Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset.

Drug-induced liver injury (DILI) remains one of the challenges in the safety profile of both authorized and candidate drugs, and predicting hepatotoxicity from the chemical structure of a substance remains a task worth pursuing. Such an approach is coherent with the current tendency for replacing non-clinical tests with in vitro or in silico alternatives. In 2016, a group of researchers from the FDA published an improved annotated list of drugs with respect to their DILI risk, constituting "the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans" (DILIrank). This paper is one of the few attempting to predict liver toxicity using the DILIrank dataset. Molecular descriptors were computed with the Dragon 7.0 software, and a variety of feature selection and machine learning algorithms were implemented in the R computing environment. Nested (double) cross-validation was used to externally validate the models selected. A total of 78 models with reasonable performance were selected and stacked through several approaches, including the building of multiple meta-models. The performance of the stacked models was slightly superior to other models published. The models were applied in a virtual screening exercise on over 100,000 compounds from the ZINC database and about 20% of them were predicted to be non-hepatotoxic.

A Survey of Plant Iron Content-A Semi-Systematic Review.

Iron is an essential mineral nutrient for all living organisms, involved in a plurality of biological processes. Its deficit is the cause of the most common form of anemia in the world: iron deficiency anemia (IDA). This paper reviews iron content in various parts of 1228 plant species and its absorption from herbal products, based on data collected from the literature in a semi-systematic manner. Five hundred genera randomly selected from the Angiosperms group, 215 genera from the Pteridophytes groups and all 95 Gymnosperm genera as listed in the Plant List version 1.1 were used as keywords together with the word "iron" in computerized searches. Iron data about additional genera returned by those searches were extracted and included in the analysis. In total, iron content values for a number of 1228 species, 5 subspecies, and 5 varieties were collected. Descriptive and inferential statistics were used to compare iron contents in various plant parts (whole plant, roots, stems, shoots, leaves, aerial parts, flowers, fruits, seeds, wood, bark, other parts) and exploratory analyses by taxonomic groups and life-forms were carried out. The absorption and potential relevance of herbal iron for iron supplementation are discussed.