A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements

Ribozyme switches are a class of RNA-encoded genetic switch that support conditional regulation of gene expression across diverse organisms. An improved elucidation of the relationships between sequence, structure, and activity can improve our capacity for de novo rational design of ribozyme switche...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Calvin M Schmidt, Christina D Smolke
Formato:	article
Lenguaje:	EN
Publicado:	eLife Sciences Publications Ltd 2021
Materias:	synthetic biology machine learning RNA engineering Medicine R Science Q Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/915fab600fbe453a9bab9db65ba07394
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:915fab600fbe453a9bab9db65ba07394
record_format	dspace
spelling	oai:doaj.org-article:915fab600fbe453a9bab9db65ba073942021-11-23T13:02:42ZA convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements10.7554/eLife.596972050-084Xe59697https://doaj.org/article/915fab600fbe453a9bab9db65ba073942021-04-01T00:00:00Zhttps://elifesciences.org/articles/59697https://doaj.org/toc/2050-084XRibozyme switches are a class of RNA-encoded genetic switch that support conditional regulation of gene expression across diverse organisms. An improved elucidation of the relationships between sequence, structure, and activity can improve our capacity for de novo rational design of ribozyme switches. Here, we generated data on the activity of hundreds of thousands of ribozyme sequences. Using automated structural analysis and machine learning, we leveraged these large data sets to develop predictive models that estimate the in vivo gene-regulatory activity of a ribozyme sequence. These models supported the de novo design of ribozyme libraries with low mean basal gene-regulatory activities and new ribozyme switches that exhibit changes in gene-regulatory activity in the presence of a target ligand, producing functional switches for four out of five aptamers. Our work examines how biases in the model and the data set that affect prediction accuracy can arise and demonstrates that machine learning can be applied to RNA sequences to predict gene-regulatory activity, providing the basis for design tools for functional RNAs.Calvin M SchmidtChristina D SmolkeeLife Sciences Publications Ltdarticlesynthetic biologymachine learningRNA engineeringMedicineRScienceQBiology (General)QH301-705.5ENeLife, Vol 10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	synthetic biology machine learning RNA engineering Medicine R Science Q Biology (General) QH301-705.5
spellingShingle	synthetic biology machine learning RNA engineering Medicine R Science Q Biology (General) QH301-705.5 Calvin M Schmidt Christina D Smolke A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
description	Ribozyme switches are a class of RNA-encoded genetic switch that support conditional regulation of gene expression across diverse organisms. An improved elucidation of the relationships between sequence, structure, and activity can improve our capacity for de novo rational design of ribozyme switches. Here, we generated data on the activity of hundreds of thousands of ribozyme sequences. Using automated structural analysis and machine learning, we leveraged these large data sets to develop predictive models that estimate the in vivo gene-regulatory activity of a ribozyme sequence. These models supported the de novo design of ribozyme libraries with low mean basal gene-regulatory activities and new ribozyme switches that exhibit changes in gene-regulatory activity in the presence of a target ligand, producing functional switches for four out of five aptamers. Our work examines how biases in the model and the data set that affect prediction accuracy can arise and demonstrates that machine learning can be applied to RNA sequences to predict gene-regulatory activity, providing the basis for design tools for functional RNAs.
format	article
author	Calvin M Schmidt Christina D Smolke
author_facet	Calvin M Schmidt Christina D Smolke
author_sort	Calvin M Schmidt
title	A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
title_short	A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
title_full	A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
title_fullStr	A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
title_full_unstemmed	A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
title_sort	convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements
publisher	eLife Sciences Publications Ltd
publishDate	2021
url	https://doaj.org/article/915fab600fbe453a9bab9db65ba07394
work_keys_str_mv	AT calvinmschmidt aconvolutionalneuralnetworkforthepredictionandforwarddesignofribozymebasedgenecontrolelements AT christinadsmolke aconvolutionalneuralnetworkforthepredictionandforwarddesignofribozymebasedgenecontrolelements AT calvinmschmidt convolutionalneuralnetworkforthepredictionandforwarddesignofribozymebasedgenecontrolelements AT christinadsmolke convolutionalneuralnetworkforthepredictionandforwarddesignofribozymebasedgenecontrolelements
_version_	1718416717014630400

A convolutional neural network for the prediction and forward design of ribozyme-based gene-control elements

Ejemplares similares