R in Grenoble DATA CHALLENGES Magali Richard & Florent Chuffart - - PowerPoint PPT Presentation

r in grenoble data challenges
SMART_READER_LITE
LIVE PREVIEW

R in Grenoble DATA CHALLENGES Magali Richard & Florent Chuffart - - PowerPoint PPT Presentation

R in Grenoble DATA CHALLENGES Magali Richard & Florent Chuffart Introduct ction Data challenges in class Data challenges for scientists Tutorial CIT-SAB MEETING 2 What is a data challenge? Ellrott et al. Genome Biology (2019) 20:195


slide-1
SLIDE 1

R in Grenoble DATA CHALLENGES

Magali Richard & Florent Chuffart

slide-2
SLIDE 2

Introduct ction Data challenges in class Data challenges for scientists Tutorial

CIT-SAB MEETING 2

slide-3
SLIDE 3

What is a data challenge?

CIT-SAB MEETING 2

Ellrott et al. Genome Biology (2019) 20:195

slide-4
SLIDE 4

The challenge platform

Ø Enables participants to submit their codes Ø Automatically rank the participants

Alexis Arnaud CIT-SAB MEETING 12

slide-5
SLIDE 5

2013: Medical data. Result submission. COMPETITION BUNDLES 2014: Computer vision, speech, NLP, IR. MSCOCO: 361 participants. 2015: CODE SUBMISSION AutoML: 687 participants

  • Hackathons. Coopetitions.

2016: ChaLab Wizard. USE IN EDUCATION 2017: 480 challenges, 10000 users. SCALABILITY, REUSABILITY, DYNAMIC COMPETITIONS See.4c: EU prize, 2 million Euros

History

slide-6
SLIDE 6

Introduction Data ch challenges in cl class Data challenges for scientists Tutorial

CIT-SAB MEETING 2

slide-7
SLIDE 7

CIT-SAB MEETING 2

A novel pedagogic approache

As practical work As homework As final evaluation

slide-8
SLIDE 8

CIT-SAB MEETING 2

Chagrade: a dedicated tool in codalab

slide-9
SLIDE 9

Introduction Data challenges in class Data ch challenges for sci cientists Tutorial

CIT-SAB MEETING 2

slide-10
SLIDE 10

Goal of our data challenge

  • Quantification of tumor heterogeneity

CIT-SAB MEETING 3 Tumor cells Immune cells Normal cells CAF ?

slide-11
SLIDE 11

A challenge for scientists

CIT-SAB MEETING 4

slide-12
SLIDE 12

2 editions of the data challenge

CIT-SAB MEETING 4

1rst edition (2018) 2nd edition (2019)

  • Methylation Data
  • One cancer type
  • Cell lines
  • Methylation and transcriptomic Data
  • Several cancer types
  • Primary tumors / cell lines
slide-13
SLIDE 13

When and where?

CIT-SAB MEETING 6

  • When: 25-29 of November 2019
  • Where: Aussois (CAES CNRS), French Alps
slide-14
SLIDE 14

About the participants (n=34)

CIT-SAB MEETING 7 Engineers Graduate students Industry Postdoc Researchers Undergrad students Bioinformatics Computer science Data science Medical science Statistics Byelorussia France Germany Luxembourg Norway Sweden

Institut Curie UGA Grenoble CRC Cordeliers INSERM CEA Innate Pharma Verteego …

10 teams of 3-4 people

slide-15
SLIDE 15

Agenda

CIT-SAB MEETING 9 PRACTICALS

Talks

#1 #1 #2 #2 #2 #2

Feed Back Brain Storming

Guidelines

Social event Poster session

slide-16
SLIDE 16

Valorization of the first edition

Ø R package medepir

https://rdrr.io/github/bcm- uga/medepir/man/medepir-package.html

Ø Guidelines

Health data challenges organization: feedback, comments and recommendations.

Authors: Elise Amblard, Yuna Blum, Jane Merlevede, Magali Richard In preparation

In review in BCM bioinformatics

Ø Article Ø Blog posts

M Richard, C Decamps , F Privé, M Blum CIT-SAB MEETING 16

slide-17
SLIDE 17

From data challenges to benchmarks

slide-18
SLIDE 18

Introduction Data challenges in class Data challenges for scientists Tu Tutorial

CIT-SAB MEETING 2

slide-19
SLIDE 19

On line tutorial by Alexis Arnaud

slide-20
SLIDE 20

It’s up to you now!

slide-21
SLIDE 21

Thank you for your attention !

CIT-SAB MEETING 20

https://app.secure.griffith.edu.au/events/event/61593