BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210402T160552Z LOCATION:Track 3 DTSTART;TZID=America/New_York:20201113T100000 DTEND;TZID=America/New_York:20201113T183000 UID:submissions.supercomputing.org_SC20_sess222@linklings.com SUMMARY:CAFCW20: Sixth Computational Approaches for Cancer Workshop DESCRIPTION:Workshop\n\nA Metapath Approach to Predicting Drug Response in Cancer Cell Lines\n\nCohn\n\nWhen applying machine learning in cancer res earch and, in particular, when trying to predict drug response in cancer c ell lines or other experimental systems, an ongoing problem is the relativ ely small number of samples when compared to the possible number of featur es. This is frequently compounde...\n\n---------------------\nCAFCW20 – Panel: HPC, Cancer, and COVID-19\n\nKovatch, Brase, Del Valle, Gnjatic, Ni renberg...\n\nCOVID-19 has transformed life around the globe. Our clinicia ns and researchers leveraged their domain expertise to focus solely on bet ter understanding and treating this new disease. The spotlight on COVID-19 created new interdisciplinary teams that have already been fruitful, and these advances wer...\n\n---------------------\nDeciphering Hallmarks of R esistance in Breast Cancer\n\nBasu\n\nBackground: Approximately seventy pe rcent of high-risk breast cancer patients with extensive residual cancer b urden (RCB-III) after neoadjuvant therapy die within 4 years of treatment. Such ‘super non-responders’ need to be recognized and predicted early and routed to more effective treatment. Curr...\n\n---------------------\nAn Efficient, Data-Driven Approach To Model Specific Cancer Cell Lines\n\nBa logh, Gounley, Randles\n\nThe transport of cancer cells through the microc irculation is a fundamental component underlying the progression and sprea d of cancer. Simulations offer the potential to provide new insights owing to the level of detail that can be captured with blood flow models that r esolve the deformation dynamic...\n\n---------------------\nDeep Learning Based Prediction of the Temporal Behavior of RAS Protein Conformations on Simulated Cell Membrane Surfaces\n\nMoody, Bhatia, Bremer, Carpenter, Dhar uman...\n\nApproximately 30% of human cancers are caused by interactions o f a mutated RAS protein with the downstream RAF near cell membranes. The DoE Cancer Pilot 2 campaign conducted numerous molecular dynamics (MD) sim ulations modeling RAS proteins in contact with the lipid bilayer of a cell membrane. In ...\n\n---------------------\nCausal Deconvolution of a Mec hanistic Model of EGFR and ERK Signaling Explains Adaptive and Genetic Res istance in Melanoma\n\nFroehlich\n\nAllosteric interactions are at the cor e of many signal transduction processes and provide robustness and enable context dependency for the underlying molecular mechanisms. This is promin ently captured by paradoxical activation, a clinically observed phenomenon where RAF inhibitors inhibit tumor grow...\n\n---------------------\nScal able Human Pharmacokinetics Property Prediction for Cancer Drug Discovery at ATOM\n\nMadej, Murad, Pasikanti, Minnich, McComas...\n\nThe drug discov ery process has been described as a large-scale multi-parameter optimizati on problem to find new chemicals to treat diseases. Not only must a new co mpound show efficacy to improve a disease state, a compound must also fit numerous criteria to become a new drug. A compound’s pharmacoki...\n\n---- -----------------\nCAFCW20 – Panel: Digital Twins for Cancer Care\n\nStahl berg, Greenspan, Arthur, Hernandez-Boussard\n\nA cancer patient’s “digital twin” would be the ideal resource for personalized treatment, and creatin g the technology stands as a grand challenge for the convergence of advanc ed computing technologies and oncology.\n\n---------------------\nCAFCW20 – Introduction: Sixth Computational Approaches for Cancer Workshop\n\nStah lberg, Hanlon, Kovatch, Ellingson, Hollingsworth...\n\nNew computational o pportunities and challenges have emerged within the cancer research and cl inical application areas as the size, source and complexity of cancer data sets have grown. Simultaneously, advances in computational capabilities, w ith exceptional growth in AI and deep learning, are reachin...\n\n-------- -------------\nToward a Data-Driven System for Personalized Cervical Cance r Screening\n\nLangberg\n\nMass-screening programs for cervical cancer in the Nordic countries have a proven strong effect for preventing cancer at the population level and have produced large amounts of data at centrally organized at nationwide registries. Despite this success, minimizing over- screening and under-treatment r...\n\n---------------------\nScaffold-Indu ced Molecular Subgraphs (SIMSG): Effective Graph Sampling Methods for High -Throughput Computational Drug Discovery\n\nClyde, Shah, Zvyagin, Ramanath an, Stevens\n\nHistorically, drugs have been discovered serendipitously ba sed on active chemicals known to interact with and bind to protein targets . Combinatorial chemistry has enabled an explosion of diverse chemical lib raries which potentially have drug-like properties; however, the main issu e that is still fac...\n\n---------------------\nCAFCW20 – Panel: Translat ing Cancer Research Advances in Artificial Intelligence into Clinical Prac tice\n\nEllingson, Blayney, Bumgardner, Harmon, Liu\n\n------------------- --\nMachine Learning Driven Importance Sampling Approach for Multiscale Si mulations\n\nBhatia, Consortium\n\nAlmost all phenomena in science and eng ineering are inherently multiscale and many require exploration across ord ers of magnitude in both space and time. Solving such problems at the fine st scales is computationally prohibitive and, instead, they are often form ulated using multiscale models. Couplin...\n\n---------------------\nCAFCW 20 – Afternoon Welcome\n\nStahlberg\n\n---------------------\nCAFCW20 – Lu nch Break\n\n\n\n---------------------\nCAFCW20 – Wrapup\n\n\n\n---------- -----------\nCAFCW20 – Break\n\n\n\n---------------------\nCAFCW20 – Break \n\n\n\n---------------------\nIntegration of Domain Knowledge Using Medic al Knowledge Graph Deep Learning for Cancer Phenotyping\n\nAlawad\n\nA key component of deep learning (DL) for natural language processing (NLP) is word embeddings. Word embeddings that effectively capture the meaning and context of the word that they represent can significantly improve the perf ormance of downstream DL models for various NLP tasks. Many existing word. ..\n\n---------------------\nKeynote: Data Science Initiatives at the Nati onal Cancer Institute, Dr. Norman "Ned" Sharpless, National Cancer Institu te Director with Introduction by Sean E. Hanlon, PhD, National Cancer Inst itute\n\nHanlon, Sharpless\n\n---------------------\nWhy I’m Not Answering : Understanding Determinants of Classification of an Abstaining Classifier for Cancer Pathology Reports\n\nDhaubhadel, McMahon\n\nSafe deployment of deep learning systems to critical real world applications requires models to make few mistakes, and only under predictable circumstances. Developme nt of such a model is not yet possible, in general. In this work, we addre ss this problem with an abstaining classifier tuned to have ...\n\n\nRegis tration Category: Workshop Reg Pass END:VEVENT END:VCALENDAR