Antibody design using LSTM based deep generative model from phage display library for affinity maturation

Abstract Molecular evolution is an important step in the development of therapeutic antibodies. However, the current method of affinity maturation is overly costly and labor-intensive because of the repetitive mutation experiments needed to adequately explore sequence space. Here, we employed a long...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Koichiro Saka, Taro Kakuzaki, Shoichi Metsugi, Daiki Kashiwagi, Kenji Yoshida, Manabu Wada, Hiroyuki Tsunoda, Reiji Teramoto
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/b637d0a8f2934168ad948f2310d11803
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b637d0a8f2934168ad948f2310d11803
record_format dspace
spelling oai:doaj.org-article:b637d0a8f2934168ad948f2310d118032021-12-02T13:16:19ZAntibody design using LSTM based deep generative model from phage display library for affinity maturation10.1038/s41598-021-85274-72045-2322https://doaj.org/article/b637d0a8f2934168ad948f2310d118032021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85274-7https://doaj.org/toc/2045-2322Abstract Molecular evolution is an important step in the development of therapeutic antibodies. However, the current method of affinity maturation is overly costly and labor-intensive because of the repetitive mutation experiments needed to adequately explore sequence space. Here, we employed a long short term memory network (LSTM)—a widely used deep generative model—based sequence generation and prioritization procedure to efficiently discover antibody sequences with higher affinity. We applied our method to the affinity maturation of antibodies against kynurenine, which is a metabolite related to the niacin synthesis pathway. Kynurenine binding sequences were enriched through phage display panning using a kynurenine-binding oriented human synthetic Fab library. We defined binding antibodies using a sequence repertoire from the NGS data to train the LSTM model. We confirmed that likelihood of generated sequences from a trained LSTM correlated well with binding affinity. The affinity of generated sequences are over 1800-fold higher than that of the parental clone. Moreover, compared to frequency based screening using the same dataset, our machine learning approach generated sequences with greater affinity.Koichiro SakaTaro KakuzakiShoichi MetsugiDaiki KashiwagiKenji YoshidaManabu WadaHiroyuki TsunodaReiji TeramotoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Koichiro Saka
Taro Kakuzaki
Shoichi Metsugi
Daiki Kashiwagi
Kenji Yoshida
Manabu Wada
Hiroyuki Tsunoda
Reiji Teramoto
Antibody design using LSTM based deep generative model from phage display library for affinity maturation
description Abstract Molecular evolution is an important step in the development of therapeutic antibodies. However, the current method of affinity maturation is overly costly and labor-intensive because of the repetitive mutation experiments needed to adequately explore sequence space. Here, we employed a long short term memory network (LSTM)—a widely used deep generative model—based sequence generation and prioritization procedure to efficiently discover antibody sequences with higher affinity. We applied our method to the affinity maturation of antibodies against kynurenine, which is a metabolite related to the niacin synthesis pathway. Kynurenine binding sequences were enriched through phage display panning using a kynurenine-binding oriented human synthetic Fab library. We defined binding antibodies using a sequence repertoire from the NGS data to train the LSTM model. We confirmed that likelihood of generated sequences from a trained LSTM correlated well with binding affinity. The affinity of generated sequences are over 1800-fold higher than that of the parental clone. Moreover, compared to frequency based screening using the same dataset, our machine learning approach generated sequences with greater affinity.
format article
author Koichiro Saka
Taro Kakuzaki
Shoichi Metsugi
Daiki Kashiwagi
Kenji Yoshida
Manabu Wada
Hiroyuki Tsunoda
Reiji Teramoto
author_facet Koichiro Saka
Taro Kakuzaki
Shoichi Metsugi
Daiki Kashiwagi
Kenji Yoshida
Manabu Wada
Hiroyuki Tsunoda
Reiji Teramoto
author_sort Koichiro Saka
title Antibody design using LSTM based deep generative model from phage display library for affinity maturation
title_short Antibody design using LSTM based deep generative model from phage display library for affinity maturation
title_full Antibody design using LSTM based deep generative model from phage display library for affinity maturation
title_fullStr Antibody design using LSTM based deep generative model from phage display library for affinity maturation
title_full_unstemmed Antibody design using LSTM based deep generative model from phage display library for affinity maturation
title_sort antibody design using lstm based deep generative model from phage display library for affinity maturation
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/b637d0a8f2934168ad948f2310d11803
work_keys_str_mv AT koichirosaka antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT tarokakuzaki antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT shoichimetsugi antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT daikikashiwagi antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT kenjiyoshida antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT manabuwada antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT hiroyukitsunoda antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
AT reijiteramoto antibodydesignusinglstmbaseddeepgenerativemodelfromphagedisplaylibraryforaffinitymaturation
_version_ 1718393352300265472