Biology subjects

Listgarten, J.

Publications and source records attributed to Listgarten, J..

4 recordsLinked to original sources

bioRxiv2021

Nanopore callers for epigenetics from limited supervised data

Nanopore sequencing platforms combined with supervised machine learning (ML) have been effective at detecting base modifications in DNA such as 5mC and 6mA. These ML-based nanopore callers have typically been trained on data that span all modifications on all possible DNA k-mer backgrounds--a complete training dataset. However, as nanopore technology is pushed to more and more epigenetic modifications, such complete training data will not be feasible to obtain. Nanopore calling has historically been performed with Hidden Markov Models (HMMs) that cannot make successful calls for k-mer contexts not seen during training because of their independent emission distributions. However, deep neural networks (DNNs), which share parameters across contexts, are increasingly being used as callers, often outperforming their HMM cousins. It stands to reason that a DNN approach should be able to better generalize to unseen k-mer contexts. Indeed, herein we demonstrate that a common DNN approach (DeepSignal) outperforms a common HMM approach (Nanopolish) in the incomplete data setting. Furthermore, we propose a novel hybrid HMM-DNN approach, Amortized-HMM, that outperforms both the pure HMM and DNN approaches on 5mC calling when the training data are incomplete. Such an approach is expected to be useful for calling 5hmC and combinations of cytosine modifications, where complete training data are not likely to be available.

bioinformatics↗

bioRxiv2021

On the sparsity of fitness functions and implications for learning

Fitness functions map biological sequences to a scalar property of interest. Accurate estimation of these functions yields biological insight and sets the foundation for model-based sequence design. However, the amount of fitness data available to learn these functions is typically small relative to the large combinatorial space of sequences; characterizing how much data is needed for accurate estimation remains an open problem. There is a growing body of evidence demonstrating that empirical fitness functions display substantial sparsity when represented in terms of epistatic interactions. Moreover, the theory of Compressed Sensing provides scaling laws for the number of samples required to exactly recover a sparse function. Motivated by these results, we develop a framework to study the sparsity of fitness functions sampled from a generalization of the NK model, a widely-used random field model of fitness functions. In particular, we present results that allow us to test the effect of the Generalized NK (GNK) models interpretable parameters--sequence length, alphabet size, and assumed interactions between sequence positions--on the sparsity of fitness functions sampled from the model and, consequently, the number of measurements required to exactly recover these functions. We validate our framework by demonstrating that GNK models with parameters set according to structural considerations can be used to accurately approximate the number of samples required to recover two empirical protein fitness functions and an RNA fitness function. In addition, we show that these GNK models identify important higher-order epistatic interactions in the empirical fitness functions using only structural information.

bioinformatics↗

bioRxiv2021

Combining evolutionary and assay-labelled data for protein fitness prediction

Predictive modelling of protein properties has become increasingly important to the field of machine-learning guided protein engineering. In one of the two existing approaches, evolutionarily-related sequences to a query protein drive the modelling process, without any property measurements from the laboratory. In the other, a set of protein variants of interest are assayed, and then a supervised regression model is estimated with the assay-labelled data. Although a handful of recent methods have shown promise in combining the evolutionary and supervised approaches, this hybrid problem has not been examined in depth, leaving it unclear how practitioners should proceed, and how method developers should build on existing work. Herein, we present a systematic assessment of methods for protein fitness prediction when evolutionary and assay-labelled data are available. We find that a simple baseline approach we introduce is competitive with and often outperforms more sophisticated methods. Moreover, our simple baseline is plug-and-play with a wide variety of established methods, and does not add any substantial computational burden. Our analysis highlights the importance of systematic evaluations and sufficient baselines.

synthetic biology↗

bioRxiv2020

Sparse Epistatic Regularization of Deep Neural Networks for Inferring Fitness Functions

Despite recent advances in high-throughput combinatorial mutagenesis assays, the number of labeled sequences available to predict molecular functions has remained small for the vastness of the sequence space combined with the ruggedness of many fitness functions. Expressive models in machine learning (ML), such as deep neural networks (DNNs), can model the nonlinearities in rugged fitness functions, which manifest as high-order epistatic interactions among the mutational sites. However, in the absence of an inductive bias, DNNs overfit to the small number of labeled sequences available for training. Herein, we exploit the recent biological evidence that epistatic interactions in many fitness functions are sparse; this knowledge can be used as an inductive bias to regularize DNNs. We have developed a method for sparse epistatic regularization of DNNs, called the epistatic net (EN), which constrains the number of non-zero coefficients in the spectral representation of DNNs. For larger sequences, where finding the spectral transform becomes computationally intractable, we have developed a scalable extension of EN, which subsamples the combinatorial sequence space uniformly inducing a sparse-graph-code structure, and regularizes DNNs using the resulting greedy optimization method. Results on several biological landscapes, from bacterial to protein fitness functions, show that EN consistently improves the prediction accuracy of DNNs and enables them to outperform competing models which assume other forms of inductive biases. EN estimates all the higher-order epistatic interactions of DNNs trained on massive sequence spaces--a computational problem that takes years to solve without leveraging the epistatic sparsity in the fitness functions.

bioinformatics↗