LARGE LANGUAGE MODELS IN BIOTECHNOLOGY: PROTEIN DESIGN, ENZYMES AND GENOMIC EDITING
Authors:
1.
Peter the Great Saint-Petersburg Polytechnic University
2.
Kazan National Research Technological University
Type:
Article
Pages:
from 118
to 125
Status:
Published
Received:
03.02.2026
Accepted:
02.03.2026
Published:
05.05.2026
Language:
Russian
Keywords:
ARTIFICIAL INTELLIGENCE, BIOTECHNOLOGY, LARGE LANGUAGE MODELS, DEEP LEARNING, MACHINE LEARNING, AMINO ACID SEQUENCE, PROTEIN ENGINEERING, ENZYME ENGINEERING, GENOMIC EDITING, TARGET-OFF EFFECT, CRISPR CAS-9, PROGEN, INTERPRETABILITY OF MODELS
Abstract:
The description of biological sequences - proteins, enzymes and nucleic acids - in the form of formalized "languages" has opened up new possibilities for their analysis, modeling and generation. Based on the analysis of publications by Russian and foreign authors, the following promising areas of use of large language models in biotechnology were identified: protein design, enzyme engineering, genomic editing. The article is devoted to the analysis of modern approaches to the use of large language models and deep learning (Deep Learning, DL) in protein and enzyme engineering, as well as in genomic editing tasks, including the assessment of unintentional modifications Cas-9 CRISPR systems. Particular attention is paid to the biotechnological potential of these methods, their limitations, problems of interpretability and biosafety. Based on the analysis of current research, the prospects for integrating language models into molecular and industrial biotechnological processes are discussed.
The description of biological sequences - proteins, enzymes and nucleic acids - in the form of formalized "languages" has opened up new possibilities for their analysis, modeling and generation. Based on the analysis of publications by Russian and foreign authors, the following promising areas of use of large language models in biotechnology were identified: protein design, enzyme engineering, genomic editing. The article is devoted to the analysis of modern approaches to the use of large language models and deep learning (Deep Learning, DL) in protein and enzyme engineering, as well as in genomic editing tasks, including the assessment of unintentional modifications Cas-9 CRISPR systems. Particular attention is paid to the biotechnological potential of these methods, their limitations, problems of interpretability and biosafety. Based on the analysis of current research, the prospects for integrating language models into molecular and industrial biotechnological processes are discussed.
Keywords:
ARTIFICIAL INTELLIGENCE, BIOTECHNOLOGY, LARGE LANGUAGE MODELS, DEEP LEARNING, MACHINE LEARNING, AMINO ACID SEQUENCE, PROTEIN ENGINEERING, ENZYME ENGINEERING, GENOMIC EDITING, TARGET-OFF EFFECT, CRISPR CAS-9, PROGEN, INTERPRETABILITY OF MODELS
ARTIFICIAL INTELLIGENCE, BIOTECHNOLOGY, LARGE LANGUAGE MODELS, DEEP LEARNING, MACHINE LEARNING, AMINO ACID SEQUENCE, PROTEIN ENGINEERING, ENZYME ENGINEERING, GENOMIC EDITING, TARGET-OFF EFFECT, CRISPR CAS-9, PROGEN, INTERPRETABILITY OF MODELS
