Using Structured Knowledge for Casual Feature Selection.
To define and understand confounding and selection bias and why addressing these is important.
To answer why addressing confounding and selection bias is difficult (and what the limitations are of conventional approaches).
To grasp the importance of computional tools (from processing the biomedical literature with natural language processing and biomedical ontologies) for identifying cofounders and to gain an awareness of the limitations and concepts for mitigating these limitations.
Navigating Cellular Complexity in Disease through Advanced Computational Models.
Learn how to detect cellular changes from single-cell data. Understand the limitations of current algorithms, specifically how they can produce false positives due to variations among individuals and cohorts.
Learn a new computional framework designed to account for individual and cohort variations in single-cell data, thereby improving the accuracy of analysis.
Learn how the transcriptome-translator, similar to a Google Translator for genomics, can tackle major challenges in cancer treatment, such as tumor heterogeneity and health care disparities.