The Reilly lab develops and applies new high-throughput experimental approaches to interrogate the genome, such as non-coding CRISPR screens (Nature Genetics) and the Massively Parallel Reporter Assay (Cell, Science), as part of our work in an ENCODE functional characterization center (Nature Methods). Computationally, we also develop machine-learning approaches to predict the functions of these CRE perturbations. Together with these new tools, we use evolution as a powerful lens for characterizing genomic signals of positive selection that impact modern human phenotypes and diseases. As affiliates of the Impact of Genomic Variation on Function (IGVF) consortium, we collaborate at the national level on variant-to-function methods development, while offering access to a vast, cutting-edge scientific support network.
This is a postdoctoral position at the Human+Artificial Intelligence Lab. This lab is seeking highly motivated and dedicated individuals who are passionate about advancing the use of machine learning in supporting and enhancing human presence in clinical care. The HAIM lab in the Department of Internal Medicine at Yale School of Medicine provides a stimulating training environment and interdisciplinary opportunities to collaborate with physician data scientists and clinical informaticians. Our laboratory is interested in developing, validating, and studying novel machine learning methods with multimodal data (electronic health record, image, and other data sources) to develop, validate, and implement robust machine learning algorithms to provide risk prediction for clinical decision support. We are also interested in developing and using machine learning tools for dynamic electronic health record phenotyping to target clinical care pathways and exploring methods to understand and test for disparities in care when using machine learning algorithms.
Facilitating Human Learning By Aquino.pdfl
Download File: https://8conriagaso.blogspot.com/?hu=2vEA12
2ff7e9595c
Comentarios