Oral Academic Seminar about Our Work ACSleuth
Date:
We discussed how to detect anomalous samples in single-cell omics data with generative models and introduced our team’s work, ACSleuth.
In this talk, we talked about the fact that generative models have been proven effective in anomaly detection tasks on industrial image datasets. However, there has been a lack of research utilizing generative models to detect cancer cells in the realm of single-cell omics data. This may be due to the insignificant differences in cell gene expression or the presence of batch effects between datasets. Therefore, we introduced our team’s work, ACSleuth, as a novel approach to address these issues.