Predicting protein residue-residue contacts using random forests and deep networks

LoCoHD: a metric for comparing local environments of proteins

Protein folds and the local environments they create can be compared using a variety of differently designed measures, such as the root mean squared deviation, the global distance test, the template modeling score or the local distance difference test. Although these measures have proven to be useful for a variety of tasks, each fails to fully incorporate the valuable chemical information inherent to atoms and residues, and considers these only partially and indirectly. Here, we develop the highly flexible local composition Hellinger distance (LoCoHD) metric, which is based on the chemical composition of local residue environments. Using LoCoHD, we analyze the chemical heterogeneity of amino acid environments and identify valines having the most conserved-, and arginines having the most variable chemical environments. We use LoCoHD to investigate structural ensembles, to evaluate critical assessment of structure prediction (CASP) competitors, to compare the results with the local distance difference test (lDDT) scoring system, and to evaluate a molecular dynamics simulation. We show that LoCoHD measurements provide unique information about protein structures that is distinct from, for example, those derived using the alignment-based RMSD metric, or the similarly distance matrix-based but alignment-free lDDT metric.

Machine learning model of the catalytic efficiency and substrate specificity of acyl-ACP thioesterase variants generated from natural and in vitro directed evolution

Modulating the catalytic activity of acyl-ACP thioesterase (TE) is an important biotechnological target for effectively increasing flux and diversifying products of the fatty acid biosynthesis pathway. In this study, a directed evolution approach was developed to improve the fatty acid titer and fatty acid diversity produced by E. coli strains expressing variant acyl-ACP TEs. A single round of in vitro directed evolution, coupled with a high-throughput colorimetric screen, identified 26 novel acyl-ACP TE variants that convey up to a 10-fold increase in fatty acid titer, and generate altered fatty acid profiles when expressed in a bacterial host strain. These in vitro-generated variant acyl-ACP TEs, in combination with 31 previously characterized natural variants isolated from diverse phylogenetic origins, were analyzed with a random forest classifier machine learning tool. The resulting quantitative model identified 22 amino acid residues, which define important structural features that determine the catalytic efficiency and substrate specificity of acyl-ACP TE.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Residue-Residue Contact Can Be a Potential Feature for the Prediction of Lysine Crotonylation Sites

Lysine crotonylation (Kcr) is involved in plenty of activities in the human body. Various technologies have been developed for Kcr prediction. Sequence-based features are typically adopted in existing methods, in which only linearly neighboring amino acid composition was considered. However, modified Kcr sites are neighbored by not only the linear-neighboring amino acid but also those spatially surrounding residues around the target site. In this paper, we have used residue-residue contact as a new feature for Kcr prediction, in which features encoded with not only linearly surrounding residues but also those spatially nearby the target site. Then, the spatial-surrounding residue was used as a new scheme for feature encoding for the first time, named residue-residue composition (RRC) and residue-residue pair composition (RRPC), which were used in supervised learning classification for Kcr prediction. As the result suggests, RRC and RRPC have achieved the best performance of RRC at an accuracy of 0.77 and an area under curve (AUC) value of 0.78, RRPC at an accuracy of 0.74, and an AUC value of 0.80. In order to show that the spatial feature is of a competitively high significance as other sequence-based features, feature selection was carried on those sequence-based features together with feature RRPC. In addition, different ranges of the surrounding amino acid compositions' radii were used for comparison of the performance. After result assessment, RRC and RRPC features have shown competitively outstanding performance as others or in some cases even around 0.20 higher in accuracy or 0.3 higher in AUC values compared with sequence-based features.

Evaluating the significance of contact maps in low-homology protein modeling using contact-assisted threading

The development of improved threading algorithms for remote homology modeling is a critical step forward in template-based protein structure prediction. We have recently demonstrated the utility of contact information to boost protein threading by developing a new contact-assisted threading method. However, the nature and extent to which the quality of a predicted contact map impacts the performance of contact-assisted threading remains elusive. Here, we systematically analyze and explore this interdependence by employing our newly-developed contact-assisted threading method over a large-scale benchmark dataset using predicted contact maps from four complementary methods including direct coupling analysis (mfDCA), sparse inverse covariance estimation (PSICOV), classical neural network-based meta approach (MetaPSICOV), and state-of-the-art ultra-deep learning model (RaptorX). Experimental results demonstrate that contact-assisted threading using high-quality contacts having the Matthews Correlation Coefficient (MCC) ≥ 0.5 improves threading performance in nearly 30% cases, while low-quality contacts with MCC <0.35 degrades the performance for 50% cases. This holds true even in CASP13 dataset, where threading using high-quality contacts (MCC ≥ 0.5) significantly improves the performance of 22 instances out of 29. Collectively, our study uncovers the mutual association between the quality of predicted contacts and its possible utility in boosting threading performance for improving low-homology protein modeling.

Convolution Neural Network-Based Prediction of Protein Thermostability

Most natural proteins exhibit poor thermostability, which limits their industrial application. Computer-aided rational design is an efficient purpose-oriented method that can improve protein thermostability. Numerous machine-learning-based methods have been designed to predict the changes in protein thermostability induced by mutations. However, all of these methods have certain limitations due to existing mutation coding methods that overlook protein sequence features. Here we propose a method to predict protein thermostability using convolutional neural networks based on an in-depth study of thermostability-related protein properties. This method comprises a three-dimensional coding algorithm, including protein mutation information and a strategy to extract neighboring features at protein mutation sites based on multiscale convolution. The accuracies on the S1615 and S388 data sets, which are widely used for protein thermostability predictions, reached 86.4 and 87%, respectively. The Matthews correlation coefficient was nearly double those produced using other methods. Furthermore, a model was constructed to predict the thermostability of Rhizomucor miehei lipase mutants based on the S3661 data set, a single amino acid mutation data set screened from the ProTherm protein thermodynamics database. Compared with the RIF strategy, which consists of three algorithms, i.e., Rosetta ddg monomer, I Mutant 3.0, and FoldX, the accuracy of the proposed method was higher (75.0 vs 66.7%), and the negative sample resolution was simultaneously enhanced. These results indicate that our prediction method more effectively assessed the protein thermostability and distinguished its features, making it a powerful tool to devise mutations that enhance the thermostability of proteins, particularly enzymes.