Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos

Purpose: This study aimed to establish a non-invasive predicting model via Raman spectroscopy for evaluating the blastocyst development potential of day 3 high-quality cleavage stage embryos.Methods: Raman spectroscopy was used to detect the metabolic spectrum of spent day 3 (D3) embryo culture medi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wei Zheng, Shuoping Zhang, Yifan Gu, Fei Gong, Lingyin Kong, Guangxiu Lu, Ge Lin, Bo Liang, Liang Hu
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	embryo viability prediction metabolomic profiling multilayer perceptron non-invasive assessment Raman spectroscopy Physiology QP1-981
Acceso en línea:	https://doaj.org/article/5d81e41b5557405aaf5c89f58675b3b4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5d81e41b5557405aaf5c89f58675b3b4
record_format	dspace
spelling	oai:doaj.org-article:5d81e41b5557405aaf5c89f58675b3b42021-11-19T07:33:14ZNon-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos1664-042X10.3389/fphys.2021.777259https://doaj.org/article/5d81e41b5557405aaf5c89f58675b3b42021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fphys.2021.777259/fullhttps://doaj.org/toc/1664-042XPurpose: This study aimed to establish a non-invasive predicting model via Raman spectroscopy for evaluating the blastocyst development potential of day 3 high-quality cleavage stage embryos.Methods: Raman spectroscopy was used to detect the metabolic spectrum of spent day 3 (D3) embryo culture medium, and a classification model based on deep learning was established to differentiate between embryos that could develop into blastocysts (blastula) and that could not (non-blastula). The full-spectrum data for 80 blastula and 48 non-blastula samples with known blastocyst development potential from 34 patients were collected for this study.Results: The accuracy of the predicting method was 73.53% and the main different Raman shifts between blastula and non-blastula groups were 863.5, 959.5, 1,008, 1,104, 1,200, 1,360, 1,408, and 1,632 cm–1 from 80 blastula and 48 non-blastula samples by the linear discriminant method.Conclusion: This study demonstrated that the developing potential of D3 cleavage stage embryos to the blastocyst stage could be predicted with spent D3 embryo culture medium using Raman spectroscopy with deep learning classification models, and the overall accuracy reached at 73.53%. In the Raman spectroscopy, ribose vibration specific to RNA were found, indicating that the difference between the blastula and non-blastula samples could be due to materials that have similar structure with RNA. This result could be used as a guide for biomarker development of embryo quality assessment in the future.Wei ZhengWei ZhengWei ZhengShuoping ZhangYifan GuYifan GuFei GongFei GongLingyin KongGuangxiu LuGuangxiu LuGe LinGe LinGe LinBo LiangLiang HuLiang HuLiang HuFrontiers Media S.A.articleembryo viability predictionmetabolomic profilingmultilayer perceptronnon-invasive assessmentRaman spectroscopyPhysiologyQP1-981ENFrontiers in Physiology, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	embryo viability prediction metabolomic profiling multilayer perceptron non-invasive assessment Raman spectroscopy Physiology QP1-981
spellingShingle	embryo viability prediction metabolomic profiling multilayer perceptron non-invasive assessment Raman spectroscopy Physiology QP1-981 Wei Zheng Wei Zheng Wei Zheng Shuoping Zhang Yifan Gu Yifan Gu Fei Gong Fei Gong Lingyin Kong Guangxiu Lu Guangxiu Lu Ge Lin Ge Lin Ge Lin Bo Liang Liang Hu Liang Hu Liang Hu Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
description	Purpose: This study aimed to establish a non-invasive predicting model via Raman spectroscopy for evaluating the blastocyst development potential of day 3 high-quality cleavage stage embryos.Methods: Raman spectroscopy was used to detect the metabolic spectrum of spent day 3 (D3) embryo culture medium, and a classification model based on deep learning was established to differentiate between embryos that could develop into blastocysts (blastula) and that could not (non-blastula). The full-spectrum data for 80 blastula and 48 non-blastula samples with known blastocyst development potential from 34 patients were collected for this study.Results: The accuracy of the predicting method was 73.53% and the main different Raman shifts between blastula and non-blastula groups were 863.5, 959.5, 1,008, 1,104, 1,200, 1,360, 1,408, and 1,632 cm–1 from 80 blastula and 48 non-blastula samples by the linear discriminant method.Conclusion: This study demonstrated that the developing potential of D3 cleavage stage embryos to the blastocyst stage could be predicted with spent D3 embryo culture medium using Raman spectroscopy with deep learning classification models, and the overall accuracy reached at 73.53%. In the Raman spectroscopy, ribose vibration specific to RNA were found, indicating that the difference between the blastula and non-blastula samples could be due to materials that have similar structure with RNA. This result could be used as a guide for biomarker development of embryo quality assessment in the future.
format	article
author	Wei Zheng Wei Zheng Wei Zheng Shuoping Zhang Yifan Gu Yifan Gu Fei Gong Fei Gong Lingyin Kong Guangxiu Lu Guangxiu Lu Ge Lin Ge Lin Ge Lin Bo Liang Liang Hu Liang Hu Liang Hu
author_facet	Wei Zheng Wei Zheng Wei Zheng Shuoping Zhang Yifan Gu Yifan Gu Fei Gong Fei Gong Lingyin Kong Guangxiu Lu Guangxiu Lu Ge Lin Ge Lin Ge Lin Bo Liang Liang Hu Liang Hu Liang Hu
author_sort	Wei Zheng
title	Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
title_short	Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
title_full	Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
title_fullStr	Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
title_full_unstemmed	Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos
title_sort	non-invasive metabolomic profiling of embryo culture medium using raman spectroscopy with deep learning model predicts the blastocyst development potential of embryos
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/5d81e41b5557405aaf5c89f58675b3b4
work_keys_str_mv	AT weizheng noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT weizheng noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT weizheng noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT shuopingzhang noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT yifangu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT yifangu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT feigong noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT feigong noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT lingyinkong noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT guangxiulu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT guangxiulu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT gelin noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT gelin noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT gelin noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT boliang noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT lianghu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT lianghu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos AT lianghu noninvasivemetabolomicprofilingofembryoculturemediumusingramanspectroscopywithdeeplearningmodelpredictstheblastocystdevelopmentpotentialofembryos
_version_	1718420260865966080

Non-invasive Metabolomic Profiling of Embryo Culture Medium Using Raman Spectroscopy With Deep Learning Model Predicts the Blastocyst Development Potential of Embryos

Ejemplares similares