Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data
Ribozymes are RNA molecules that catalyze biochemical reactions. Self-cleaving ribozymes are a common naturally occurring class of ribozymes that catalyze site-specific cleavage of their own phosphodiester backbone. In addition to their natural functions, self-cleaving ribozymes have been used to en...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Molecular Biosciences |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmolb.2022.893864/full |
| _version_ | 1811215398029230080 |
|---|---|
| author | James D. Beck Jessica M. Roberts Joey M. Kitzhaber Ashlyn Trapp Edoardo Serra Francesca Spezzano Eric J. Hayden Eric J. Hayden |
| author_facet | James D. Beck Jessica M. Roberts Joey M. Kitzhaber Ashlyn Trapp Edoardo Serra Francesca Spezzano Eric J. Hayden Eric J. Hayden |
| author_sort | James D. Beck |
| collection | DOAJ |
| description | Ribozymes are RNA molecules that catalyze biochemical reactions. Self-cleaving ribozymes are a common naturally occurring class of ribozymes that catalyze site-specific cleavage of their own phosphodiester backbone. In addition to their natural functions, self-cleaving ribozymes have been used to engineer control of gene expression because they can be designed to alter RNA processing and stability. However, the rational design of ribozyme activity remains challenging, and many ribozyme-based systems are engineered or improved by random mutagenesis and selection (in vitro evolution). Improving a ribozyme-based system often requires several mutations to achieve the desired function, but extensive pairwise and higher-order epistasis prevent a simple prediction of the effect of multiple mutations that is needed for rational design. Recently, high-throughput sequencing-based approaches have produced data sets on the effects of numerous mutations in different ribozymes (RNA fitness landscapes). Here we used such high-throughput experimental data from variants of the CPEB3 self-cleaving ribozyme to train a predictive model through machine learning approaches. We trained models using either a random forest or long short-term memory (LSTM) recurrent neural network approach. We found that models trained on a comprehensive set of pairwise mutant data could predict active sequences at higher mutational distances, but the correlation between predicted and experimentally observed self-cleavage activity decreased with increasing mutational distance. Adding sequences with increasingly higher numbers of mutations to the training data improved the correlation at increasing mutational distances. Systematically reducing the size of the training data set suggests that a wide distribution of ribozyme activity may be the key to accurate predictions. Because the model predictions are based only on sequence and activity data, the results demonstrate that this machine learning approach allows readily obtainable experimental data to be used for RNA design efforts even for RNA molecules with unknown structures. The accurate prediction of RNA functions will enable a more comprehensive understanding of RNA fitness landscapes for studying evolution and for guiding RNA-based engineering efforts. |
| first_indexed | 2024-04-12T06:20:57Z |
| format | Article |
| id | doaj.art-e46cab43d4814433b5fda892ae8a0f3a |
| institution | Directory Open Access Journal |
| issn | 2296-889X |
| language | English |
| last_indexed | 2024-04-12T06:20:57Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Molecular Biosciences |
| spelling | doaj.art-e46cab43d4814433b5fda892ae8a0f3a2022-12-22T03:44:19ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2022-08-01910.3389/fmolb.2022.893864893864Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental dataJames D. Beck0Jessica M. Roberts1Joey M. Kitzhaber2Ashlyn Trapp3Edoardo Serra4Francesca Spezzano5Eric J. Hayden6Eric J. Hayden7Boise State University, Boise, ID, United StatesBiomolecular Sciences Graduate Programs, Boise State University, Boise, ID, United StatesDepartment of Computer Science, Boise State University, Boise, ID, United StatesDepartment of Biological Sciences, Boise State University, Boise, ID, United StatesBoise State University, Boise, ID, United StatesBoise State University, Boise, ID, United StatesBiomolecular Sciences Graduate Programs, Boise State University, Boise, ID, United StatesDepartment of Computer Science, Boise State University, Boise, ID, United StatesRibozymes are RNA molecules that catalyze biochemical reactions. Self-cleaving ribozymes are a common naturally occurring class of ribozymes that catalyze site-specific cleavage of their own phosphodiester backbone. In addition to their natural functions, self-cleaving ribozymes have been used to engineer control of gene expression because they can be designed to alter RNA processing and stability. However, the rational design of ribozyme activity remains challenging, and many ribozyme-based systems are engineered or improved by random mutagenesis and selection (in vitro evolution). Improving a ribozyme-based system often requires several mutations to achieve the desired function, but extensive pairwise and higher-order epistasis prevent a simple prediction of the effect of multiple mutations that is needed for rational design. Recently, high-throughput sequencing-based approaches have produced data sets on the effects of numerous mutations in different ribozymes (RNA fitness landscapes). Here we used such high-throughput experimental data from variants of the CPEB3 self-cleaving ribozyme to train a predictive model through machine learning approaches. We trained models using either a random forest or long short-term memory (LSTM) recurrent neural network approach. We found that models trained on a comprehensive set of pairwise mutant data could predict active sequences at higher mutational distances, but the correlation between predicted and experimentally observed self-cleavage activity decreased with increasing mutational distance. Adding sequences with increasingly higher numbers of mutations to the training data improved the correlation at increasing mutational distances. Systematically reducing the size of the training data set suggests that a wide distribution of ribozyme activity may be the key to accurate predictions. Because the model predictions are based only on sequence and activity data, the results demonstrate that this machine learning approach allows readily obtainable experimental data to be used for RNA design efforts even for RNA molecules with unknown structures. The accurate prediction of RNA functions will enable a more comprehensive understanding of RNA fitness landscapes for studying evolution and for guiding RNA-based engineering efforts.https://www.frontiersin.org/articles/10.3389/fmolb.2022.893864/fullribozymefitness landscapeRNAepistasismachine learninglong short-term memory |
| spellingShingle | James D. Beck Jessica M. Roberts Joey M. Kitzhaber Ashlyn Trapp Edoardo Serra Francesca Spezzano Eric J. Hayden Eric J. Hayden Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data Frontiers in Molecular Biosciences ribozyme fitness landscape RNA epistasis machine learning long short-term memory |
| title | Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data |
| title_full | Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data |
| title_fullStr | Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data |
| title_full_unstemmed | Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data |
| title_short | Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data |
| title_sort | predicting higher order mutational effects in an rna enzyme by machine learning of high throughput experimental data |
| topic | ribozyme fitness landscape RNA epistasis machine learning long short-term memory |
| url | https://www.frontiersin.org/articles/10.3389/fmolb.2022.893864/full |
| work_keys_str_mv | AT jamesdbeck predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT jessicamroberts predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT joeymkitzhaber predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT ashlyntrapp predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT edoardoserra predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT francescaspezzano predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT ericjhayden predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata AT ericjhayden predictinghigherordermutationaleffectsinanrnaenzymebymachinelearningofhighthroughputexperimentaldata |