Bank and various genome sequence databases, providing an astronomical amount of data for model training. These databases contain evolutionary information explicitly and implicitly, allowing accurate predictions and deep insights into biological questions. Here, we describe recent state-of-the-art applications of AI that exploit evolutionary relationships. This includes structure prediction and design, conformational ensemble generation, and functional... (More)
The advent of AlphaFold and consumer large language models have elicited unprecedented development of artificial intelligence (AI). AI has had substantial impact in every area of research, including in molecular biology. This is principally in thanks to contributions to the Protein Data Bank and various genome sequence databases, providing an astronomical amount of data for model training. These databases contain evolutionary information explicitly and implicitly, allowing accurate predictions and deep insights into biological questions. Here, we describe recent state-of-the-art applications of AI that exploit evolutionary relationships. This includes structure prediction and design, conformational ensemble generation, and functional site identification. We present a brief snapshot of AI usage in studying protein structure and dynamics, a field that is advancing at breakneck speed.
(Less)
- author
- Brownless, Alfie Louise R.
; Yehorova, Dariia
; Welsh, Colin L.
and Kamerlin, Shina Caroline Lynn
LU
- organization
- publishing date
- 2025-10
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Current Opinion in Structural Biology
- volume
- 94
- article number
- 103135
- publisher
- Elsevier
- external identifiers
-
- pmid:40815917
- scopus:105013150192
- ISSN
- 0959-440X
- DOI
- 10.1016/j.sbi.2025.103135
- language
- English
- LU publication?
- yes
- id
- 621e34bc-24bb-4744-9c8b-32cabf3150cb
- date added to LUP
- 2026-01-13 13:47:10
- date last changed
- 2026-01-14 03:46:58
@article{621e34bc-24bb-4744-9c8b-32cabf3150cb,
abstract = {{<p>The advent of AlphaFold and consumer large language models have elicited unprecedented development of artificial intelligence (AI). AI has had substantial impact in every area of research, including in molecular biology. This is principally in thanks to contributions to the Protein Data Bank and various genome sequence databases, providing an astronomical amount of data for model training. These databases contain evolutionary information explicitly and implicitly, allowing accurate predictions and deep insights into biological questions. Here, we describe recent state-of-the-art applications of AI that exploit evolutionary relationships. This includes structure prediction and design, conformational ensemble generation, and functional site identification. We present a brief snapshot of AI usage in studying protein structure and dynamics, a field that is advancing at breakneck speed.</p>}},
author = {{Brownless, Alfie Louise R. and Yehorova, Dariia and Welsh, Colin L. and Kamerlin, Shina Caroline Lynn}},
issn = {{0959-440X}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Current Opinion in Structural Biology}},
title = {{Generative AI techniques for conformational diversity and evolutionary adaptation of proteins}},
url = {{http://dx.doi.org/10.1016/j.sbi.2025.103135}},
doi = {{10.1016/j.sbi.2025.103135}},
volume = {{94}},
year = {{2025}},
}