Key points are not available for this paper at this time.
In this article, we discussed the emerging informatics issues of high-throughput screening (HTS) using automated fluorescence microscopy technology, otherwise known as high-content screening (HCS) in the pharmaceutical industry. Optimal methods of scoring biomarkers and identifying candidate hits have been actively studied in academia and industry, with the exception of data modeling topics. To find candidate hits, we need to score the images associated with different compound interventions. In the application example of RNAi genome-wide screening, we aim to find the candidate effectors or genes which correspond to the images acquired using the three channels. Scoring the effectors is equivalent to scoring the images based on the number of phenotypes existing in those images. Our ultimate objective of studying HTS is to model the relationship between gene networks and cellular phenotypes, investigate cellular communication via protein interaction, and study the disease mechanism beyond the prediction based on the molecular structure of the compound. Finally, computational image analysis has become a powerful tool in cellular and molecular biology studies. Signal processing and modeling for high-throughput image screening is an emerging filed that requires novel algorithms for dynamical system analysis, image processing, and statistical modeling. We hope that this article will motivate the signal processing communities to address challenging data modeling and other informatics issues of HTS
Zhou et al. (Mon,) studied this question.