Modelling ligand selectivity of serine proteases using integrative proteochemometric approaches improves model performance and allows the multi-target dependent interpretation of features

PSnpBind-ML: predicting the effect of binding site mutations on protein-ligand binding affinity

Protein mutations, especially those which occur in the binding site, play an important role in inter-individual drug response and may alter binding affinity and thus impact the drug's efficacy and side effects. Unfortunately, large-scale experimental screening of ligand-binding against protein variants is still time-consuming and expensive. Alternatively, in silico approaches can play a role in guiding those experiments. Methods ranging from computationally cheaper machine learning (ML) to the more expensive molecular dynamics have been applied to accurately predict the mutation effects. However, these effects have been mostly studied on limited and small datasets, while ideally a large dataset of binding affinity changes due to binding site mutations is needed. In this work, we used the PSnpBind database with six hundred thousand docking experiments to train a machine learning model predicting protein-ligand binding affinity for both wild-type proteins and their variants with a single-point mutation in the binding site. A numerical representation of the protein, binding site, mutation, and ligand information was encoded using 256 features, half of them were manually selected based on domain knowledge. A machine learning approach composed of two regression models is proposed, the first predicting wild-type protein-ligand binding affinity while the second predicting the mutated protein-ligand binding affinity. The best performing models reported an RMSE value within 0.5 [Formula: see text] 0.6 kcal/mol^-1 on an independent test set with an R² value of 0.87 [Formula: see text] 0.90. We report an improvement in the prediction performance compared to several reported models developed for protein-ligand binding affinity prediction. The obtained models can be used as a complementary method in early-stage drug discovery. They can be applied to rapidly obtain a better overview of the ligand binding affinity changes across protein variants carried by people in the population and narrow down the search space where more time-demanding methods can be used to identify potential leads that achieve a better affinity for all protein variants.

How to approach machine learning-based prediction of drug/compound-target interactions

The identification of drug/compound-target interactions (DTIs) constitutes the basis of drug discovery, for which computational predictive approaches have been developed. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as a pair at the input level and processes them via statistical/machine learning. The representation of input samples (i.e., proteins and their ligands) in the form of quantitative feature vectors is crucial for the extraction of interaction-related properties during the artificial learning and subsequent prediction of DTIs. Lately, the representation learning approach, in which input samples are automatically featurized via training and applying a machine/deep learning model, has been utilized in biomedical sciences. In this study, we performed a comprehensive investigation of different computational approaches/techniques for protein featurization (including both conventional approaches and the novel learned embeddings), data preparation and exploration, machine learning-based modeling, and performance evaluation with the aim of achieving better data representations and more successful learning in DTI prediction. For this, we first constructed realistic and challenging benchmark datasets on small, medium, and large scales to be used as reliable gold standards for specific DTI modeling tasks. We developed and applied a network analysis-based splitting strategy to divide datasets into structurally different training and test folds. Using these datasets together with various featurization methods, we trained and tested DTI prediction models and evaluated their performance from different angles. Our main findings can be summarized under 3 items: (i) random splitting of datasets into train and test folds leads to near-complete data memorization and produce highly over-optimistic results, as a result, should be avoided, (ii) learned protein sequence embeddings work well in DTI prediction and offer high potential, despite interaction-related properties (e.g., structures) of proteins are unused during their self-supervised model training, and (iii) during the learning process, PCM models tend to rely heavily on compound features while partially ignoring protein features, primarily due to the inherent bias in DTI data, indicating the requirement for new and unbiased datasets. We hope this study will aid researchers in designing robust and high-performing data-driven DTI prediction systems that have real-world translational value in drug discovery.

In silico investigations of some Cyperus rotundus compounds as potential anti-inflammatory inhibitors of 5-LO and LTA4H enzymes

The present study aimed to experimentally identify the essential oil of Algerian Cyperus rotundus L. and to model the interaction of some known anti-inflammatory molecules with two key enzymes involved in inflammation, 5-Lypoxygenase (5-LO) and leukotriene A4 hydrolase (LTA4H). Gas chromatography/gas chromatography-mass spectrometry (GC/GC-MS) revealed that 92.7% of the essential oil contains 35 compounds, including oxygenated sesquiterpenes (44.2%), oxygenated monoterpenes (30.2%), monoterpene hydrocarbons (11.8%) and sesquiterpene hydrocarbons (6.5%). The major identified oxygenated terpenes are humulene oxide II, caryophyllene oxide, khusinol, agarospirol, spathulinol and trans-pinocarveol Myrtenol and α-terpineol are known to exhibit anti-inflammatory activities. Several complexes obtained after docking the natural terpenes with 5-LO and LTA4H have shown strong hydrogen bonding interactions. The best docking energies were found with α-terpineol, Myrtenol and khusinol. The interaction between the natural products and amino-acid residues HIS367, ILE673 and GLN363 appears to be critical for 5-LO inhibition, while the interaction with residues GLU271, HIS295, TYR383, TYR378, GLU318, GLU296 and ASP375 is critical for LTA4H inhibition. Molecular dynamics (MD) trajectories of the selected docked complexes showed stable backbone root mean square deviation (RMSD), supporting the stability of the natural product-enzyme interaction.Communicated by Ramaswamy H. Sarma.

Development of a proteochemometric-based support vector machine model for predicting bioactive molecules of tubulin receptors

Microtubules are receiving enormous interest in drug discovery due to the important roles they play in cellular functions. Targeting tubulin polymerization presents an excellent opportunity for the development of anti-tubulin drugs. Drug resistance and high toxicity of currently used tubulin-binding agents have necessitated the pursuit of novel drug candidates with increased therapeutic potency. The design of novel drug candidates can be achieved using efficient computational techniques to support existing efforts. Proteochemometric (PCM) modeling is a computational technique that can be employed to elucidate the bioactivity relations between related targets and multiple ligands. We have developed a PCM-based Support Vector Machine (SVM) approach for predicting the bioactivity between tubulin receptors and small, drug-like molecules. The bioactivity datasets used for training the SVM algorithm were obtained from the Binding DB database. The SVM-based PCM model yielded a good overall predictive performance with an area under the curve (AUC) of 87%, Matthews correlation coefficient (MCC) of 72%, overall accuracy of 93%, and a classification error of 7%. The algorithm allows the prediction of the likelihood of new interactions based on confidence scores between the query datasets, comprising ligands in SMILES format and protein sequences of tubulin targets. The algorithm has been implemented as a web server known as TubPred, accessible via http://35.167.90.225:5000/ .

Prediction of Protein-ligand Interaction Based on Sequence Similarity and Ligand Structural Features

Computationally predicting the interaction of proteins and ligands presents three main directions: the search of new target proteins for ligands, the search of new ligands for targets, and predicting the interaction of new proteins and new ligands. We proposed an approach providing the fuzzy classification of protein sequences based on the ligand structural features to analyze the latter most complicated case. We tested our approach on five protein groups, which represented promised targets for drug-like ligands and differed in functional peculiarities. The training sets were built with the original procedure overcoming the data ambiguity. Our study showed the effective prediction of new targets for ligands with an average accuracy of 0.96. The prediction of new ligands for targets displayed the average accuracy 0.95; accuracy estimates were close to our previous results, comparable in accuracy to those of other methods or exceeded them. Using the fuzzy coefficients reflecting the target-to-ligand specificity, we provided predicting interactions for new proteins and new ligands; the obtained accuracy values from 0.89 to 0.99 were acceptable for such a sophisticated task. The protein kinase family case demonstrated the ability to account for subtle features of proteins and ligands required for the specificity of protein–ligand interaction.

Prediction of Protein-Ligand Interaction Based on the Positional Similarity Scores Derived from Amino Acid Sequences

The affinity of different drug-like ligands to multiple protein targets reflects general chemical–biological interactions. Computational methods estimating such interactions analyze the available information about the structure of the targets, ligands, or both. Prediction of protein–ligand interactions based on pairwise sequence alignment provides reasonable accuracy if the ligands’ specificity well coincides with the phylogenic taxonomy of the proteins. Methods using multiple alignment require an accurate match of functionally significant residues. Such conditions may not be met in the case of diverged protein families. To overcome these limitations, we propose an approach based on the analysis of local sequence similarity within the set of analyzed proteins. The positional scores, calculated by sequence fragment comparisons, are used as input data for the Bayesian classifier. Our approach provides a prediction accuracy comparable or exceeding those of other methods. It was demonstrated on the popular Gold Standard test sets, presenting different sequence heterogeneity and varying from the group, including different protein families to the more specific groups. A reasonable prediction accuracy was also found for protein kinases, displaying weak relationships between sequence phylogeny and inhibitor specificity. Thus, our method can be applied to the broad area of protein–ligand interactions.

Current computational methods for predicting protein interactions of natural products

Natural products (NPs) are an indispensable source of drugs and they have a better coverage of the pharmacological space than synthetic compounds, owing to their high structural diversity. The prediction of their interaction profiles with druggable protein targets remains a major challenge in modern drug discovery. Experimental (off-)target predictions of NPs are cost- and time-consuming, whereas computational methods, on the other hand, are much faster and cheaper. As a result, computational predictions are preferentially used in the first instance for NP profiling, prior to experimental validations. This review covers recent advances in computational approaches which have been developed to aid the annotation of unknown drug-target interactions (DTIs), by focusing on three broad classes, namely: ligand-based, target-based, and target-ligand-based (hybrid) approaches. Computational DTI prediction methods have the potential to significantly advance the discovery and development of novel selective drugs exhibiting minimal side effects. We highlight some inherent caveats of these methods which must be overcome to enable them to realize their full potential, and a future outlook is given.

Novel Consensus Architecture To Improve Performance of Large-Scale Multitask Deep Learning QSAR Models

Advances in the development of high-throughput screening and automated chemistry have rapidly accelerated the production of chemical and biological data, much of them freely accessible through literature aggregator services such as ChEMBL and PubChem. Here, we explore how to use this comprehensive mapping of chemical biology space to support the development of large-scale quantitative structure-activity relationship (QSAR) models. We propose a new deep learning consensus architecture (DLCA) that combines consensus and multitask deep learning approaches together to generate large-scale QSAR models. This method improves knowledge transfer across different target/assays while also integrating contributions from models based on different descriptors. The proposed approach was validated and compared with proteochemometrics, multitask deep learning, and Random Forest methods paired with various descriptors types. DLCA models demonstrated improved prediction accuracy for both regression and classification tasks. The best models together with their modeling sets are provided through publicly available web services at https://predictor.ncats.io .

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

Learning from the ligand: using ligand-based features to improve binding affinity prediction

Motivation

Machine learning scoring functions for protein–ligand binding affinity prediction have been found to consistently outperform classical scoring functions. Structure-based scoring functions for universal affinity prediction typically use features describing interactions derived from the protein–ligand complex, with limited information about the chemical or topological properties of the ligand itself.

Results

We demonstrate that the performance of machine learning scoring functions are consistently improved by the inclusion of diverse ligand-based features. For example, a Random Forest (RF) combining the features of RF-Score v3 with RDKit molecular descriptors achieved Pearson correlation coefficients of up to 0.836, 0.780 and 0.821 on the PDBbind 2007, 2013 and 2016 core sets, respectively, compared to 0.790, 0.746 and 0.814 when using the features of RF-Score v3 alone. Excluding proteins and/or ligands that are similar to those in the test sets from the training set has a significant effect on scoring function performance, but does not remove the predictive power of ligand-based features. Furthermore a RF using only ligand-based features is predictive at a level similar to classical scoring functions and it appears to be predicting the mean binding affinity of a ligand for its protein targets.

Availability and implementation

Data and code to reproduce all the results are freely available at http://opig.stats.ox.ac.uk/resources.

Supplementary information

Supplementary data are available at Bioinformatics online.

In Silico Studies in Drug Research Against Neurodegenerative Diseases

Background

Neurodegenerative diseases such as Alzheimer's disease (AD), amyotrophic lateral sclerosis, Parkinson's disease (PD), spinal cerebellar ataxias, and spinal and bulbar muscular atrophy are described by slow and selective degeneration of neurons and axons in the central nervous system (CNS) and constitute one of the major challenges of modern medicine. Computer-aided or in silico drug design methods have matured into powerful tools for reducing the number of ligands that should be screened in experimental assays.

Methods

In the present review, the authors provide a basic background about neurodegenerative diseases and in silico techniques in the drug research. Furthermore, they review the various in silico studies reported against various targets in neurodegenerative diseases, including homology modeling, molecular docking, virtual high-throughput screening, quantitative structure activity relationship (QSAR), hologram quantitative structure activity relationship (HQSAR), 3D pharmacophore mapping, proteochemometrics modeling (PCM), fingerprints, fragment-based drug discovery, Monte Carlo simulation, molecular dynamic (MD) simulation, quantum-mechanical methods for drug design, support vector machines, and machine learning approaches.

Results

Detailed analysis of the recently reported case studies revealed that the majority of them use a sequential combination of ligand and structure-based virtual screening techniques, with particular focus on pharmacophore models and the docking approach.

Conclusion

Neurodegenerative diseases have a multifactorial pathoetiological origin, so scientists have become persuaded that a multi-target therapeutic strategy aimed at the simultaneous targeting of multiple proteins (and therefore etiologies) involved in the development of a disease is recommended in future.

Kinome-Wide Profiling Prediction of Small Molecules

Extensive kinase profiling data, covering more than half of the human kinome, are available nowadays and allow the construction of activity prediction models of high practical utility. Proteochemometric (PCM) approaches use compound and protein descriptors, which enables the extrapolation of bioactivity values to thus far unexplored kinases. In this study, the potential of PCM to make large-scale predictions on the entire kinome is explored, considering the applicability on novel compounds and kinases, including clinically relevant mutants. A rigorous validation indicates high predictive power on left-out kinases and superiority over individual kinase QSAR models for new compounds. Furthermore, external validation on clinically relevant mutant kinases reveals an excellent predictive power for mutations spread across the ATP binding site.

3D proteochemometrics: using three-dimensional information of proteins and ligands to address aspects of the selectivity of serine proteases

The high similarity between certain sub-pockets of serine proteases may lead to low selectivity of protease inhibitors. Therefore the application of proteochemometrics (PCM), which quantifies the relationship between protein/ligand descriptors and affinity for multiple ligands and targets simultaneously, is useful to understand and improve the selectivity profiles of potential inhibitors. In this study, protein field-based PCM that uses knowledge-based and WaterMap derived fields to describe proteins in combination with 2D (RDKit and MOE fingerprints) and 3D (4 point pharmacophoric fingerprints and GRIND) ligand descriptors was used to model the bioactivities of 24 homologous serine proteases and 5863 inhibitors in an integrated fashion. Of the multiple field-based PCM models generated based on different ligand descriptors, RDKit fingerprints showed the best performance in terms of external prediction with Rtest2 of 0.72 and RMSEP of 0.81. Further, visual interpretation of the models highlights sub-pocket specific regions that influence affinity and selectivity of serine protease inhibitors.

Analysis of Differential Efficacy and Affinity of GABAA (α1/α2) Selective Modulators

Selective modulators of the γ-amino butyric acid (GABA_A) family of receptors have the potential to treat a range of disease states related to cognition, pain, and anxiety. While the development of various α subunit-selective modulators is currently underway for the treatment of anxiety disorders, a mechanistic understanding of the correlation between their bioactivity and efficacy, based on ligand-target interactions, is currently still lacking. In order to alleviate this situation, in the current study we have analyzed, using ligand- and structure-based methods, a data set of 5440 GABA_A modulators. The Spearman correlation (ρ) between binding activity and efficacy of compounds was calculated to be 0.008 and 0.31 against the α1 and α2 subunits of GABA receptor, respectively; in other words, the compounds had little diversity in structure and bioactivity, but they differed significantly in efficacy. Two compounds were selected as a case study for detailed interaction analysis due to the small difference in their structures and affinities (ΔpK_{i(comp1_α1 - comp2_α1)} = 0.45 log units, ΔpK_{i(comp1_α2 - comp2_α2)} = 0 log units) as compared to larger relative efficacies (ΔRE_{(comp1_α1 - comp2_α1)} = 1.03, ΔRE_{(comp1_α2 - comp2_α2)} = 0.21). Docking analysis suggested that His-101 is involved in a characteristic interaction of the α1 receptor with both compounds 1 and 2. Residues such as Phe-77, Thr-142, Asn-60, and Arg-144 of the γ chain of the α1γ2 complex also showed interactions with heterocyclic rings of both compounds 1 and 2, but these interactions were disturbed in the case of α2γ2 complex docking results. Binding pocket stability analysis based on molecular dynamics identified three substitutions in the loop C region of the α2 subunit, namely, G200E, I201T, and V202I, causing a reduction in the flexibility of α2 compared to α1. These amino acids in α2, as compared to α1, were also observed to decrease the vibrational and dihedral entropy and to increase the hydrogen bond content in α2 in the apo state. However, freezing of both α1 and α2 was observed in the ligand-bound state, with an increased number of internal hydrogen bonds and increased entropy. Therefore, we hypothesize that the amino acid differences in the loop C region of α2 are responsible for conformational changes in the protein structure compared to α1, as well as for the binding modes of compounds and hence their functional signaling.

Drug Design for CNS Diseases: Polypharmacological Profiling of Compounds Using Cheminformatic, 3D-QSAR and Virtual Screening Methodologies

HIGHLIGHTS

Many CNS targets are being explored for multi-target drug design

New databases and cheminformatic methods enable prediction of primary pharmaceutical target and off-targets of compounds

QSAR, virtual screening and docking methods increase the potential of rational drug design

The diverse cerebral mechanisms implicated in Central Nervous System (CNS) diseases together with the heterogeneous and overlapping nature of phenotypes indicated that multitarget strategies may be appropriate for the improved treatment of complex brain diseases. Understanding how the neurotransmitter systems interact is also important in optimizing therapeutic strategies. Pharmacological intervention on one target will often influence another one, such as the well-established serotonin-dopamine interaction or the dopamine-glutamate interaction. It is now accepted that drug action can involve plural targets and that polypharmacological interaction with multiple targets, to address disease in more subtle and effective ways, is a key concept for development of novel drug candidates against complex CNS diseases. A multi-target therapeutic strategy for Alzheimer‘s disease resulted in the development of very effective Multi-Target Designed Ligands (MTDL) that act on both the cholinergic and monoaminergic systems, and also retard the progression of neurodegeneration by inhibiting amyloid aggregation. Many compounds already in databases have been investigated as ligands for multiple targets in drug-discovery programs. A probabilistic method, the Parzen-Rosenblatt Window approach, was used to build a “predictor” model using data collected from the ChEMBL database. The model can be used to predict both the primary pharmaceutical target and off-targets of a compound based on its structure. Several multi-target ligands were selected for further study, as compounds with possible additional beneficial pharmacological activities. Based on all these findings, it is concluded that multipotent ligands targeting AChE/MAO-A/MAO-B and also D₁-R/D₂-R/5-HT_2A-R/H₃-R are promising novel drug candidates with improved efficacy and beneficial neuroleptic and procognitive activities in treatment of Alzheimer's and related neurodegenerative diseases. Structural information for drug targets permits docking and virtual screening and exploration of the molecular determinants of binding, hence facilitating the design of multi-targeted drugs. The crystal structures and models of enzymes of the monoaminergic and cholinergic systems have been used to investigate the structural origins of target selectivity and to identify molecular determinants, in order to design MTDLs.

Bioalerts: a python library for the derivation of structural alerts from bioactivity and toxicity data sets

BACKGROUND

Assessing compound toxicity at early stages of the drug discovery process is a crucial task to dismiss drug candidates likely to fail in clinical trials. Screening drug candidates against structural alerts, i.e. chemical fragments associated to a toxicological response prior or after being metabolized (bioactivation), has proved a valuable approach for this task. During the last decades, diverse algorithms have been proposed for the automatic derivation of structural alerts from categorical toxicity data sets.

RESULTS AND CONCLUSIONS

Here, the python library bioalerts is presented, which comprises functionalities for the automatic derivation of structural alerts from categorical (dichotomous), e.g. toxic/non-toxic, and continuous bioactivity data sets, e.g. [Formula: see text] or [Formula: see text] values. The library bioalerts relies on the RDKit implementation of the circular Morgan fingerprint algorithm to compute chemical substructures, which are derived by considering radial atom neighbourhoods of increasing bond radius. In addition to the derivation of structural alerts, bioalerts provides functionalities for the calculation of unhashed (keyed) Morgan fingerprints, which can be used in predictive bioactivity modelling with the advantage of allowing for a chemically meaningful deconvolution of the chemical space. Finally, bioalerts provides functionalities for the easy visualization of the derived structural alerts.

The recent progress in proteochemometric modelling: focusing on target descriptors, cross-term descriptors and application scope

As an extension of the conventional quantitative structure activity relationship models, proteochemometric (PCM) modelling is a computational method that can predict the bioactivity relations between multiple ligands and multiple targets. Traditional PCM modelling includes three essential elements: descriptors (including target descriptors, ligand descriptors and cross-term descriptors), bioactivity data and appropriate learning functions that link the descriptors to the bioactivity data. Since its appearance, PCM modelling has developed rapidly over the past decade by taking advantage of the progress of different descriptors and machine learning techniques, along with the increasing amounts of available bioactivity data. Specifically, the new emerging target descriptors and cross-term descriptors not only significantly increased the performance of PCM modelling but also expanded its application scope from traditional protein-ligand interaction to more abundant interactions, including protein-peptide, protein-DNA and even protein-protein interactions. In this review, target descriptors and cross-term descriptors, as well as the corresponding application scope, are intensively summarized. Additionally, we look forward to seeing PCM modelling extend into new application scopes, such as Target-Catalyst-Ligand systems, with the further development of descriptors, machine learning techniques and increasing amounts of available bioactivity data.