Prediction of functional microexons by transfer learning

Abstract Background Microexons are a particular kind of exon of less than 30 nucleotides in length. More than 60% of annotated human microexons were found to have high levels of sequence conservation, suggesting their potential functions. There is thus a need to develop a method for predicting funct...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qi Cheng, Bo He, Chengkui Zhao, Hongyuan Bi, Duojiao Chen, Shuangze Han, Haikuan Gao, Weixing Feng
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Microexon Microindel Transfer learning Functional prediction Biotechnology TP248.13-248.65 Genetics QH426-470
Acceso en línea:	https://doaj.org/article/a41ebdf243e64952b53255a68065586c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a41ebdf243e64952b53255a68065586c
record_format	dspace
spelling	oai:doaj.org-article:a41ebdf243e64952b53255a68065586c2021-11-28T12:23:13ZPrediction of functional microexons by transfer learning10.1186/s12864-021-08187-91471-2164https://doaj.org/article/a41ebdf243e64952b53255a68065586c2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12864-021-08187-9https://doaj.org/toc/1471-2164Abstract Background Microexons are a particular kind of exon of less than 30 nucleotides in length. More than 60% of annotated human microexons were found to have high levels of sequence conservation, suggesting their potential functions. There is thus a need to develop a method for predicting functional microexons. Results Given the lack of a publicly available functional label for microexons, we employed a transfer learning skill called Transfer Component Analysis (TCA) to transfer the knowledge obtained from feature mapping for the prediction of functional microexons. To provide reference knowledge, microindels were chosen because of their similarities to microexons. Then, Support Vector Machine (SVM) was used to train a classification model in the newly built feature space for the functional microindels. With the trained model, functional microexons were predicted. We also built a tool based on this model to predict other functional microexons. We then used this tool to predict a total of 19 functional microexons reported in the literature. This approach successfully predicted 16 out of 19 samples, giving accuracy greater than 80%. Conclusions In this study, we proposed a method for predicting functional microexons and applied it, with the predictive results being largely consistent with records in the literature.Qi ChengBo HeChengkui ZhaoHongyuan BiDuojiao ChenShuangze HanHaikuan GaoWeixing FengBMCarticleMicroexonMicroindelTransfer learningFunctional predictionBiotechnologyTP248.13-248.65GeneticsQH426-470ENBMC Genomics, Vol 22, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Microexon Microindel Transfer learning Functional prediction Biotechnology TP248.13-248.65 Genetics QH426-470
spellingShingle	Microexon Microindel Transfer learning Functional prediction Biotechnology TP248.13-248.65 Genetics QH426-470 Qi Cheng Bo He Chengkui Zhao Hongyuan Bi Duojiao Chen Shuangze Han Haikuan Gao Weixing Feng Prediction of functional microexons by transfer learning
description	Abstract Background Microexons are a particular kind of exon of less than 30 nucleotides in length. More than 60% of annotated human microexons were found to have high levels of sequence conservation, suggesting their potential functions. There is thus a need to develop a method for predicting functional microexons. Results Given the lack of a publicly available functional label for microexons, we employed a transfer learning skill called Transfer Component Analysis (TCA) to transfer the knowledge obtained from feature mapping for the prediction of functional microexons. To provide reference knowledge, microindels were chosen because of their similarities to microexons. Then, Support Vector Machine (SVM) was used to train a classification model in the newly built feature space for the functional microindels. With the trained model, functional microexons were predicted. We also built a tool based on this model to predict other functional microexons. We then used this tool to predict a total of 19 functional microexons reported in the literature. This approach successfully predicted 16 out of 19 samples, giving accuracy greater than 80%. Conclusions In this study, we proposed a method for predicting functional microexons and applied it, with the predictive results being largely consistent with records in the literature.
format	article
author	Qi Cheng Bo He Chengkui Zhao Hongyuan Bi Duojiao Chen Shuangze Han Haikuan Gao Weixing Feng
author_facet	Qi Cheng Bo He Chengkui Zhao Hongyuan Bi Duojiao Chen Shuangze Han Haikuan Gao Weixing Feng
author_sort	Qi Cheng
title	Prediction of functional microexons by transfer learning
title_short	Prediction of functional microexons by transfer learning
title_full	Prediction of functional microexons by transfer learning
title_fullStr	Prediction of functional microexons by transfer learning
title_full_unstemmed	Prediction of functional microexons by transfer learning
title_sort	prediction of functional microexons by transfer learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/a41ebdf243e64952b53255a68065586c
work_keys_str_mv	AT qicheng predictionoffunctionalmicroexonsbytransferlearning AT bohe predictionoffunctionalmicroexonsbytransferlearning AT chengkuizhao predictionoffunctionalmicroexonsbytransferlearning AT hongyuanbi predictionoffunctionalmicroexonsbytransferlearning AT duojiaochen predictionoffunctionalmicroexonsbytransferlearning AT shuangzehan predictionoffunctionalmicroexonsbytransferlearning AT haikuangao predictionoffunctionalmicroexonsbytransferlearning AT weixingfeng predictionoffunctionalmicroexonsbytransferlearning
_version_	1718408034330345472

Prediction of functional microexons by transfer learning

Ejemplares similares