BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Manifold Learning Uncovers Hidden Structure in Complex Cellular St
 ate Space
DTSTART:20190321T141500
DTSTAMP:20260407T043205Z
UID:99593f2e017e392fa19c70dcbab46f96d93d5e14047b8cb36ab2f24f
CATEGORIES:Conferences - Seminars
DESCRIPTION:David van Dijk\, Ph.D.\, Yale University\, New Haven\, CT (USA
 )\nBIOENGINEERING SEMINAR\n \nAbstract:\nIn the era of big biological dat
 a\, there is a pressing need for methods that visualize\, integrate and in
 terpret high-throughput high-dimensional data to enable biological discove
 ry. There are several major challenges in analyzing high-throughput biolog
 ical data. These include the curse of (high) dimensionality\, noise\, spar
 sity\, missing values\, bias\, and collection artifacts. In my work\, I tr
 y to solve these problems using computational methods that are based on ma
 nifold learning. A manifold is a smoothly varying low-dimensional structur
 e embedded within high-dimensional ambient measurement space. In my talk\,
  I will present a number of recently completed and ongoing projects that u
 tilize the manifold\, implemented using graph signal processing and deep l
 earning\, to understand large biomedical datasets. First\, I will present 
 MAGIC\, a data denoising and imputation method designed to ‘fix’ singl
 e-cell RNA-sequencing data. MAGIC uses data diffusion to learn the data ma
 nifold and at the same time fill in and smooth the data\, thereby revealin
 g the underlying structure of the data. I will show how MAGIC reveals a co
 ntinuous phenotypic state-space in an epithelial-to-mesenchymal transition
  system. I will then talk about PHATE\, a dimensionality reduction and vis
 ualization method specifically designed to reveal continuous progression s
 tructure. I will demonstrate how PHATE can give profound insight into a ne
 wly measured human embryonic stem cell system. Finally\, I will talk about
  two deep learning methods that use specially designed constraints to allo
 w for deep interpretable representations of heterogeneous systems such as 
 gut microbiome data and single cell-data of tumor infiltrating lymphocytes
 .\n\nBio:\nDavid van Dijk is an Associate Research Scientist in the lab of
  Smita Krishnaswamy at Yale University\, departments of Genetics and Compu
 ter Science. His current research focuses on machine learning\, and in spe
 cific manifold learning\, applied to big biological data.\nPreviously\, Dr
 . van Dijk worked with Eran Segal at the Weizmann Institute of Science\,
  where he developed methods for predicting gene expression from DNA seque
 nce.\nHe did his Ph.D. with Jaap Kaandorp in the Computational Science g
 roup at the University of Amsterdam\, and with Eran Segal at the Weizmann
  Institute of Science in Rehovot\, Israel.\n\n\nZoom link for attending re
 motely:  https://epfl.zoom.us/j/943730674
LOCATION:AI 1153 https://plan.epfl.ch/?room==AI%201153
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR