Identifying novel drugs that inhibit bacterial infection has gained a considerable amount of attention in recent years. This is in part due to the increased number of highly resistant bacteria and the serious health threat it poses around the world. In order to combat this threat, a significant hurdle to overcome is the relatively low success rate of identifying novel chemical compounds that are effective at inhibiting bacterial infection. Despite increasing the vast amount of data that is currently generated during drug discovery endeavors, traditional analysis methods have not increased the overall success rate. In this paper, we investigate whether multivariate Image-based high content screening (HCS) platforms can identify chemical compounds using significantly reduced data while retaining its competitiveness. Image-based HCS is still predominantly used in biological compound activity assessments (bioassays) with univariate methods, not utilizing the data to its full potential. We propose a novel method that uses a small number of cells in high dimensional space to analyze interactions between cells, bacteria, and chemical compounds. Our results further indicate that our method can identify compounds that inhibit bacterial infection with a fraction of the control data generated.