A widespread role for SLC transmembrane transporters in resistance to cytotoxic drugs.

Solute carriers (SLCs) are the largest family of transmembrane transporters in humans and are major determinants of cellular metabolism. Several SLCs have been shown to be required for the uptake of chemical compounds into cellular systems, but systematic surveys of transporter-drug relationships in human cells are currently lacking. We performed a series of genetic screens in a haploid human cell line against 60 cytotoxic compounds representative of the chemical space populated by approved drugs. By using an SLC-focused CRISPR-Cas9 library, we identified transporters whose absence induced resistance to the drugs tested. This included dependencies involving the transporters SLC11A2/SLC16A1 for artemisinin derivatives and SLC35A2/SLC38A5 for cisplatin. The functional dependence on SLCs observed for a significant proportion of the screened compounds suggests a widespread role for SLCs in the uptake and cellular activity of cytotoxic drugs and provides an experimentally validated set of SLC-drug associations for a number of clinically relevant compounds.

Using Machine Learning Methods and Structural Alerts for Prediction of Mitochondrial Toxicity.

Over the last few years more and more organ and idiosyncratic toxicities were linked to mitochondrial toxicity. Despite well-established assays, such as the seahorse and Glucose/Galactose assay, an in silico approach to mitochondrial toxicity is still feasible, particularly when it comes to the assessment of large compound libraries. Therefore, in silico approaches could be very beneficial to indicate hazards early in the drug development pipeline. By combining multiple endpoints, we derived the largest so far published dataset on mitochondrial toxicity. A thorough data analysis shows that molecules causing mitochondrial toxicity can be distinguished by physicochemical properties. Finally, the combination of machine learning and structural alerts highlights the suitability for in silico risk assessment of mitochondrial toxicity.

Image Based Liver Toxicity Prediction.

The drugs we use to cure our diseases can cause damage to the liver as it is the primary organ responsible for metabolism of environmental chemicals and drugs. To identify and eliminate potentially problematic drug candidates in the early stages of drug discovery, in silico techniques provide quick and practical solutions for toxicity determination. Deep learning has emerged as one of the solutions in recent years in the field of pharmaceutical chemistry. Generally, in the case of small data sets as used in toxicology, these data-hungry algorithms are prone to overfitting. We approach the problem from two sides. First, we use images of the three-dimensional conformations and benefit from convolutional neural networks which have fewer parameters than the standard deep neural networks with similar depth. Using images allows connecting various chemical features to the geometry of the compounds. Second, we employ the method COVER to up-sample the data set. It is used not only for increasing the size of the data set, but also for balancing the two classes, i.e., toxic and not toxic. The proof of concept is performed on the p53 end point from the Tox21 data set. The results, which are compatible with the winners of the data challenge, encouraged us to use our methods to predict liver toxicity. We use the most extensive publicly available liver toxicity data set by Mulliner et al. and obtain a sensitivity of 0.79 and a specificity of 0.52. These results demonstrate the applicability of image based toxicity prediction using deep neural networks.

In silico toxicology: From structure-activity relationships towards deep learning and adverse outcome pathways.

In silico toxicology is an emerging field. It gains increasing importance as research is aiming to decrease the use of animal experiments as suggested in the 3R principles by Russell and Burch. In silico toxicology is a means to identify hazards of compounds before synthesis, and thus in very early stages of drug development. For chemical industries, as well as regulatory agencies it can aid in gap-filling and guide risk minimization strategies. Techniques such as structural alerts, read-across, quantitative structure-activity relationship, machine learning, and deep learning allow to use in silico toxicology in many cases, some even when data is scarce. Especially the concept of adverse outcome pathways puts all techniques into a broader context and can elucidate predictions by mechanistic insights. This article is categorized under:Structure and Mechanism > Computational Biochemistry and BiophysicsData Science > Chemoinformatics.

COVER: conformational oversampling as data augmentation for molecules.

Training neural networks with small and imbalanced datasets often leads to overfitting and disregard of the minority class. For predictive toxicology, however, models with a good balance between sensitivity and specificity are needed. In this paper we introduce conformational oversampling as a means to balance and oversample datasets for prediction of toxicity. Conformational oversampling enhances a dataset by generation of multiple conformations of a molecule. These conformations can be used to balance, as well as oversample a dataset, thereby increasing the dataset size without the need of artificial samples. We show that conformational oversampling facilitates training of neural networks and provides state-of-the-art results on the Tox21 dataset.

Accessing Public Compound Databases with KNIME.

BACKGROUND: The KNIME platform offers several tools for the analysis of chem- and pharmacoinformatics data. Unless one has sufficient in-house data available for the analysis of interest, it is necessary to fetch third party data into KNIME. Many data sources offer valuable data, but including this data in a workflow is not always straightforward. OBJECTIVE: Here we discuss different ways of accessing public data sources. We give an overview of KNIME nodes for different sources, with references to available example workflows. For data sources with no individual KNIME node available, we present a general approach of accessing a web interface via KNIME. In addition, we discuss necessary steps before the data can be analysed, such as data curation, chemical standardisation and the merging of datasets.