Casey Greene's Keynote for Rocky 2015

Post on 19-Feb-2017

561 views 0 download

Transcript of Casey Greene's Keynote for Rocky 2015

supermarketnews.com

10 Assays ~1 Experiment

100 Assays ~Pseudomonas syringae compendium

1000 Assays ~Pseudomonas aeruginosa Compendium

10,000 Assays ~Zebrafish Compendium

100,000 Assays ~Rat Compendium

1,800,000 Assays ~Publicly Available Compendium

~Human Compendium

One Recent Experiment (Macosko et al. Cell. 2015)

Research is to see what everybody else has seen and to think what

nobody else has thought.�Albert Szent-Györgyi

Image by J.W. McGuire/NIH

Image from You Don’t Know Jack. Vol 3.

Unsupervised discovery from large gene expression

compendia with ADAGE

Casey Greene

Assistant Professor Systems Pharmacology and Translational Therapeutics

Image by Lisbeth Salander

If you showed 16,000 computers 10 million images from youtube, what would they see?

Le et al. 2012

Deep Learning from Youtube

Internet Videos

Computing Cluster

Object Detector

pbs.org Le et al. 2012

Google Research

Analysis with Denoising Autoencoders of �Gene Expression (ADAGE)

Tan et al. Pac Sym Bio 2015; Tan et al. In Press.

LeCun, Bengio, and Hinton. Nature 2015.

High-weight Contributors

ADAGE Identifies Genes’ Pathways

Assign Pathway

… and produces useful networks

ADAGE Identifies Strain Differences

Genome Hybridization

ADAGE Identifies Strain Differences

The Transcription Factor Anr Controls P.a. Response to Low O2

Low O2

O2

O2

O2

O2

O2 O2

O2 O2

O2

O2

O2

O2

O2

O2

O2 O2

O2

O2 O2

O2

O2

O2 O2

O2

O2

O2 O2 O2

O2 O2

O2

O2

O2

Anr

CF Lung Epithelium

Node42 reflects Anr Activity

New Experiment Validates Node 42’s Low-O2 Signature

CF lung epithelial cells Jack Hammond

ADAGE complements PCA/ICANode 42 PC4 PC7 IC14 IC49

Cross-platform normalization of microarray and RNA-seq data for machine learning applications

Thompson, Tan, Greene. PeerJ Preprint: https://peerj.com/preprints/1460/ Jeff Thompson

Cross-platform normalization of microarray and RNA-seq data for machine learning applications

Thompson, Tan, Greene. PeerJ Preprint: https://peerj.com/preprints/1460/

ADAGE complements PCA/ICA

Tan et al. In Press. Supplemental Figures 1-3

Node 42 PC4 PC7 IC14 IC49

How do we move from �this to mechanisms?

What “pathways” did my experiment affect?

ADAGE-based Pathway Analysis of Transcriptomic Changes

P19: ADAGE analysis of publicly available gene expression data collections illuminates Pseudomonas aeruginosa-host interactions�bioRxiv: http://dx.doi.org/10.1101/030650

P54: Cross-population analysis of high-grade serous ovarian cancer reveals only two robust subtypes. bioRxiv: http://dx.doi.org/10.1101/030239

Mine Your�

Own Business

Image by DixiePistols

Mine Your�

Own Business

Greene and Troyanskaya, Nucleic Acids Research. 2011

Mine Your�

Own Business

Wong*, Park*, Greene* et al., Nucleic Acids Research. 2012

Mine Your�

Own Business

Greene,* Wong,* Krishnan,* et al. Nature Genetics. 2015.

Mine Your�

Own Business

Zelaya and Greene, In Preparation

ADAGE Webserver coming soon! http://www.greenelab.com

When you’re caught in the data deluge…

Image by Lisbeth Salander

… don’t grab an umbrella…

Image by Lena Vasiljeva

… get a bucket.

Image by SantiMB.Photos

Greene Lab: Jie Tan+ (Grad Student) Gregory Way (Grad Student) René Zelaya (Programmer) Matt Huyck (Programmer) Kathy Chen (Undergrad) Mulin Xiong (Undergrad) Jeff Thompson (Marsit Lab/Dartmouth) Data: All investigators who publicly release their gene expression data. Images: Artists who release their work under a Creative Commons license. Funding: G&B Moore Investigator in Data-Driven Discovery National Science Foundation Cystic Fibrosis Foundation Norris Cotton Cancer Center Prouty Grant American Cancer Society Dartmouth SYNERGY +Neukom Institute Graduate Fellowship Find us online: http://www.greenelab.com Twitter: @GreeneScientist