Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides

Abstract Cell-penetrating peptides have important therapeutic applications in drug delivery, but the variety of known cell-penetrating peptides is still limited. With a promise to accelerate peptide development, artificial intelligence (AI) techniques including deep generative models are currently i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Duy Phuoc Tran, Seiichi Tada, Akiko Yumoto, Akio Kitao, Yoshihiro Ito, Takanori Uzawa, Koji Tsuda
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0a9cf7df2c9b4a0ea4bd512001748a5c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0a9cf7df2c9b4a0ea4bd512001748a5c
record_format	dspace
spelling	oai:doaj.org-article:0a9cf7df2c9b4a0ea4bd512001748a5c2021-12-02T16:51:14ZUsing molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides10.1038/s41598-021-90245-z2045-2322https://doaj.org/article/0a9cf7df2c9b4a0ea4bd512001748a5c2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90245-zhttps://doaj.org/toc/2045-2322Abstract Cell-penetrating peptides have important therapeutic applications in drug delivery, but the variety of known cell-penetrating peptides is still limited. With a promise to accelerate peptide development, artificial intelligence (AI) techniques including deep generative models are currently in spotlight. Scientists, however, are often overwhelmed by an excessive number of unannotated sequences generated by AI and find it difficult to obtain insights to prioritize them for experimental validation. To avoid this pitfall, we leverage molecular dynamics (MD) simulations to obtain mechanistic information to prioritize and understand AI-generated peptides. A mechanistic score of permeability is computed from five steered MD simulations starting from different initial structures predicted by homology modelling. To compensate for variability of predicted structures, the score is computed with sample variance penalization so that a peptide with consistent behaviour is highly evaluated. Our computational pipeline involving deep learning, homology modelling, MD simulations and synthesizability assessment generated 24 novel peptide sequences. The top-scoring peptide showed a consistent pattern of conformational change in all simulations regardless of initial structures. As a result of wet-lab-experiments, our peptide showed better permeability and weaker toxicity in comparison to a clinically used peptide, TAT. Our result demonstrates how MD simulations can support de novo peptide design by providing mechanistic information supplementing statistical inference.Duy Phuoc TranSeiichi TadaAkiko YumotoAkio KitaoYoshihiro ItoTakanori UzawaKoji TsudaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Duy Phuoc Tran Seiichi Tada Akiko Yumoto Akio Kitao Yoshihiro Ito Takanori Uzawa Koji Tsuda Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
description	Abstract Cell-penetrating peptides have important therapeutic applications in drug delivery, but the variety of known cell-penetrating peptides is still limited. With a promise to accelerate peptide development, artificial intelligence (AI) techniques including deep generative models are currently in spotlight. Scientists, however, are often overwhelmed by an excessive number of unannotated sequences generated by AI and find it difficult to obtain insights to prioritize them for experimental validation. To avoid this pitfall, we leverage molecular dynamics (MD) simulations to obtain mechanistic information to prioritize and understand AI-generated peptides. A mechanistic score of permeability is computed from five steered MD simulations starting from different initial structures predicted by homology modelling. To compensate for variability of predicted structures, the score is computed with sample variance penalization so that a peptide with consistent behaviour is highly evaluated. Our computational pipeline involving deep learning, homology modelling, MD simulations and synthesizability assessment generated 24 novel peptide sequences. The top-scoring peptide showed a consistent pattern of conformational change in all simulations regardless of initial structures. As a result of wet-lab-experiments, our peptide showed better permeability and weaker toxicity in comparison to a clinically used peptide, TAT. Our result demonstrates how MD simulations can support de novo peptide design by providing mechanistic information supplementing statistical inference.
format	article
author	Duy Phuoc Tran Seiichi Tada Akiko Yumoto Akio Kitao Yoshihiro Ito Takanori Uzawa Koji Tsuda
author_facet	Duy Phuoc Tran Seiichi Tada Akiko Yumoto Akio Kitao Yoshihiro Ito Takanori Uzawa Koji Tsuda
author_sort	Duy Phuoc Tran
title	Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
title_short	Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
title_full	Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
title_fullStr	Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
title_full_unstemmed	Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides
title_sort	using molecular dynamics simulations to prioritize and understand ai-generated cell penetrating peptides
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0a9cf7df2c9b4a0ea4bd512001748a5c
work_keys_str_mv	AT duyphuoctran usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT seiichitada usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT akikoyumoto usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT akiokitao usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT yoshihiroito usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT takanoriuzawa usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides AT kojitsuda usingmoleculardynamicssimulationstoprioritizeandunderstandaigeneratedcellpenetratingpeptides
_version_	1718382959576219648

Using molecular dynamics simulations to prioritize and understand AI-generated cell penetrating peptides

Ejemplares similares