Dr. Elana J. Fertig (whose lab also uses multiplatform genomics data, blended with mathematical modeling and artificial intelligence) will demonstrate how CoGAPS, an established method for identifying transcriptional signatures related to cell type and state, can be applied to single cell data to identify patterns underlying immunotherapy response and resistance. Combining CoGAPS with transfer learning approaches provides insight into the patterns found in preclinical models, which then can be applied to patient samples to find shared features across data sets from different species.

In this talk, Mrs. Aya Abdelsalam Ismail will give an overview on interpreting Deep Neural Networks (DNNs), focusing on the use of DNNs to track and predict changes over time.

In this talk, Dr. James Lacey will describe the choices the cancer research community should consider and the questions they need to ask when transitioning their research projects to a cloud-based ecosystem.

In this talk, Dr. David Kepplinger will describe the detrimental effects of “data-artifacts,” specifically as they relate to biomarker discovery and related feature selection techniques. He will also discuss a novel method for reliably identifying relevant biomarkers in the presence of such artifacts.

Dr. Deborah Guadalupe Duran will define social determinants of health (SDOH). More specifically, she will give examples of how SDOH influence health outcomes; describe challenges related to collecting and using SDOH data; and offer resources for additional information on SDOH. She also will provide/suggest a new socio-cultural approach for including SDOH in biomedical research and policies.

In this webinar, Dr. Yanjun Qi will demonstrate AttentiveChrome, an attention-based deep learning approach that uses a unified architecture to model and interpret interactions and dependencies among the chromatin factors underlying gene regulation.

Dr. Paul Marjoram will discuss how statistical analysis of polymorphism data can be used to explore a number of issues relating to cancer.

In this Data Science Seminar, Dr. Kristen Naegle will address both the advances and challenges in using phosphoproteomic data to better predict kinase activity and consequently strengthen precision medicine.

Dr. Eliezer Van Allen will describe how a patient’s cancer genome can be used to guide individualized treatment choices for precision medicine. He will examine how to identify treatment resistance mechanisms and show how certain phenotypic patterns can be paired with new modes of computation to further inform treatment decisions.

Dr. Charles Wang will address the need for guidance in selecting algorithms for accurate biological interpretations of varied data types acquired with different single-cell RNA sequencing platforms.