Cargando…

Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models

The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speec...

Descripción completa

Detalles Bibliográficos
Autores principales: Yue, Tianwei, Wang, Yuanxin, Zhang, Longxiang, Gu, Chunming, Xue, Haoru, Wang, Wenping, Lyu, Qi, Dun, Yujie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10649223/
https://www.ncbi.nlm.nih.gov/pubmed/37958843
http://dx.doi.org/10.3390/ijms242115858
_version_ 1785135516748873728
author Yue, Tianwei
Wang, Yuanxin
Zhang, Longxiang
Gu, Chunming
Xue, Haoru
Wang, Wenping
Lyu, Qi
Dun, Yujie
author_facet Yue, Tianwei
Wang, Yuanxin
Zhang, Longxiang
Gu, Chunming
Xue, Haoru
Wang, Wenping
Lyu, Qi
Dun, Yujie
author_sort Yue, Tianwei
collection PubMed
description The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.
format Online
Article
Text
id pubmed-10649223
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106492232023-11-01 Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models Yue, Tianwei Wang, Yuanxin Zhang, Longxiang Gu, Chunming Xue, Haoru Wang, Wenping Lyu, Qi Dun, Yujie Int J Mol Sci Review The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics. MDPI 2023-11-01 /pmc/articles/PMC10649223/ /pubmed/37958843 http://dx.doi.org/10.3390/ijms242115858 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Yue, Tianwei
Wang, Yuanxin
Zhang, Longxiang
Gu, Chunming
Xue, Haoru
Wang, Wenping
Lyu, Qi
Dun, Yujie
Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title_full Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title_fullStr Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title_full_unstemmed Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title_short Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models
title_sort deep learning for genomics: from early neural nets to modern large language models
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10649223/
https://www.ncbi.nlm.nih.gov/pubmed/37958843
http://dx.doi.org/10.3390/ijms242115858
work_keys_str_mv AT yuetianwei deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT wangyuanxin deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT zhanglongxiang deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT guchunming deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT xuehaoru deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT wangwenping deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT lyuqi deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels
AT dunyujie deeplearningforgenomicsfromearlyneuralnetstomodernlargelanguagemodels