Sa-TTCA: An SVM-based approach for tumor T-cell antigen classification using features extracted from biological sequencing and natural language processing

Accurately predicting tumor T-cell antigen (TTCA) sequences is a crucial task in the development of cancer vaccines and immunotherapies. TTCAs derived from tumor cells, are presented to immune cells (T cells) through major histocompatibility complex (MHC), via the recognition of specific portions of their structure known as epitopes. More specifically, MHC class I introduces TTCAs to T-cell receptors (TCR) which are located on the surface of CD8+ T cells. However, TTCA sequences are varied and lead to struggles in vaccine design. Recently, Machine learning (ML) models have been developed to predict TTCA sequences which could aid in fast and correct TTCA identification. During the construction of the TTCA predictor, the peptide encoding strategy is an important step. Previous studies have used biological descriptors for encoding TTCA sequences. However, there have been no studies that use natural language processing (NLP), a potential approach for this purpose. As sentences have their own words with diverse properties, biological sequences also hold unique characteristics that reflect evolutionary information, physicochemical values, and structural information. We hypothesized that NLP methods would benefit the prediction of TTCA. To develop a new identifying TTCA model, we first constructed a based model with widely used ML algorithms and extracted features from biological descriptors. Then, to improve our model performance, we added extracted features from biological language models (BLMs) based on NLP methods. Besides, we conducted feature selection by using Chi-square and Pearson Correlation Coefficient techniques. Then, SMOTE, Up-sampling, and Near-Miss were used to treat unbalanced data. Finally, we optimized Sa-TTCA by the SVM algorithm to the four most effective feature groups. The best performance of Sa-TTCA showed a competitive balanced accuracy of 87.5% on a training set, and 72.0% on an independent testing set. Our results suggest that integrating biological descriptors with natural language processing has the potential to improve the precision of predicting protein/peptide functionality, which could be beneficial for developing cancer vaccines.

Computational resources and chemoinformatics for translational health research

The integration of computational resources and chemoinformatics has revolutionized translational health research. It has offered a powerful set of tools for accelerating drug discovery. This chapter overviews the computational resources and chemoinformatics methods used in translational health research. The resources and methods can be used to analyze large datasets, identify potential drug candidates, predict drug-target interactions, and optimize treatment regimens. These resources have the potential to transform the drug discovery process and foster personalized medicine research. We discuss insights into their various applications in translational health and emphasize the need for addressing challenges, promoting collaboration, and advancing the field to fully realize the potential of these tools in transforming healthcare.

Efficient mapping of RNA-binding residues in RNA-binding proteins using local sequence features of binding site residues in protein-RNA complexes

Protein-RNA interactions play vital roles in plethora of biological processes such as regulation of gene expression, protein synthesis, mRNA processing and biogenesis. Identification of RNA-binding residues (RBRs) in proteins is essential to understand RNA-mediated protein functioning, to perform site-directed mutagenesis and to develop novel targeted drug therapies. Moreover, the extensive gap between sequence and structural data restricts the identification of binding sites in unsolved structures. However, efficient use of computational methods demanding only sequence to identify binding residues can bridge this huge sequence-structure gap. In this study, we have extensively studied protein-RNA interface in known RNA-binding proteins (RBPs). We find that the interface is highly enriched in basic and polar residues with Gly being the most common interface neighbor. We investigated several amino acid features and developed a method to predict putative RBRs from amino acid sequence. We have implemented balanced random forest (BRF) classifier with local residue features of protein sequences for prediction. With 5-fold cross-validations, the sequence pattern derived dipeptide composition based BRF model (DCP-BRF) resulted in an accuracy of 87.9%, specificity of 88.8%, sensitivity of 82.2%, Mathew's correlation coefficient of 0.60 and AUC of 0.93, performing better than few existing methods. We further validated our prediction model on known human RBPs through RBR prediction and could map ~54% of them. Further, knowledge of binding site preferences obtained from computational predictions combined with experimental validations of potential RNA binding sites can enhance our understanding of protein-RNA interactions. This may serve to accelerate investigations on functional roles of many novel RBPs.

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.

Machine learning approaches and their applications in drug discovery and design

This review is focused on several machine learning approaches used in chemoinformatics. Machine learning approaches provide tools and algorithms to improve drug discovery. Many physicochemical properties of drugs like toxicity, absorption, drug-drug interaction, carcinogenesis, and distribution have been effectively modeled by QSAR techniques. Machine learning is a subset of artificial intelligence, and this technique has shown tremendous potential in the field of drug discovery. Techniques discussed in this review are capable of modeling non-linear datasets, as well as big data of increasing depth and complexity. Various machine learning-based approaches are being used for drug target prediction, modeling the structure of drug target, binding site prediction, ligand-based similarity searching, de novo designing of ligands with desired properties, developing scoring functions for molecular docking, building QSAR model for biological activity prediction, and prediction of pharmacokinetic and pharmacodynamic properties of ligands. In recent years, these predictive tools and models have achieved good accuracy. By the use of more related input data, relevant parameters, and appropriate algorithms, the accuracy of these predictions can be further improved.

Protein–Protein Interactions Prediction Base on Multiple Information Fusion via Graph Representation Learning

It is a critical impact on the processing of biological cells to protein–protein interactions (PPIs) in nature. Traditional PPIs predictive biological experiments consume a lot of human and material costs and time. Therefore, there is a great need to use computational methods to forecast PPIs. Most of the existing calculation methods are based on the sequence characteristics or internal structural characteristics of proteins, and most of them have the singleness of features. Therefore, we propose a novel method to predict PPIs base on multiple information fusion through graph representation learning. Specifically, firstly, the known protein sequences are calculated, and the properties of each protein are obtained by k-mer. Then, the known protein relationship pairs were constructed into an adjacency graph, and the graph representation learning method–graph convolution network was used to fuse the attributes of each protein with the graph structure information to obtain the features containing a variety of information. Finally, we put the multi-information features into the random forest classifier species for prediction and classification. Experimental results indicate that our method has high accuracy and AUC of 78.83% and 86.10%, respectively. In conclusion, our method has an excellent application prospect for predicting unknown PPIs.

Selecting Machine Learning Models to Support the Design of Al/CuO Nanothermites

Novel properties associated with nanothermites have attracted great interest for several applications, including lead-free primers and igniters. However, the prediction of quantitative structure-energetic performance relationships is still challenging. This study investigates machine learning methods as tools to surrogate complex physical models to design novel nanothermites with optimized burning rates chosen for energetic performance. The study focuses on Al/CuO nanolaminates, for which nine supervised regressors commonly used in ML applied to materials science are investigated. For each, an ML model is built using a database containing a set of 2700 Al/CuO nanolaminate systems, specifically generated for this study. We demonstrate the superiority of the multilayer perceptron algorithm to surrogate conventional physical-based models and predict the Al/CuO nanolaminate microstructure-burn rate relationship with good efficiency: the burn rate is estimated with less than 1% error (0.07 m·s^-1), which is very good for designing nano-engineered energetic materials, knowing that it typically varies from approximately 8-20 m·s^-1. In addition, the optimization of the Al/CuO nanolaminate structure for burn rate maximization through machine learning takes a few milliseconds, against several days to achieve this task using a physical model, and months experimentally.

The promise of graphene-based transistors for democratizing multiomics studies

As biological research has synthesized genomics, proteomics, metabolomics, and transcriptomics into systems biology, a new multiomics approach to biological research has emerged. Today, multiomics studies are challenging and expensive. An experimental platform that could unify the multiple omics approaches to measurement could increase access to multiomics data by enabling more individual labs to successfully attempt multiomics studies. Field effect biosensing based on graphene transistors have gained significant attention as a potential unifying technology for such multiomics studies. This review article highlights the outstanding performance characteristics that makes graphene field effect transistor an attractive sensing platform for a wide variety of analytes important to system biology. In addition to many studies demonstrating the biosensing capabilities of graphene field effect transistors, they are uniquely suited to address the challenges of multiomics studies by providing an integrative multiplex platform for large scale manufacturing using the well-established processes of semiconductor industry. Furthermore, the resulting digital data is readily analyzable by machine learning to derive actionable biological insight to address the challenge of data compatibility for multiomics studies. A critical stage of systems biology will be democratizing multiomics study, and the graphene field effect transistor is uniquely positioned to serve as an accessible multiomics platform.

Identification of stress response proteins through fusion of machine learning models and statistical paradigms

Proteins are a vital component of cells that perform physiological functions to ensure smooth operations of bodily functions. Identification of a protein's function involves a detailed understanding of the structure of proteins. Stress proteins are essential mediators of several responses to cellular stress and are categorized based on their structural characteristics. These proteins are found to be conserved across many eukaryotic and prokaryotic linkages and demonstrate varied crucial functional activities inside a cell. The in-vivo, ex vivo, and in-vitro identification of stress proteins are a time-consuming and costly task. This study is aimed at the identification of stress protein sequences with the aid of mathematical modelling and machine learning methods to supplement the aforementioned wet lab methods. The model developed using Random Forest showed remarkable results with 91.1% accuracy while models based on neural network and support vector machine showed 87.7% and 47.0% accuracy, respectively. Based on evaluation results it was concluded that random-forest based classifier surpassed all other predictors and is suitable for use in practical applications for the identification of stress proteins. Live web server is available at http://biopred.org/stressprotiens , while the webserver code available is at https://github.com/abdullah5naveed/SRP_WebServer.git.

Machine learning-enabled predictive modeling to precisely identify the antimicrobial peptides

The ubiquitous antimicrobial peptides (AMPs), with a broad range of antimicrobial activities, represent a great promise for combating the multi-drug resistant infections. In this study, using a large and diverse set of AMPs (2638) and non-AMPs (3700), we have explored a variety of machine learning classifiers to build in silico models for AMP prediction, including Random Forest (RF), k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB), Quadratic Discriminant Analysis (QDA), and ensemble learning. Among the various models generated, the RF classifier-based model top-performed in both the internal [Accuracy: 91.40%, Precision: 89.37%, Sensitivity: 90.05%, and Specificity: 92.36%] and external validations [Accuracy: 89.43%, Precision: 88.92%, Sensitivity: 85.21%, and Specificity: 92.43%]. In addition, the RF classifier-based model correctly predicted the known AMPs and non-AMPs; those kept aside as an additional external validation set. The performance assessment revealed three features viz. ChargeD2001, PAAC12 (pseudo amino acid composition), and polarity T13 that are likely to play vital roles in the antimicrobial activity of AMPs. The developed RF-based classification model may further be useful in the design and prediction of the novel potential AMPs.

Assigning secondary structure in proteins using AI

Knowledge about protein structure assignment enriches the structural and functional understanding of proteins. Accurate and reliable structure assignment data is crucial for secondary structure prediction systems. Since the 1980s, various methods based on hydrogen bond analysis and atomic coordinate geometry, followed by machine learning, have been employed in protein structure assignment. However, the assignment process becomes challenging when missing atoms are present in the protein files. Our method proposed a multi-class classifier program named DLFSA for assigning protein secondary structure elements (SSE) using convolutional neural networks (CNNs). A fast and efficient GPU-based parallel procedure extracts fragments from protein files. The model implemented in this work is trained with a subset of the protein fragments and achieves 88.1% and 82.5% train and test accuracy, respectively. The model uses only C_α coordinates for secondary structure assignments. The model has been successfully tested on a few full-length proteins also. Results from the fragment-based studies demonstrate the feasibility of applying deep learning solutions for structure assignment problems.

SSA: Subset sum approach to protein β-sheet structure prediction

The three-dimensional structures of proteins provide their functions and incorrect folding of its β-strands can be the cause of many diseases. There are two major approaches for determining protein structures: computational prediction and experimental methods that employ technologies such as Cryo-electron microscopy. Due to experimental methods's high costs, extended wait times for its lengthy processes, and incompleteness of results, computational prediction is an attractive alternative. As the focus of the present paper, β-sheet structure prediction is a major portion of overall protein structure prediction. Prediction of other substructures, such as α-helices, is simpler with lower computational time complexities. Brute force methods are the most common approach and dynamic programming is also utilized to generate all possible conformations. The current study introduces the Subset Sum Approach (SSA) for the direct search space generation method, which is shown to outperform the dynamic programming approach in terms of both time and space. For the first time, the present work has calculated both the state space cardinality of the dynamic programming approach and the search space cardinality of the general brute force approaches. In regard to a set of pruning rules, SSA has demonstrated higher efficiency with respect to both time and accuracy in comparison to state-of-the-art methods.

Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

The new advances in deep learning methods have influenced many aspects of scientific research, including the study of the protein system. The prediction of proteins' 3D structural components is now heavily dependent on machine learning techniques that interpret how protein sequences and their homology govern the inter-residue contacts and structural organization. Especially, methods employing deep neural networks have had a significant impact on recent CASP13 and CASP14 competition. Here, we explore the recent applications of deep learning methods in the protein structure prediction area. We also look at the potential opportunities for deep learning methods to identify unknown protein structures and functions to be discovered and help guide drug-target interactions. Although significant problems still need to be addressed, we expect these techniques in the near future to play crucial roles in protein structural bioinformatics as well as in drug discovery.

Trends in application of advancing computational approaches in GPCR ligand discovery

G protein-coupled receptors (GPCRs) comprise the most important superfamily of protein targets in current ligand discovery and drug development. GPCRs are integral membrane proteins that play key roles in various cellular signaling processes. Therefore, GPCR signaling pathways are closely associated with numerous diseases, including cancer and several neurological, immunological, and hematological disorders. Computer-aided drug design (CADD) can expedite the process of GPCR drug discovery and potentially reduce the actual cost of research and development. Increasing knowledge of biological structures, as well as improvements on computer power and algorithms, have led to unprecedented use of CADD for the discovery of novel GPCR modulators. Similarly, machine learning approaches are now widely applied in various fields of drug target research. This review briefly summarizes the application of rising CADD methodologies, as well as novel machine learning techniques, in GPCR structural studies and bioligand discovery in the past few years. Recent novel computational strategies and feasible workflows are updated, and representative cases addressing challenging issues on olfactory receptors, biased agonism, and drug-induced cardiotoxic effects are highlighted to provide insights into future GPCR drug discovery.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

A Hybrid Levenberg-Marquardt Algorithm on a Recursive Neural Network for Scoring Protein Models

We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the Levenberg-Marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization.

Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples

The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.

A generalized machine-learning aided method for targeted identification of industrial enzymes from metagenome: A xylanase temperature dependence case study

Growing industrial utilization of enzymes and the increasing availability of metagenomic data highlight the demand for effective methods of targeted identification and verification of novel enzymes from various environmental microbiota. Xylanases are a class of enzymes with numerous industrial applications and are involved in the degradation of xylose, a component of lignocellulose. The optimum temperature of enzymes is an essential factor to be considered when choosing appropriate biocatalysts for a particular purpose. Therefore, in silico prediction of this attribute is a significant cost and time-effective step in the effort to characterize novel enzymes. The objective of this study was to develop a computational method to predict the thermal dependence of xylanases. This tool was then implemented for targeted screening of putative xylanases with specific thermal dependencies from metagenomic data and resulted in the identification of three novel xylanases from sheep and cow rumen microbiota. Here we present thermal activity prediction for xylanase, a new sequence-based machine learning method that has been trained using a selected combination of various protein features. This random forest classifier discriminates non-thermophilic, thermophilic, and hyper-thermophilic xylanases. The model's performance was evaluated through multiple iterations of sixfold cross-validations as well as holdout tests, and it is freely accessible as a web-service at arimees.com.

MCIC: Automated Identification of Cellulases From Metagenomic Data and Characterization Based on Temperature and pH Dependence

As the availability of high-throughput metagenomic data is increasing, agile and accurate tools are required to analyze and exploit this valuable and plentiful resource. Cellulose-degrading enzymes have various applications, and finding appropriate cellulases for different purposes is becoming increasingly challenging. An in silico screening method for high-throughput data can be of great assistance when combined with the characterization of thermal and pH dependence. By this means, various metagenomic sources with high cellulolytic potentials can be explored. Using a sequence similarity-based annotation and an ensemble of supervised learning algorithms, this study aims to identify and characterize cellulolytic enzymes from a given high-throughput metagenomic data based on optimum temperature and pH. The prediction performance of MCIC (metagenome cellulase identification and characterization) was evaluated through multiple iterations of sixfold cross-validation tests. This tool was also implemented for a comparative analysis of four metagenomic sources to estimate their cellulolytic profile and capabilities. For experimental validation of MCIC’s screening and prediction abilities, two identified enzymes from cattle rumen were subjected to cloning, expression, and characterization. To the best of our knowledge, this is the first time that a sequence-similarity based method is used alongside an ensemble machine learning model to identify and characterize cellulase enzymes from extensive metagenomic data. This study highlights the strength of machine learning techniques to predict enzymatic properties solely based on their sequence. MCIC is freely available as a python package and standalone toolkit for Windows and Linux-based operating systems with several functions to facilitate the screening and thermal and pH dependence prediction of cellulases.

Large-Scale Atomic Simulation via Machine Learning Potentials Constructed by Global Potential Energy Surface Exploration

Atomic simulations based on quantum mechanics (QM) calculations have entered into the tool box of chemists over the past few decades, facilitating an understanding of a wide range of chemistry problems, from structure characterization to reactivity determination. Due to the poor scaling and high computational cost intrinsic to QM calculations, one has to either sacrifice accuracy or time when performing large-scale atomic simulations. The battle to find a better compromise between accuracy and speed has been central to the development of new theoretical methods.The recent advances of machine-learning (ML)-based large-scale atomic simulations has shown great promise to the benefit of many branches of chemistry. Instead of solving the Schrödinger equation directly, ML-based simulations rely on a large data set of accurate potential energy surfaces (PESs) and complex numerical models to predict the total energy. These simulations feature both a high speed and a high accuracy for computing large systems. Due to the lack of a physical foundation in numerical models, ML models are often frustrated in their predictivity and robustness, which are key to applications. Focusing on these concerns, here we overview the recent advances in ML methodologies for atomic simulations on three key aspects. Namely, the generation of a representative data set, the extensity of ML models, and the continuity of data representation. While global optimization methods are the natural choice for building a representative data set, the stochastic surface walking method is shown to provide the desired PES sampling for both minima and transition regions on the PES. The current ML models generally utilize local geometrical descriptors as an input and consider the total energy as the sum of atomic energies. There are many flavors of data descriptors and ML models, but the applications for material and reaction predictions are still limited, not least because of the difficulty to train the associated vast global data sets. We show that our recently designed power-type structure descriptors together with a feed-forward neural network (NN) model are compatible with highly complex global PES data, which has led to a large family of global NN (G-NN) potentials.Two recent applications of G-NN potentials in material and reaction simulations are selected to illustrate how ML-based atomic simulations can help the discovery of new materials and reactions.

Artificial Intelligence and Machine learning based prediction of resistant and susceptible mutations in Mycobacterium tuberculosis

Tuberculosis (TB), an infectious disease caused by Mycobacterium tuberculosis (M.tb), causes highest number of deaths globally for any bacterial disease necessitating novel diagnosis and treatment strategies. High-throughput sequencing methods generate a large amount of data which could be exploited in determining multi-drug resistant (MDR-TB) associated mutations. The present work is a computational framework that uses artificial intelligence (AI) based machine learning (ML) approaches for predicting resistance in the genes rpoB, inhA, katG, pncA, gyrA and gyrB for the drugs rifampicin, isoniazid, pyrazinamide and fluoroquinolones. The single nucleotide variations were represented by several sequence and structural features that indicate the influence of mutations on the target protein coded by each gene. We used ML algorithms - naïve bayes, k nearest neighbor, support vector machine, and artificial neural network, to build the prediction models. The classification models had an average accuracy of 85% across all examined genes and were evaluated on an external unseen dataset to demonstrate their application. Further, molecular docking and molecular dynamics simulations were performed for wild type and predicted resistance causing mutant protein and anti-TB drug complexes to study their impact on the conformation of proteins to confirm the observed phenotype.

The Order-Disorder Continuum: Linking Predictions of Protein Structure and Disorder through Molecular Simulation

Intrinsically disordered proteins (IDPs) and intrinsically disordered regions within proteins (IDRs) serve an increasingly expansive list of biological functions, including regulation of transcription and translation, protein phosphorylation, cellular signal transduction, as well as mechanical roles. The strong link between protein function and disorder motivates a deeper fundamental characterization of IDPs and IDRs for discovering new functions and relevant mechanisms. We review recent advances in experimental techniques that have improved identification of disordered regions in proteins. Yet, experimentally curated disorder information still does not currently scale to the level of experimentally determined structural information in folded protein databases, and disorder predictors rely on several different binary definitions of disorder. To link secondary structure prediction algorithms developed for folded proteins and protein disorder predictors, we conduct molecular dynamics simulations on representative proteins from the Protein Data Bank, comparing secondary structure and disorder predictions with simulation results. We find that structure predictor performance from neural networks can be leveraged for the identification of highly dynamic regions within molecules, linked to disorder. Low accuracy structure predictions suggest a lack of static structure for regions that disorder predictors fail to identify. While disorder databases continue to expand, secondary structure predictors and molecular simulations can improve disorder predictor performance, which aids discovery of novel functions of IDPs and IDRs. These observations provide a platform for the development of new, integrated structural databases and fusion of prediction tools toward protein disorder characterization in health and disease.

Relevance of Machine Learning Techniques and Various Protein Features in Protein Fold Classification: A Review

Background:

Protein fold prediction is a fundamental step in Structural Bioinformatics. The tertiary structure of a protein determines its function and to predict its tertiary structure, fold prediction serves an important role. Protein fold is simply the arrangement of the secondary structure elements relative to each other in space. A number of studies have been carried out till date by different research groups working worldwide in this field by using the combination of different benchmark datasets, different types of descriptors, features and classification techniques.

Objective:

In this study, we have tried to put all these contributions together, analyze their study and to compare different techniques used by them.

Methods:

Different features are derived from protein sequence, its secondary structure, different physicochemical properties of amino acids, domain composition, Position Specific Scoring Matrix, profile and threading techniques.

Conclusion:

Combination of these different features can improve classification accuracy to a large extent. With the help of this survey, one can know the most suitable feature/attribute set and classification technique for this multi-class protein fold classification problem.

Protein secondary structure prediction improved by recurrent neural networks integrated with two-dimensional convolutional neural networks

Protein secondary structure prediction (PSSP) is an important research field in bioinformatics. The representation of protein sequence features could be treated as a matrix, which includes the amino-acid residue (time-step) dimension and the feature vector dimension. Common approaches to predict secondary structures only focus on the amino-acid residue dimension. However, the feature vector dimension may also contain useful information for PSSP. To integrate the information on both dimensions of the matrix, we propose a hybrid deep learning framework, two-dimensional convolutional bidirectional recurrent neural network (2C-BRNN), for improving the accuracy of 8-class secondary structure prediction. The proposed hybrid framework is to extract the discriminative local interactions between amino-acid residues by two-dimensional convolutional neural networks (2DCNNs), and then further capture long-range interactions between amino-acid residues by bidirectional gated recurrent units (BGRUs) or bidirectional long short-term memory (BLSTM). Specifically, our proposed 2C-BRNNs framework consists of four models: 2DConv-BGRUs, 2DCNN-BGRUs, 2DConv-BLSTM and 2DCNN-BLSTM. Among these four models, the 2DConv- models only contain two-dimensional (2D) convolution operations. Moreover, the 2DCNN- models contain 2D convolutional and pooling operations. Experiments are conducted on four public datasets. The experimental results show that our proposed 2DConv-BLSTM model performs significantly better than the benchmark models. Furthermore, the experiments also demonstrate that the proposed models can extract more meaningful features from the matrix of proteins, and the feature vector dimension is also useful for PSSP. The codes and datasets of our proposed methods are available at https://github.com/guoyanb/JBCB2018/ .

Machine Learning From Molecular Dynamics Trajectories to Predict Caspase-8 Inhibitors Against Alzheimer's Disease

Alzheimer’s disease (AD) is a neurodegenerative disorder in which the death of brain cells takes place leading to loss of memory and decreased cognitive ability. AD is a leading cause of death worldwide and is progressive in nature with symptoms worsening over time. Machine learning–based computational predictive models based on 2D and 3D descriptors have been effective in identifying potential active compounds. However, the use of data from molecular dynamics (MD) trajectories for training machine learning models still needs to be explored. In the present study, descriptors have been extracted from the MD trajectories of caspase-8 ligand complexes to train models using artificial neural networks and random forest algorithms. Caspase-8 plays a key role in causing AD by cleaving amyloid precursor proteins during apoptosis leading to increased formation of the amyloid-beta peptide. A total of 43 ligands were docked using the glide module of Schrodinger software, and short MD simulations of 10 ns were performed for the calculation of MD descriptors. The MD descriptors were also combined with the 2D and 3D descriptors of chemical compounds, and individual descriptor based as well as combination models were generated. This study demonstrated that MD descriptors could be effectively used for the characterization of bioactive compounds along with lead prioritization and optimization.

Survey of Machine Learning Techniques in Drug Discovery

Background:

Drug discovery, which is the process of discovering new candidate medications, is very important for pharmaceutical industries. At its current stage, discovering new drugs is still a very expensive and time-consuming process, requiring Phases I, II and III for clinical trials. Recently, machine learning techniques in Artificial Intelligence (AI), especially the deep learning techniques which allow a computational model to generate multiple layers, have been widely applied and achieved state-of-the-art performance in different fields, such as speech recognition, image classification, bioinformatics, etc. One very important application of these AI techniques is in the field of drug discovery.

Methods:

We did a large-scale literature search on existing scientific websites (e.g, ScienceDirect, Arxiv) and startup companies to understand current status of machine learning techniques in drug discovery.

Results:

Our experiments demonstrated that there are different patterns in machine learning fields and drug discovery fields. For example, keywords like prediction, brain, discovery, and treatment are usually in drug discovery fields. Also, the total number of papers published in drug discovery fields with machine learning techniques is increasing every year.

Conclusion:

The main focus of this survey is to understand the current status of machine learning techniques in the drug discovery field within both academic and industrial settings, and discuss its potential future applications. Several interesting patterns for machine learning techniques in drug discovery fields are discussed in this survey.

Computational advances in combating colloidal aggregation in drug discovery

Small molecule effectors are essential for drug discovery. Specific molecular recognition, reversible binding and dose-dependency are usually key requirements to ensure utility of a novel chemical entity. However, artefactual frequent-hitter and assay interference compounds may divert lead optimization and screening programmes towards attrition-prone chemical matter. Colloidal aggregates are the prime source of false positive readouts, either through protein sequestration or protein-scaffold mimicry. Nevertheless, assessment of colloidal aggregation remains somewhat overlooked and under-appreciated. In this Review, we discuss the impact of aggregation in drug discovery by analysing select examples from the literature and publicly-available datasets. We also examine and comment on technologies used to experimentally identify these potentially problematic entities. We focus on evidence-based computational filters and machine learning algorithms that may be swiftly deployed to flag chemical matter and mitigate the impact of aggregates in discovery programmes. We highlight the tools that can be used to scrutinize libraries, and identify and eliminate these problematic compounds.

Systems Biology and Machine Learning in Plant-Pathogen Interactions

Systems biology is an inclusive approach to study the static and dynamic emergent properties on a global scale by integrating multiomics datasets to establish qualitative and quantitative associations among multiple biological components. With an abundance of improved high throughput -omics datasets, network-based analyses and machine learning technologies are playing a pivotal role in comprehensive understanding of biological systems. Network topological features reveal most important nodes within a network as well as prioritize significant molecular components for diverse biological networks, including coexpression, protein-protein interaction, and gene regulatory networks. Machine learning techniques provide enormous predictive power through specific feature extraction from biological data. Deep learning, a subtype of machine learning, has plausible future applications because a domain expert for feature extraction is not needed in this algorithm. Inspired by diverse domains of biology, we here review classic systems biology techniques applied in plant immunity thus far. We also discuss additional advanced approaches in both graph theory and machine learning, which may provide new insights for understanding plant-microbe interactions. Finally, we propose a hybrid approach in plant immune systems that harnesses the power of both network biology and machine learning, with a potential to be applicable to both model systems and agronomically important crop plants.

How data science can advance mental health research

Accessibility of powerful computers and availability of so-called big data from a variety of sources means that data science approaches are becoming pervasive. However, their application in mental health research is often considered to be at an earlier stage than in other areas despite the complexity of mental health and illness making such a sophisticated approach particularly suitable. In this Perspective, we discuss current and potential applications of data science in mental health research using the UK Clinical Research Collaboration classification: underpinning research; aetiology; detection and diagnosis; treatment development; treatment evaluation; disease management; and health services research. We demonstrate that data science is already being widely applied in mental health research, but there is much more to be done now and in the future. The possibilities for data science in mental health research are substantial.

Deep Learning in Biomedical Data Science

Since the 1980s, deep learning and biomedical data have been coevolving and feeding each other. The breadth, complexity, and rapidly expanding size of biomedical data have stimulated the development of novel deep learning methods, and application of these methods to biomedical data have led to scientific discoveries and practical solutions. This overview provides technical and historical pointers to the field, and surveys current applications of deep learning to biomedical data organized around five subareas, roughly of increasing spatial scale: chemoinformatics, proteomics, genomics and transcriptomics, biomedical imaging, and health care. The black box problem of deep learning methods is also briefly discussed.

Protein alignment based on higher order conditional random fields for template-based modeling

The query-template alignment of proteins is one of the most critical steps of template-based modeling methods used to predict the 3D structure of a query protein. This alignment can be interpreted as a temporal classification or structured prediction task and first order Conditional Random Fields have been proposed for protein alignment and proven to be rather successful. Some other popular structured prediction problems, such as speech or image classification, have gained from the use of higher order Conditional Random Fields due to the well known higher order correlations that exist between their labels and features. In this paper, we propose and describe the use of higher order Conditional Random Fields for query-template protein alignment. The experiments carried out on different public datasets validate our proposal, especially on distantly-related protein pairs which are the most difficult to align.

PyBioMed: a python library for various molecular representations of chemicals, proteins and DNAs and their interactions

Background

With the increasing development of biotechnology and informatics technology, publicly available data in chemistry and biology are undergoing explosive growth. Such wealthy information in these data needs to be extracted and transformed to useful knowledge by various data mining methods. Considering the amazing rate at which data are accumulated in chemistry and biology fields, new tools that process and interpret large and complex interaction data are increasingly important. So far, there are no suitable toolkits that can effectively link the chemical and biological space in view of molecular representation. To further explore these complex data, an integrated toolkit for various molecular representation is urgently needed which could be easily integrated with data mining algorithms to start a full data analysis pipeline.

Results

Herein, the python library PyBioMed is presented, which comprises functionalities for online download for various molecular objects by providing different IDs, the pretreatment of molecular structures, the computation of various molecular descriptors for chemicals, proteins, DNAs and their interactions. PyBioMed is a feature-rich and highly customized python library used for the characterization of various complex chemical and biological molecules and interaction samples. The current version of PyBioMed could calculate 775 chemical descriptors and 19 kinds of chemical fingerprints, 9920 protein descriptors based on protein sequences, more than 6000 DNA descriptors from nucleotide sequences, and interaction descriptors from pairwise samples using three different combining strategies. Several examples and five real-life applications were provided to clearly guide the users how to use PyBioMed as an integral part of data analysis projects. By using PyBioMed, users are able to start a full pipelining from getting molecular data, pretreating molecules, molecular representation to constructing machine learning models conveniently.

Conclusion

PyBioMed provides various user-friendly and highly customized APIs to calculate various features of biological molecules and complex interaction samples conveniently, which aims at building integrated analysis pipelines from data acquisition, data checking, and descriptor calculation to modeling. PyBioMed is freely available at http://projects.scbdd.com/pybiomed.html.

Computational and Experimental Approaches to Predict Host-Parasite Protein-Protein Interactions

In host-parasite systems, protein-protein interactions are key to allow the pathogen to enter the host and persist within the host. The study of host-parasite molecular communication improves the understanding the mechanisms of infection, evasion of the host immune system and tropism across different tissues. Current trends in parasitology focus on unraveling host-parasite protein-protein interactions to aid the development of new strategies to combat pathogenic parasites with better treatments and prevention mechanisms. Due to the complexity of capturing experimentally these interactions, computational approaches integrating data from different sources (mainly "omics" data) become key to complement or support experimental approaches. Here, we focus on the application of experimental and computational methods in the prediction of host-parasite interactions and highlight the potential of each of these methods in specific contexts.

ChemSAR: an online pipelining platform for molecular SAR modeling

Background

In recent years, predictive models based on machine learning techniques have proven to be feasible and effective in drug discovery. However, to develop such a model, researchers usually have to combine multiple tools and undergo several different steps (e.g., RDKit or ChemoPy package for molecular descriptor calculation, ChemAxon Standardizer for structure preprocessing, scikit-learn package for model building, and ggplot2 package for statistical analysis and visualization, etc.). In addition, it may require strong programming skills to accomplish these jobs, which poses severe challenges for users without advanced training in computer programming. Therefore, an online pipelining platform that integrates a number of selected tools is a valuable and efficient solution that can meet the needs of related researchers.

Results

This work presents a web-based pipelining platform, called ChemSAR, for generating SAR classification models of small molecules. The capabilities of ChemSAR include the validation and standardization of chemical structure representation, the computation of 783 1D/2D molecular descriptors and ten types of widely-used fingerprints for small molecules, the filtering methods for feature selection, the generation of predictive models via a step-by-step job submission process, model interpretation in terms of feature importance and tree visualization, as well as a helpful report generation system. The results can be visualized as high-quality plots and downloaded as local files.

Conclusion

ChemSAR provides an integrated web-based platform for generating SAR classification models that will benefit cheminformatics and other biomedical users. It is freely available at: http://chemsar.scbdd.com.Graphical abstract

Use of machine learning approaches for novel drug discovery

INTRODUCTION

The use of computational tools in the early stages of drug development has increased in recent decades. Machine learning (ML) approaches have been of special interest, since they can be applied in several steps of the drug discovery methodology, such as prediction of target structure, prediction of biological activity of new ligands through model construction, discovery or optimization of hits, and construction of models that predict the pharmacokinetic and toxicological (ADMET) profile of compounds.

AREAS COVERED

This article presents an overview on some applications of ML techniques in drug design. These techniques can be employed in ligand-based drug design (LBDD) and structure-based drug design (SBDD) studies, such as similarity searches, construction of classification and/or prediction models of biological activity, prediction of secondary structures and binding sites docking and virtual screening.

EXPERT OPINION

Successful cases have been reported in the literature, demonstrating the efficiency of ML techniques combined with traditional approaches to study medicinal chemistry problems. Some ML techniques used in drug design are: support vector machine, random forest, decision trees and artificial neural networks. Currently, an important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.

A new protein structure representation for efficient protein function prediction

One of the challenging problems in bioinformatics is the prediction of protein function. Protein function is the main key that can be used to classify different proteins. Protein function can be inferred experimentally with very small throughput or computationally with very high throughput. Computational methods are sequence based or structure based. Structure-based methods produce more accurate protein function prediction. In this article, we propose a new protein structure representation for efficient protein function prediction. The representation is based on three-dimensional patterns of protein residues. In the analysis, we used protein function based on enzyme activity through six mechanistically diverse enzyme superfamilies: amidohydrolase, crotonase, haloacid dehalogenase, isoprenoid synthase type I, and vicinal oxygen chelate. We applied three different classification methods, naïve Bayes, k-nearest neighbors, and random forest, to predict the enzyme superfamily of a given protein. The prediction accuracy using the proposed representation outperforms a recently introduced representation method that is based only on the distance patterns. The results show that the proposed representation achieved prediction accuracy up to 98%, with improvement of about 10% on average.

Improving protein fold recognition by random forest

BACKGROUND

Recognizing the correct structural fold among known template protein structures for a target protein (i.e. fold recognition) is essential for template-based protein structure modeling. Since the fold recognition problem can be defined as a binary classification problem of predicting whether or not the unknown fold of a target protein is similar to an already known template protein structure in a library, machine learning methods have been effectively applied to tackle this problem. In our work, we developed RF-Fold that uses random forest - one of the most powerful and scalable machine learning classification methods - to recognize protein folds.

RESULTS

RF-Fold consists of hundreds of decision trees that can be trained efficiently on very large datasets to make accurate predictions on a highly imbalanced dataset. We evaluated RF-Fold on the standard Lindahl's benchmark dataset comprised of 976 × 975 target-template protein pairs through cross-validation. Compared with 17 different fold recognition methods, the performance of RF-Fold is generally comparable to the best performance in fold recognition of different difficulty ranging from the easiest family level, the medium-hard superfamily level, and to the hardest fold level. Based on the top-one template protein ranked by RF-Fold, the correct recognition rate is 84.5%, 63.4%, and 40.8% at family, superfamily, and fold levels, respectively. Based on the top-five template protein folds ranked by RF-Fold, the correct recognition rate increases to 91.5%, 79.3% and 58.3% at family, superfamily, and fold levels.

CONCLUSIONS

The good performance achieved by the RF-Fold demonstrates the random forest's effectiveness for protein fold recognition.

Computational evolutionary analysis of the overlapped surface (S) and polymerase (P) region in hepatitis B virus indicates the spacer domain in P is crucial for survival

Introduction

The Hepatitis B Virus (HBV) genome contains four ORFs, S (surface), P (polymerase), C (core) and X. S is completely overlapped by P and as a consequence the overlapping region is subject to distinctive evolutionary constraints compared to the remainder of the genome. Specifically, a non-synonymous substitution in one coding frame may produce a synonymous substitution in the alternative frame, suggesting a possible conflict between requirements for diversifying and purifying forces. To examine how these contrasting requirements are balanced within this region, we investigated the relationship amongst positive selection sites, conserved regions, epitopes and elements of protein structure to consider how HBV balances the contrasting evolutionary pressures.

Methodology/Results

323 HBV genotype D genome sequences were collected and analyzed to identify sites under positive selection and highly conserved regions. Epitopes sequences were retrieved from previously published experimental studies stored in the Immune Epitope Database. Predicted secondary structures were used to investigate the association between structure and conservation. Entropy was used as a measure of conservation and bivariate logistic regression was used to investigate the relationship between positive selection/conserved sites and epitope/secondary structure regions. Our results indicate: (i) conservation in S is primarily dictated by α-helix elements in the protein structure, (ii) variable residues are mainly located in PreS, the major hydrophilic region (MHR) and the C-terminus, (iii) epitopes in S, which are directly targeted by the host immune system, are significantly associated with sites under positive selection.

Conclusions

The highly variable spacer domain in P, which corresponds to PreS in S, appears to act as a harbor for the accumulation of mutations that can provide flexibility for conformational changes and responding to immune pressure.