Search

Motivation: The absorption, distribution, metabolism, excretion, and toxicity (ADMET) of drugs plays a key role in determining which among the potential candidates are to be prioritized. In silico approaches based on machine learning methods are becoming increasing popular, but are nonetheless limited by the availability of data. With a view to making both data and models available to the scientific community, we have developed FPADMET which is a repository of molecular fingerprint-based predictive models for ADMET properties. In this article, we have examined the efficacy of fingerprint-based machine learning models for a large number of ADMET-related properties. The predictive ability of a set of 20 different binary fingerprints (based on substructure keys, atom pairs, local path environments, as well as custom fingerprints such as all-shortest paths) for over 50 ADMET and ADMET-related endpoints have been evaluated as part of the study. We find that for a majority of the properties, fingerprint-based random forest models yield comparable or better performance compared with traditional 2D/3D molecular descriptors., Availability: The models are made available as part of open access software that can be downloaded from https://gitlab.com/vishsoft/fpadmet ., (© 2021. The Author(s).)

• The concept of a universal translator was used to learn molecular features and stored them in a universal digital chemical space by translating and projecting the chemical representation SMILES to a high-dimensional space that can be collapsed into different molecular fingerprints. • This universal digital chemical space can serve as a unified regressor for predicting different pure component properties. Successful applications to computed electrical and thermodynamic properties were demonstrated Computer-aided molecular design requires the ability to predict different molecular properties of interesting from using molecular structure. Traditional quantitative structural property relations were developed by extracting molecular features for predicting various properties. Hence domains of molecular features are different for predictions of different properties. In this work, the concept of a universal translator was used to develop a universal digital chemical space by translating and projecting the chemical representation SMILES to a high-dimensional space that can be collapsed into different molecular fingerprints. We demonstrated different kinds of pure component properties, such as electrical and thermodynamic properties can be predicted by a simple input of molecular structure, SMILES. This method eliminates the need to manually extract different molecular features for predicting different properties. The ability of model to predict sigma profiles also pave the way of prediction phase equilibria of mixtures using molecular structure only. Image, graphical abstract [ABSTRACT FROM AUTHOR]

The process of blocking 5-lipoxygenase (5-LOX) catalyzed leukotriene biosynthesis has been recognized for the past few decades as a promising therapeutic strategy for acute inflammatory, allergic, and respiratory diseases. Due to the toxicity effect of FDA approved 5-LOX inhibitor zileuton, novel 5-LOX inhibitors have been sought by the scientific community. As a result, a significant and relevant amount of information on the structure-activity of 5-LOX inhibitors has been released and stored in public databases. In this study, we aimed at the comprehensive cheminformatic characterization of the diversity and complexity of the chemical space of 5-LOX inhibitors and its activating protein FLAP inhibitors by comparing it with the Approved drug space and virtual LOX library. The visual representation of the property space indicates some compounds in the 5-LOX inhibitors space broaden the traditional medicinal space. The structural diversity of the databases is computed using complementary approaches, including Physicochemical Property (PCP) descriptors, molecular fingerprints, and molecular scaffold. With the apparent exception of approved drugs, the 5-LOX dataset shows more diversity compared to FLAP and LOX virtual library set. This study was able to identify the underlying patterns in the chemical and pharmacological properties space that were decisive for the drug discovery and development of 5-LOX inhibitors. Image 1 • Diversity and complexity of the 5-LOX and FLAP inhibitors sets has been explored. • These databases show a comparable polarity and flexibility to the approved drugs. • 5-LOX inhibitors cover most medicinal property space, but some are broadened. • New chemical structures must be created as FLAP inhibitors due to limited diversity. • Enamine LOX virtual library could provide novel potent 5-LOX inhibitor scaffolds. [ABSTRACT FROM AUTHOR]

Computational methods for predicting the macromolecular targets of drugs and drug-like compounds have evolved as a key technology in drug discovery. However, the established validation protocols leave several key questions regarding the performance and scope of methods unaddressed. For example, prediction success rates are commonly reported as averages over all compounds of a test set and do not consider the structural relationship between the individual test compounds and the training instances. In order to obtain a better understanding of the value of ligand-based methods for target prediction, we benchmarked a similarity-based method and a random forest based machine learning approach (both employing 2D molecular fingerprints) under three testing scenarios: a standard testing scenario with external data, a standard time-split scenario, and a scenario that is designed to most closely resemble real-world conditions. In addition, we deconvoluted the results based on the distances of the individual test molecules from the training data. We found that, surprisingly, the similarity-based approach generally outperformed the machine learning approach in all testing scenarios, even in cases where queries were structurally clearly distinct from the instances in the training (or reference) data, and despite a much higher coverage of the known target space. [ABSTRACT FROM AUTHOR]

• Molecular fingerprints (MF) were inputs for a deep neural network (DNN) for QSAR. • MF can be generated and understood more easily than molecular descriptors. • DNN-MF is a fast, robust, and easy modeling approach for predictive models. • DNN-MF is promising in other environmental fields, e.g., adsorption and toxicity. This work combined a Deep Neural Network (DNN) with molecular fingerprints (MF) to develop models to predict the OH radical rate constants of 593 organic contaminants. Molecular descriptors, most often used in establishing quantitative structural-activity relationships (QSARs), were not used here because of their complicated generation processes that rely on advanced physicochemical and computational knowledge. Instead, we only fed the most basic information of the contaminant structures, i.e., MF encoding the types of atoms and how they are connected, to DNN and DNN then developed predictive models automatically. Here, a dataset containing 457 contaminants and their OH rate constants was first used to develop predictive models by DNN-MF. The hence developed models showed comparable accuracy to the traditional QSARs. The root mean square error (RMSE) values of the test sets were 0.358-0.384. The length of 2048 bits for the MF and 3 hidden layers (each with 1024 neurons) were found to be the optimal parameters for DNN. The model containing additional 89 micorpollutants in the training set was then successfully applied to predict the OH rate constants of 17 organophosphorus flame retardants and 29 additional micropollutants, with comparable accuracy to the reported molecular descriptors-based QSARs. [ABSTRACT FROM AUTHOR]

Similarity measures are widely used in various areas from taxonomy to cheminformatics. To this end, a large number of similarity and distance measures (or, collectively, comparative measures) have been introduced, with only a few studies directed to revealing their inner relationships. We present a thorough analytical study of the conditions leading to two comparative measures providing equivalent results over a given set of molecules. A key part of this work is the introduction of a novel way to study the consistency between comparative measures: the differential consistency analysis (DCA). This tool reveals how the consistency can be established in an analytical way with minimal (or no) assumptions. We found that the consensus between Tanimoto and the Cosine coefficients improved by choosing a reference whose similarity to the rest of the molecules varies less, or by representing the molecules in a way that does not depend strongly on their size (i. e. bit frequency in the chosen fingerprint representation). The presented derivations are just some generic examples; DCA can be applied widely and for all binary similarity coefficients introduced so far, independently from the molecular representations., (© 2021 Wiley-VCH GmbH.)

Drug-induced liver injury (DILI) is a major factor in the development of drugs and the safety of drugs. If the DILI cannot be effectively predicted during the development of the drug, it will cause the drug to be withdrawn from markets. Therefore, DILI is crucial at the early stages of drug research. This work presents a 2-class ensemble classifier model for predicting DILI, with 2D molecular descriptors and fingerprints on a dataset of 450 compounds. The purpose of our study is to investigate which are the key molecular fingerprints that may cause DILI risk, and then to obtain a reliable ensemble model to predict DILI risk with these key factors. Experimental results suggested that 8 molecular fingerprints are very critical for predicting DILI, and also obtained the best ratio of molecular fingerprints to molecular descriptors. The result of the 5-fold cross-validation of the ensemble vote classifier method obtain an accuracy of 77.25%, and the accuracy of the test set was 81.67%. This model could be used for drug-induced liver injury prediction. [ABSTRACT FROM AUTHOR]

Natural products (NPs) remain the most prolific resource for the development of small-molecule drugs. Here we report a new machine learning approach that allows the identification of natural products with high accuracy. The method also generates similarity maps, which highlight atoms that contribute significantly to the classification of small molecules as a natural product or synthetic molecule. The method can hence be utilized to (i) identify natural products in large molecular libraries, (ii) quantify the natural product-likeness of small molecules, and (iii) visualize atoms in small molecules that are characteristic of natural products or synthetic molecules. The models are based on random forest classifiers trained on data sets consisting of more than 265,000 to 322,000 natural products and synthetic molecules. Two-dimensional molecular descriptors, MACCS keys and Morgan2 fingerprints were explored. On an independent test set the models reached areas under the receiver operating characteristic curve (AUC) of 0.997 and Matthews correlation coefficients (MCCs) of 0.954 and higher. The method was further tested on data from the Dictionary of Natural Products, ChEMBL and other resources. The best-performing models are accessible as a free web service at http://npscout.zbh.uni-hamburg.de/npscout. [ABSTRACT FROM AUTHOR]

In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure in the form of a SMILES sequence, gene expression profiles of tumors, and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based encoder significantly outperforms a baseline model trained on Morgan fingerprints and a selection of encoders based on SMILES, as well as the previously reported state-of-the-art for multimodal drug sensitivity prediction ( R 2 = 0.86 and RMSE = 0.89). Moreover, the explainability of our approach is demonstrated by a thorough analysis of the attention weights. We show that the attended genes significantly enrich apoptotic processes and that the drug attention is strongly correlated with a standard chemical structure similarity index. Finally, we report a case study of two receptor tyrosine kinase (RTK) inhibitors acting on a leukemia cell line, showcasing the ability of the model to focus on informative genes and submolecular regions of the two compounds. The demonstrated generalizability and the interpretability of our model testify to its potential for in silico prediction of anticancer compound efficacy on unseen cancer cells, positioning it as a valid solution for the development of personalized therapies as well as for the evaluation of candidate compounds in de novo drug design.

Transform-MinER (Transforming Molecules in Enzyme Reactions) is a web application facilitating the exploration of chemical biosynthetic space, guiding the user toward promising start points for enzyme design projects or directed evolution experiments. Two types of search are possible: Molecule Search allows a user to submit a source substrate enabling Transform-MinER to search for enzyme reactions acting on similar substrates, whereas Path Search additionally allows a user to submit a target molecule enabling Transform-MinER to search for a path of enzyme reactions acting on similar substrates to link source and target. Transform-MinER searches for potential reaction centers in the source substrate and uses chemoinformatic fingerprints to identify those that are situated in molecular environments similar to native counterparts, prioritizing steps that move closer to the target using reactions most similar to native in its exploration of search space. The ligand-based methodology behind Transform-MinER is presented, and its performance is validated yielding 90% success rates: first, on a data set of native pathways from the KEGG database, and second, on a data set of de novo enzyme reactions.

Aim: Fragment-based drug design or bioisosteric replacement is used to find new actives with low (or no) similarity to existing ones but requires the synthesis of nonexisting compounds to prove their predicted bioactivity. Protein-ligand docking or pharmacophore screening are alternatives but they can become computationally expensive when applied to very large databases such as ZINC. Therefore, fast strategies are necessary to find new leads in such databases. Materials & methods: We designed a computational strategy to find lead molecules with very low (or no) similarity to existing actives and applied it to DPP-IV. Results: The bioactivity assays confirm that this strategy finds new leads for DPP-IV inhibitors. Conclusion: This computational strategy reduces the time of finding new lead molecules.

The search and use of bioactive compounds for different applications have been investigated, since ancient time. Virtual screening (VS) has emerged as alternative methodological approach to the Combinatory Chemistry and High-Throughput Screening (HTS) in identifying novel drug candidates. In VS, only compounds that are selected applying different computational tools to huge virtual libraries of compounds are further tested in vitro. However, the effective use of VS model applications have some challenges such as the inherent complexity of the ligand-receptor interactions as well as by other factors such as ligand and receptor multiple conformations and also ligand metabolic stabilities and toxicities. Altogether these difficulties are hardly overcome using only one computational tool. Therefore, in the literature, it has been suggested to apply a sequence of different filters, such as filters that select compounds through similarity, pharmacophore and docking. In this review, we describe the advantages, limitations and examples of recent successful applications of some of these filters, including drug-like properties, structural properties, 2D similarity, pharmacophore, shape and docking filters. Moreover, we present the main steps involved in the preparation of virtual libraries of compounds that can be used in the VS.

Drug promiscuity or polypharmacology is the ability of small molecules to interact with multiple protein targets simultaneously. In drug discovery, understanding the polypharmacology of potential drug molecules is crucial to improve their efficacy and safety, and to discover the new therapeutic potentials of existing drugs. Over the past decade, several computational methods have been developed to study the polypharmacology of small molecules, many of which are available as Web services. In this chapter, we review some of these Web tools focusing on ligand based approaches. We highlight in particular our recently developed polypharmacology browser (PPB) and its application for finding the side targets of a new inhibitor of the TRPV6 calcium channel.

Virtual screening has become a widely used technique for helping in drug discovery processes. The key to this success is its ability to aid in the identification of novel bioactive compounds by screening large molecular databases. Several web servers have emerged in the last few years supplying platforms to guide users in screening publicly accessible chemical databases in a reasonable time. In this review, we discuss a representative set of online virtual screening servers and their underlying similarity algorithms. Other related topics, such as molecular representation or freely accessible databases are also treated. The most relevant contributions to this review arise from critical discussions concerning the pros and cons of servers and algorithms, and the challenges that future works must solve in a virtual screening framework.

Increase in the number of new chemicals synthesized in past decades has resulted in constant growth in the development and application of computational models for prediction of activity as well as safety profiles of the chemicals. Most of the time, such computational models and its application must deal with imbalanced chemical data. It is indeed a challenge to construct a classifier using imbalanced data set. In this study, we analyzed and validated the importance of different sampling methods over non-sampling method, to achieve a well-balanced sensitivity and specificity of a machine learning model trained on imbalanced chemical data. Additionally, this study has achieved an accuracy of 93.00%, an AUC of 0.94, F1 measure of 0.90, sensitivity of 96.00% and specificity of 91.00% using SMOTE sampling and Random Forest classifier for the prediction of Drug Induced Liver Injury (DILI). Our results suggest that, irrespective of data set used, sampling methods can have major influence on reducing the gap between sensitivity and specificity of a model. This study demonstrates the efficacy of different sampling methods for class imbalanced problem using binary chemical data sets.

Aim: HDAC8 is one of the crucial enzymes involved in malignancy. Structural explorations of HDAC8 inhibitory activity and selectivity are required., Materials & Methods: A mathematical framework was constructed to explore important molecular fragments responsible for HDAC8 inhibition. Bayesian classification models were developed on a large set of structurally diverse HDAC8 inhibitors., Results: This study helps to understand the structural importance of HDAC8 inhibitors. The hydrophobic aryl cap function is important for HDAC8 inhibition whereas benzamide moiety shows a negative impact on HDAC8 inhibition., Conclusion: This work validates our previously proposed structural features for better HDAC8 inhibition. The comparative learning between the statistical and intelligent methods will surely enrich future drug design aspects of HDAC8 inhibitors.

The 7th edition of Union for International Cancer Control (UICC) staging system moved gastroesophageal junction (GEJ) cancers from gastric to esophageal group. Since clinical management is strongly influenced by this staging system, we looked at molecular fingerprints of GEJ tumors and compared to gastric and esophageal profiles. We aimed at elucidating whether GEJ cancers cluster with gastric or esophageal groups according to mRNA and microRNA expression pattern, since this might represent tumor identity. The clinical and expression data were downloaded from The Cancer Genome Atlas (TCGA) with 395 stomach, 184 esophagus and 521 colon samples for mRNA analyses and 392 stomach, 175 esophagus and 459 colon samples for microRNA comparisons. Both Principal Component Analysis (PCA) and Heat Map plots were performed in R platform, using Log 2 transformation of RPKM normalized data. Differential Expression Analysis was also performed in R, using RAW data and the DESeq2 package. The mRNAs and microRNAs were tagged as differentially expressed if they met the following criteria: i) FDR adjusted p-value < 0.05; and ii) |Log 2 (fold-change)| > 2. Esophagus squamous cell carcinoma (ESCC) clustered apart of the others tumors, while adenocarcinomas (AC) clustered all together according to both mRNAs and microRNAs expression patterns. The HMs of the differentially expressed mRNAs and microRNAs also demonstrated that ESCC belongs to a different group, while AC molecular signature of esophagus looks like AC of the cardia and non cardia regions. Even distal gastric cancers are quite similar to AC of the lower esophagus, demonstrating that esophagus AC relies much closer to gastric cancers than to esophagus cancers. By using robust molecular fingerprints, it was strongly demonstrated that GEJ tumors looks more like gastric cancers than esophageal cancers, despite of tumor heterogeneity., Competing Interests: CONFLICTS OF INTEREST The authors declare that they have no conflicts of interest.

In recent years, integration of in silico approaches to natural product (NP) research reawakened the declined interest in NP-based drug discovery efforts. In particular, advancements in cheminformatics enabled comparison of NP databases with contemporary small-molecule libraries in terms of molecular properties and chemical space localizations. Virtual screening and target fishing approaches were successful in recognizing the untold macromolecular targets for NPs to exploit the unmet therapeutic needs. Developments in molecular docking and scoring methods along with molecular dynamics enabled to predict the target-ligand interactions more accurately taking into consideration the remarkable structural complexity of NPs. Hence, innovative in silico strategies have contributed valuably to the NP research in drug discovery processes as reviewed herein. [Formula: see text].

Beef, buffalo, and pork adulteration in the food chain is an emerging and sensitive issue. Current molecular techniques to authenticate these species depend on polymerase chain reaction (PCR) assays involving long and single targets which break down under natural decomposition and/or processing treatments. This novel multiplex polymerase chain reaction-restriction fragment length polymorphism assay targeted two different gene sites for each of the bovine, buffalo, and porcine materials. This authentication ensured better security, first through a complementation approach because it is highly unlikely that both sites will be missing under compromised states, and second through molecular fingerprints. Mitochondrial cytochrome b and ND5 genes were targeted, and all targets (73, 90, 106, 120, 138, and 146 bp) were stable under extreme boiling and autoclaving treatments. Target specificity and authenticity were ensured through cross-amplification reaction and restriction digestion of PCR products with AluI, EciI, FatI, and CviKI-1 enzymes. A survey of Malaysian frankfurter products revealed rampant substitution of beef with buffalo but purity in porcine materials.

Information about the interactions of drug compounds with proteins in cellular networking is very important for drug development. Unfortunately, all the existing predictors for identifying drug-protein interactions were trained by a skewed benchmark data-set where the number of non-interactive drug-protein pairs is overwhelmingly larger than that of the interactive ones. Using this kind of highly unbalanced benchmark data-set to train predictors would lead to the outcome that many interactive drug-protein pairs might be mispredicted as non-interactive. Since the minority interactive pairs often contain the most important information for drug design, it is necessary to minimize this kind of misprediction. In this study, we adopted the neighborhood cleaning rule and synthetic minority over-sampling technique to treat the skewed benchmark datasets and balance the positive and negative subsets. The new benchmark datasets thus obtained are called the optimized benchmark datasets, based on which a new predictor called iDrug-Target was developed that contains four sub-predictors: iDrug-GPCR, iDrug-Chl, iDrug-Ezy, and iDrug-NR, specialized for identifying the interactions of drug compounds with GPCRs (G-protein-coupled receptors), ion channels, enzymes, and NR (nuclear receptors), respectively. Rigorous cross-validations on a set of experiment-confirmed datasets have indicated that these new predictors remarkably outperformed the existing ones for the same purpose. To maximize users' convenience, a public accessible Web server for iDrug-Target has been established at http://www.jci-bioinfo.cn/iDrug-Target/ , by which users can easily get their desired results. It has not escaped our notice that the aforementioned strategy can be widely used in many other areas as well.

A docking-rescoring method, based on per-residue van der Waals (VDW), electrostatic (ES), or hydrogen bond (HB) energies has been developed to aid discovery of ligands that have interaction signatures with a target (footprints) similar to that of a reference. Biologically useful references could include known drugs, inhibitors, substrates, transition states, or side-chains that mediate protein-protein interactions. Termed footprint similarity (FPS) score, the method, as implemented in the program DOCK, was validated and characterized using: (1) pose identification, (2) crossdocking, (3) enrichment, and (4) virtual screening. Improvements in pose identification (6–12%) were obtained using footprint-based (FPS(VDW+ES)) vs. standard DOCK (DCE(VDW+ES)) scoring as evaluated on three large datasets (680–775 systems) from the SB2010 database. Enhanced pose identification was also observed using FPS (45.4% or 70.9%) compared with DCE (17.8%) methods to rank challenging crossdocking ensembles from carbonic anhydrase. Enrichment tests, for three representative systems, revealed FPSVDW+ES scoring yields significant early fold enrichment in the top 10% of ranked databases. For EGFR, top FPS poses are nicely accommodated in the molecular envelope defined by the reference in comparison with DCE, which yields distinct molecular weight bias toward larger molecules. Results from a representative virtual screen of ca. 1 million compounds additionally illustrate how ligands with footprints similar to a known inhibitor can readily be identified from within large commercially available databases. By providing an alternative way to rank ligand poses in a simple yet directed manner we anticipate that FPS scoring will be a useful tool for docking and structure-based design., (2011 Wiley Periodicals, Inc.)