How to winnow actives from inactives: introducing molecular orthogonal sparse bigrams (MOSBs) and multiclass Winnow

An olive oil phenolic is a new chemotype of mutant isocitrate dehydrogenase 1 (IDH1) inhibitors

Mutations in the isocitrate dehydrogenase 1 (IDH1) gene confer an oncogenic gain-of-function activity that allows the conversion of α-ketoglutarate (α-KG) to the oncometabolite R-2-hydroxyglutarate (2HG). The accumulation of 2HG inhibits α-KG-dependent histone and DNA demethylases, thereby generating genome-wide hypermethylation phenotypes with cancer-initiating properties. Several chemotypes of mutant IDH1/2-targeted inhibitors have been reported, and some of them are under evaluation in clinical trials. However, the recognition of acquired resistance to such inhibitors within a few years of clinical use raises an urgent need to discover new mutant IDH1 antagonists. Here, we report that a naturally occurring phenolic compound in extra-virgin olive oil (EVOO) selectively inhibits the production of 2HG by neomorphic IDH1 mutations. In silico docking, molecular dynamics, including steered simulations, predicted the ability of the oleoside decarboxymethyl oleuropein aglycone (DOA) to preferentially occupy the allosteric pocket of mutant IDH1. DOA inhibited the enzymatic activity of recombinant mutant IDH1 (R132H) protein in the low micromolar range, whereas >10-fold higher concentrations were required to inhibit the activity of wild-type (WT) IDH1. DOA suppressed 2HG overproduction in engineered human cells expressing a heterozygous IDH1-R132H mutation. DOA restored the 2HG-suppressed activity of histone demethylases as it fully reversed the hypermethylation of H3K9me3 in IDH1-mutant cells. DOA epigenetically restored the expression of PD-L1, an immunosuppressive gene silenced in IDH1 mutant cells via 2HG-driven DNA hypermethylation. DOA selectively blocked colony formation of IDH1 mutant cells while sparing WT IDH1 isogenic counterparts. In sum, the EVOO-derived oleoside DOA is a new, naturally occurring chemotype of mutant IDH1 inhibitors.

Metformin directly targets the H3K27me3 demethylase KDM6A/UTX

Metformin, the first drug chosen to be tested in a clinical trial aimed to target the biology of aging per se, has been clinically exploited for decades in the absence of a complete understanding of its therapeutic targets or chemical determinants. We here outline a systematic chemoinformatics approach to computationally predict biomolecular targets of metformin. Using several structure‐ and ligand‐based software tools and reference databases containing 1,300,000 chemical compounds and more than 9,000 binding sites protein cavities, we identified 41 putative metformin targets including several epigenetic modifiers such as the member of the H3K27me3‐specific demethylase subfamily, KDM6A/UTX. AlphaScreen and AlphaLISA assays confirmed the ability of metformin to inhibit the demethylation activity of purified KDM6A/UTX enzyme. Structural studies revealed that metformin might occupy the same set of residues involved in H3K27me3 binding and demethylation within the catalytic pocket of KDM6A/UTX. Millimolar metformin augmented global levels of H3K27me3 in cultured cells, including reversion of global loss of H3K27me3 occurring in premature aging syndromes, irrespective of mitochondrial complex I or AMPK. Pharmacological doses of metformin in drinking water or intraperitoneal injection significantly elevated the global levels of H3K27me3 in the hepatic tissue of low‐density lipoprotein receptor‐deficient mice and in the tumor tissues of highly aggressive breast cancer xenograft‐bearing mice. Moreover, nondiabetic breast cancer patients receiving oral metformin in addition to standard therapy presented an elevated level of circulating H3K27me3. Our biocomputational approach coupled to experimental validation reveals that metformin might directly regulate the biological machinery of aging by targeting core chromatin modifiers of the epigenome.

Drug Metabolism in Preclinical Drug Development: A Survey of the Discovery Process, Toxicology, and Computational Tools

BACKGROUND

While establishing efficacy in translational models and humans through clinically-relevant endpoints for disease is of great interest, assessing the potential toxicity of a putative therapeutic drug is critical. Toxicological assessments in the pre-clinical discovery phase help to avoid future failure in the clinical phases of drug development. Many in vitro assays exist to aid in modular toxicological assessment, such as hepatotoxicity and genotoxicity. While these methods have provided tremendous insight into human toxicity by investigational new drugs, they are expensive, require substantial resources, and do not account for pharmacogenomics as well as critical ADME properties. Computational tools can fill this niche in toxicology if in silico models are accurate in relating drug molecular properties to toxicological endpoints as well as reliable in predicting important drug-target interactions that mediate known adverse events or adverse outcome pathways (AOPs).

METHODS

We undertook an unstructured search of multiple bibliographic databases for peer-reviewed literature regarding computational methods in predictive toxicology for in silico drug discovery. As this review paper is meant to serve as a survey of available methods for the interested reader, no focused criteria were applied. Literature chosen was based on the writers' expertise and intent in communicating important aspects of in silico toxicology to the interested reader.

CONCLUSION

This review provides a purview of computational methods of pre-clinical toxicologic assessments for novel small molecule drugs that may be of use for novice and experienced investigators as well as academic and commercial drug discovery entities.

Machine learning methods in chemoinformatics

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure-activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers.

Note on naive Bayes based on binary descriptors in cheminformatics

A plethora of articles on naive Bayes classifiers, where the chemical compounds to be classified are represented by binary-valued (absent or present type) descriptors, have appeared in the cheminformatics literature over the past decade. The principal goal of this paper is to describe how a naive Bayes classifier based on binary descriptors (NBCBBD) can be employed as a feature selector in an efficient manner suitable for cheminformatics. In the process, we point out a fact well documented in other disciplines that NBCBBD is a linear classifier and is therefore intrinsically suboptimal for classifying compounds that are nonlinearly separable in their binary descriptor space. We investigate the performance of the proposed algorithm on classifying a subset of the MDDR data set, a standard molecular benchmark data set, into active and inactive compounds.

Informatics, machine learning and computational medicinal chemistry

This article reviews the use of informatics and computational chemistry methods in medicinal chemistry, with special consideration of how computational techniques can be adapted and extended to obtain more and higher-quality information. Special consideration is given to the computation of protein–ligand binding affinities, to the prediction of off-target bioactivities, bioactivity spectra and computational toxicology, and also to calculating absorption-, distribution-, metabolism- and excretion-relevant properties, such as solubility.