UNIVERSITY PARK, Pa. — A panel of Penn State researchers will offer insights into how researchers can tap artificial intelligence — AI — to be a powerful tool for scientific discovery.
Moderated by Vasant Honavar, professor, Edward Frymoyer Chair of Information Sciences and Technology, and associate director of the Institute for Computational and Data Sciences, the panel will be held from noon to 1:30 p.m. Oct. 13 on Zoom.
The panelists include:
— Nicholas G Zaorsky is a radiation oncologist at Penn State Cancer Institute in Hershey, where he is a funded, board-certified, tenure-track clinical investigator. As a clinician, his focuses on the treatment of genitourinary cancers, specifically prostate and kidney. As an investigator, he is interested in epidemiology, metastasis, identifying and preventing specific causes of death in cancer patients, comparative effectiveness research, quality of care, and lifestyle interventions. His research projects often use “big data,” with millions of patients, events, covariates, and time points; he is using artificial intelligence to help improve predictive power in these works.
— Edward Patrick O'Brien Jr., associate professor of chemistry, and his group use artificial intelligence techniques to guide the development of molecular and physics-based models of protein translation within cells. This work uses AI techniques to help sort through the large feature space to identify essential and robust features that then form the basis for molecular modeling of these processes. O’Brien’s research has implications for our general understanding of protein translation associated with improperly formed proteins that lead to altered structure and function, and can contribute to changes in phenotype and disease.
— Santhosh Girirajan, associate professor of genomics biochemistry, whose research is focused on understanding the molecular basis of complex neurodevelopmental disorders such as autism, intellectual disability and schizophrenia. His lab uses human genetics, functional studies in model organisms and computational approaches to identify how specific combinations of genetic mutations cause or modulate developmental, psychiatric and cellular features associated with these disorders.
“We use AI techniques in several aspects of our work, including identification of genetic variants, such as large deletions and duplications, from genome sequencing data, and correlating cognitive, developmental and behavioral quantitative traits with genes and genetic variants from large cohorts of affected and healthy individuals,” Girirajan said. “These approaches provide hypothesis-generating correlations between genotypes and clinical phenotypes that we are able to iteratively validate in independent cohorts and further explore using functional molecular studies.”
— Sarah Rajtmajer, assistant professor of information sciences and technology and research associate in the Rock Ethics Institute. Emergent collective behavior has been a major focus for researchers across the social and behavioral sciences for more than a century. Sociologists, psychologists and economists have proposed theories to explain group behaviors that cannot be understood as a sum of constituent parts. Rather, complex interactions amongst individuals give rise to novel and unexpected system-level organization and norms. Further challenging our understanding of emergence, macro-social properties feedback to individual behaviors, reinforcing effects (immergence). Increased digital connectedness has accelerated and highlighted these phenomena, as we have witnessed striking examples of self-organization and crowd behavior powered by social media, from the emergence of altruistic norms in crises to radicalization and extremism. In parallel, this same digital connectivity has furnished researchers with comprehensive behavioral traces of and detailed social ties at massive scale. This data, paired with recent innovations in AI, represents a disruptive opportunity to advance the science of collective behavior. Advances in AI will support critical cross-domain exploration and synthesis of the exceptionally broad and diverse literatures relevant to the enigmatic questions of collective behavior, while model-based machine learning can serve to meaningfully integrate longstanding theories of collective behavior into data-driven predictions.
Advance registration will be required at this Zoom link.