Feature-based multiple models improve classification of mutation-induced stability changes

Prediction of protein stability changes upon single-point variant using 3D structure profile

Identifying protein thermodynamic stability changes upon single-point variants is crucial for studying mutation-induced alterations in protein biophysics, genomic variants, and mutation-related diseases. In the last decade, various computational methods have been developed to predict the effects of single-point variants, but the prediction accuracy is still far from satisfactory for practical applications. Herein, we review approaches and tools for predicting stability changes upon the single-point variant. Most of these methods require tertiary protein structure as input to achieve reliable predictions. However, the availability of protein structures limits the immediate application of these tools. To improve the performance of a computational prediction from a protein sequence without experimental structural information, we introduce a new computational framework: MU3DSP. This method assesses the effects of single-point variants on protein thermodynamic stability based on point mutated protein 3D structure profile. Given a protein sequence with a single variant as input, MU3DSP integrates both sequence-level features and averaged features of 3D structures obtained from sequence alignment to PDB to assess the change of thermodynamic stability induced by the substitution. MU3DSP outperforms existing methods on various benchmarks, making it a reliable tool to assess both somatic and germline substitution variants and assist in protein design. MU3DSP is available as an open-source tool at https://github.com/hurraygong/MU3DSP.

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit–explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring “the state of the art” in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI–PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI–PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI–PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the “state of the art” on research in the AI–PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

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.

mGPfusion: predicting protein stability changes with Gaussian process kernel learning and data fusion

Motivation

Proteins are commonly used by biochemical industry for numerous processes. Refining these proteins’ properties via mutations causes stability effects as well. Accurate computational method to predict how mutations affect protein stability is necessary to facilitate efficient protein design. However, accuracy of predictive models is ultimately constrained by the limited availability of experimental data.

Results

We have developed mGPfusion, a novel Gaussian process (GP) method for predicting protein’s stability changes upon single and multiple mutations. This method complements the limited experimental data with large amounts of molecular simulation data. We introduce a Bayesian data fusion model that re-calibrates the experimental and in silico data sources and then learns a predictive GP model from the combined data. Our protein-specific model requires experimental data only regarding the protein of interest and performs well even with few experimental measurements. The mGPfusion models proteins by contact maps and infers the stability effects caused by mutations with a mixture of graph kernels. Our results show that mGPfusion outperforms state-of-the-art methods in predicting protein stability on a dataset of 15 different proteins and that incorporating molecular simulation data improves the model learning and prediction accuracy.

Availability and implementation

Software implementation and datasets are available at github.com/emmijokinen/mgpfusion.

Supplementary information

Supplementary data are available at Bioinformatics online.

KStable: A Computational Method for Predicting Protein Thermal Stability Changes by K-Star with Regular-mRMR Feature Selection

Thermostability is a protein property that impacts many types of studies, including protein activity enhancement, protein structure determination, and drug development. However, most computational tools designed to predict protein thermostability require tertiary structure data as input. The few tools that are dependent only on the primary structure of a protein to predict its thermostability have one or more of the following problems: a slow execution speed, an inability to make large-scale mutation predictions, and the absence of temperature and pH as input parameters. Therefore, we developed a computational tool, named KStable, that is sequence-based, computationally rapid, and includes temperature and pH values to predict changes in the thermostability of a protein upon the introduction of a mutation at a single site. KStable was trained using basis features and minimal redundancy–maximal relevance (mRMR) features, and 58 classifiers were subsequently tested. To find the representative features, a regular-mRMR method was developed. When KStable was evaluated with an independent test set, it achieved an accuracy of 0.708.

Applications of Protein Thermodynamic Database for Understanding Protein Mutant Stability and Designing Stable Mutants

Protein stability is the free energy difference between unfolded and folded states of a protein, which lies in the range of 5-25 kcal/mol. Experimentally, protein stability is measured with circular dichroism, differential scanning calorimetry, and fluorescence spectroscopy using thermal and denaturant denaturation methods. These experimental data have been accumulated in the form of a database, ProTherm, thermodynamic database for proteins and mutants. It also contains sequence and structure information of a protein, experimental methods and conditions, and literature information. Different features such as search, display, and sorting options and visualization tools have been incorporated in the database. ProTherm is a valuable resource for understanding/predicting the stability of proteins and it can be accessed at http://www.abren.net/protherm/ . ProTherm has been effectively used to examine the relationship among thermodynamics, structure, and function of proteins. We describe the recent progress on the development of methods for understanding/predicting protein stability, such as (1) general trends on mutational effects on stability, (2) relationship between the stability of protein mutants and amino acid properties, (3) applications of protein three-dimensional structures for predicting their stability upon point mutations, (4) prediction of protein stability upon single mutations from amino acid sequence, and (5) prediction methods for addressing double mutants. A list of online resources for predicting has also been provided.

PETs: A Stable and Accurate Predictor of Protein-Protein Interacting Sites Based on Extremely-Randomized Trees

Protein-protein interaction (PPI) plays crucial roles in the performance of various biological processes. A variety of methods are dedicated to identify whether proteins have interaction residues, but it is often more crucial to recognize each amino acid. In practical applications, the stability of a prediction model is as important as its accuracy. However, random sampling, which is widely used in previous prediction models, often brings large difference between each training model. In this paper, a Predictor of protein-protein interaction sites based on Extremely-randomized Trees (PETs) is proposed to improve the prediction accuracy while maintaining the prediction stability. In PETs, a cluster-based sampling strategy is proposed to ensure the model stability: first, the training dataset is divided into subsets using specific features; second, the subsets are clustered using K-means; and finally the samples are selected from each cluster. Using the proposed sampling strategy, samples which have different types of significant features could be selected independently from different clusters. The evaluation shows that PETs is able to achieve better accuracy while maintaining a good stability. The source code and toolkit are available at https://github.com/BinXia/PETs.

Personalized biochemistry and biophysics

Whole human genome sequencing of individuals is becoming rapid and inexpensive, enabling new strategies for using personal genome information to help diagnose, treat, and even prevent human disorders for which genetic variations are causative or are known to be risk factors. Many of the exploding number of newly discovered genetic variations alter the structure, function, dynamics, stability, and/or interactions of specific proteins and RNA molecules. Accordingly, there are a host of opportunities for biochemists and biophysicists to participate in (1) developing tools to allow accurate and sometimes medically actionable assessment of the potential pathogenicity of individual variations and (2) establishing the mechanistic linkage between pathogenic variations and their physiological consequences, providing a rational basis for treatment or preventive care. In this review, we provide an overview of these opportunities and their associated challenges in light of the current status of genomic science and personalized medicine, the latter often termed precision medicine.

DDIG-in: detecting disease-causing genetic variations due to frameshifting indels and nonsense mutations employing sequence and structural properties at nucleotide and protein levels

MOTIVATION

Frameshifting (FS) indels and nonsense (NS) variants disrupt the protein-coding sequence downstream of the mutation site by changing the reading frame or introducing a premature termination codon, respectively. Despite such drastic changes to the protein sequence, FS indels and NS variants have been discovered in healthy individuals. How to discriminate disease-causing from neutral FS indels and NS variants is an understudied problem.

RESULTS

We have built a machine learning method called DDIG-in (FS) based on real human genetic variations from the Human Gene Mutation Database (inherited disease-causing) and the 1000 Genomes Project (GP) (putatively neutral). The method incorporates both sequence and predicted structural features and yields a robust performance by 10-fold cross-validation and independent tests on both FS indels and NS variants. We showed that human-derived NS variants and FS indels derived from animal orthologs can be effectively employed for independent testing of our method trained on human-derived FS indels. DDIG-in (FS) achieves a Matthews correlation coefficient (MCC) of 0.59, a sensitivity of 86%, and a specificity of 72% for FS indels. Application of DDIG-in (FS) to NS variants yields essentially the same performance (MCC of 0.43) as a method that was specifically trained for NS variants. DDIG-in (FS) was shown to make a significant improvement over existing techniques.