Machine Learning-Guided Protein Engineering

J 2023

Machine Learning-Guided Protein Engineering

KOUBA, Petr; Pavel KOHOUT; Faraneh HADDADI; Anton BUSHUIEV; Raman SAMUSEVICH et al.

Základní údaje

Originální název

Machine Learning-Guided Protein Engineering

Autoři

KOUBA, Petr; Pavel KOHOUT; Faraneh HADDADI; Anton BUSHUIEV; Raman SAMUSEVICH; Jiri SEDLAR; Jiří DAMBORSKÝ; Tomáš PLUSKAL; Josef SIVIC a Stanislav MAZURENKO

Vydání

ACS Catalysis, WASHINGTON, AMER CHEMICAL SOC, 2023, 2155-5435

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10403 Physical chemistry

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 11.700

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14310/23:00133331

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

activity; artificial intelligence; biocatalysis; deep learning; protein design

Štítky

14314010, 143180, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 5. 4. 2024 16:07, Mgr. Marie Novosadová Šípková, DiS.

Anotace

V originále

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

Návaznosti

EF17_043/0009632, projekt VaV

Název: CETOCOEN Excellence

LM2023055, projekt VaV

Název: Česká národní infrastruktura pro biologická data

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, ELIXIR-CZ: Česká národní infrastruktura pro biologická data

LM2023069, projekt VaV

Název: Výzkumná infrastruktura RECETOX

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Výzkumná infrastruktura RECETOX

LX22NPO5102, projekt VaV

Název: Národní ústav pro výzkum rakoviny (Akronym: NÚVR)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Národní ústav pro výzkum rakoviny, 5.1 EXCELES

857560, interní kód MU
(Kód CEP: EF17_043/0009632)

Název: CETOCOEN Excellence (Akronym: CETOCOEN Excellence)

Investor: Evropská unie, CETOCOEN Excellence, Spreading excellence and widening participation

Přiložené soubory

2367877.pdf

Citovat

KOUBA, Petr; Pavel KOHOUT; Faraneh HADDADI; Anton BUSHUIEV; Raman SAMUSEVICH; Jiri SEDLAR; Jiří DAMBORSKÝ; Tomáš PLUSKAL; Josef SIVIC a Stanislav MAZURENKO. Machine Learning-Guided Protein Engineering. ACS Catalysis. WASHINGTON: AMER CHEMICAL SOC, 2023, roč. 13, č. 21, s. 13863-13895. ISSN 2155-5435. Dostupné z: https://doi.org/10.1021/acscatal.3c02743.

@article{2367877,
   author = {Kouba, Petr and Kohout, Pavel and Haddadi, Faraneh and Bushuiev, Anton and Samusevich, Raman and Sedlar, Jiri and Damborský, Jiří and Pluskal, Tomáš and Sivic, Josef and Mazurenko, Stanislav},
   article_location = {WASHINGTON},
   article_number = {21},
   doi = {https://doi.org/10.1021/acscatal.3c02743},
   keywords = {activity; artificial intelligence; biocatalysis; deep learning; protein design},
   language = {eng},
   issn = {2155-5435},
   journal = {ACS Catalysis},
   title = {Machine Learning-Guided Protein Engineering},
   url = {https://pubs.acs.org/doi/10.1021/acscatal.3c02743},
   volume = {13},
   year = {2023}
}

TY  - JOUR
ID  - 2367877
AU  - Kouba, Petr - Kohout, Pavel - Haddadi, Faraneh - Bushuiev, Anton - Samusevich, Raman - Sedlar, Jiri - Damborský, Jiří - Pluskal, Tomáš - Sivic, Josef - Mazurenko, Stanislav
PY  - 2023
TI  - Machine Learning-Guided Protein Engineering
JF  - ACS Catalysis
VL  - 13
IS  - 21
SP  - 13863-13895
EP  - 13863-13895
PB  - AMER CHEMICAL SOC
SN  - 21555435
KW  - activity
KW  - artificial intelligence
KW  - biocatalysis
KW  - deep learning
KW  - protein design
UR  - https://pubs.acs.org/doi/10.1021/acscatal.3c02743
N2  - Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.
ER  -

KOUBA, Petr; Pavel KOHOUT; Faraneh HADDADI; Anton BUSHUIEV; Raman SAMUSEVICH; Jiri SEDLAR; Jiří DAMBORSKÝ; Tomáš PLUSKAL; Josef SIVIC a Stanislav MAZURENKO. Machine Learning-Guided Protein Engineering. \textit{ACS Catalysis}. WASHINGTON: AMER CHEMICAL SOC, 2023, roč.~13, č.~21, s.~13863-13895. ISSN~2155-5435. Dostupné z: https://doi.org/10.1021/acscatal.3c02743.

Přehled o publikaci