DrugMint: a webserver for predicting and designing of drug-like molecules

Automation of Drug Discovery through Cutting-edge In-silico Research in Pharmaceuticals: Challenges and Future Scope

The rapidity and high-throughput nature of in silico technologies make them advantageous for predicting the properties of a large array of substances. In silico approaches can be used for compounds intended for synthesis at the beginning of drug development when there is either no or very little compound available. In silico approaches can be used for impurities or degradation products. Quantifying drugs and related substances (RS) with pharmaceutical drug analysis (PDA) can also improve drug discovery (DD) by providing additional avenues to pursue. Potential future applications of PDA include combining it with other methods to make insilico predictions about drugs and RS. One possible outcome of this is a determination of the drug potential of nontoxic RS. ADME estimation, QSAR research, molecular docking, bioactivity prediction, and toxicity testing all involve impurity profiling. Before committing to DD, RS with minimal toxicity can be utilised in silico. The efficacy of molecular docking in getting a medication to market is still debated despite its refinement and improvement. Biomedical labs and pharmaceutical companies were hesitant to adopt molecular docking algorithms for drug screening despite their decades of development and improvement. Despite the widespread use of "force fields" to represent the energy exerted within and between molecules, it has been impossible to reliably predict or compute the binding affinities between proteins and potential binding medications.

Integrated Molecular Modeling and Machine Learning for Drug Design

Modern therapeutic development often involves several stages that are interconnected, and multiple iterations are usually required to bring a new drug to the market. Computational approaches have increasingly become an indispensable part of helping reduce the time and cost of the research and development of new drugs. In this Perspective, we summarize our recent efforts on integrating molecular modeling and machine learning to develop computational tools for modulator design, including a pocket-guided rational design approach based on AlphaSpace to target protein-protein interactions, delta machine learning scoring functions for protein-ligand docking as well as virtual screening, and state-of-the-art deep learning models to predict calculated and experimental molecular properties based on molecular mechanics optimized geometries. Meanwhile, we discuss remaining challenges and promising directions for further development and use a retrospective example of FDA approved kinase inhibitor Erlotinib to demonstrate the use of these newly developed computational tools.

Current Trends and Challenges in Drug-Likeness Prediction: Are They Generalizable and Interpretable?

Importance: Drug-likeness of a compound is an overall assessment of its potential to succeed in clinical trials, and is essential for economizing research expenditures by filtering compounds with unfavorable properties and poor development potential. To this end, a robust drug-likeness prediction method is indispensable. Various approaches, including discriminative rules, statistical models, and machine learning models, have been developed to predict drug-likeness based on physiochemical properties and structural features. Notably, recent advancements in novel deep learning techniques have significantly advanced drug-likeness prediction, especially in classification performance. Highlights: In this review, we addressed the evolving landscape of drug-likeness prediction, with emphasis on methods employing novel deep learning techniques, and highlighted the current challenges in drug-likeness prediction, specifically regarding the aspects of generalization and interpretability. Moreover, we explored potential remedies and outlined promising avenues for future research. Conclusion: Despite the hurdles of generalization and interpretability, novel deep learning techniques have great potential in drug-likeness prediction and are worthy of further research efforts.

Comparative analysis of weka-based classification algorithms on medical diagnosis datasets

BACKGROUND

With the advent of 5G and the era of Big Data, the rapid development of medical information technology around the world, the massive application of electronic medical records and cases, and the digitization of medical equipment and instruments, a large amount of data has accumulated in the database system of hospitals, which includes clinical diagnosis data and hospital management data.

OBJECTIVE

This study aimed to examine the classification effects of different machine learning algorithms on medical datasets so as to better explore the value of machine learning methods in aiding medical diagnosis.

METHODS

The classification datasets of four different medical fields in the University of California Irvine machine learning database were used as the research object. Also, six categories of classification models based on the Bayesian theorem idea, integrated learning idea, and rule-based and tree-based idea were constructed using the Weka platform.

RESULTS

The between-group experiments showed that the Random Forest algorithm achieved the best results on the Indian liver disease patient dataset (ILPD), delivery cardiotocography (CADG), and lymphatic tractography (LYMP) datasets, followed by Bagging and partition and regression tree. In the within-group algorithm comparison experiments, the Bagging algorithm achieved better results than other algorithms based on the integration idea for 11 metrics on all datasets, mainly focusing on 2 binary datasets. Logit Boost had only 7 metrics with significant performance, and the best algorithm was Rotation Forest, with 28 metrics achieving optimal values. Among the algorithms based on tree ideas, the logistic model tree algorithm achieved optimal results on all metrics on the mammographic dataset (MAGR). The classification performance of BFTree, J48, and Random Tree was poor on each dataset. The best algorithm was Random Forest on the ILPD, CADG, and LYMP datasets with 27 metrics reaching the optimum.

CONCLUSION

Machine learning algorithms have good application value in disease prediction and can provide a reference basis for disease diagnosis.

Pfeature: A Tool for Computing Wide Range of Protein Features and Building Prediction Models

In the last three decades, a wide range of protein features have been discovered to annotate a protein. Numerous attempts have been made to integrate these features in a software package/platform so that the user may compute a wide range of features from a single source. To complement the existing methods, we developed a method, Pfeature, for computing a wide range of protein features. Pfeature allows to compute more than 200,000 features required for predicting the overall function of a protein, residue-level annotation of a protein, and function of chemically modified peptides. It has six major modules, namely, composition, binary profiles, evolutionary information, structural features, patterns, and model building. Composition module facilitates to compute most of the existing compositional features, plus novel features. The binary profile of amino acid sequences allows to compute the fraction of each type of residue as well as its position. The evolutionary information module allows to compute evolutionary information of a protein in the form of a position-specific scoring matrix profile generated using Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST); fit for annotation of a protein and its residues. A structural module was developed for computing of structural features/descriptors from a tertiary structure of a protein. These features are suitable to predict the therapeutic potential of a protein containing non-natural or chemically modified residues. The model-building module allows to implement various machine learning techniques for developing classification and regression models as well as feature selection. Pfeature also allows the generation of overlapping patterns and features from a protein. A user-friendly Pfeature is available as a web server python library and stand-alone package.

Virtual screening of Indonesian herbal compounds as COVID-19 supportive therapy: machine learning and pharmacophore modeling approaches

Background

The number of COVID-19 cases continues to grow in Indonesia. This phenomenon motivates researchers to find alternative drugs that function for prevention or treatment. Due to the rich biodiversity of Indonesian medicinal plants, one alternative is to examine the potential of herbal medicines to support COVID therapy. This study aims to identify potential compound candidates in Indonesian herbal using a machine learning and pharmacophore modeling approaches.

Methods

We used three classification methods that had different decision-making processes: support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF). For the pharmacophore modeling approach, we performed a structure-based analysis on the 3D structure of the main protease SARS-CoV-2 (3CLPro) and repurposed SARS, MERS, and SARS-CoV-2 drugs identified from the literature as datasets in the ligand-based method. Lastly, we used molecular docking to analyze the interactions between the 3CLpro and 14 hit compounds from the Indonesian Herbal Database (HerbalDB), with lopinavir as a positive control.

Results

From the molecular docking analysis, we found six potential compounds that may act as the main proteases of the SARS-CoV-2 inhibitor: hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside.

Conclusions

Our layered virtual screening with machine learning and pharmacophore modeling approaches provided a more objective and optimal virtual screening and avoided subjective decision making of the results. Herbal compounds from the screening, i.e. hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside are potential antiviral candidates for SARS-CoV-2. Moringa oleifera and Psidium guajava that consist of those compounds, could be an alternative option as COVID-19 herbal preventions.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12906-022-03686-y.

Recent Advances in the Prediction of Pharmacokinetics Properties in Drug Design Studies: A Review

This review presents the main aspects related to pharmacokinetic properties, which are essential for the efficacy and safety of drugs. This topic is very important because the analysis of pharmacokinetic aspects in the initial design stages of drug candidates can increase the chances of success for the entire process. In this scenario, experimental and in silico techniques have been widely used. Due to the difficulties encountered with the use of some experimental tests to determine pharmacokinetic properties, several in silico tools have been developed and have shown promising results. Therefore, in this review, we address the main free tools/servers that have been used in this area, as well as some cases of application. Finally, we present some studies that employ a multidisciplinary approach with synergy between in silico, in vitro, and in vivo techniques to assess ADME properties of bioactive substances, achieving successful results in drug discovery and design.

In silico methods and tools for drug discovery

In the past, conventional drug discovery strategies have been successfully employed to develop new drugs, but the process from lead identification to clinical trials takes more than 12 years and costs approximately $1.8 billion USD on average. Recently, in silico approaches have been attracting considerable interest because of their potential to accelerate drug discovery in terms of time, labor, and costs. Many new drug compounds have been successfully developed using computational methods. In this review, we briefly introduce computational drug discovery strategies and outline up-to-date tools to perform the strategies as well as available knowledge bases for those who develop their own computational models. Finally, we introduce successful examples of anti-bacterial, anti-viral, and anti-cancer drug discoveries that were made using computational methods.

Computer-aided prediction of inhibitors against STAT3 for managing COVID-19 associated cytokine storm

Background

Proinflammatory cytokines are correlated with the severity of disease in patients with COVID-19. IL6-mediated activation of STAT3 proliferates proinflammatory responses that lead to cytokine storm promotion. Thus, STAT3 inhibitors may play a crucial role in managing the COVID-19 pathogenesis. The present study discusses a method for predicting inhibitors against the STAT3 signaling pathway.

Method

The main dataset comprises 1565 STAT3 inhibitors and 1671 non-inhibitors used for training, testing, and evaluation of models. A number of machine learning classifiers have been implemented to develop the models.

Results

The outcomes of the data analysis show that rings and aromatic groups are significantly abundant in STAT3 inhibitors compared to non-inhibitors. First, we developed models using 2-D and 3-D chemical descriptors and achieved a maximum AUC of 0.84 and 0.73, respectively. Second, fingerprints are used to build predictive models and achieved 0.86 AUC with an accuracy of 78.70% on the validation dataset. Finally, models were developed using hybrid descriptors, which achieved a maximum of 0.87 AUC with 78.55% accuracy on the validation dataset.

Conclusion

We used the best model to identify STAT3 inhibitors in FDA-approved drugs and found few drugs (e.g., Tamoxifen and Perindopril) to manage the cytokine storm in COVID-19 patients. A webserver “STAT3In” (https://webs.iiitd.edu.in/raghava/stat3in/) has been developed to predict and design STAT3 inhibitors.

ChAlPred: A web server for prediction of allergenicity of chemical compounds

BACKGROUND

Allergy is the abrupt reaction of the immune system that may occur after the exposure to allergens such as proteins, peptides, or chemicals. In the past, various methods have been generated for predicting allergenicity of proteins and peptides. In contrast, there is no method that can predict allergenic potential of chemicals. In this paper, we described a method ChAlPred developed for predicting chemical allergens as well as for designing chemical analogs with desired allergenicity.

METHOD

In this study, we have used 403 allergenic and 1074 non-allergenic chemical compounds obtained from IEDB database. The PaDEL software was used to compute the molecular descriptors of the chemical compounds to develop different prediction models. All the models were trained and tested on the 80% training data and evaluated on the 20% validation data using the 2D, 3D and FP descriptors.

RESULTS

In this study, we have developed different prediction models using several machine learning approaches. It was observed that the Random Forest based model developed using hybrid descriptors performed the best, and achieved the maximum accuracy of 83.39% and AUC of 0.93 on validation dataset. The fingerprint analysis of the dataset indicates that certain chemical fingerprints are more abundant in allergens that include PubChemFP129 and GraphFP1014. We have also predicted allergenicity potential of FDA-approved drugs using our best model and identified the drugs causing allergic symptoms (e.g., Cefuroxime, Spironolactone, Tioconazole). Our results agreed with allergenicity of these drugs reported in literature.

CONCLUSIONS

To aid the research community, we developed a smart-device compatible web server ChAlPred (https://webs.iiitd.edu.in/raghava/chalpred/) that allows to predict and design the chemicals with allergenic properties.

Cheminformatic Characterization of Natural Antimicrobial Products for the Development of New Lead Compounds

The growing antimicrobial resistance (AMR) of pathogenic organisms to currently prescribed drugs has resulted in the failure to treat various infections caused by these superbugs. Therefore, to keep pace with the increasing drug resistance, there is a pressing need for novel antimicrobial agents, especially from non-conventional sources. Several natural products (NPs) have been shown to display promising in vitro activities against multidrug-resistant pathogens. Still, only a few of these compounds have been studied as prospective drug candidates. This may be due to the expensive and time-consuming process of conducting important studies on these compounds. The present review focuses on applying cheminformatics strategies to characterize, prioritize, and optimize NPs to develop new lead compounds against antimicrobial resistance pathogens. Moreover, case studies where these strategies have been used to identify potential drug candidates, including a few selected open-access tools commonly used for these studies, are briefly outlined.

Deciphering the key heterocyclic scaffolds in targeting microtubules, kinases and carbonic anhydrases for cancer drug development

Heterocyclic scaffolds are widely utilized for drug design by taking into account the molecular structure of therapeutic targets that are related to a broad spectrum of ailments, including tumors. Such compounds display various covalent and non-covalent interactions with the specific residues of the target proteins while causing their inhibition. There is a substantial number of heterocyclic compounds approved for cancer treatment, and these compounds function by interacting with different therapeutic targets involved in tumorogenesis. In this review, we trace and emphasize the privileged heterocyclic pharmacophores that have immense potency against several essential chemotherapeutic tumor targets: microtubules, kinases and carbonic anhydrases. Potent compounds currently undergoing pre-clinical and clinical studies have also been assessed for ascertaining the effective class of chemical scaffolds that have significant therapeutic potential against multiple malignancies. In addition, we also describe briefly the role of heterocyclic compounds in various chemotherapy regimens. The optimized molecular hybridization of delineated motifs may result in the discovery of more active anticancer therapeutics and circumvent the development of resistance by specific targets in the future.

Characterisation of twelve newly synthesised N-(substituted phenyl)-2-chloroacetamides with QSAR analysis and antimicrobial activity tests

In this study we screened twelve newly synthesised N-(substituted phenyl)-2-chloroacetamides for antimicrobial potential relying on quantitative structure-activity relationship (QSAR) analysis based on the available cheminformatics prediction models (Molinspiration, SwissADME, PreADMET, and PkcSM) and verified it through standard antimicrobial testing against Escherichia coli, Staphylococcus aureus, methicillin-resistant S. aureus (MRSA), and Candida albicans. Our compounds met all the screening criteria of Lipinski’s rule of five (Ro5) as well as Veber’s and Egan’s methods for predicting biological activity. In antimicrobial activity tests, all chloroacetamides were effective against Gram-positive S. aureus and MRSA, less effective against the Gram-negative E. coli, and moderately effective against the yeast C. albicans. Our study confirmed that the biological activity of chloroacetamides varied with the position of substituents bound to the phenyl ring, which explains why some molecules were more effective against Gram-negative than Gram-positive bacteria or C. albicans. Bearing the halogenated p-substituted phenyl ring, N-(4-chlorophenyl), N-(4-fluorophenyl), and N-(3-bromophenyl) chloroacetamides were among the most active thanks to high lipophilicity, which allows them to pass rapidly through the phospholipid bilayer of the cell membrane. They are the most promising compounds for further investigation, particularly against Gram-positive bacteria and pathogenic yeasts.

Predicting Drug-Target Interactions with Electrotopological State Fingerprints and Amphiphilic Pseudo Amino Acid Composition

The task of drug-target interaction (DTI) prediction plays important roles in drug development. The experimental methods in DTIs are time-consuming, expensive and challenging. To solve these problems, machine learning-based methods are introduced, which are restricted by effective feature extraction and negative sampling. In this work, features with electrotopological state (E-state) fingerprints for drugs and amphiphilic pseudo amino acid composition (APAAC) for target proteins are tested. E-state fingerprints are extracted based on both molecular electronic and topological features with the same metric. APAAC is an extension of amino acid composition (AAC), which is calculated based on hydrophilic and hydrophobic characters to construct sequence order information. Using the combination of these feature pairs, the prediction model is established by support vector machines. In order to enhance the effectiveness of features, a distance-based negative sampling is proposed to obtain reliable negative samples. It is shown that the prediction results of area under curve for Receiver Operating Characteristic (AUC) are above 98.5% for all the three datasets in this work. The comparison of state-of-the-art methods demonstrates the effectiveness and efficiency of proposed method, which will be helpful for further drug development.

Open access in silico tools to predict the ADMET profiling of drug candidates

INTRODUCTION

We are in an era of bioinformatics and cheminformatics where we can predict data in the fields of medicine, the environment, engineering and public health. Approaches with open access in silico tools have revolutionized disease management due to early prediction of the absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles of the chemically designed and eco-friendly next-generation drugs.

AREAS COVERED

This review meticulously encompasses the fundamental functions of open access in silico prediction tools (webservers and standalone software) and advocates their use in drug discovery research for the safety and reliability of any candidate-drug. This review also aims to help support new researchers in the field of drug design.

EXPERT OPINION

The choice of in silico tools is critically important for drug discovery and the accuracy of ADMET prediction. The accuracy largely depends on the types of dataset, the algorithm used, the quality of the model, the available endpoints for prediction, and user requirement. The key is to use multiple in silico tools for predictions and comparing the results, followed by the identification of the most probable prediction.

PaccMann: a web service for interpretable anticancer compound sensitivity prediction

The identification of new targeted and personalized therapies for cancer requires the fast and accurate assessment of the drug efficacy of potential compounds against a particular biomolecular sample. It has been suggested that the integration of complementary sources of information might strengthen the accuracy of a drug efficacy prediction model. Here, we present a web-based platform for the Prediction of AntiCancer Compound sensitivity with Multimodal Attention-based Neural Networks (PaccMann). PaccMann is trained on public transcriptomic cell line profiles, compound structure information and drug sensitivity screenings, and outperforms state-of-the-art methods on anticancer drug sensitivity prediction. On the open-access web service (https://ibm.biz/paccmann-aas), users can select a known drug compound or design their own compound structure in an interactive editor, perform in-silico drug testing and investigate compound efficacy on publicly available or user-provided transcriptomic profiles. PaccMann leverages methods for model interpretability and outputs confidence scores as well as attention heatmaps that highlight the genes and chemical sub-structures that were more important to make a prediction, hence facilitating the understanding of the model's decision making and the involved biochemical processes. We hope to serve the community with a toolbox for fast and efficient validation in drug repositioning or lead compound identification regimes.

In-silico approaches to detect inhibitors of the human severe acute respiratory syndrome coronavirus envelope protein ion channel

Recent outbreak of Coronavirus disease (COVID-19) pandemic around the world is associated with ‘severe acute respiratory syndrome’ (SARS-CoV2) in humans. SARS-CoV2 is an enveloped virus and E proteins present in them are reported to form ion channels, which is mainly associated with pathogenesis. Thus, there is always a quest to inhibit these ion channels, which in turn may help in controlling diseases caused by SARS-CoV2 in humans. Considering this, in the present study, authors employed computational approaches for studying the structure as well as function of the human ‘SARS-CoV2 E’ protein as well as its interaction with various phytochemicals. Result obtained revealed that α-helix and loops present in this protein experience random movement under optimal condition, which in turn modulate ion channel activity; thereby aiding the pathogenesis caused via SARS-CoV2 in human and other vertebrates. However, after binding with Belachinal, Macaflavanone E, and Vibsanol B, the random motion of the human ‘SARS-CoV2 E’ protein gets reduced, this, in turn, inhibits the function of the ‘SARS-CoV2 E’ protein. It is pertinent to note that two amino acids, namely VAL25 and PHE26, play a key role while interacting with these three phytochemicals. As these three phytochemicals, namely, Belachinal, Macaflavanone E & Vibsanol B, have passed the ADMET (Absorption, Distribution, Metabolism, Excretion and Toxicity) property as well as ‘Lipinski’s Rule of 5s’, they may be utilized as drugs in controlling disease caused via SARS-COV2, after further investigation.

Communicated by Ramaswamy H. Sarma

Distinguishing drug/non-drug-like small molecules in drug discovery using deep belief network

The advent of computational methods for efficient prediction of the druglikeness of small molecules and their ever-burgeoning applications in the fields of medicinal chemistry and drug industries have been a profound scientific development, since only a few amounts of the small molecule libraries were identified as approvable drugs. In this study, a deep belief network was utilized to construct a druglikeness classification model. For this purpose, small molecules and approved drugs from the ZINC database were selected for the unsupervised pre-training step and supervised training step. Various binary fingerprints such as Macc 166 bit, PubChem 881 bit, and Morgan 2048 bit as data features were investigated. The report revealed that using an unsupervised pre-training phase can lead to a good performance model and generalizability capability. Accuracy, precision, and recall of the model for Macc features were 97%, 96%, and 99%, respectively. For more consideration about the generalizability of the model, the external data by expression and investigational drugs in drug banks as drug data and randomly selected data from the ZINC database as non-drug were created. The results confirmed the good performance and generalizability capability of the model. Also, the outcomes depicted that a large proportion of misclassified non-drug small molecules ascertain the bioavailability conditions and could be investigated as a drug in the future. Furthermore, our model attempted to tap potential opportunities as a drug filter in drug discovery.

A computational structural biology study to understand the impact of mutation on structure-function relationship of inward-rectifier potassium ion channel Kir6.2 in human

Type 2 diabetes (T2D) is clinically characterized via hyperglycemia. Polymorphism rs5219 in the KCNJ11 gene is a risk factor for developing T2D in humans. KCNJ11 encodes the 'inward-rectifier potassium ion channel (Kir6.2)'. However, because of the absence of the complete crystal/NMR structures of Kir6.2 proteins, insight into its structure and function and its interaction with diverse ligands remain elusive to date. Therefore, a computational approach was employed for predicting the best plausible 'three-dimensional' structure of Kir6.2 as well as for studying the influence of mutation (p. GLU23LYS) on both architectures as well as the function of Kir6.2 employing simulation studies. Results obtained revealed that though, with increased time, 'Gibbs free energy' becomes positive, residues in wild type Kir6.2 experiences less random movement as compared to mutant Kir6.2. The less random movement of residues in wild type Kir6.2 represents the standard coupling between open and closing of 'K_ATP channel' and thus the normal secretion of insulin. The more dispersed motion of mutant Kir6.2 residues represents 'overactivity' of the 'K_ATP channel' and thus insulin 'under-secretion'. Further, molecular docking and simulation studies identified two phytochemicals/drugs, namely, A-348441 and chushizisin I, which retains the wild type property of Kir6.2 after binding with mutant protein. Unlike A-348441, this is for the first time, the present study is reporting about the plausible anti-diabetic property of chushizisin I. As these two phytochemicals/drugs, namely, A-348441 and chushizisin I, have passed ADMET test, in the near future, they may be utilized as anti-diabetic drugs after further investigation.Communicated by Ramaswamy H. Sarma.

A drug-likeness toolbox facilitates ADMET study in drug discovery

Undesirable pharmacokinetic (PK) properties or unacceptable toxicity are the main causes of the failure of drug candidates at the clinical trial stage. Since the concept of drug-likeness was first proposed, it has become an important consideration in the selection of compounds with desirable bioavailability during the early phases of drug discovery. Over the past decade, online resources have effectively facilitated drug-likeness studies in an economical and time-efficient manner. Here, we provide a comprehensive summary and comparison of current accessible online resources, in terms of their key features, application fields, and performance for in silico drug-likeness studies. We hope that the assembled toolbox will provide useful guidance to facilitate future in silico drug-likeness research.

Data Mining and Machine Learning Models for Predicting Drug Likeness and Their Disease or Organ Category

Data mining approaches can uncover underlying patterns in chemical and pharmacological property space decisive for drug discovery and development. Two of the most common approaches are visualization and machine learning methods. Visualization methods use dimensionality reduction techniques in order to reduce multi-dimension data into 2D or 3D representations with a minimal loss of information. Machine learning attempts to find correlations between specific activities or classifications for a set of compounds and their features by means of recurring mathematical models. Both models take advantage of the different and deep relationships that can exist between features of compounds, and helpfully provide classification of compounds based on such features or in case of visualization methods uncover underlying patterns in the feature space. Drug-likeness has been studied from several viewpoints, but here we provide the first implementation in chemoinformatics of the t-Distributed Stochastic Neighbor Embedding (t-SNE) method for the visualization and the representation of chemical space, and the use of different machine learning methods separately and together to form a new ensemble learning method called AL Boost. The models obtained from AL Boost synergistically combine decision tree, random forests (RF), support vector machine (SVM), artificial neural network (ANN), k nearest neighbors (kNN), and logistic regression models. In this work, we show that together they form a predictive model that not only improves the predictive force but also decreases bias. This resulted in a corrected classification rate of over 0.81, as well as higher sensitivity and specificity rates for the models. In addition, separation and good models were also achieved for disease categories such as antineoplastic compounds and nervous system diseases, among others. Such models can be used to guide decision on the feature landscape of compounds and their likeness to either drugs or other characteristics, such as specific or multiple disease-category(ies) or organ(s) of action of a molecule.

Prediction of anticancer molecules using hybrid model developed on molecules screened against NCI-60 cancer cell lines

Background

In past, numerous quantitative structure-activity relationship (QSAR) based models have been developed for predicting anticancer activity for a specific class of molecules against different cancer drug targets. In contrast, limited attempt have been made to predict the anticancer activity of a diverse class of chemicals against a wide variety of cancer cell lines. In this study, we described a hybrid method developed on thousands of anticancer and non-anticancer molecules tested against National Cancer Institute (NCI) 60 cancer cell lines.

Results

Our analysis of anticancer molecules revealed that majority of anticancer molecules contains 18–24 carbon atoms and are dominated by functional groups like R₂NH, R₃N, ROH, RCOR, and ROR. It was also observed that certain substructures (e.g., 1-methoxy-4-methylbenzene, 1-methoxy benzene, Nitrobenzene, Indole, Propenyl benzene) are more abundant in anticancer molecules. Next, we developed anticancer molecule prediction models using various machine-learning techniques and achieved maximum matthews correlation coefficient (MCC) of 0.81 with 90.40 % accuracy using support vector machine (SVM) based models. In another approach, a novel similarity or potency score based method has been developed using selected fragments/fingerprints and achieved maximum MCC of 0.82 with 90.65 % accuracy. Finally, we combined the strength of above methods and developed a hybrid method with maximum MCC of 0.85 with 92.47 % accuracy.

Conclusions

We developed a hybrid method utilizing the best of machine learning and potency score based method. The highly accurate hybrid method can be used for classification of anticancer and non-anticancer molecules. In order to facilitate scientific community working in the field of anticancer drug discovery, we integrate hybrid and potency method in a web server CancerIN. This server provides various facilities that includes; virtual screening of anticancer molecules, analog based drug design, and similarity with known anticancer molecules (http://crdd.osdd.net/oscadd/cancerin).

Electronic supplementary material

The online version of this article (doi:10.1186/s12885-016-2082-y) contains supplementary material, which is available to authorized users.

Drug-symptom networking: Linking drug-likeness screening to drug discovery

Understanding the relationships between drugs and symptoms has broad medical consequences, yet a comprehensive description of the drug-symptom associations is currently lacking. Here, 1441 FDA-approved drugs were collected, and PCA was used to extract 122 descriptors which explained 91% of the variance. Then, a k-means++ method was employed to partition the drug dataset into 3 clusters, and 3 corresponding SVDD models (drug-likeness screening models) were constructed with an overall accuracy of up to 95.6%. Furthermore, 6878 herbal molecules from the TcmSP™ database were screened by the above 3 SVDD model to obtain 5309 candidate drug molecules with highly accept classification of 77.19%. To assess the accuracy of the SVDD models, 8559 herbal molecule-symptom co-occurrences were mined from Pubmed abstracts, involving 697 herbal molecules and 314 symptoms. Most of the 697 herbal molecules could be found in the accepted SVDD data (5309 molecules), showing the potential of the SVDD for the screening of drug candidates. Moreover, a herbal molecule-herbal molecule network and a herbal molecule-symptom were constructed. Overall, the results provided a new drug-likeness screening approach independent to abnormal training data, and the comprehensive collection of herbal molecule-symptom associations formed a new data resource for systematic characterization of the symptom-oriented medicines.

Insights into the Interactions of Fasciola hepatica Cathepsin L3 with a Substrate and Potential Novel Inhibitors through In Silico Approaches

Background

Fasciola hepatica is the causative agent of fascioliasis, a disease affecting grazing animals, causing economic losses in global agriculture and currently being an important human zoonosis. Overuse of chemotherapeutics against fascioliasis has increased the populations of drug resistant parasites. F. hepatica cathepsin L3 is a protease that plays important roles during the life cycle of fluke. Due to its particular collagenolytic activity it is considered an attractive target against the infective phase of F. hepatica.

Methodology/Principal Findings

Starting with a three dimensional model of FhCL3 we performed a structure-based design of novel inhibitors through a computational study that combined virtual screening, molecular dynamics simulations, and binding free energy (ΔG_bind) calculations. Virtual screening was carried out by docking inhibitors obtained from the MYBRIDGE-HitFinder database inside FhCL3 and human cathepsin L substrate-binding sites. On the basis of dock-scores, five compounds were predicted as selective inhibitors of FhCL3. Molecular dynamic simulations were performed and, subsequently, an end-point method was employed to predict ΔG_bind values. Two compounds with the best ΔG_bind values (-10.68 kcal/mol and -7.16 kcal/mol), comparable to that of the positive control (-10.55 kcal/mol), were identified. A similar approach was followed to structurally and energetically characterize the interface of FhCL3 in complex with a peptidic substrate. Finally, through pair-wise and per-residue free energy decomposition we identified residues that are critical for the substrate/ligand binding and for the enzyme specificity.

Conclusions/Significance

The present study is the first computer-aided drug design approach against F. hepatica cathepsins. Here we predict the principal determinants of binding of FhCL3 in complex with a natural substrate by detailed energetic characterization of protease interaction surface. We also propose novel compounds as FhCL3 inhibitors. Overall, these results will foster the future rational design of new inhibitors against FhCL3, as well as other F. hepatica cathepsins.

Fascioliosis is considered an emerging disease in humans, causing important losses in global agriculture through the infection of livestock animals. The outcome of resistant parasites has increased the search for new drugs which may contribute to disease control. In recent decades, Fasciola cathepsins (FhCs) have been defined as the principal virulence factors of this parasite. Despite being in the same protein family, they have different specificities and, thus, distinct roles throughout the fluke life cycle. Differences in specificity have been attributed to a few variations in the sequence of key FhCs subsites. Currently, the structure-based drug design of inhibitors against Fasciola cathepsin Ls (FhCLs) with unknown structures is possible due to the availability of the three-dimensional structure of FhCL1. Our detailed structural analysis of the major infective juvenile enzyme (FhCL3) identifies the molecular determinants for protein binding. Also, novel potential inhibitors against FhCL3 are proposed, which might reduce host invasion and penetration processes. These compounds are predicted to interact with the binding site of the enzyme, therefore they could prevent substrate processing by competitive inhibition. The structure-based drug design strategy described here will be useful for the development of new potent and selective inhibitors against other FhCs.

QSAR based model for discriminating EGFR inhibitors and non-inhibitors using Random forest

BACKGROUND

Epidermal Growth Factor Receptor (EGFR) is a well-characterized cancer drug target. In the past, several QSAR models have been developed for predicting inhibition activity of molecules against EGFR. These models are useful to a limited set of molecules for a particular class like quinazoline-derivatives. In this study, an attempt has been made to develop prediction models on a large set of molecules (~3500 molecules) that include diverse scaffolds like quinazoline, pyrimidine, quinoline and indole.

RESULTS

We train, test and validate our classification models on a dataset called EGFR10 that contains 508 inhibitors (having inhibition activity IC50 less than 10 nM) and 2997 non-inhibitors. Our Random forest based model achieved maximum MCC 0.49 with accuracy 83.7% on a validation set using 881 PubChem fingerprints. In this study, frequency-based feature selection technique has been used to identify best fingerprints. It was observed that PubChem fingerprints FP380 (C(~O) (~O)), FP579 (O = C-C-C-C), FP388 (C(:C) (:N) (:N)) and FP 816 (ClC1CC(Br)CCC1) are more frequent in the inhibitors in comparison to non-inhibitors. In addition, we created different datasets namely EGFR100 containing inhibitors having IC50 < 100 nM and EGFR1000 containing inhibitors having IC50 < 1000 nM. We trained, test and validate our models on datasets EGFR100 and EGFR1000 datasets and achieved and maximum MCC 0.58 and 0.71 respectively. In addition, models were developed for predicting quinazoline and pyrimidine based EGFR inhibitors.

CONCLUSIONS

In summary, models have been developed on a large set of molecules of various classes for discriminating EGFR inhibitors and non-inhibitors. These highly accurate prediction models can be used to design and discover novel EGFR inhibitors. In order to provide service to the scientific community, a web server/standalone EGFRpred also has been developed ( http://crdd.osdd.net/oscadd/egfrpred/ ).

Prediction of cancer proteins by integrating protein interaction, domain frequency, and domain interaction data using machine learning algorithms

Many proteins are known to be associated with cancer diseases. It is quite often that their precise functional role in disease pathogenesis remains unclear. A strategy to gain a better understanding of the function of these proteins is to make use of a combination of different aspects of proteomics data types. In this study, we extended Aragues's method by employing the protein-protein interaction (PPI) data, domain-domain interaction (DDI) data, weighted domain frequency score (DFS), and cancer linker degree (CLD) data to predict cancer proteins. Performances were benchmarked based on three kinds of experiments as follows: (I) using individual algorithm, (II) combining algorithms, and (III) combining the same classification types of algorithms. When compared with Aragues's method, our proposed methods, that is, machine learning algorithm and voting with the majority, are significantly superior in all seven performance measures. We demonstrated the accuracy of the proposed method on two independent datasets. The best algorithm can achieve a hit ratio of 89.4% and 72.8% for lung cancer dataset and lung cancer microarray study, respectively. It is anticipated that the current research could help understand disease mechanisms and diagnosis.

Synthesis and antiprotozoal activities of new 3-azabicyclo[3.2.2]nonanes

Some antimalarial agents in use typically bear basic side chains as ligands. Such ligands were attached to the amino substituent of a bridgehead atom of already antiprotozoal active 3-azabicyclo[3.2.2]nonanes. Structure verification was done by NMR measurements. The new compounds were tested for their antiplasmodial and antitrypanosomal activities against Plasmodium falciparum K 1 (multiresistant) and Trypanosoma brucei rhodesiense as well as for their cytotoxicity against L6 cells. Their activities are compared to those of already prepared compounds and structure-activity relationships are discussed.

A 'rule of 0.5' for the metabolite-likeness of approved pharmaceutical drugs

We exploit the recent availability of a community reconstruction of the human metabolic network ('Recon2') to study how close in structural terms are marketed drugs to the nearest known metabolite(s) that Recon2 contains. While other encodings using different kinds of chemical fingerprints give greater differences, we find using the 166 Public MDL Molecular Access (MACCS) keys that 90 % of marketed drugs have a Tanimoto similarity of more than 0.5 to the (structurally) 'nearest' human metabolite. This suggests a 'rule of 0.5' mnemonic for assessing the metabolite-like properties that characterise successful, marketed drugs. Multiobjective clustering leads to a similar conclusion, while artificial (synthetic) structures are seen to be less human-metabolite-like. This 'rule of 0.5' may have considerable predictive value in chemical biology and drug discovery, and may represent a powerful filter for decision making processes.

Bio/chemoinformatics in India: an outlook

With the advent of significant establishment and development of Internet facilities and computational infrastructure, an overview on bio/chemoinformatics is presented along with its multidisciplinary facts, promises and challenges. The Government of India has paved the way for more profound research in biological field with the use of computational facilities and schemes/projects to collaborate with scientists from different disciplines. Simultaneously, the growth of available biomedical data has provided fresh insight into the nature of redundant and compensatory data. Today, bioinformatics research in India is characterized by a powerful grid computing systems, great variety of biological questions addressed and the close collaborations between scientists and clinicians, with a full spectrum of focuses ranging from database building and methods development to biological discoveries. In fact, this outlook provides a resourceful platform highlighting the funding agencies, institutes and industries working in this direction, which would certainly be of great help to students seeking their career in bioinformatics. Thus, in short, this review highlights the current bio/chemoinformatics trend, educations, status, diverse applicability and demands for further development.