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.

Accurate detection of somatic mutations is challenging but critical to understanding how cancer forms and progresses. In this Data Science Seminar, Dr. Mohammad Sahraeian will demonstrate how a neural network called NeuSomatic can outperform conventional detection approaches that involve low coverage, low mutation frequency, damaged DNA, and/or ambiguous genomic regions.

Matthew Trunnell will discuss the concept of a capability maturity model and describe how this model can be applied to today’s data commons to create a more comprehensive data ecosystem in the future.

Drs. Helen Moore, Esmeralda Casas-Silva, Veena Gopalakrishnan, and Ms. Claire Blaustein will showcase the design and functionality of the NCI Cancer Moonshot Biobank website. By highlighting the challenges and successes they encountered when developing the website, their hope is that it will serve as an archetype for similar participant-engagement efforts within NCI.

Dr. Noémie Elhadad will show how patient-record summation tools can help clinicians make sense of seemingly overwhelming amounts of patient data at the point of care.

Dr. Nicolas Fernandez will demonstrate the latest version of Clustergrammer2, a visualization tool that allows users to perform more refined clustering on cell lines and genes.

Dr. James Zou will present new computer vision algorithms and describe how these can help identify the morphologies and phenotypes associated with complex diseases, such as cancer. He will also discuss the general principles behind this technology as well as current machine learning tools, such as Ghorbani, NeurIPS 2020, Abid, and Nature MI 2020.

In this talk, Dr. Gabor Marth will present the Functional Precision Oncology Initiative, which combines model-based drug screening with multi-omic and subclonal analyses of the tumor to predict the extent of the response.

Drs. Del Fiol and Bradshaw will discuss OpenCDS, a clinical decision support platform, and show how it can be integrated with electronic health records (EHRs) to identify and manage patients who may benefit from genetic evaluation of their hereditary cancer risk.