I have always appreciated the unusual, unexpected, and surprising in science and in data. As famous science author Arthur C. Clarke once said, "The most exciting phrase to hear in science, the one that heralds new discoveries, is not'Eureka!' (I found it) but'That's funny!'" This is the primary reason that I motivated most of the doctoral students that I mentored at GMU to work on some variation of Novelty Discovery (or Surprise Discovery) for their Ph.D. dissertations. "Surprise discovery" for me is a much more positive, exciting phrase than "outlier detection" or "anomaly detection", and it is much richer in meaning, in algorithms, and in new opportunities. Finding the surprising unexpected thing in your data is what inspires our exclamation "That's funny!" that may be signaling a great discovery (either about your data's quality, or about your data pipeline's deficiencies, or about some wholly new scientific concept). As famous astronomer, Vera Rubin said, "Science progresses best when observations force us to alter our preconceptions."

Caris Life Sciences, a leading innovator in molecular science focused on fulfilling the promise of precision medicine, today presented a poster demonstrating how its advanced machine learning approach, Caris Next Generation Profiling, enables a proprietary algorithm to molecularly classify tumor samples into cancer types. These results, presented at the 2019 American Society of Clinical Oncology (ASCO) Annual Meeting, showcase how analysis of large combined molecular and clinical datasets can improve diagnosis of challenging cases, which is expected to inform increasingly personalized and precise cancer treatments. The poster, "Machine Learning Algorithm Analysis using a Commercial 592-gene NGS Panel to Accurately Predict Tumor Lineage for Carcinoma of Unknown Primary (CUP)," was presented at this morning's Developmental Therapeutics and Tumor Biology (Nonimmuno) Poster Session. Caris scientists detailed how Caris Next Generation Profiling identified molecular classifications for tumor samples with over 95% accuracy using next generation sequencing (NGS) data from 55,780 tumor patients. It generated an unequivocal result in the vast majority of cases of carcinoma of unknown primary (CUP), when there was ambiguity about tissue of origin.