Optimizing drug discovery by Investigative Toxicology: Current and future trends.

Investigative Toxicology describes the de-risking and mechanistic elucidation of toxicities, supporting early safety decisions in the pharmaceutical industry. Recently, Investigative Toxicology has contributed to a shift in pharmaceutical toxicology, from a descriptive to an evidence-based, mechanistic discipline. This was triggered by high costs and low throughput of Good Laboratory Practice in vivo studies, and increasing demands for adhering to the 3R (Replacement, Reduction and Refinement) principles of animal welfare. Outside the boundaries of regulatory toxicology, Investigative Toxicology has the flexibility to embrace new technologies, enhancing translational steps from in silico, in vitro to in vivo mechanistic understanding to eventually predict human response. One major goal of Investigative Toxicology is improving preclinical decisions, which coincides with the concept of animal-free safety testing. Currently, compounds under preclinical development are being discarded due to the use of inappropriate animal models. Progress in Investigative Toxicology could lead to humanized in vitro test systems and the development of medicines less reliant on animal tests. To advance this field a group of 14 European-based leaders from the pharmaceutical industry founded the Investigative Toxicology Leaders Forum (ITLF), an open, non-exclusive and pre-competitive group that shares knowledge and experience. The ITLF collaborated with the Centre for Alternatives to Animal Testing Europe (CAAT-Europe) to organize an "Investigative Toxicology Think-Tank", which aimed to enhance the interaction with experts from academia and regulatory bodies in the field. Summarizing the topics and discussion of the workshop, this article highlights Investigative Toxicology's position by identifying key challenges and perspectives.

A method for characterizing phenotypic changes in highly variable cell populations and its application to high content screening of Arabidopsis thaliana protoplasts.

Quantitative image analysis procedures are necessary for the automated discovery of effects of drug treatment in large collections of fluorescent micrographs. When compared to their mammalian counterparts, the effects of drug conditions on protein localization in plant species are poorly understood and underexplored. To investigate this relationship, we generated a large collection of images of single plant cells after various drug treatments. For this, protoplasts were isolated from six transgenic lines of A. thaliana expressing fluorescently tagged proteins. Eight drugs at three concentrations were applied to protoplast cultures followed by automated image acquisition. For image analysis, we developed a cell segmentation protocol for detecting drug effects using a Hough transform-based region of interest detector and a novel cross-channel texture feature descriptor. In order to determine treatment effects, we summarized differences between treated and untreated experiments with an L1 Cramér-von Mises statistic. The distribution of these statistics across all pairs of treated and untreated replicates was compared to the variation within control replicates to determine the statistical significance of observed effects. Using this pipeline, we report the dose dependent drug effects in the first high-content Arabidopsis thaliana drug screen of its kind. These results can function as a baseline for comparison to other protein organization modeling approaches in plant cells. © 2017 International Society for Advancement of Cytometry.

Active machine learning-driven experimentation to determine compound effects on protein patterns.

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.

Efficient discovery of responses of proteins to compounds using active learning.

BACKGROUND: Drug discovery and development has been aided by high throughput screening methods that detect compound effects on a single target. However, when using focused initial screening, undesirable secondary effects are often detected late in the development process after significant investment has been made. An alternative approach would be to screen against undesired effects early in the process, but the number of possible secondary targets makes this prohibitively expensive. RESULTS: This paper describes methods for making this global approach practical by constructing predictive models for many target responses to many compounds and using them to guide experimentation. We demonstrate for the first time that by jointly modeling targets and compounds using descriptive features and using active machine learning methods, accurate models can be built by doing only a small fraction of possible experiments. The methods were evaluated by computational experiments using a dataset of 177 assays and 20,000 compounds constructed from the PubChem database. CONCLUSIONS: An average of nearly 60% of all hits in the dataset were found after exploring only 3% of the experimental space which suggests that active learning can be used to enable more complete characterization of compound effects than otherwise affordable. The methods described are also likely to find widespread application outside drug discovery, such as for characterizing the effects of a large number of compounds or inhibitory RNAs on a large number of cell or tissue phenotypes.

Efficient modeling and active learning discovery of biological responses.

High throughput and high content screening involve determination of the effect of many compounds on a given target. As currently practiced, screening for each new target typically makes little use of information from screens of prior targets. Further, choices of compounds to advance to drug development are made without significant screening against off-target effects. The overall drug development process could be made more effective, as well as less expensive and time consuming, if potential effects of all compounds on all possible targets could be considered, yet the cost of such full experimentation would be prohibitive. In this paper, we describe a potential solution: probabilistic models that can be used to predict results for unmeasured combinations, and active learning algorithms for efficiently selecting which experiments to perform in order to build those models and determining when to stop. Using simulated and experimental data, we show that our approaches can produce powerful predictive models without exhaustive experimentation and can learn them much faster than by selecting experiments at random.

Determining the subcellular location of new proteins from microscope images using local features.

MOTIVATION: Evaluation of previous systems for automated determination of subcellular location from microscope images has been done using datasets in which each location class consisted of multiple images of the same representative protein. Here, we frame a more challenging and useful problem where previously unseen proteins are to be classified. RESULTS: Using CD-tagging, we generated two new image datasets for evaluation of this problem, which contain several different proteins for each location class. Evaluation of previous methods on these new datasets showed that it is much harder to train a classifier that generalizes across different proteins than one that simply recognizes a protein it was trained on. We therefore developed and evaluated additional approaches, incorporating novel modifications of local features techniques. These extended the notion of local features to exploit both the protein image and any reference markers that were imaged in parallel. With these, we obtained a large accuracy improvement in our new datasets over existing methods. Additionally, these features help achieve classification improvements for other previously studied datasets. AVAILABILITY: The datasets are available for download at http://murphylab.web.cmu.edu/data/. The software was written in Python and C++ and is available under an open-source license at http://murphylab.web.cmu.edu/software/. The code is split into a library, which can be easily reused for other data and a small driver script for reproducing all results presented here. A step-by-step tutorial on applying the methods to new datasets is also available at that address. CONTACT: murphy@cmu.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.