Machine learning on large scale perturbation screens for SARS-CoV-2 host factors identifies ß-catenin/CBP inhibitor PRI-724 as a potent antiviral.

Expanding antiviral treatment options against SARS-CoV-2 remains crucial as the virus evolves under selection pressure which already led to the emergence of several drug resistant strains. Broad spectrum host-directed antivirals (HDA) are promising therapeutic options, however the robust identification of relevant host factors by CRISPR/Cas9 or RNA interference screens remains challenging due to low consistency in the resulting hits. To address this issue, we employed machine learning, based on experimental data from several knockout screens and a drug screen. We trained classifiers using genes essential for virus life cycle obtained from the knockout screens. The machines based their predictions on features describing cellular localization, protein domains, annotated gene sets from Gene Ontology, gene and protein sequences, and experimental data from proteomics, phospho-proteomics, protein interaction and transcriptomic profiles of SARS-CoV-2 infected cells. The models reached a remarkable performance suggesting patterns of intrinsic data consistency. The predicted HDF were enriched in sets of genes particularly encoding development, morphogenesis, and neural processes. Focusing on development and morphogenesis-associated gene sets, we found ß-catenin to be central and selected PRI-724, a canonical ß-catenin/CBP disruptor, as a potential HDA. PRI-724 limited infection with SARS-CoV-2 variants, SARS-CoV-1, MERS-CoV and IAV in different cell line models. We detected a concentration-dependent reduction in cytopathic effects, viral RNA replication, and infectious virus production in SARS-CoV-2 and SARS-CoV-1-infected cells. Independent of virus infection, PRI-724 treatment caused cell cycle deregulation which substantiates its potential as a broad spectrum antiviral. Our proposed machine learning concept supports focusing and accelerating the discovery of host dependency factors and identification of potential host-directed antivirals.

Facile One Step Formation and Screening of Tumor Spheroids Using Droplet-Microarray Platform.

Tumor spheroids or microtumors are important 3D in vitro tumor models that closely resemble a tumor's in vivo "microenvironment" compared to 2D cell culture. Microtumors are widely applied in the fields of fundamental cancer research, drug discovery, and precision medicine. In precision medicine tumor spheroids derived from patient tumor cells represent a promising system for drug sensitivity and resistance testing. Established and commonly used platforms for routine screenings of cell spheroids, based on microtiter plates of 96- and 384-well formats, require relatively large numbers of cells and compounds, and often lead to the formation of multiple spheroids per well. In this study, an application of the Droplet Microarray platform, based on hydrophilic-superhydrophobic patterning, in combination with the method of hanging droplet, is demonstrated for the formation of highly miniaturized single-spheroid-microarrays. Formation of spheroids from several commonly used cancer cell lines in 100 nL droplets starting with as few as 150 cells per spheroid within 24-48 h is demonstrated. Established methodology carries a potential to be adopted for routine workflows of high-throughput compound screening in 3D cancer spheroids or microtumors, which is crucial for the fields of fundamental cancer research, drug discovery, and precision medicine.

High-Density Cell Arrays for Genome-Scale Phenotypic Screening.

Due to high associated costs and considerable time investments of cell-based screening, there is a strong demand for new technologies that enable preclinical development and tests of diverse biologicals in a cost-saving and time-efficient manner. For those reasons we developed the high-density cell array (HD-CA) platform, which miniaturizes cell-based screening in the form of preprinted and ready-to-run screening arrays. With the HD-CA technology, up to 24,576 samples can be tested in a single experiment, thereby saving costs and time for microscopy-based screening by 75%. Experiments on the scale of the entire human genome can be addressed in a real parallel manner, with screening campaigns becoming more comfortable and devoid of robotics infrastructure on the user side. The high degree of miniaturization enables working with expensive reagents and rare and difficult-to-obtain cell lines. We have also optimized an automated imaging procedure for HD-CA and demonstrate the applicability of HD-CA to CRISPR-Cas9- and RNAi-mediated phenotypic assessment of the gene function.