Cheminformatics Analysis and Modeling with MacrolactoneDB

Machine learning models to predict ligand binding affinity for the orexin 1 receptor

The orexin 1 receptor (OX1R) is a G-protein coupled receptor that regulates a variety of physiological processes through interactions with the neuropeptides orexin A and B. Selective OX1R antagonists exhibit therapeutic effects in preclinical models of several behavioral disorders, including drug seeking and overeating. However, currently there are no selective OX1R antagonists approved for clinical use, fueling demand for novel compounds that act at this target. In this study, we meticulously curated a dataset comprising over 1300 OX1R ligands using a stringent filter and criteria cascade. Subsequently, we developed highly predictive quantitative structure-activity relationship (QSAR) models employing the optimized hyper-parameters for the random forest machine learning algorithm and twelve 2D molecular descriptors selected by recursive feature elimination with a 5-fold cross-validation process. The predictive capacity of the QSAR model was further assessed using an external test set and enrichment study, confirming its high predictivity. The practical applicability of our final QSAR model was demonstrated through virtual screening of the DrugBank database. This revealed two FDA-approved drugs (isavuconazole and cabozantinib) as potential OX1R ligands, confirmed by radiolabeled OX1R binding assays. To our best knowledge, this study represents the first report of highly predictive QSAR models on a large comprehensive dataset of diverse OX1R ligands, which should prove useful for the discovery and design of new compounds targeting this receptor.

A critical assessment of bioactive compounds databases

Compound databases (DBs) are essential tools for drug discovery. The number of DBs in public domain is increasing, so it is important to analyze these DBs. In this article, the main characteristics of 64 DBs will be presented. The methodological strategy used was a literature search. To analyze the characteristics obtained in the review, the DBs were categorized into two subsections: Open Access and Commercial DBs. Open access includes generalist DBs (containing compounds of diverse origins), DBs with specific applicability, DBs exclusive to natural products and those containing compounds with specific pharmacological action. The literature review showed that there are challenges to making these repositories available, such as standardizing information curation practices and funding to maintain and sustain them.

Current State-of-the-Art Toward Chemoenzymatic Synthesis of Polyketide Natural Products

Polyketide natural products have significant promise as pharmaceutical targets for human health and as molecular tools to probe disease and complex biological systems. While the biosynthetic logic of polyketide synthases (PKS) is well-understood, biosynthesis of designer polyketides remains challenging due to several bottlenecks, including substrate specificity constraints, disrupted protein-protein interactions, and protein solubility and folding issues. Focusing on substrate specificity, PKSs are typically interrogated using synthetic thioesters. PKS assembly lines and their products offer a wealth of information when studied in a chemoenzymatic fashion. This review provides an overview of the past two decades of polyketide chemoenzymatic synthesis and their contributions to the field of chemical biology. These synthetic strategies have successfully yielded natural product derivatives while providing critical insights into enzymatic promiscuity and mechanistic activity.

Prediction of lead (Pb) adsorption on attapulgite clay using the feasibility of data intelligence models

This study investigates the performance of support vector machine (SVM), multivariate adaptive regression spline (MARS), and random forest (RF) models for predicting the lead (Pb) adsorption by attapulgite clay. Models are constructed using batch stochastic data of heavy metal (HM) concentrations under different physicochemical conditions. Implementation of auto-hyper-parameter tuning using grid-search approach and comparative analysis is performed against the benchmark artificial intelligence (AI) models. Models are constructed based on Pb concentration (IC), the dosage of attapulgite clay (dose), contact time (CT), pH, and NaNO3 (SN). Principle component analysis (PCA) and correlation analysis (CA) methods are integrated to assess the importance of the applied predictors and their relationship with the target. Research findings approved the potential of the grid-RF model as a marginal superior predictive model against the grid-SVM in terms of MAE, i.e., 3.29 and 3.34, respectively; moreover, the md scored the same, i.e., 0.93, which reveals the potential predictability for both. Nonetheless, grid-MARS and standalone MARS models remained likewise in their predictability. IC parameter demonstrated the highest influential among all the predictors with the highest value of importance in the case of all three evaluators. The solution pH and dose stands together with marginal differences in case of PCA method; however, solution pH and CT appeared with similarity impact using the PCA method.

Macrocycle-Antibiotic Hybrids: A Path to Clinical Candidates

The tale of abate in antibiotics continued defense mechanisms that chaperone the rise of drug-defying superbugs—on the other hand, the astray in antibacterial drug discovery and development. Our salvation lies in circumventing the genesis of resistance. Considering the competitive advantages of antibacterial chemotherapeutic agents equipped with multiple warheads against resistance, the development of hybrids has rejuvenated. The adoption of antibiotic hybrid paradigm to macrocycles has advanced novel chemical entities to clinical trials. The multi-targeted TD-1792, for instance, retained potent antibacterial activities against multiple strains that are resistant to its constituent, vancomycin. Moreover, the antibiotic conjugation of rifamycins has provided hybrid clinical candidates with desirable efficacy and safety profiles. In 2020, the U.S. FDA has granted an orphan drug designation to TNP-2092, a conjugate of rifamycin and fluoroquinolone, for the treatment of prosthetic joint infections. DSTA4637S is a pioneer antibacterial agent under clinical development and represents a novel class of bacterial therapy, that is, antibody–antibiotic conjugates. DSTA4637S is effective against the notorious persistent S. aureus bacteremia, a revelation of the abracadabra potential of antibiotic hybrid approaches.

Partitioning Pattern of Natural Products Based on Molecular Properties Descriptors Representing Drug-Likeness

A cheminformatics procedure for a partitioning model based on 135 natural compounds including Flavonoids, Saponins, Alkaloids, Terpenes and Triterpenes with drug-like features based on a descriptors pool was developed. The knowledge about the applicability of natural products as a unique source for the development of new candidates towards deadly infectious disease is a contemporary challenge for drug discovery. We propose a partitioning scheme for unveiling drug-likeness candidates with properties that are important for a prompt and efficient drug discovery process. In the present study, the vantage point is about the matching of descriptors to build the partitioning model applied to natural compounds with diversity in structures and complexity of action towards the severe diseases, as the actual SARS-CoV-2 virus. In the times of the de novo design techniques, such tools based on a chemometric and symmetrical effect by the implied descriptors represent another noticeable sign for the power and level of the descriptors applicability in drug discovery in establishing activity and target prediction pipeline for unknown drugs properties.

StreptomeDB 3.0: an updated compendium of streptomycetes natural products

Antimicrobial resistance is an emerging global health threat necessitating the rapid development of novel antimicrobials. Remarkably, the vast majority of currently available antibiotics are natural products (NPs) isolated from streptomycetes, soil-dwelling bacteria of the genus Streptomyces. However, there is still a huge reservoir of streptomycetes NPs which remains pharmaceutically untapped and a compendium thereof could serve as a source of inspiration for the rational design of novel antibiotics. Initially released in 2012, StreptomeDB (http://www.pharmbioinf.uni-freiburg.de/streptomedb) is the first and only public online database that enables the interactive phylogenetic exploration of streptomycetes and their isolated or mutasynthesized NPs. In this third release, there are substantial improvements over its forerunners, especially in terms of data content. For instance, about 2500 unique NPs were newly annotated through manual curation of about 1300 PubMed-indexed articles, published in the last five years since the second release. To increase interoperability, StreptomeDB entries were hyperlinked to several spectral, (bio)chemical and chemical vendor databases, and also to a genome-based NP prediction server. Moreover, predicted pharmacokinetic and toxicity profiles were added. Lastly, some recent real-world use cases of StreptomeDB are highlighted, to illustrate its applicability in life sciences.

The year 2020 in natural product bioinformatics: an overview of the latest tools and databases

Covering: 2020 Bioinformatic approaches to document and analyse chemical structures, biosynthetic gene clusters and analytical data play an important role in the study of natural products. Every year, such a large number of new algorithms, tools and databases are released, that it is difficult to keep track of all the latest developments. The aim of this short article is to provide a concise overview of and reference to the major tools, methods and databases that have been released in the past year.

Bioactivity Comparison across Multiple Machine Learning Algorithms Using over 5000 Datasets for Drug Discovery

Machine learning methods are attracting considerable attention from the pharmaceutical industry for use in drug discovery and applications beyond. In recent studies, we and others have applied multiple machine learning algorithms and modeling metrics and, in some cases, compared molecular descriptors to build models for individual targets or properties on a relatively small scale. Several research groups have used large numbers of datasets from public databases such as ChEMBL in order to evaluate machine learning methods of interest to them. The largest of these types of studies used on the order of 1400 datasets. We have now extracted well over 5000 datasets from CHEMBL for use with the ECFP6 fingerprint and in comparison of our proprietary software Assay Central with random forest, k-nearest neighbors, support vector classification, naïve Bayesian, AdaBoosted decision trees, and deep neural networks (three layers). Model performance was assessed using an array of fivefold cross-validation metrics including area-under-the-curve, F1 score, Cohen's kappa, and Matthews correlation coefficient. Based on ranked normalized scores for the metrics or datasets, all methods appeared comparable, while the distance from the top indicated that Assay Central and support vector classification were comparable. Unlike prior studies which have placed considerable emphasis on deep neural networks (deep learning), no advantage was seen in this case. If anything, Assay Central may have been at a slight advantage as the activity cutoff for each of the over 5000 datasets representing over 570,000 unique compounds was based on Assay Central performance, although support vector classification seems to be a strong competitor. We also applied Assay Central to perform prospective predictions for the toxicity targets PXR and hERG to further validate these models. This work appears to be the largest scale comparison of these machine learning algorithms to date. Future studies will likely evaluate additional databases, descriptors, and machine learning algorithms and further refine the methods for evaluating and comparing such models.

Synthetic biology enabling access to designer polyketides

The full potential of polyketide discovery has yet to be reached owing to a lack of suitable technologies and knowledge required to advance engineering of polyketide biosynthesis. Recent investigations on the discovery, enhancement, and non-natural use of these biosynthetic gene clusters via computational biology, metabolic engineering, structural biology, and enzymology-guided approaches have facilitated improved access to designer polyketides. Here, we discuss recent successes in gene cluster discovery, host strain engineering, precursor-directed biosynthesis, combinatorial biosynthesis, polyketide tailoring, and high-throughput synthetic biology, as well as challenges and outlooks for rapidly generating useful target polyketides.

SIME: synthetic insight-based macrolide enumerator to generate the V1B library of 1 billion macrolides

We report on a new cheminformatics enumeration technology—SIME, synthetic insight-based macrolide enumerator—a new and improved software technology. SIME can enumerate fully assembled macrolides with synthetic feasibility by utilizing the constitutional and structural knowledge extracted from biosynthetic aspects of macrolides. Taken into account by the software are key information such as positions in macrolide structures at which chemical components can be inserted, and the types of structural motifs and sugars of interest that can be synthesized and incorporated at those positions. Additionally, we report on the chemical distribution analysis of the newly SIME-generated V1B (virtual 1 billion) library of macrolides. Those compounds were built based on the core of the Erythromycin structure, 13 structural motifs and a library of sugars derived from eighteen bioactive macrolides. This new enumeration technology can be coupled with cheminformatics approaches such as QSAR modeling and molecular docking to aid in drug discovery for rational designing of next generation macrolide therapeutics with desirable pharmacokinetic properties.