Chemical Similarity Searching

GuacaMol: Benchmarking Models for de Novo Molecular Design

De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, models for molecular design based on neural networks appeared recently and show promising results. However, the new models have not been profiled on consistent tasks, and comparative studies to well-established algorithms have only seldom been performed. To standardize the assessment of both classical and neural models for de novo molecular design, we propose an evaluation framework, GuacaMol, based on a suite of standardized benchmarks. The benchmark tasks encompass measuring the fidelity of the models to reproduce the property distribution of the training sets, the ability to generate novel molecules, the exploration and exploitation of chemical space, and a variety of single and multiobjective optimization tasks. The benchmarking open-source Python code and a leaderboard can be found on https://benevolent.ai/guacamol .

Introduction to cheminformatics for green chemistry education

The tools of cheminformatics are used for describing chemical structures for use in computer databases and in analyzing the connections between structure and molecular properties. As several aspects of Green Chemistry are also concerned with structure, properties and the relationships between them, cheminformatics provides tools that can be valuable in the teaching of Green Chemistry. This paper will provide an introduction to cheminformatics with a special emphasis on its value in chemical education and Green Chemistry.

Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations

There has been a recent surge of interest in using machine learning across chemical space in order to predict properties of molecules or design molecules and materials with the desired properties. Most of this work relies on defining clever feature representations, in which the chemical graph structure is encoded in a uniform way such that predictions across chemical space can be made. In this work, we propose to exploit the powerful ability of deep neural networks to learn a feature representation from low-level encodings of a huge corpus of chemical structures. Our model borrows ideas from neural machine translation: it translates between two semantically equivalent but syntactically different representations of molecular structures, compressing the meaningful information both representations have in common in a low-dimensional representation vector. Once the model is trained, this representation can be extracted for any new molecule and utilized as a descriptor. In fair benchmarks with respect to various human-engineered molecular fingerprints and graph-convolution models, our method shows competitive performance in modelling quantitative structure-activity relationships in all analysed datasets. Additionally, we show that our descriptor significantly outperforms all baseline molecular fingerprints in two ligand-based virtual screening tasks. Overall, our descriptors show the most consistent performances in all experiments. The continuity of the descriptor space and the existence of the decoder that permits deducing a chemical structure from an embedding vector allow for exploration of the space and open up new opportunities for compound optimization and idea generation.

An analysis of characterized plant sesquiterpene synthases

Plants exhibit a vast array of sesquiterpenes, C15 hydrocarbons which often function as herbivore-repellents or pollinator-attractants. These in turn are produced by a diverse range of sesquiterpene synthases. A comprehensive analysis of these enzymes in terms of product specificity has been hampered by the lack of a centralized resource of sufficient functionally annotated sequence data. To address this, we have gathered 262 plant sesquiterpene synthase sequences with experimentally characterized products. The annotated enzyme sequences allowed for an analysis of terpene synthase motifs, leading to the extension of one motif and recognition of a variant of another. In addition, putative terpene synthase sequences were obtained from various resources and compared with the annotated sesquiterpene synthases. This analysis indicated regions of terpene synthase sequence space which so far are unexplored experimentally. Finally, we present a case describing mutational studies on residues altering product specificity, for which we analyzed conservation in our database. This demonstrates an application of our database in choosing likely-functional residues for mutagenesis studies aimed at understanding or changing sesquiterpene synthase product specificity.

Substance-Based Bibliometrics: Identifying Research Gaps by Counting and Analyzing Substances

Identifying research gaps and generating research questions are often a first step in developing ideas for writing a research paper or grant proposal. The concept of substance-based bibliometrics uses the counts of substances in the scientific literature to better understand, assess, and clarify the state and impact of information in the chemical sciences. Connecting substances indexed to specific bioactivity or target indicators can lead to assessing the biochemical, biological, and medicinal relevance of substances as well as developing ideas for expanding drug design and discovery through identifying and modifying the structural features of molecules. This study uses Chemical Abstracts through the SciFinder database to count for the occurrence of substances in the scientific literature. The study sets out search strategies for discovering potential research gaps and new ideas through visualization of chemical structures with known bioactivity and target indicators. The author recommends that subject librarians integrate research gap training in their bibliographic instruction classes, particularly to upper-level undergraduate and graduate chemistry students.

Comprehensive anticancer drug response prediction based on a simple cell line-drug complex network model

Background

Accurate prediction of anticancer drug responses in cell lines is a crucial step to accomplish the precision medicine in oncology. Although many popular computational models have been proposed towards this non-trivial issue, there is still room for improving the prediction performance by combining multiple types of genome-wide molecular data.

Results

We first demonstrated an observation on the CCLE and GDSC datasets, i.e., genetically similar cell lines always exhibit higher response correlations to structurally related drugs. Based on this observation we built a cell line-drug complex network model, named CDCN model. It captures different contributions of all available cell line-drug responses through cell line similarities and drug similarities. We executed anticancer drug response prediction on CCLE and GDSC independently. The result is significantly superior to that of some existing studies. More importantly, our model could predict the response of new drug to new cell line with considerable performance. We also divided all possible cell lines into “sensitive” and “resistant” groups by their response values to a given drug, the prediction accuracy, sensitivity, specificity and goodness of fit are also very promising.

Conclusion

CDCN model is a comprehensive tool to predict anticancer drug responses. Compared with existing methods, it is able to provide more satisfactory prediction results with less computational consumption.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-2608-9) contains supplementary material, which is available to authorized users.

In Silico Target Prediction for Small Molecules

Drugs modulate disease states through their actions on targets in the body. Determining these targets aids the focused development of new treatments, and helps to better characterize those already employed. One means of accomplishing this is through the deployment of in silico methodologies, harnessing computational analytical and predictive power to produce educated hypotheses for experimental verification. Here, we provide an overview of the current state of the art, describe some of the well-established methods in detail, and reflect on how they, and emerging technologies promoting the incorporation of complex and heterogeneous data-sets, can be employed to improve our understanding of (poly)pharmacology.

A New Approach for Drug Target and Bioactivity Prediction: The Multifingerprint Similarity Search Algorithm (MuSSeL)

We present MuSSeL, a multifingerprint similarity search algorithm, able to predict putative drug targets for a given query small molecule as well as to return a quantitative assessment of its bioactivity in terms of K_i or IC₅₀ values. Predictions are automatically made exploiting a large collection of high quality experimental bioactivity data available from ChEMBL (version 22.1) combining, in a consensus-like approach, predictions resulting from a similarity search performed using 13 different fingerprint definitions. Importantly, the herein proposed algorithm is also effective in detecting and handling activity cliffs. A calibration set including small molecules present in the last updated version of ChEMBL (version 23) was employed to properly tune the algorithm parameters. Three randomly built external sets were instead challenged for model performances. The potential use of MuSSeL was also challenged by a prospective exercise for the prediction of five bioactive compounds taken from articles published in the Journal of Medicinal Chemistry just few months ago. The paper emphasizes the importance of implementing multifingerprint consensus strategies to increase the confidence in prediction of similarity search algorithms and provides a fast and easy-to-run tool for drug target and bioactivity prediction.

Three-dimensional descriptors for aminergic GPCRs: dependence on docking conformation and crystal structure

Three-dimensional descriptors are often used to search for new biologically active compounds, in both ligand- and structure-based approaches, capturing the spatial orientation of molecules. They frequently constitute an input for machine learning-based predictions of compound activity or quantitative structure-activity relationship modeling; however, the distribution of their values and the accuracy of depicting compound orientations might have an impact on the power of the obtained predictive models. In this study, we analyzed the distribution of three-dimensional descriptors calculated for docking poses of active and inactive compounds for all aminergic G protein-coupled receptors with available crystal structures, focusing on the variation in conformations for different receptors and crystals. We demonstrated that the consistency in compound orientation in the binding site is rather not correlated with the affinity itself, but is more influenced by other factors, such as the number of rotatable bonds and crystal structure used for docking studies. The visualizations of the descriptors distributions were prepared and made available online at http://chem.gmum.net/vischem_stability , which enables the investigation of chemical structures referring to particular data points depicted in the figures. Moreover, the performed analysis can assist in choosing crystal structure for docking studies, helping in selection of conditions providing the best discrimination between active and inactive compounds in machine learning-based experiments.

Systems pharmacology approach to investigate the molecular mechanisms of herb Rhodiola rosea L. radix

Rhodiola rosea L. radix (RRL) is one of the most popular medical herb which has been widely used for the treatment of different diseases effectively, including cardiovascular diseases and nerve system diseases. However, due to the multiple compounds in RRL, the underlying molecular mechanisms of RRL are remained unclear. To decipher the action mechanisms of RRL from a systematic perspective, a systems pharmacology approach integrated absorption, distribution, metabolism, and excretion (ADME) system, drug targeting, and network analysis was introduced. First, by the ADME screening system and the target fishing process, 56 potential active compounds and 62 targets were obtained, respectively. In addition, compound-target network demonstrated that most compounds interacted with multiple targets, indicating that RRL may enhance its therapeutic effects probably through hitting on multiple targets in a holistic level. Moreover, target-pathway network and gene ontology analysis showed that multiple targets of RRL were involved in several biological pathways, i.e. Neuroactive ligand-receptor interaction, calcium signaling pathway, adrenergic signaling in cardiomyocytes, and VEGF signaling pathway, which dissecting the therapeutic effects of RRL on various diseases, such as cardiovascular diseases, depression, adaptation diseases, etc. In summary, this work successfully explains the potential active compounds and the multi-scale curative action mechanisms of RRL for treating various diseases; meanwhile, it implies that RRL could be applied as a novel therapeutic agent in arthritic diseases. Most importantly, this work provides an in silico strategy to understand the action mechanisms of herbal medicines from molecular/system levels, which will promote the new drug development of traditional Chinese medicine.

Inhibitors of DNA Methyltransferases From Natural Sources: A Computational Perspective

Naturally occurring small molecules include a large variety of natural products from different sources that have confirmed activity against epigenetic targets. In this work we review chemoinformatic, molecular modeling, and other computational approaches that have been used to uncover natural products as inhibitors of DNA methyltransferases, a major family of epigenetic targets with therapeutic interest. Examples of computational approaches surveyed in this work are docking, similarity-based virtual screening, and pharmacophore modeling. It is also discussed the chemoinformatic-guided exploration of the chemical space of naturally occurring compounds as epigenetic modulators which may have significant implications in epigenetic drug discovery and nutriepigenetics.

Network-Based Methods for Prediction of Drug-Target Interactions

Drug-target interaction (DTI) is the basis of drug discovery. However, it is time-consuming and costly to determine DTIs experimentally. Over the past decade, various computational methods were proposed to predict potential DTIs with high efficiency and low costs. These methods can be roughly divided into several categories, such as molecular docking-based, pharmacophore-based, similarity-based, machine learning-based, and network-based methods. Among them, network-based methods, which do not rely on three-dimensional structures of targets and negative samples, have shown great advantages over the others. In this article, we focused on network-based methods for DTI prediction, in particular our network-based inference (NBI) methods that were derived from recommendation algorithms. We first introduced the methodologies and evaluation of network-based methods, and then the emphasis was put on their applications in a wide range of fields, including target prediction and elucidation of molecular mechanisms of therapeutic effects or safety problems. Finally, limitations and perspectives of network-based methods were discussed. In a word, network-based methods provide alternative tools for studies in drug repurposing, new drug discovery, systems pharmacology and systems toxicology.

Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening

The versatility of similarity searching and quantitative structure-activity relationships to model the activity of compound sets within given bioactivity ranges (i.e., interpolation) is well established. However, their relative performance in the common scenario in early stage drug discovery where lots of inactive data but no active data points are available (i.e., extrapolation from the low-activity to the high-activity range) has not been thoroughly examined yet. To this aim, we have designed an iterative virtual screening strategy which was evaluated on 25 diverse bioactivity data sets from ChEMBL. We benchmark the efficiency of random forest (RF), multiple linear regression, ridge regression, similarity searching, and random selection of compounds to identify a highly active molecule in the test set among a large number of low-potency compounds. We use the number of iterations required to find this active molecule to evaluate the performance of each experimental setup. We show that linear and ridge regression often outperform RF and similarity searching, reducing the number of iterations to find an active compound by a factor of 2 or more. Even simple regression methods seem better able to extrapolate to high-bioactivity ranges than RF, which only provides output values in the range covered by the training set. In addition, examination of the scaffold diversity in the data sets used shows that in some cases similarity searching and RF require two times as many iterations as random selection depending on the chemical space covered in the initial training data. Lastly, we show using bioactivity data for COX-1 and COX-2 that our framework can be extended to multitarget drug discovery, where compounds are selected by concomitantly considering their activity against multiple targets. Overall, this study provides an approach for iterative screening where only inactive data are present in early stages of drug discovery in order to discover highly potent compounds and the best experimental set up in which to do so.

Exploring DrugBank in Virtual Reality Chemical Space

The recent general availability of low-cost virtual reality headsets and accompanying three-dimensional (3D) engine support presents an opportunity to bring the concept of chemical space into virtual environments. While virtual reality applications represent a category of widespread tools in other fields, their use in the visualization and exploration of abstract data such as chemical spaces has been experimental. In our previous work, we established the concept of interactive two-dimensional (2D) maps of chemical spaces followed by interactive web-based 3D visualizations, culminating in the interactive web-based 3D visualization of extremely large chemical spaces. Virtual reality chemical spaces are a natural extension of these concepts. As 2D and 3D embeddings and projections of high-dimensional chemical fingerprint spaces have been shown to be valuable tools in chemical space visualization and exploration, existing pipelines of data mining and preparation can be extended to be used in virtual reality applications. Here we present an application based on the Unity engine and the Virtual Reality Toolkit, allowing for the interactive exploration of chemical space populated by DrugBank compounds in virtual reality. The source code of the application as well as the most recent build are available on GitHub ( https://github.com/reymond-group/virtual-reality-chemical-space ).

Predictive classification models and targets identification for betulin derivatives as Leishmania donovani inhibitors

Betulin derivatives have been proven effective in vitro against Leishmania donovani amastigotes, which cause visceral leishmaniasis. Identifying the molecular targets and molecular mechanisms underlying their action is a currently an unmet challenge. In the present study, we tackle this problem using computational methods to establish properties essential for activity as well as to screen betulin derivatives against potential targets. Recursive partitioning classification methods were explored to develop predictive models for 58 diverse betulin derivatives inhibitors of L. donovani amastigotes. The established models were validated on a testing set, showing excellent performance. Molecular fingerprints FCFP_6 and ALogP were extracted as the physicochemical properties most extensively involved in separating inhibitors from non-inhibitors. The potential targets of betulin derivatives inhibitors were predicted by in silico target fishing using structure-based pharmacophore searching and compound-pharmacophore-target-pathway network analysis, first on PDB and then among L. donovani homologs using a PSI-BLAST search. The essential identified proteins are all related to protein kinase family. Previous research already suggested members of the cyclin-dependent kinase family and MAP kinases as Leishmania potential drug targets. The PSI-BLAST search suggests two L. donovani proteins to be especially attractive as putative betulin target, heat shock protein 83 and membrane transporter D1.

Review and comparative assessment of similarity-based methods for prediction of drug–protein interactions in the druggable human proteome

Drug–protein interactions (DPIs) underlie the desired therapeutic actions and the adverse side effects of a significant majority of drugs. Computational prediction of DPIs facilitates research in drug discovery, characterization and repurposing. Similarity-based methods that do not require knowledge of protein structures are particularly suitable for druggable genome-wide predictions of DPIs. We review 35 high-impact similarity-based predictors that were published in the past decade. We group them based on three types of similarities and their combinations that they use. We discuss and compare key aspects of these methods including source databases, internal databases and their predictive models. Using our novel benchmark database, we perform comparative empirical analysis of predictive performance of seven types of representative predictors that utilize each type of similarity individually and all possible combinations of similarities. We assess predictive quality at the database-wide DPI level and we are the first to also include evaluation over individual drugs. Our comprehensive analysis shows that predictors that use more similarity types outperform methods that employ fewer similarities, and that the model combining all three types of similarities secures area under the receiver operating characteristic curve of 0.93. We offer a comprehensive analysis of sensitivity of predictive performance to intrinsic and extrinsic characteristics of the considered predictors. We find that predictive performance is sensitive to low levels of similarities between sequences of the drug targets and several extrinsic properties of the input drug structures, drug profiles and drug targets. The benchmark database and a webserver for the seven predictors are freely available at http://biomine.cs.vcu.edu/servers/CONNECTOR/.

iPSC-Based Compound Screening and In Vitro Trials Identify a Synergistic Anti-amyloid β Combination for Alzheimer's Disease

In the process of drug development, in vitro studies do not always adequately predict human-specific drug responsiveness in clinical trials. Here, we applied the advantage of human iPSC-derived neurons, which offer human-specific drug responsiveness, to screen and evaluate therapeutic candidates for Alzheimer's disease (AD). Using AD patient neurons with nearly 100% purity from iPSCs, we established a robust and reproducible assay for amyloid β peptide (Aβ), a pathogenic molecule in AD, and screened a pharmaceutical compound library. We acquired 27 Aβ-lowering screen hits, prioritized hits by chemical structure-based clustering, and selected 6 leading compounds. Next, to maximize the anti-Aβ effect, we selected a synergistic combination of bromocriptine, cromolyn, and topiramate as an anti-Aβ cocktail. Finally, using neurons from familial and sporadic AD patients, we found that the cocktail showed a significant and potent anti-Aβ effect on patient cells. This human iPSC-based platform promises to be useful for AD drug development.

Molecular docking and 4D-QSAR studies of metastatic cancer inhibitor thiazoles

By using the molecular docking and 4D-QSAR analysis, it is aimed to find the interaction points in the receptor binding site of transforming growth factor-beta (TGF-beta) used to inhibit invasion and metastasis. To elucidate the interaction points of receptor, different types of local reactive descriptor (LRD) of ligands have been used. Activity values related to interaction energy between the ligand-receptor (L-R) were determined by nonlinear least squares (NLLS) using the Levenberg-Marquardt (LM) algorithm. Using the Molecule Comparative Electron Topology (MCET) method, the 3D pharmacophore model (3D-PhaM) was obtained after alignment and superimposition of the molecules, and also confirmed by molecular docking method. With the leave one out-cross validation (LOO-CV) method, the best predictions are q² or r_CV² = 0.789 for the 51 compounds in the internal training set and r² = 0.785 for the 13 compounds in the external test set. Furthermore, the predictive capability of the advanced QSAR model is more precisely calculated with the r_m² metric (r_m² = 0.769).

Multi-Descriptor Read Across (MuDRA): A Simple and Transparent Approach for Developing Accurate Quantitative Structure-Activity Relationship Models

Multiple approaches to quantitative structure-activity relationship (QSAR) modeling using various statistical or machine learning techniques and different types of chemical descriptors have been developed over the years. Oftentimes models are used in consensus to make more accurate predictions at the expense of model interpretation. We propose a simple, fast, and reliable method termed Multi-Descriptor Read Across (MuDRA) for developing both accurate and interpretable models. The method is conceptually related to the well-known kNN approach but uses different types of chemical descriptors simultaneously for similarity assessment. To benchmark the new method, we have built MuDRA models for six different end points (Ames mutagenicity, aquatic toxicity, hepatotoxicity, hERG liability, skin sensitization, and endocrine disruption) and compared the results with those generated with conventional consensus QSAR modeling. We find that models built with MuDRA show consistently high external accuracy similar to that of conventional QSAR models. However, MuDRA models excel in terms of transparency, interpretability, and computational efficiency. We posit that due to its methodological simplicity and reliable predictive accuracy, MuDRA provides a powerful alternative to a much more complex consensus QSAR modeling. MuDRA is implemented and freely available at the Chembench web portal ( https://chembench.mml.unc.edu/mudra ).

Predicting opioid receptor binding affinity of pharmacologically unclassified designer substances using molecular docking

Opioids represent a highly-abused and highly potent class of drugs that have become a significant threat to public safety. Often there are little to no pharmacological and toxicological data available for new, illicitly used and abused opioids, and this has resulted in a growing number of serious adverse events, including death. The large influx of new synthetic opioids permeating the street-drug market, including fentanyl and fentanyl analogs, has generated the need for a fast and effective method to evaluate the risk a substance poses to public safety. In response, the US FDA’s Center for Drug Evaluation and Research (CDER) has developed a rapidly-deployable, multi-pronged computational approach to assess a drug’s risk to public health. A key component of this approach is a molecular docking model to predict the binding affinity of biologically uncharacterized fentanyl analogs to the mu opioid receptor. The model was validated by correlating the docking scores of structurally diverse opioids with experimentally determined binding affinities. Fentanyl derivatives with sub-nanomolar binding affinity at the mu receptor (e.g. carfentanil and lofentanil) have significantly lower binding scores, while less potent fentanyl derivatives have increased binding scores. The strong correlation between the binding scores and the experimental binding affinities suggests that this approach can be used to accurately predict the binding strength of newly identified fentanyl analogs at the mu receptor in the absence of in vitro data and may assist in the temporary scheduling of those substances that pose a risk to public safety.

Using SMILES strings for the description of chemical connectivity in the Crystallography Open Database

Computer descriptions of chemical molecular connectivity are necessary for searching chemical databases and for predicting chemical properties from molecular structure. In this article, the ongoing work to describe the chemical connectivity of entries contained in the Crystallography Open Database (COD) in SMILES format is reported. This collection of SMILES is publicly available for chemical (substructure) search or for any other purpose on an open-access basis, as is the COD itself. The conventions that have been followed for the representation of compounds that do not fit into the valence bond theory are outlined for the most frequently found cases. The procedure for getting the SMILES out of the CIF files starts with checking whether the atoms in the asymmetric unit are a chemically acceptable image of the compound. When they are not (molecule in a symmetry element, disorder, polymeric species,etc.), the previously published cif_molecule program is used to get such image in many cases. The program package Open Babel is then applied to get SMILES strings from the CIF files (either those directly taken from the COD or those produced by cif_molecule when applicable). The results are then checked and/or fixed by a human editor, in a computer-aided task that at present still consumes a great deal of human time. Even if the procedure still needs to be improved to make it more automatic (and hence faster), it has already yielded more than 160,000 curated chemical structures and the purpose of this article is to announce the existence of this work to the chemical community as well as to spread the use of its results.

Prediction of Compound Profiling Matrices Using Machine Learning

Screening of compound libraries against panels of targets yields profiling matrices. Such matrices typically contain structurally diverse screening compounds, large numbers of inactives, and small numbers of hits per assay. As such, they represent interesting and challenging test cases for computational screening and activity predictions. In this work, modeling of large compound profiling matrices was attempted that were extracted from publicly available screening data. Different machine learning methods including deep learning were compared and different prediction strategies explored. Prediction accuracy varied for assays with different numbers of active compounds, and alternative machine learning approaches often produced comparable results. Deep learning did not further increase the prediction accuracy of standard methods such as random forests or support vector machines. Target-based random forest models were prioritized and yielded successful predictions of active compounds for many assays.

Combining Similarity Searching and Network Analysis for the Identification of Active Compounds

A variety of computational screening methods generate similarity-based compound rankings for hit identification. However, these rankings are difficult to interpret. It is essentially impossible to determine where novel active compounds might be found in database rankings. Thus, compound selection largely depends on intuition and guesswork. Herein, we show that molecular networks can substantially aid in the analysis of similarity-based compound rankings. A series of networks generated for rankings provides visual access to search results and adds chemical neighborhood and context information for reference compounds that are not available in rankings. Network structure is shown to serve as a diagnostic criterion for the likelihood to successfully select active compounds from rankings. In addition, comparison of different networks makes it possible to prioritize alternative similarity measures for search calculations and optimize the enrichment of active compounds in rankings.

Progress with modeling activity landscapes in drug discovery

INTRODUCTION

Activity landscapes (ALs) are representations and models of compound data sets annotated with a target-specific activity. In contrast to quantitative structure-activity relationship (QSAR) models, ALs aim at characterizing structure-activity relationships (SARs) on a large-scale level encompassing all active compounds for specific targets. The popularity of AL modeling has grown substantially with the public availability of large activity-annotated compound data sets. AL modeling crucially depends on molecular representations and similarity metrics used to assess structural similarity. Areas covered: The concepts of AL modeling are introduced and its basis in quantitatively assessing molecular similarity is discussed. The different types of AL modeling approaches are introduced. AL designs can broadly be divided into three categories: compound-pair based, dimensionality reduction, and network approaches. Recent developments for each of these categories are discussed focusing on the application of mathematical, statistical, and machine learning tools for AL modeling. AL modeling using chemical space networks is covered in more detail. Expert opinion: AL modeling has remained a largely descriptive approach for the analysis of SARs. Beyond mere visualization, the application of analytical tools from statistics, machine learning and network theory has aided in the sophistication of AL designs and provides a step forward in transforming ALs from descriptive to predictive tools. To this end, optimizing representations that encode activity relevant features of molecules might prove to be a crucial step.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods

In-silico bitterant prediction received the considerable attention due to the expensive and laborious experimental-screening of the bitterant. In this work, we collect the fully experimental dataset containing 707 bitterants and 592 non-bitterants, which is distinct from the fully or partially hypothetical non-bitterant dataset used in the previous works. Based on this experimental dataset, we harness the consensus votes from the multiple machine-learning methods (e.g., deep learning etc.) combined with the molecular fingerprint to build the bitter/bitterless classification models with five-fold cross-validation, which are further inspected by the Y-randomization test and applicability domain analysis. One of the best consensus models affords the accuracy, precision, specificity, sensitivity, F1-score, and Matthews correlation coefficient (MCC) of 0.929, 0.918, 0.898, 0.954, 0.936, and 0.856 respectively on our test set. For the automatic prediction of bitterant, a graphic program “e-Bitter” is developed for the convenience of users via the simple mouse click. To our best knowledge, it is for the first time to adopt the consensus model for the bitterant prediction and develop the first free stand-alone software for the experimental food scientist.

Folic acid derived-P5779 mimetics regulate DAMP-mediated inflammation through disruption of HMGB1:TLR4:MD-2 axes

High mobility group box 1 (HMGB1) is a damage-associated molecular pattern (DAMP) protein that mediates inflammatory responses after infection or injury. Previously, we reported a peptide inhibitor of HMGB1 (P5779) that acts by directly interrupting HMGB1/MD-2 binding. Here, fingerprint similarity search and docking studies suggest folic acid derived-drugs function as P5779 mimetopes. Molecular dynamic (MD) simulation studies demonstrate that folic acid mimics the binding of P5779 at the TLR4 and MD-2 intersection. In surface plasmon resonance (SPR) studies, these drugs showed direct binding to TLR4/MD-2 but not HMGB1. Furthermore, these P5779 mimetopes inhibit HMGB1 and MD-2 binding and suppress HMGB1-induced TNF release in human macrophages in the nanomolar range. We assert from our findings that their demonstrated anti-inflammatory effects may be working through TLR4-dependent signaling.

Weighted Averaging Scheme and Local Atomic Descriptor for pKa Prediction Based on Density Functional Theory

As a continuation of our work on developing a density functional theory-based pK_a predictor, we present conceptual improvements to our previously published shell model, which is a hierarchical organization of pK_a training sets and which, in principle, covers all chemical space. The improvements concern the way the studied chemical compound is associated with the data points from the training sets. By introducing a new descriptor of the local atomic environment which foregoes dependence on chemical bonding and connectivity, we are able to automatically locate molecules from the training set that are most relevant to the proton dissociation equilibrium under study. This new scheme leads to the prediction of a single pK_a value weighted across multiple training sets and thus patches a defect disclosed in the formulation of our previous model. Using the new parametrization approach, the pK_a prediction gets rid of outliers reported in previous applications of our approach, eliminates ambiguity in interpreting the results, and improves the overall accuracy. Our new treatment accounts for multiple conformations both on the level of energetics and parametrization. Illustrative results are shown for several types of chemical structures containing guanidine, amidine, amine, and phenol functional groups, and which are representative of practically important large and flexible drug-like molecules. Our method's performance is compared to the performance of other previously published pK_a prediction methods. Further possible improvements to the organization of the training sets and the potential application of our new local atomic descriptor to other kinds of parametrizations are discussed.

Docking-based inverse virtual screening: methods, applications, and challenges

Identifying potential protein targets for a small-compound ligand query is crucial to the process of drug development. However, there are tens of thousands of proteins in human alone, and it is almost impossible to scan all the existing proteins for a query ligand using current experimental methods. Recently, a computational technology called docking-based inverse virtual screening (IVS) has attracted much attention. In docking-based IVS, a panel of proteins is screened by a molecular docking program to identify potential targets for a query ligand. Ever since the first paper describing a docking-based IVS program was published about a decade ago, the approach has been gradually improved and utilized for a variety of purposes in the field of drug discovery. In this article, the methods employed in docking-based IVS are reviewed in detail, including target databases, docking engines, and scoring function methodologies. Several web servers developed for non-expert users are also reviewed. Then, a number of applications are presented according to different research purposes, such as target identification, side effects/toxicity, drug repositioning, drug-target network development, and receptor design. The review concludes by discussing the challenges that docking-based IVS needs to overcome to become a robust tool for pharmaceutical engineering.

Adverse drug reactions triggered by the common HLA-B*57:01 variant: virtual screening of DrugBank using 3D molecular docking

BACKGROUND

Idiosyncratic adverse drug reactions have been linked to a drug's ability to bind with a human leukocyte antigen (HLA) protein. However, due to the thousands of HLA variants and limited structural data for drug-HLA complexes, predicting a specific drug-HLA combination represents a significant challenge. Recently, we investigated the binding mode of abacavir with the HLA-B*57:01 variant using molecular docking. Herein, we developed a new ensemble screening workflow involving three X-ray crystal derived docking procedures to screen the DrugBank database and identify potentially HLA-B*57:01 liable drugs. Then, we compared our workflow's performance with another model recently developed by Metushi et al., which proposed seven in silico HLA-B*57:01 actives, but were later found to be experimentally inactive.

METHODS

After curation, there were over 6000 approved and experimental drugs remaining in DrugBank for docking using Schrodinger's GLIDE SP and XP scoring functions. Docking was performed with our new consensus-like ensemble workflow, relying on three different X-ray crystals (3VRI, 3VRJ, and 3UPR) in presence and absence of co-binding peptides. The binding modes of HLA-B*57:01 hit compounds for all three peptides were further explored using 3D interaction fingerprints and hierarchical clustering.

RESULTS

The screening resulted in 22 hit compounds forecasted to bind HLA-B*57:01 in all docking conditions (SP and XP with and without peptides P1, P2, and P3). These 22 compounds afforded 2D-Tanimoto similarities being less than 0.6 when compared to the structure of native abacavir, whereas their 3D binding mode similarities varied in a broader range (0.2-0.8). Hierarchical clustering using a Ward Linkage revealed different clustering patterns for each co-binding peptide. When we docked Metushi et al.'s seven proposed hits using our workflow, our screening platform identified six out of seven as being inactive. Molecular dynamic simulations were used to explore the stability of abacavir and acyclovir in complex with peptide P3.

CONCLUSIONS

This study reports on the extensive docking of the DrugBank database and the 22 HLA-B*57:01 liable candidates we identified. Importantly, comparisons between this study and the one by Metushi et al. highlighted new critical and complementary knowledge for the development of future HLA-specific in silico models.

Big data and computational biology strategy for personalized prognosis

The era of big data and precision medicine has led to accumulation of massive datasets of gene expression data and clinical information of patients. For a new patient, we propose that identification of a highly similar reference patient from an existing patient database via similarity matching of both clinical and expression data could be useful for predicting the prognostic risk or therapeutic efficacy.

Here, we propose a novel methodology to predict disease/treatment outcome via analysis of the similarity between any pair of patients who are each characterized by a certain set of pre-defined biological variables (biomarkers or clinical features) represented initially as a prognostic binary variable vector (PBVV) and subsequently transformed to a prognostic signature vector (PSV). Our analyses revealed that Euclidean distance rather correlation distance measure was effective in defining an unbiased similarity measure calculated between two PSVs.

We implemented our methods to high-grade serous ovarian cancer (HGSC) based on a 36-mRNA predictor that was previously shown to stratify patients into 3 distinct prognostic subgroups. We studied and revealed that patient's age, when converted into binary variable, was positively correlated with the overall risk of succumbing to the disease. When applied to an independent testing dataset, the inclusion of age into the molecular predictor provided more robust personalized prognosis of overall survival correlated with the therapeutic response of HGSC and provided benefit for treatment targeting of the tumors in HGSC patients.

Finally, our method can be generalized and implemented in many other diseases to accurately predict personalized patients’ outcomes.

Opioid and Psychostimulant Plasticity: Targeting Overlap in Nucleus Accumbens Glutamate Signaling

Commonalities in addictive behavior, such as craving, stimuli-driven drug seeking, and a high propensity for relapse following abstinence, have pushed for a unified theory of addiction that encompasses most abused substances. This unitary theory has recently been challenged - citing distinctions in structural neural plasticity, biochemical signaling, and neural circuitry to argue that addiction to opioids and psychostimulants is behaviorally and neurobiologically distinct. Recent more selective examination of drug-induced plasticity has highlighted that these two drug classes promote an overall reward circuitry signaling overlap through modifying excitatory synapses in the nucleus accumbens - a key constituent of the reward system. We discuss adaptations in presynaptic/postsynaptic and extrasynaptic glutamate signaling produced by opioids and psychostimulants, and their relevance to circuit remodeling and addiction-related behavior - arguing that these core neural adaptations are important targets for developing pharmacotherapies to treat addiction to multiple drugs.

Ensemble learning method for the prediction of new bioactive molecules

Pharmacologically active molecules can provide remedies for a range of different illnesses and infections. Therefore, the search for such bioactive molecules has been an enduring mission. As such, there is a need to employ a more suitable, reliable, and robust classification method for enhancing the prediction of the existence of new bioactive molecules. In this paper, we adopt a recently developed combination of different boosting methods (Adaboost) for the prediction of new bioactive molecules. We conducted the research experiments utilizing the widely used MDL Drug Data Report (MDDR) database. The proposed boosting method generated better results than other machine learning methods. This finding suggests that the method is suitable for inclusion among the in silico tools for use in cheminformatics, computational chemistry and molecular biology.

Identification of potential aryl hydrocarbon receptor ligands by virtual screening of industrial chemicals

We have developed a virtual screening procedure to identify potential ligands to the aryl hydrocarbon receptor (AhR) among a set of industrial chemicals. AhR is a key target for dioxin-like compounds, which is related to these compounds' potential to induce cancer and a wide range of endocrine and immune system-related effects. The virtual screening procedure included an initial filtration aiming at identifying chemicals with structural similarities to 66 known AhR binders, followed by 3 enrichment methods run in parallel. These include two ligand-based methods (structural fingerprints and nearest neighbor analysis) and one structure-based method using an AhR homology model. A set of 6445 commonly used industrial chemicals was processed, and each step identified unique potential ligands. Seven compounds were identified by all three enrichment methods, and these compounds included known activators and suppressors of AhR. Only approximately 0.7% (41 compounds) of the studied industrial compounds was identified as potential AhR ligands and among these, 28 compounds have to our knowledge not been tested for AhR-mediated effects or have been screened with low purity. We suggest assessment of AhR-related activities of these compounds and in particular 2-chlorotrityl chloride, 3-p-hydroxyanilino-carbazole, and 3-(2-chloro-4-nitrophenyl)-5-(1,1-dimethylethyl)-1,3,4-oxadiazol-2(3H)-one.

Niclosamide suppresses acute myeloid leukemia cell proliferation through inhibition of CREB-dependent signaling pathways

CREB (cAMP Response Element Binding protein) is a transcription factor that is overexpressed in primary acute myeloid leukemia (AML) cells and associated with a decreased event-free survival and increased risk of relapse. We recently reported a small molecule inhibitor of CREB, XX-650-23, which inhibits CREB activity in AML cells. Structure-activity relationship analysis for chemical compounds with structures similar to XX-650-23 led to the identification of the anthelminthic drug niclosamide as a potent anti-leukemic agent that suppresses cell viability of AML cell lines and primary AML cells without a significant decrease in colony forming activity of normal bone marrow cells. Niclosamide significantly inhibited CREB function and CREB-mediated gene expression in cells, leading to apoptosis and G1/S cell cycle arrest with reduced phosphorylated CREB levels. CREB knockdown protected cells from niclosamide treatment-mediated cytotoxic effects. Furthermore, treatment with a combination of niclosamide and CREB inhibitor XX-650-23 showed an additive anti-proliferative effect, consistent with the hypothesis that niclosamide and XX-650-23 regulate the same targets or pathways to inhibit proliferation and survival of AML cells. Niclosamide significantly inhibited the progression of disease in AML patient-derived xenograft (PDX) mice, and prolonged survival of PDX mice. Niclosamide also showed synergistic effects with chemotherapy drugs to inhibit AML cell proliferation. While chemotherapy antagonized the cytotoxic potential of niclosamide, pretreatment with niclosamide sensitized cells to chemotherapeutic drugs, cytarabine, daunorubicin, and vincristine. Therefore, our results demonstrate niclosamide as a potential drug to treat AML by inducing apoptosis and cell cycle arrest through inhibition of CREB-dependent pathways in AML cells.

QSAR Methods

In this chapter, we introduce the basis of computational chemistry and discuss how computational methods have been extended to some biological properties and toxicology, in particular. Since about 20 years, chemical experimentation is more and more replaced by modeling and virtual experimentation, using a large core of mathematics, chemistry, physics, and algorithms. Then we see how animal experiments, aimed at providing a standardized result about a biological property, can be mimicked by new in silico methods. Our emphasis here is on toxicology and on predicting properties through chemical structures. Two main streams of such models are available: models that consider the whole molecular structure to predict a value, namely QSAR (Quantitative Structure Activity Relationships), and models that find relevant substructures to predict a class, namely SAR. The term in silico discovery is applied to chemical design, to computational toxicology, and to drug discovery. We discuss how the experimental practice in biological science is moving more and more toward modeling and simulation. Such virtual experiments confirm hypotheses, provide data for regulation, and help in designing new chemicals.