What we're about
Upcoming events (5)
Dana Farber Cancer Institute, Yawkey 306-307
Approaches for integration of multi 'omics datasets. Yawkey Center for Cancer Care YCCC, Room 306/307 Thurs Feb 28th 5:30pm -7:30pm Excellent Science, Networking, Food, Please contact us if you would like to present a 5 min Lightning Talk. Nathalie Pochet, Ph.D. ------------------------------- Assistant Professor, Department of Neurology, Harvard Medical School Associate Member, Cell Circuits Program, Broad Institute of MIT and Harvard Associate Scientist, Ann Romney Center for Neurologic Diseases, Brigham and Women’s Hospital Title: AMARETTO: a regulatory network inference tool for multi-omics data fusion across systems and diseases Abstract: The availability of increasing volumes of multi-omics profiles from model systems to patient studies promises to improve our understanding of the regulatory mechanisms underlying human diseases. The main challenges are to integrate these multiple levels of omics data and to translate them across in vitro and in vivo systems. We recently developed the AMARETTO and Community-AMARETTO algorithms that learn regulatory networks shared and distinct across biological systems with a broad range of applications, from diagnostic subtyping to driver and drug discovery in studies of human disease. The AMARETTO framework is available via GitHub and as user-friendly tools in Bioconductor and GenePattern. Bio: Nathalie received an extensive and unusually broad training resulting in three M.Sc. degrees in the fields of Engineering in Computer Science, Artificial Intelligence, and Bioinformatics, and a Ph.D. degree in Engineering in Machine Learning and Bioinformatics. Training with leaders in the fields of machine learning, computer science, statistics, biology, genomics and medicine, she became an expert in developing tools that help advance and overcome challenges in biomedical research for better understanding, diagnosis and treatment of human disease. Her lab at HMS/BWH/Broad continues to focus on the development and dissemination of algorithms and software tools and their applications to studies of human disease, including cancer, infectious, neurologic and immune-mediated diseases, to accelerate biomedical research and healthcare delivery. https://personal.broadinstitute.org/npochet/ https://connects.catalyst.harvard.edu/Profiles/display/Person/115197 Aedin Culhane, Ph.D --------------------------- Senior Research Scientist Dept of Data Sciences, Dana-Farber Cancer Institute, Dept of Biostatistics, Harvard TH Chan School of Public Health Title: moGSA, Integrative multi' omics single sample gene set analysis Abstract: Gene set analysis (GSA) has become an indispensable step in the interpretation of large scale omics data through summarizing individual molecular measurements to more interpretable pathways or gene sets. However, current GSA methods are limited to the analysis of single omics data. We describe a new computation method, multi-omics gene set analysis (MOGSA), a multivariate single sample gene-set analysis method that integrates multiple experimental and molecular data types measured over the same set of samples. MOGSA is available in the Bioconductor R package “mogsa”. A preprint describing MOGSA is available at https://www.biorxiv.org/content/10.1101/046904v2 Bio: Dr. Culhane develops computational approaches to integrate and analyze large scale cancer genomics data at Biostatistics and Computational Biology at the Dana-Farber Cancer Institute, Harvard TH Chan School of Public Health She is an R developer and maintains several Bioconductor/R packages for clustering, matrix factorization and integrative exploratory analysis of big data in genomics. She is a member of the technical advisory board for Bioconductor, a founding member of the Boston R/Bioconductor for genomics meetup and is an advocate for reproducibility in academic research and women in STEM. https://www.hsph.harvard.edu/aedin-culhane/ http://www.dfhcc.harvard.edu/insider/member-detail/member/aedin-culhane-phd/
JJ Allaire founder and CEO of RStudio (https://www.rstudio.com/) will be the guest speaker Abstract: Machine Learning with TensorFlow and R TensorFlow is an open-source software library for numerical computation and machine intelligence developed by researchers and engineers working on the Google Brain Team. In this talk we'll cover the R interface to TensorFlow (https://tensorflow.rstudio.com), a suite of packages that provide high-level interfaces to both deep learning models (Keras) and standard regression and classification models (Estimators), as well as tools for cloud training, experiment management, and production deployment. The talk will also discuss deep learning more broadly (what it is, how it works, and where it might be relevant to users of R in the years ahead). Bio: J.J. Allaire is the Founder of RStudio and the creator of the RStudio IDE. J.J. is the author of the R interfaces to TensorFlow and Keras.