video1.0<iframe src="https://www.loom.com/embed/faf7065a8085408d802b06f4c8183929" frameborder="0" width="640" height="480" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>480640Loomhttps://www.loom.com480640https://cdn.loom.com/sessions/thumbnails/faf7065a8085408d802b06f4c8183929-00001.gif625Here I talk about ICAN's innovations in data science and engineering for our computational genomics thrust, funded by National Institutes of Health [NIH, BDMA vision] in collaboration with Purdue ECE [Milind Kulkarni, Saurabh Bagchi], Purdue CS [Ananth Grama], and Argonne National Lab [Folker Meyer, Andreas Wilke, Wolfgang Gerlach, Travis Harrison]. Our innovations span distributed computation for metagenomics workloads [OptimusCloud, Usenix ATC 2020; Sophia, Usenix ATC 2019, Nucleic Acids Research, Briefings in Bioinformatics], data science for epigenetic pattern recognition [Nature Science Reports, BMC Systems Biology], data science for RNA-based targeting and regulation [ACM-BCB best paper award, BMC Genomics, Theranostics, TCBB], NLP for sequencing error correction [Athena, Nature Scientific Reports], etc.