Big data and artificial intelligence (AI) methodologies for computer-aided drug design (CADD)

There have been numerous advances in the development of computational and statistical methods and applications of big data and artificial intelligence (AI) techniques for computer-aided drug design (CADD). Drug design is a costly and laborious process considering the biological complexity of diseases. To effectively and efficiently design and develop a new drug, CADD can be used to apply cutting-edge techniques to various limitations in the drug design field. Data pre-processing approaches, which clean the raw data for consistent and reproducible applications of big data and AI methods are introduced. We include the current status of the applicability of big data and AI methods to drug design areas such as the identification of binding sites in target proteins, structure-based virtual screening (SBVS), and absorption, distribution, metabolism, excretion and toxicity (ADMET) property prediction. Data pre-processing and applications of big data and AI methods enable the accurate and comprehensive analysis of massive biomedical data and the development of predictive models in the field of drug design. Understanding and analyzing biological, chemical, or pharmaceutical architectures of biomedical entities related to drug design will provide beneficial information in the biomedical big data era.

Design of Novel Drug-like Molecules Using Informatics Rich Secondary Metabolites Analysis of Indian Medicinal and Aromatic Plants

BACKGROUND

Several medicinal plants are being used in Indian medicine systems from ancient times. However, in most cases, the specific molecules or the active ingredients responsible for the medicinal or therapeutic properties are not yet known.

OBJECTIVE

This study aimed to report a computational protocol as well as a tool for generating novel potential drug candidates from the bioactive molecules of Indian medicinal and aromatic plants through the chemoinformatics approach.

METHODS

We built a database of the Indian medicinal and aromatic plants coupled with associated information (plant families, plant parts used for the medicinal purpose, structural information, therapeutic properties, etc.) We also developed a Java-based chemoinformatics open-source tool called DoMINE (Database of Medicinally Important Natural products from plantaE) for the generation of virtual library and screening of novel molecules from known medicinal plant molecules. We employed chemoinformatics approaches to in-silico screened metabolites from 104 Indian medicinal and aromatic plants and designed novel drug-like bioactive molecules. For this purpose, 1665 ring containing molecules were identified by text mining of literature related to the medicinal plant species, which were later used to extract 209 molecular scaffolds. Different scaffolds were further used to build a focused virtual library. Virtual screening was performed with cluster analysis to predict drug-like and lead-like molecules from these plant molecules in the context of drug discovery. The predicted drug-like and lead-like molecules were evaluated using chemoinformatics approaches and statistical parameters, and only the most significant molecules were proposed as the candidate molecules to develop new drugs.

RESULTS AND CONCLUSION

The supra network of molecules and scaffolds identifies the relationship between the plant molecules and drugs. Cluster analysis of virtual library molecules showed that novel molecules had more pharmacophoric properties than toxicophoric and chemophoric properties. We also developed the DoMINE toolkit for the advancement of natural product-based drug discovery through chemoinformatics approaches. This study will be useful in developing new drug molecules from the known medicinal plant molecules. Hence, this work will encourage experimental organic chemists to synthesize these molecules based on the predicted values. These synthesized molecules need to be subjected to biological screening to identify potential molecules for drug discovery research.

Evidence-Based Precision Oncology with the Cancer Targetome

A core tenet of precision oncology is the rational choice of drugs to interact with patient-specific biological targets of interest, but it is currently difficult for researchers to obtain consistent and well-supported target information for pharmaceutical drugs. We review current drug-target interaction resources and critically assess how supporting evidence is handled. We introduce the concept of a unified Cancer Targetome to aggregate drug-target interactions in an evidence-based framework. We discuss current unmet needs and the implications for evidence-based clinical omics. The focus of this review is precision oncology but the discussion is highly relevant to targeted therapies in any area.

Detecting similar binding pockets to enable systems polypharmacology

In the era of systems biology, multi-target pharmacological strategies hold promise for tackling disease-related networks. In this regard, drug promiscuity may be leveraged to interfere with multiple receptors: the so-called polypharmacology of drugs can be anticipated by analyzing the similarity of binding sites across the proteome. Here, we perform a pairwise comparison of 90,000 putative binding pockets detected in 3,700 proteins, and find that 23,000 pairs of proteins have at least one similar cavity that could, in principle, accommodate similar ligands. By inspecting these pairs, we demonstrate how the detection of similar binding sites expands the space of opportunities for the rational design of drug polypharmacology. Finally, we illustrate how to leverage these opportunities in protein-protein interaction networks related to several therapeutic classes and tumor types, and in a genome-scale metabolic model of leukemia.

Traditionally, the fact that most drugs are promiscuous binders has been a major concern in pharmacology, due to the occurrence of undesired off-target clinical events. In the recent years, however, the realization that many diseases are the result of complex biological processes has encouraged rethinking of drug promiscuity as a promising feature, since it is sometimes necessary to interfere with multiple receptors in order to overcome the robustness of disease-related networks. One way to identify groups of proteins that could be targeted simultaneously is to look for similar binding sites. We have massively done so for all human proteins with a known high-resolution three-dimensional structure, unveiling a vast space of ‘polypharmacology’ opportunities. Of these, we know, a great majority is not of therapeutic interest. To pinpoint promising multi-target combinations, we advocate for the use of computational tools that are able to rapidly simulate the effect of drug-target interactions on biological networks.

Identification of potential inhibitors based on compound proposal contest: Tyrosine-protein kinase Yes as a target

A search of broader range of chemical space is important for drug discovery. Different methods of computer-aided drug discovery (CADD) are known to propose compounds in different chemical spaces as hit molecules for the same target protein. This study aimed at using multiple CADD methods through open innovation to achieve a level of hit molecule diversity that is not achievable with any particular single method. We held a compound proposal contest, in which multiple research groups participated and predicted inhibitors of tyrosine-protein kinase Yes. This showed whether collective knowledge based on individual approaches helped to obtain hit compounds from a broad range of chemical space and whether the contest-based approach was effective.

Pocketome of human kinases: prioritizing the ATP binding sites of (yet) untapped protein kinases for drug discovery

Protein kinases are involved in a variety of diseases including cancer, inflammation, and autoimmune disorders. Although the development of new kinase inhibitors is a major focus in pharmaceutical research, a large number of kinases remained so far unexplored in drug discovery projects. The selection and assessment of targets is an essential but challenging area. Today, a few thousands of experimentally determined kinase structures are available, covering about half of the human kinome. This large structural source allows guiding the target selection via structure-based druggability prediction approaches such as DoGSiteScorer. Here, a thorough analysis of the ATP pockets of the entire human kinome in the DFG-in state is presented in order to prioritize novel kinase structures for drug discovery projects. For this, all human kinase X-ray structures available in the PDB were collected, and homology models were generated for the missing part of the kinome. DoGSiteScorer was used to calculate geometrical and physicochemical properties of the ATP pockets and to predict the potential of each kinase to be druggable. The results indicate that about 75% of the kinome are in principle druggable. Top ranking structures comprise kinases that are primary targets of known approved drugs but additionally point to so far less explored kinases. The presented analysis provides new insights into the druggability of ATP binding pockets of the entire kinome. We anticipate this comprehensive druggability assessment of protein kinases to be helpful for the community to prioritize so far untapped kinases for drug discovery efforts.

Ligand biological activity predictions using fingerprint-based artificial neural networks (FANN-QSAR)

This chapter focuses on the fingerprint-based artificial neural networks QSAR (FANN-QSAR) approach to predict biological activities of structurally diverse compounds. Three types of fingerprints, namely ECFP6, FP2, and MACCS, were used as inputs to train the FANN-QSAR models. The results were benchmarked against known 2D and 3D QSAR methods, and the derived models were used to predict cannabinoid (CB) ligand binding activities as a case study. In addition, the FANN-QSAR model was used as a virtual screening tool to search a large NCI compound database for lead cannabinoid compounds. We discovered several compounds with good CB2 binding affinities ranging from 6.70 nM to 3.75 μM. The studies proved that the FANN-QSAR method is a useful approach to predict bioactivities or properties of ligands and to find novel lead compounds for drug discovery research.

A chemo-centric view of human health and disease

Efforts to compile the phenotypic effects of drugs and environmental chemicals offer the opportunity to adopt a chemo-centric view of human health that does not require detailed mechanistic information. Here, we consider thousands of chemicals and analyze the relationship of their structures with adverse and therapeutic responses. Our study includes molecules related to the etiology of 934 health threatening conditions and used to treat 835 diseases. We first identify chemical moieties that could be independently associated with each phenotypic effect. Using these fragments, we build accurate predictors for approximately 400 clinical phenotypes, finding many privileged and liable structures. Finally, we connect two diseases if they relate to similar chemical structures. The resulting networks of human conditions are able to predict disease comorbidities, as well as identifying potential drug side effects and opportunities for drug repositioning, and show a remarkable coincidence with clinical observations.

Fast and accurate semantic annotation of bioassays exploiting a hybrid of machine learning and user confirmation

Bioinformatics and computer aided drug design rely on the curation of a large number of protocols for biological assays that measure the ability of potential drugs to achieve a therapeutic effect. These assay protocols are generally published by scientists in the form of plain text, which needs to be more precisely annotated in order to be useful to software methods. We have developed a pragmatic approach to describing assays according to the semantic definitions of the BioAssay Ontology (BAO) project, using a hybrid of machine learning based on natural language processing, and a simplified user interface designed to help scientists curate their data with minimum effort. We have carried out this work based on the premise that pure machine learning is insufficiently accurate, and that expecting scientists to find the time to annotate their protocols manually is unrealistic. By combining these approaches, we have created an effective prototype for which annotation of bioassay text within the domain of the training set can be accomplished very quickly. Well-trained annotations require single-click user approval, while annotations from outside the training set domain can be identified using the search feature of a well-designed user interface, and subsequently used to improve the underlying models. By drastically reducing the time required for scientists to annotate their assays, we can realistically advocate for semantic annotation to become a standard part of the publication process. Once even a small proportion of the public body of bioassay data is marked up, bioinformatics researchers can begin to construct sophisticated and useful searching and analysis algorithms that will provide a diverse and powerful set of tools for drug discovery researchers.

Antibody informatics for drug discovery

More and more antibody therapeutics are being approved every year, mainly due to their high efficacy and antigen selectivity. However, it is still difficult to identify the antigen, and thereby the function, of an antibody if no other information is available. There are obstacles inherent to the antibody science in every project in antibody drug discovery. Recent experimental technologies allow for the rapid generation of large-scale data on antibody sequences, affinity, potency, structures, and biological functions; this should accelerate drug discovery research. Therefore, a robust bioinformatic infrastructure for these large data sets has become necessary. In this article, we first identify and discuss the typical obstacles faced during the antibody drug discovery process. We then summarize the current status of three sub-fields of antibody informatics as follows: (i) recent progress in technologies for antibody rational design using computational approaches to affinity and stability improvement, as well as ab-initio and homology-based antibody modeling; (ii) resources for antibody sequences, structures, and immune epitopes and open drug discovery resources for development of antibody drugs; and (iii) antibody numbering and IMGT. Here, we review "antibody informatics," which may integrate the above three fields so that bridging the gaps between industrial needs and academic solutions can be accelerated. This article is part of a Special Issue entitled: Recent advances in molecular engineering of antibody.

VAV3 mediates resistance to breast cancer endocrine therapy

Introduction

Endocrine therapies targeting cell proliferation and survival mediated by estrogen receptor α (ERα) are among the most effective systemic treatments for ERα-positive breast cancer. However, most tumors initially responsive to these therapies acquire resistance through mechanisms that involve ERα transcriptional regulatory plasticity. Herein we identify VAV3 as a critical component in this process.

Methods

A cell-based chemical compound screen was carried out to identify therapeutic strategies against resistance to endocrine therapy. Binding to ERα was evaluated by molecular docking analyses, an agonist fluoligand assay and short hairpin (sh)RNA–mediated protein depletion. Microarray analyses were performed to identify altered gene expression. Western blot analysis of signaling and proliferation markers, and shRNA-mediated protein depletion in viability and clonogenic assays, were performed to delineate the role of VAV3. Genetic variation in VAV3 was assessed for association with the response to tamoxifen. Immunohistochemical analyses of VAV3 were carried out to determine its association with therapeutic response and different tumor markers. An analysis of gene expression association with drug sensitivity was carried out to identify a potential therapeutic approach based on differential VAV3 expression.

Results

The compound YC-1 was found to comparatively reduce the viability of cell models of acquired resistance. This effect was probably not due to activation of its canonical target (soluble guanylyl cyclase), but instead was likely a result of binding to ERα. VAV3 was selectively reduced upon exposure to YC-1 or ERα depletion, and, accordingly, VAV3 depletion comparatively reduced the viability of cell models of acquired resistance. In the clinical scenario, germline variation in VAV3 was associated with the response to tamoxifen in Japanese breast cancer patients (rs10494071 combined P value = 8.4 × 10⁻⁴). The allele association combined with gene expression analyses indicated that low VAV3 expression predicts better clinical outcome. Conversely, high nuclear VAV3 expression in tumor cells was associated with poorer endocrine therapy response. Based on VAV3 expression levels and the response to erlotinib in cancer cell lines, targeting EGFR signaling may be a promising therapeutic strategy.

Conclusions

This study proposes VAV3 as a biomarker and a rationale for its use as a signaling target to prevent and/or overcome resistance to endocrine therapy in breast cancer.

Compound activity prediction using models of binding pockets or ligand properties in 3D

Transient interactions of endogenous and exogenous small molecules with flexible binding sites in proteins or macromolecular assemblies play a critical role in all biological processes. Current advances in high-resolution protein structure determination, database development, and docking methodology make it possible to design three-dimensional models for prediction of such interactions with increasing accuracy and specificity. Using the data collected in the Pocketome encyclopedia, we here provide an overview of two types of the three-dimensional ligand activity models, pocketbased and ligand property-based, for two important classes of proteins, nuclear and G-protein coupled receptors. For half the targets, the pocket models discriminate actives from property matched decoys with acceptable accuracy (the area under ROC curve, AUC, exceeding 84%) and for about one fifth of the targets with high accuracy (AUC > 95%). The 3D ligand property field models performed better than 95% in half of the cases. The high performance models can already become a basis of activity predictions for new chemicals. Family-wide benchmarking of the models highlights strengths of both approaches and helps identify their inherent bottlenecks and challenges.

KLIFS: a knowledge-based structural database to navigate kinase-ligand interaction space

Protein kinases regulate the majority of signal transduction pathways in cells and have become important targets for the development of designer drugs. We present a systematic analysis of kinase-ligand interactions in all regions of the catalytic cleft of all 1252 human kinase-ligand cocrystal structures present in the Protein Data Bank (PDB). The kinase-ligand interaction fingerprints and structure database (KLIFS) contains a consistent alignment of 85 kinase ligand binding site residues that enables the identification of family specific interaction features and classification of ligands according to their binding modes. We illustrate how systematic mining of kinase-ligand interaction space gives new insights into how conserved and selective kinase interaction hot spots can accommodate the large diversity of chemical scaffolds in kinase ligands. These analyses lead to an improved understanding of the structural requirements of kinase binding that will be useful in ligand discovery and design studies.

The genome and developmental transcriptome of the strongylid nematode Haemonchus contortus

Background

The barber's pole worm, Haemonchus contortus, is one of the most economically important parasites of small ruminants worldwide. Although this parasite can be controlled using anthelmintic drugs, resistance against most drugs in common use has become a widespread problem. We provide a draft of the genome and the transcriptomes of all key developmental stages of H. contortus to support biological and biotechnological research areas of this and related parasites.

Results

The draft genome of H. contortus is 320 Mb in size and encodes 23,610 protein-coding genes. On a fundamental level, we elucidate transcriptional alterations taking place throughout the life cycle, characterize the parasite's gene silencing machinery, and explore molecules involved in development, reproduction, host-parasite interactions, immunity, and disease. The secretome of H. contortus is particularly rich in peptidases linked to blood-feeding activity and interactions with host tissues, and a diverse array of molecules is involved in complex immune responses. On an applied level, we predict drug targets and identify vaccine molecules.

Conclusions

The draft genome and developmental transcriptome of H. contortus provide a major resource to the scientific community for a wide range of genomic, genetic, proteomic, metabolomic, evolutionary, biological, ecological, and epidemiological investigations, and a solid foundation for biotechnological outcomes, including new anthelmintics, vaccines and diagnostic tests. This first draft genome of any strongylid nematode paves the way for a rapid acceleration in our understanding of a wide range of socioeconomically important parasites of one of the largest nematode orders.

Molecular fingerprint-based artificial neural networks QSAR for ligand biological activity predictions

In this manuscript, we have reported a novel 2D fingerprint-based artificial neural network QSAR (FANN-QSAR) method in order to effectively predict biological activities of structurally diverse chemical ligands. Three different types of fingerprints, namely, ECFP6, FP2 and MACCS, were used in FANN-QSAR algorithm development, and FANN-QSAR models were compared to known 3D and 2D QSAR methods using five data sets previously reported. In addition, the derived models were used to predict GPCR cannabinoid ligand binding affinities using our manually curated cannabinoid ligand database containing 1699 structurally diverse compounds with reported cannabinoid receptor subtype CB(2) activities. To demonstrate its useful applications, the established FANN-QSAR algorithm was used as a virtual screening tool to search a large NCI compound database for lead cannabinoid compounds, and we have discovered several compounds with good CB(2) binding affinities ranging from 6.70 nM to 3.75 μM. To the best of our knowledge, this is the first report for a fingerprint-based neural network approach validated with a successful virtual screening application in identifying lead compounds. The studies proved that the FANN-QSAR method is a useful approach to predict bioactivities or properties of ligands and to find novel lead compounds for drug discovery research.

Towards a Universal SMILES representation - A standard method to generate canonical SMILES based on the InChI

BACKGROUND

There are two line notations of chemical structures that have established themselves in the field: the SMILES string and the InChI string. The InChI aims to provide a unique, or canonical, identifier for chemical structures, while SMILES strings are widely used for storage and interchange of chemical structures, but no standard exists to generate a canonical SMILES string.

RESULTS

I describe how to use the InChI canonicalisation to derive a canonical SMILES string in a straightforward way, either incorporating the InChI normalisations (Inchified SMILES) or not (Universal SMILES). This is the first description of a method to generate canonical SMILES that takes stereochemistry into account. When tested on the 1.1 m compounds in the ChEMBL database, and a 1 m compound subset of the PubChem Substance database, no canonicalisation failures were found with Inchified SMILES. Using Universal SMILES, 99.79% of the ChEMBL database was canonicalised successfully and 99.77% of the PubChem subset.

CONCLUSIONS

The InChI canonicalisation algorithm can successfully be used as the basis for a common standard for canonical SMILES. While challenges remain - such as the development of a standard aromatic model for SMILES - the ability to create the same SMILES using different toolkits will mean that for the first time it will be possible to easily compare the chemical models used by different toolkits.

Large-Scale QSAR in Target Prediction and Phenotypic HTS Assessment

The advent of in silico compound target prediction offers a potential paradigm shift in how large compound collections are understood and used strategically in high-throughput screens (HTS). Specifically, phenotypic HTS hits may be annotated both with known targets and predicted targets using large-scale QSAR models, enabling a more sophisticated hit assessment. Efforts in massive bioactivity data integration and standardization is empowering such compound-target annotations. These approaches differ fundamentally from the traditional role of QSAR in lead optimization and binding affinity predictions to global, probabilistic target predictions for thousands of human proteins.

A two-step target binding and selectivity support vector machines approach for virtual screening of dopamine receptor subtype-selective ligands

Target selective drugs, such as dopamine receptor (DR) subtype selective ligands, are developed for enhanced therapeutics and reduced side effects. In silico methods have been explored for searching DR selective ligands, but encountered difficulties associated with high subtype similarity and ligand structural diversity. Machine learning methods have shown promising potential in searching target selective compounds. Their target selective capability can be further enhanced. In this work, we introduced a new two-step support vector machines target-binding and selectivity screening method for searching DR subtype-selective ligands, which was tested together with three previously-used machine learning methods for searching D1, D2, D3 and D4 selective ligands. It correctly identified 50.6%–88.0% of the 21–408 subtype selective and 71.7%–81.0% of the 39–147 multi-subtype ligands. Its subtype selective ligand identification rates are significantly better than, and its multi-subtype ligand identification rates are comparable to the best rates of the previously used methods. Our method produced low false-hit rates in screening 13.56 M PubChem, 168,016 MDDR and 657,736 ChEMBLdb compounds. Molecular features important for subtype selectivity were extracted by using the recursive feature elimination feature selection method. These features are consistent with literature-reported features. Our method showed similar performance in searching estrogen receptor subtype selective ligands. Our study demonstrated the usefulness of the two-step target binding and selectivity screening method in searching subtype selective ligands from large compound libraries.

The impact of network biology in pharmacology and toxicology

With the need to investigate alternative approaches and emerging technologies in order to increase drug efficacy and reduce adverse drug effects, network biology offers a novel way of approaching drug discovery by considering the effect of a molecule and protein's function in a global physiological environment. By studying drug action across multiple scales of complexity, from molecular to cellular and tissue level, network-based computational methods have the potential to improve our understanding of the impact of chemicals in human health. In this review we present the available large-scale databases and tools that allow integration and analysis of such information for understanding the properties of small molecules in the context of cellular networks. With the recent advances in the omics area, global integrative approaches are necessary to cope with the massive amounts of data, and biomedical researchers are urged to implement new types of analyses that can lead to new therapeutic interventions with increased safety and efficacy compared with existing medications.

Nonlinear dimensionality reduction and mapping of compound libraries for drug discovery

Visualization of 'chemical space' and compound distributions has received much attraction by medicinal chemists as it may help to intuitively comprehend pharmaceutically relevant molecular features. It has been realized that for meaningful feature extraction from complex multivariate chemical data, such as compound libraries represented by many molecular descriptors, nonlinear projection techniques are required. Recent advances in machine-learning and artificial intelligence have resulted in a transfer of such methods to chemistry. We provide an overview of prominent visualization methods based on nonlinear dimensionality reduction, and highlight applications in drug discovery. Emphasis is on neural network techniques, kernel methods and stochastic embedding approaches, which have been successfully used for ligand-based virtual screening, SAR landscape analysis, combinatorial library design, and screening compound selection.