Protein Family Sequence Generation through ProGen2 Fine-Tuning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10490448" target="_blank" >RIV/00216208:11320/24:10490448 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/BIBM62325.2024.10822651" target="_blank" >https://doi.org/10.1109/BIBM62325.2024.10822651</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/BIBM62325.2024.10822651" target="_blank" >10.1109/BIBM62325.2024.10822651</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Protein Family Sequence Generation through ProGen2 Fine-Tuning

Popis výsledku v původním jazyce

Proteins are biomolecules involved in virtually all biological processes, making the design of novel proteins with specific functions crucial for advancing drug development and biological research. Large protein sequence databases allow for training language models adapted from natural language processing, treating amino acid sequences as a biological &quot;language&quot;. However, these generative protein language models lack a straightforward, user-friendly method for prompting them to generate specific sequences with desired properties. In this work, we demonstrate how the pre-trained protein language model ProGen2 can be effectively fine-tuned for controllable generation of protein sequences from several distinct protein families. We validate the generated sequences using various in-silico metrics and show that the model is able to generate viable protein sequences that exhibit low similarity to existing proteins.

Název v anglickém jazyce

Protein Family Sequence Generation through ProGen2 Fine-Tuning

Popis výsledku anglicky

Proteins are biomolecules involved in virtually all biological processes, making the design of novel proteins with specific functions crucial for advancing drug development and biological research. Large protein sequence databases allow for training language models adapted from natural language processing, treating amino acid sequences as a biological &quot;language&quot;. However, these generative protein language models lack a straightforward, user-friendly method for prompting them to generate specific sequences with desired properties. In this work, we demonstrate how the pre-trained protein language model ProGen2 can be effectively fine-tuned for controllable generation of protein sequences from several distinct protein families. We validate the generated sequences using various in-silico metrics and show that the model is able to generate viable protein sequences that exhibit low similarity to existing proteins.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

ISBN

979-8-3503-8622-6

ISSN

2156-1133

e-ISSN

—

Počet stran výsledku

3

Strana od-do

7058-7060

Název nakladatele

IEEE

Místo vydání

USA

Místo konání akce

Lisbon, Portugal

Datum konání akce

3. 12. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—