NetSolP: predicting protein solubility in Escherichia coli using language models

Abstract

Motivation Solubility and expression levels of proteins can be a limiting factor for large-scale studies and industrial production. By determining the solubility and expression directly from the protein sequence, the success rate of wet-lab experiments can be increased. Results In this study, we focus on predicting the solubility and usability for purification of proteins expressed in Escherichia coli directly from the sequence. Our model NetSolP is based on deep learning protein language models called transformers and we show that it achieves state-of-the-art performance and improves extrapolation across datasets. As we find current methods are built on biased datasets, we curate existing datasets by using strict sequence-identity partitioning and ensure that there is minimal bias in the sequences. Availability The predictor and data are available at https://services.healthtech.dtu.dk/service.php?NetSolP and the open-sourced code is available at https://github.com/tvinet/NetSolP-1.0 Supplementary information Supplementary data is attached in submission.

Codon language embeddings provide strong signals for protein engineering

“…Self-supervised training endows the latent variables of the model with highly informative features, known as learned representations, which can then be leveraged in downstream tasks where limited training data is available. Learned protein representations are currently central to the state-of-the-art tools for predicting variant fitness [3][4][5][6], protein function [7,8], subcellular localisation [9], solubility [10], binding sites [11], signal peptides [12], post-translational modifications [13], intrinsic disorder [14], and others [15,16], and they have shown promise in the path towards accurate alignment-free protein structure prediction [17][18][19][20][21]. Improving learned representations is therefore a potential path to deliver consistent, substantial improvements across computational protein engineering.…”

Machine Learning-Guided Protein Engineering

“…Therefore, the strategy of taking the difference between the predicted labels for a reference protein and its variant typically fails to produce reliable predictors for mutational effects. 130 A more promising route is to use labeled mutational data sets for training. This strategy has its own limitations, since such data sets are not only scarce but also sparse in terms of the extent of the mutational landscape that is probed (the sequence space grows exponentially with the number of mutated residues) and biased toward several overrepresented proteins.…”

“…, solubility scores), in contrast to dramatic changes often observed in experiments. Therefore, the strategy of taking the difference between the predicted labels for a reference protein and its variant typically fails to produce reliable predictors for mutational effects …”

ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a language diffusion model

“…End-to-end models based on deep learning that predict various structural features [e.g., secondary structure type and content (28)(29)(30)(31)(32)(33), binding sites (34), and surfaces (35)] and properties [e.g., solubility (16,36,37), melting temperature (38), natural vibrational frequencies (39,40), and strength (41)] for given sequences have also been reported. At the sample time, the inverse design of de novo proteins that meet desired structural or property features presents a more challenging task.…”