BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Women@CL Talklet Event - Emma Rocheteau and Michal Rozenwald
DTSTART:20191129T130000Z
DTEND:20191129T140000Z
UID:TALK135487@talks.cam.ac.uk
CONTACT:Zahra Tarkhani
DESCRIPTION:Speaker: Emma Rocheteau\n\nTitle: Deep Learning with Electroni
 c Health Records\n\n*Abstract:* \n\nDeep Learning has the potential to cha
 nge the future of healthcare. I am particularly interested in projects tha
 t bring different aspects of the Electronic Health Record together to make
  predictions such as length of stay and mortality. In this talk I will cov
 er two of my current research projects. The first is a collaboration with 
 Microsoft Research\; we use transformers to predict length of stay and dis
 charge location in the Intensive Care Unit (ICU). In the second we focus o
 n the best way to use the diagnosis data in a mortality predict task (agai
 n in the ICU). We form a graph of hospital patients based on diagnostic si
 milarity using an autoencoder. We propose a “sequential graph neural net
 work”\; a graph neural network that uses data from neighbouring patients
  to co-attend over the time series hidden states. I will briefly discuss s
 ome preliminary results for both projects.\n\n----------------------------
 ------\n\nSpeaker: Michal Rozenwald\n\nTitle: Neural Networks for 3D Chrom
 atin folding \n\n\n*Abstract:* \n\nRecent technological development has en
 abled the generation of large amounts of biological data. One area which h
 as seen rapid advances is in the field of chromatin folding. The developme
 nt of the Hi-C method has unraveled many basic principles of nuclear organ
 ization including the subdivision of the genome into chromosome territorie
 s\, chromatin compartments and Topologically Associating Domains (TADs). I
 n addition\, several studies have confirmed a correlation between 3D chrom
 atin organization and a host of epigenetic features relevant to cellular a
 ctivity and cell fate decisions. However\, a full description of the funct
 ional interplay between 3D organization and cellular behavior remains elus
 ive. Currently\, my main research focus is on applying Machine Learning me
 thods to analyze this 3D chromatin organization and its correlations with 
 epigenetic and transcriptional behavior. In this talk\, I will present our
  work at the lab of Dr. Mikhail Gelfand at HSE University\, Moscow on pred
 icting TAD characteristics using ChIP-seq epigenetic data on chromatin mar
 kers. We have presented a set of baselines including Linear regression mod
 els\, Gradient Boosting Trees and Recurrent Neural Networks.  Following th
 at project\, I am now working with Dr. Pietro Lio (Department of Computer 
 Science and Technology) and Dr. Ernest Laue (Department of Biochemistry) a
 s a visiting student at the University of Cambridge. In this project\, we 
 aim to combine population-level and single-cell Hi-C data and use Graph Ne
 ural Networks to gain new insights about genome organization and its links
  (if any) with transcriptional behavior during differentiation of mouse em
 bryonic stem cells. \nBesides that\, I'll be happy to share some tips on a
 pplications for summer internships and preparation for the SWE interviews.
  \n\n*Bio:* \n\nMichal (Miki) Rozenwald is a research assistant at the Bio
 informatics laboratory of Prof. Mikhail Gelfand at HSE University working 
 on applying Neural Networks to 3D chromatin structure analysis. She finish
 ed her BSc in Computer Science and is an MSc in Data Analysis in Biology a
 nd Medicine at the National Research University Higher School of Economics
  (HSE) in Moscow. She is currently a visiting student at Cambridge Univers
 ity working with Prof. Pietro Lio and Prof. Ernest Laue on combining popul
 ation and single-cell Hi-C methods to explore links between chromatin fold
 ing and epigenetics.Michal has interned at Google (Munich and Zurich)\, Fa
 cebook (London and California) working on various machine learning project
 s. She also interned at the bioinformatics lab of Dr. Noam Shomron at Tel-
 Aviv University\, Israel. 
LOCATION:Computer Laboratory\, William Gates Building\, Room FW11
END:VEVENT
END:VCALENDAR