Predicting higher-order mutational effects in an RNA enzyme by machine learning of high-throughput experimental data

Abstract

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.

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

“…A deeper analysis of the data is still needed to examine whether possible higher-order epistatic interactions are at play in these variants. Beck et al used a machine-learning model based on a high-throughput data set of the effects of mutations in the CPEB3 self-cleaving ribozyme to predict the activity of CPEB3 variants . The authors found that the model trained with pairwise interactions could predict active sequences at high mutational distances.…”

“…Trained with higher-order interactions, the correlation of predicted and measured activity could be increased for higher mutational distances. 124 In 2022, Giessel et al used a VAE approach to successfully engineer an ornithine transcarbamylase for increased catalytic activity and thermal stability, as a potentially therapeutically relevant enzyme against a rare metabolic disease. The authors pointed out that higher-order coevolutionary effects have the potential to provide a deeper understanding of the structure− function relationship in novel ways.…”

“…Beck et al used a machine-learning model based on a high-throughput data set of the effects of mutations in the CPEB3 self-cleaving ribozyme to predict the activity of CPEB3 variants. 124 The authors found that the model trained with pairwise interactions could predict active sequences at high mutational distances. The accuracy of the predictions decreased with mutational distance.…”

“…The accuracy of the predictions decreased with mutational distance. Trained with higher-order interactions, the correlation of predicted and measured activity could be increased for higher mutational distances …”