Practical Outcomes of Applying Ensemble Machine Learning Classifiers to High-Throughput Screening (HTS) Data Analysis and Screening

Exploring the potential of machine learning to design antidiabetic molecules: a comprehensive study with experimental validation

Recent advances in hardware and software algorithms have led to the rise of data-driven approaches for designing therapeutic modalities. One of the major causes of human mortality is diabetes. Thus, there is a tremendous opportunity for research into effective antidiabetic designs. Therefore, in this study, we used machine learning-based small molecule design. We used various chemoinformatic and binary fingerprint techniques on small molecules to construct multiple models for alpha-amylase inhibitors. Among these models, the top models were used for ensemble-based machine learning predictions on libraries of organic molecules supplemented with synthetic scaffolds that could be used as antidiabetic agents. Further, involved identifying 10 promising molecules from computational studies and determining their inhibitory effects on alpha-amylase. These molecules were synthesised and thoroughly analysed to assess their biological inhibitory properties. Then, thermodynamic simulations were conducted to determine the stability and affinity of experimentally active molecules. The research results showcased the top 10 ML models recorded impressive statistics with an average model score of 0.8216, Pearson-r value of 0.827 and external validation yielding a Q2 value of 0.835, proving their reliability and accuracy. Ten derivatives of benzothiophene dioxolane was prime research focus due to computational predictions. The biological inhibitory assay of synthesised molecules showed that small molecules with ID ALC5 and ALC6 exhibited inhibitory efficiencies (IC50) of 2.1 ± 0.14 µM and 5.71 ± 0.02 µM against alpha-amylase enzyme, whereas other molecules showed moderate inhibition. In conclusion, the positive results of the experiment indicate that researchers should explore machine learning-driven design.Communicated by Ramaswamy H. Sarma.

Debaryomyces hansenii: an old acquaintance for a fresh start in the era of the green biotechnology

The halophilic yeast Debaryomyces hansenii has been studied for several decades, serving as eukaryotic model for understanding salt and osmotic tolerance. Nevertheless, lack of consensus among different studies is found and, sometimes, contradictory information derived from studies performed in very diverse conditions. These two factors hampered its establishment as the key biotechnological player that was called to be in the past decade. On top of that, very limited (often deficient) engineering tools are available for this yeast. Fortunately Debaryomyces is again gaining momentum and recent advances using highly instrumented lab scale bioreactors, together with advanced –omics and HT-robotics, have revealed a new set of interesting results. Those forecast a very promising future for D. hansenii in the era of the so-called green biotechnology. Moreover, novel genetic tools enabling precise gene editing on this yeast are now available. In this review, we highlight the most recent developments, which include the identification of a novel gene implicated in salt tolerance, a newly proposed survival mechanism for D. hansenii at very high salt and limiting nutrient concentrations, and its utilization as production host in biotechnological processes.

Autonomous Molecular Design: Then and Now

The success of deep machine learning in processing of large amounts of data, for example, in image or voice recognition and generation, raises the possibilities that these tools can also be applied for solving complex problems in materials science. In this forum article, we focus on molecular design that aims to answer the question on how we can predict and synthesize molecules with tailored physical, chemical, or biological properties. A potential answer to this question could be found by using intelligent systems that integrate physical models and computational machine learning techniques with automated synthesis and characterization tools. Such systems learn through every single experiment in an analogy to a human scientific expert. While the general idea of an autonomous system for molecular synthesis and characterization has been around for a while, its implementations for the materials sciences are sparse. Here we provide an overview of the developments in chemistry automation and the applications of machine learning techniques in the chemical and pharmaceutical industries with a focus on the novel capabilities that deep learning brings in.

Benchmarking ligand-based virtual High-Throughput Screening with the PubChem database

With the rapidly increasing availability of High-Throughput Screening (HTS) data in the public domain, such as the PubChem database, methods for ligand-based computer-aided drug discovery (LB-CADD) have the potential to accelerate and reduce the cost of probe development and drug discovery efforts in academia. We assemble nine data sets from realistic HTS campaigns representing major families of drug target proteins for benchmarking LB-CADD methods. Each data set is public domain through PubChem and carefully collated through confirmation screens validating active compounds. These data sets provide the foundation for benchmarking a new cheminformatics framework BCL::ChemInfo, which is freely available for non-commercial use. Quantitative structure activity relationship (QSAR) models are built using Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Decision Trees (DTs), and Kohonen networks (KNs). Problem-specific descriptor optimization protocols are assessed including Sequential Feature Forward Selection (SFFS) and various information content measures. Measures of predictive power and confidence are evaluated through cross-validation, and a consensus prediction scheme is tested that combines orthogonal machine learning algorithms into a single predictor. Enrichments ranging from 15 to 101 for a TPR cutoff of 25% are observed.

A perspective on the role of quantitative structure-activity and structure-property relationships in herbicide discovery

BACKGROUND

For the last 15 years the agrochemical industry has focused on using genetic modification to put genes that confer resistance to existing commercial herbicides into crop plants rather than on discovering new herbicides with novel modes of action. The widespread appearance of weeds resistant to those herbicides is now causing the industry to revive their herbicide discovery programs.

RESULTS

Elucidation of quantitative structure-activity relationships (QSARs) played a major role in the discovery and development of existing commercial herbicides, but the advent of genetically modified crops has caused published work (at least) in the area to drift from the industrial arena into academic studies. The focus has also turned inward, to refining models for established herbicide targets instead of elucidating new ones.

CONCLUSION

This perspective highlights the importance of QSARs and quantitative structure-property relationships (QSPRs) to herbicide discovery in an historical context and provides some guidance as to how they might profitably be applied going forward.

Comparison of three preprocessing filters efficiency in virtual screening: identification of new putative LXRbeta regulators as a test case

In silico screening methodologies are widely recognized as efficient approaches in early steps of drug discovery. However, in the virtual high-throughput screening (VHTS) context, where hit compounds are searched among millions of candidates, three-dimensional comparison techniques and knowledge discovery from databases should offer a better efficiency to finding novel drug leads than those of computationally expensive molecular dockings. Therefore, the present study aims at developing a filtering methodology to efficiently eliminate unsuitable compounds in VHTS process. Several filters are evaluated in this paper. The first two are structure-based and rely on either geometrical docking or pharmacophore depiction. The third filter is ligand-based and uses knowledge-based and fingerprint similarity techniques. These filtering methods were tested with the Liver X Receptor (LXR) as a target of therapeutic interest, as LXR is a key regulator in maintaining cholesterol homeostasis. The results show that the three considered filters are complementary so that their combination should generate consistent compound lists of potential hits.

Modelling atypical small-molecule mimics of an important stem cell cytokine, thrombopoietin

We report the first comprehensive 3D QSAR study of a large, structurally diverse set of compounds that act as atypical thrombopoietin (TPO) mimics by interacting with the transmembrane domain of the TPO receptor, c-MPL. These agonists of c-MPL were superimposed according to a pharmacophore hypothesis, resulting in 3D QSAR models of high statistical significance. The pharmacophore-based superimposition and comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA) were used to derive the QSAR models relating structure to the published in vitro bioactivities of the TPO mimics. The CoMFA and CoMSIA models gave high correlation coefficients of the bioactivities with the derived fields, resulting in robust prediction of agonist activity of the superimposed compounds. The models have been interpreted in terms of the requirements for binding to the transmembrane domain of the TPO receptor.