Deep2Full: Evaluating strategies for selecting the minimal mutational experiments for optimal computational predictions of deep mutational scan outcomes

Flattening the curve-How to get better results with small deep-mutational-scanning datasets

Proteins are used in various biotechnological applications, often requiring the optimization of protein properties by introducing specific amino-acid exchanges. Deep mutational scanning (DMS) is an effective high-throughput method for evaluating the effects of these exchanges on protein function. DMS data can then inform the training of a neural network to predict the impact of mutations. Most approaches use some representation of the protein sequence for training and prediction. As proteins are characterized by complex structures and intricate residue interaction networks, directly providing structural information as input reduces the need to learn these features from the data. We introduce a method for encoding protein structures as stacked 2D contact maps, which capture residue interactions, their evolutionary conservation, and mutation-induced interaction changes. Furthermore, we explored techniques to augment neural network training performance on smaller DMS datasets. To validate our approach, we trained three neural network architectures originally used for image analysis on three DMS datasets, and we compared their performances with networks trained solely on protein sequences. The results confirm the effectiveness of the protein structure encoding in machine learning efforts on DMS data. Using structural representations as direct input to the networks, along with data augmentation and pretraining, significantly reduced demands on training data size and improved prediction performance, especially on smaller datasets, while performance on large datasets was on par with state-of-the-art sequence convolutional neural networks. The methods presented here have the potential to provide the same workflow as DMS without the experimental and financial burden of testing thousands of mutants. Additionally, we present an open-source, user-friendly software tool to make these data analysis techniques accessible, particularly to biotechnology and protein engineering researchers who wish to apply them to their mutagenesis data.

Genome interpretation using in silico predictors of variant impact

Estimating the effects of variants found in disease driver genes opens the door to personalized therapeutic opportunities. Clinical associations and laboratory experiments can only characterize a tiny fraction of all the available variants, leaving the majority as variants of unknown significance (VUS). In silico methods bridge this gap by providing instant estimates on a large scale, most often based on the numerous genetic differences between species. Despite concerns that these methods may lack reliability in individual subjects, their numerous practical applications over cohorts suggest they are already helpful and have a role to play in genome interpretation when used at the proper scale and context. In this review, we aim to gain insights into the training and validation of these variant effect predicting methods and illustrate representative types of experimental and clinical applications. Objective performance assessments using various datasets that are not yet published indicate the strengths and limitations of each method. These show that cautious use of in silico variant impact predictors is essential for addressing genome interpretation challenges.

Facilitating Machine Learning-Guided Protein Engineering with Smart Library Design and Massively Parallel Assays

Protein design plays an important role in recent medical advances from antibody therapy to vaccine design. Typically, exhaustive mutational screens or directed evolution experiments are used for the identification of the best design or for improvements to the wild-type variant. Even with a high-throughput screening on pooled libraries and Next-Generation Sequencing to boost the scale of read-outs, surveying all the variants with combinatorial mutations for their empirical fitness scores is still of magnitudes beyond the capacity of existing experimental settings. To tackle this challenge, in-silico approaches using machine learning to predict the fitness of novel variants based on a subset of empirical measurements are now employed. These machine learning models turn out to be useful in many cases, with the premise that the experimentally determined fitness scores and the amino-acid descriptors of the models are informative. The machine learning models can guide the search for the highest fitness variants, resolve complex epistatic relationships, and highlight bio-physical rules for protein folding. Using machine learning-guided approaches, researchers can build more focused libraries, thus relieving themselves from labor-intensive screens and fast-tracking the optimization process. Here, we describe the current advances in massive-scale variant screens, and how machine learning and mutagenesis strategies can be integrated to accelerate protein engineering. More specifically, we examine strategies to make screens more economical, informative, and effective in discovery of useful variants.

Disentangling the Contribution of Each Descriptive Characteristic of Every Single Mutation to Its Functional Effects

Mutational effects predictions continue to improve in accuracy as advanced artificial intelligence (AI) algorithms are trained on exhaustive experimental data. The next natural questions to ask are if it is possible to gain insights into which attribute of the mutation contributes how much to the mutational effects and if one can develop universal rules for mapping the descriptors to mutational effects. In this work, we mainly address the former aspect using a framework of interpretable AI. Relations between the physicochemical descriptors and their contributions to the mutational effects are extracted by analyzing the data on 29,832 variants from eight systematic deep mutational scan studies. An opposite trend in the dependence of fitness and solubility on the distance of the amino acid from the catalytic sites could be extracted and quantified. The dependence of the mutational effect contributions on the position-specific scoring matrix (PSSM) score for the amino acid after mutation or the BLOSUM score of the substitution showed universal trends. Our attempts in the present work to explain the quantitative differences in the dependence on conservation and SASA across proteins were not successful. The work nevertheless brings transparency into the predictions and development of rules, and will hopefully lead to empirically uncovering the universalities among these rules.

Toward Developing Intuitive Rules for Protein Variant Effect Prediction Using Deep Mutational Scanning Data

Protein structure and function can be severely altered by even a single amino acid mutation. Predictions of mutational effects using extensive artificial intelligence (AI)-based models, although accurate, remain as enigmatic as the experimental observations in terms of improving intuitions about the contributions of various factors. Inspired by Lipinski's rules for drug-likeness, we devise simple thresholding criteria on five different descriptors such as conservation, which have so far been limited to qualitative interpretations such as high conservation implies high mutational effect. We analyze systematic deep mutational scanning data of all possible single amino acid substitutions on seven proteins (25153 mutations) to first define these thresholds and then to evaluate the scope and limits of the predictions. At this stage, the approach allows us to comment easily and with a low error rate on the subset of mutations classified as neutral or deleterious by all of the descriptors. We hope that complementary to the accurate AI predictions, these thresholding rules or their subsequent modifications will serve the purpose of codifying the knowledge about the effects of mutations.

HARP: a database of structural impacts of systematic missense mutations in drug targets of Mycobacterium leprae

Computational Saturation Mutagenesis is an in-silico approach that employs systematic mutagenesis of each amino acid residue in the protein to all other amino acid types, and predicts changes in thermodynamic stability and affinity to the other subunits/protein counterparts, ligands and nucleic acid molecules. The data thus generated are useful in understanding the functional consequences of mutations in antimicrobial resistance phenotypes. In this study, we applied computational saturation mutagenesis to three important drug-targets in Mycobacterium leprae (M. leprae) for the drugs dapsone, rifampin and ofloxacin namely Dihydropteroate Synthase (DHPS), RNA Polymerase (RNAP) and DNA Gyrase (GYR), respectively. M. leprae causes leprosy and is an obligate intracellular bacillus with limited protein structural information associating mutations with phenotypic resistance outcomes in leprosy. Experimentally solved structures of DHPS, RNAP and GYR of M. leprae are not available in the Protein Data Bank, therefore, we modelled the structures of these proteins using template-based comparative modelling and introduced systematic mutations in each model generating 80,902 mutations and mutant structures for all the three proteins. Impacts of mutations on stability and protein-subunit, protein-ligand and protein-nucleic acid affinities were computed using various in-house developed and other published protein stability and affinity prediction software. A consensus impact was estimated for each mutation using qualitative scoring metrics for physicochemical properties and by a categorical grouping of stability and affinity predictions. We developed a web database named HARP (a database of Hansen's Disease Antimicrobial Resistance Profiles), which is accessible at the URL - https://harp-leprosy.org and provides the details to each of these predictions.