adabmDCA: Adaptive Boltzmann machine learning for biological sequences

TL;DR

adabmDCA introduces an adaptive Boltzmann machine learning method for biological sequences, enhancing the modeling of protein and RNA families by improving contact prediction and sequence generation with flexible training options.

Contribution

It presents a versatile, adaptive implementation of Boltzmann machine learning applicable to both proteins and RNAs, with improved training efficiency and parameter pruning capabilities.

Findings

Models achieve contact map accuracy comparable to state-of-the-art methods.

Generated sequences are similar in quality to those from existing techniques.

The method efficiently handles complex data with equilibrium and out-of-equilibrium training.

Abstract

Boltzmann machines are energy-based models that have been shown to provide an accurate statistical description of domains of evolutionary-related protein and RNA families. They are parametrized in terms of local biases accounting for residue conservation, and pairwise terms to model epistatic coevolution between residues. From the model parameters, it is possible to extract an accurate prediction of the three-dimensional contact map of the target domain. More recently, the accuracy of these models has been also assessed in terms of their ability in predicting mutational effects and generating in silico functional sequences. Our adaptive implementation of Boltzmann machine learning, adabmDCA, can be generally applied to both protein and RNA families and accomplishes several learning set-ups, depending on the complexity of the input data and on the user requirements. The code is fully available at https://github.com/anna-pa-m/adabmDCA. As an example, we have performed the learning of three Boltzmann machines modeling the Kunitz and Beta-lactamase2 protein domains and TPP-riboswitch RNA domain. The models learned by adabmDCA are comparable to those obtained by state-of-the-art techniques for this task, in terms of the quality of the inferred contact map as well as of the synthetically generated sequences. In addition, the code implements both equilibrium and out-of-equilibrium learning, which allows for an accurate and lossless training when the equilibrium one is prohibitive in terms of computational time, and allows for pruning irrelevant parameters using an information-based criterion.