Integrating high-content screening and ligand-target prediction to identify mechanism of action

Abstract

High-content screening is transforming drug discovery by enabling simultaneous measurement of multiple features of cellular phenotype that are relevant to therapeutic and toxic activities of compounds. High-content screening studies typically generate immense datasets of image-based phenotypic information, and how best to mine relevant phenotypic data is an unsolved challenge. Here, we introduce factor analysis as a data-driven tool for defining cell phenotypes and profiling compound activities. This method allows a large data reduction while retaining relevant information, and the data-derived factors used to quantify phenotype have discernable biological meaning. We used factor analysis of cells stained with fluorescent markers of cell cycle state to profile a compound library and cluster the hits into seven phenotypic categories. We then compared phenotypic profiles, chemical similarity and predicted protein binding activities of active compounds. By integrating these different descriptors of measured and potential biological activity, we can effectively draw mechanism-of-action inferences.

Identification of the anti-tumor activity and mechanisms of nuciferine through a network pharmacology approach

“…Therefore, nuciferine may potentially affect the activities or expression of these gene products directly or indirectly, leading to tumor regression. The biological significance of the results obtained through clustering analyses of "profile data" generated by computational predictions and high-throughput experiments have been demonstrated in many studies [34] . Because the predicted target profiles used in our study lacked signal (ie, activation or inhibition) and interaction strength (ie, strong or weak binding), these profiles may suggest the likelihood and importance of any target proteins affected by a given herbal compound but cannot predict whether a compound would have an active or inhibitory response against a target protein.…”

Scoring diverse cellular morphologies in image-based screens with iterative feedback and machine learning

“…Other machine learning methods are likely to be equally effective, based on their performance in previous work (15)(16)(17)(18)(19)(20)(21)(22)(23)(24). The system then presents the researcher with a new batch of cells, which it has classified based on the tentative rule, and the researcher corrects errors.…”

“…Cell image analysis allows accurate identification and measurement of cells' features, enabling automated analysis of certain phenotypes that were previously intractable (13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26). However, many interesting phenotypes require the assessment of several measured features of cells.…”

“…However, many interesting phenotypes require the assessment of several measured features of cells. Machine learning methods that select and combine multiple features for automated cell classification have been used to score many phenotypes (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26). These methods require the provision of example cells that do and do not display the morphology of interest (i.e., positive and negative cells).…”

Diversity-oriented synthesis as a tool for identifying new modulators of mitosis

“…One avenue to identify an antimitotic compound is by conducting a phenotypic screen for mitotic arrest. Therefore we focused our attention on a high-content screen using automated microscopy 35,36 . The screen was performed using U2OS osteosarcoma cells, which were incubated for 20 h with all of the library compounds, stained for the mitotic marker phosphohistone H3 and imaged on a Cellomics Arrayscan high-content microscope.…”