Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach

Abstract The light-dependent ion-transport function of microbial rhodopsin has been widely used in optogenetics for optical control of neural activity. In order to increase the variety of rhodopsin proteins having a wide range of absorption wavelengths, the light absorption properties of various wil...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Masayuki Karasuyama, Keiichi Inoue, Ryoko Nakamura, Hideki Kandori, Ichiro Takeuchi
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2018
Materias:
R
Q
Acceso en línea:https://doaj.org/article/6d5f6523e95c47b9a3267d31656cf7dd
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:6d5f6523e95c47b9a3267d31656cf7dd
record_format dspace
spelling oai:doaj.org-article:6d5f6523e95c47b9a3267d31656cf7dd2021-12-02T11:40:46ZUnderstanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach10.1038/s41598-018-33984-w2045-2322https://doaj.org/article/6d5f6523e95c47b9a3267d31656cf7dd2018-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-33984-whttps://doaj.org/toc/2045-2322Abstract The light-dependent ion-transport function of microbial rhodopsin has been widely used in optogenetics for optical control of neural activity. In order to increase the variety of rhodopsin proteins having a wide range of absorption wavelengths, the light absorption properties of various wild-type rhodopsins and their artificially mutated variants were investigated in the literature. Here, we demonstrate that a machine-learning-based (ML-based) data-driven approach is useful for understanding and predicting the light-absorption properties of microbial rhodopsin proteins. We constructed a database of 796 proteins consisting of microbial rhodopsin wildtypes and their variants. We then proposed an ML method that produces a statistical model describing the relationship between amino-acid sequences and absorption wavelengths and demonstrated that the fitted statistical model is useful for understanding colour tuning rules and predicting absorption wavelengths. By applying the ML method to the database, two residues that were not considered in previous studies are newly identified to be important to colour shift.Masayuki KarasuyamaKeiichi InoueRyoko NakamuraHideki KandoriIchiro TakeuchiNature PortfolioarticleMicrobial RhodopsinsColor TuningAbsorption WavelengthData-driven Machine Learning ApproachProtein RhodopsinMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-11 (2018)
institution DOAJ
collection DOAJ
language EN
topic Microbial Rhodopsins
Color Tuning
Absorption Wavelength
Data-driven Machine Learning Approach
Protein Rhodopsin
Medicine
R
Science
Q
spellingShingle Microbial Rhodopsins
Color Tuning
Absorption Wavelength
Data-driven Machine Learning Approach
Protein Rhodopsin
Medicine
R
Science
Q
Masayuki Karasuyama
Keiichi Inoue
Ryoko Nakamura
Hideki Kandori
Ichiro Takeuchi
Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
description Abstract The light-dependent ion-transport function of microbial rhodopsin has been widely used in optogenetics for optical control of neural activity. In order to increase the variety of rhodopsin proteins having a wide range of absorption wavelengths, the light absorption properties of various wild-type rhodopsins and their artificially mutated variants were investigated in the literature. Here, we demonstrate that a machine-learning-based (ML-based) data-driven approach is useful for understanding and predicting the light-absorption properties of microbial rhodopsin proteins. We constructed a database of 796 proteins consisting of microbial rhodopsin wildtypes and their variants. We then proposed an ML method that produces a statistical model describing the relationship between amino-acid sequences and absorption wavelengths and demonstrated that the fitted statistical model is useful for understanding colour tuning rules and predicting absorption wavelengths. By applying the ML method to the database, two residues that were not considered in previous studies are newly identified to be important to colour shift.
format article
author Masayuki Karasuyama
Keiichi Inoue
Ryoko Nakamura
Hideki Kandori
Ichiro Takeuchi
author_facet Masayuki Karasuyama
Keiichi Inoue
Ryoko Nakamura
Hideki Kandori
Ichiro Takeuchi
author_sort Masayuki Karasuyama
title Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
title_short Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
title_full Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
title_fullStr Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
title_full_unstemmed Understanding Colour Tuning Rules and Predicting Absorption Wavelengths of Microbial Rhodopsins by Data-Driven Machine-Learning Approach
title_sort understanding colour tuning rules and predicting absorption wavelengths of microbial rhodopsins by data-driven machine-learning approach
publisher Nature Portfolio
publishDate 2018
url https://doaj.org/article/6d5f6523e95c47b9a3267d31656cf7dd
work_keys_str_mv AT masayukikarasuyama understandingcolourtuningrulesandpredictingabsorptionwavelengthsofmicrobialrhodopsinsbydatadrivenmachinelearningapproach
AT keiichiinoue understandingcolourtuningrulesandpredictingabsorptionwavelengthsofmicrobialrhodopsinsbydatadrivenmachinelearningapproach
AT ryokonakamura understandingcolourtuningrulesandpredictingabsorptionwavelengthsofmicrobialrhodopsinsbydatadrivenmachinelearningapproach
AT hidekikandori understandingcolourtuningrulesandpredictingabsorptionwavelengthsofmicrobialrhodopsinsbydatadrivenmachinelearningapproach
AT ichirotakeuchi understandingcolourtuningrulesandpredictingabsorptionwavelengthsofmicrobialrhodopsinsbydatadrivenmachinelearningapproach
_version_ 1718395521756823552