Towards Parsimonious Generative Modeling of RNA Families

TL;DR

This paper presents eaDCA, a simple, efficient, and interpretable generative model for RNA sequences that accurately mimics natural sequences and estimates the vast number of potential functional RNAs within a family.

Contribution

The paper introduces eaDCA, a sparse coevolutionary model tailored for RNA, which achieves high performance with fewer parameters and provides insights into the size of functional RNA sequence space.

Findings

eaDCA generates RNA sequences similar to natural ones in experiments.

eaDCA estimates approximately 10^39 functional sequences for a specific RNA family.

The model operates with significantly fewer parameters than complex existing methods.

Abstract

Generative probabilistic models emerge as a new paradigm in data-driven, evolution-informed design of biomolecular sequences. This paper introduces a novel approach, called Edge Activation Direct Coupling Analysis (eaDCA), tailored to the characteristics of RNA sequences, with a strong emphasis on simplicity, efficiency, and interpretability. eaDCA explicitly constructs sparse coevolutionary models for RNA families, achieving performance levels comparable to more complex methods while utilizing a significantly lower number of parameters. Our approach demonstrates efficiency in generating artificial RNA sequences that closely resemble their natural counterparts in both statistical analyses and SHAPE-MaP experiments, and in predicting the effect of mutations. Notably, eaDCA provides a unique feature: estimating the number of potential functional sequences within a given RNA family. For example, in the case of cyclic di-AMP riboswitches (RF00379), our analysis suggests the existence of approximately $\mathbf{10^{39}}$ functional nucleotide sequences. While huge compared to the known $< \mathbf{4,000}$ natural sequences, this number represents only a tiny fraction of the vast pool of nearly $\mathbf{10^{82}}$ possible nucleotide sequences of the same length (136 nucleotides). These results underscore the promise of sparse and interpretable generative models, such as eaDCA, in enhancing our understanding of the expansive RNA sequence space.