Slides online at: slides.com

/dhimmel

/rocky

Friday December 9, 2016

10:05–10:15 am (OP 18)

cognition

+

carcinoma

presentation abstract

(as seen on GitHub and the Rocky Program)

Precision oncology requires that we functionally categorize cancers into treatment-relevant subtypes. The predominant approach—characterizing tumors based solely on actionable mutations—struggles to detect complex changes in gene or pathway function. Alternatively, genome-wide expression profiles provide a comprehensive reflection of aberrant cellular states resulting from mutation events. Therefore, we embarked on Project Cognoma to translate between gene expression and mutation in cancer.

Cognoma is an open-source/citizen-science philanthropy being developed as a collaboration between the Greene Lab at Penn and the DataPhilly and Code for Philly meetups. This arrangement leverages the collective fullstack expertise of our diverse contributor base. Hitherto, hundreds of individuals have attended Cognoma meetups, and more than fifty have gotten involved on GitHub. Our priorities are everyone learns something new and putting machine learning in the hands of cancer biologists.

Our product is cognoma.org, a webapp that makes it easy to build mutation status classifiers from gene expression on 7,306 TCGA samples representing 33 cancer types. The publicly available dataset contains RNA-seq gene expression for 20,530 genes, non-silent mutation calls for 21,940 genes, and sample attributes such as the patient's disease, age, sex, and survival. Cognoma enables a cancer biologist to assign each sample a mutation status based on one or more selected genes. Next, a disciplined classifier is trained using gene expression and sample attributes as features. As output, the user receives the importance of each feature—offering insight into the molecular effects of their chosen mutation—as well as a mutation scores for samples—which potentially identify hidden responders to targeted pharmacotherapies.

Authors: Daniel Himmelstein, Gregory Way, Andrew Madonna, Alan Elkner, Benjamin Dolly, Yichuan Liu, Claire McLeod, Derek Goss, Haitao Cai, Chris Fuller, Robert Paul Miller, Nabeel Sarwar, Branka Jokanovic, Mans Singh, Stephen Shank, Joel Eden, Karin Wolok, Casey Greene

putting machine learning in the hands of cancer biologists

Cognoma Motto 1

machine learning

Predicting cancer mutations from gene expression

Using public domain TCGA data

(from Xena Browser)

7,306 samples

20,468 genes with expression

RNA-Seq

21,960 genes with mutation.

Sequencing

covariates

elastic net logistic regression

TP53

Sample Organ Mutation Prediction
0
0
0
0
0
0
0
99.2%
99.2%
99.1%
98.8%
98.4%
98.4%
98.2%
Esophagus
Esophagus
Ovary
Breast
Lung
Esophagus
Rectum
TCGA-L5-A8NR-01
TCGA-L5-A4OH-01
TCGA-09-2051-01
TCGA-B6-A0I6-01
TCGA-55-6981-01
TCGA-L5-A4OO-01
TCGA-EI-6513-01

Could gene expression identify hidden responders?

everyone learns something new

Cognoma Motto 2

Pull requests model for contribution

Contribution per user by GitHub repository

Full Stack Data Science

Four teams:

  • Cancer data
  • Machine learning
  • Backend
  • Frontend

Thanks!

Organization Members: Andrew Madonna, Benjamin Dolly, Gregory Way,  Casey Greene, Karin Wolok, Jesse Prestwood-Taylor, Claire McLeod, Stephen Shank, Josh Levy, Yichuan Liu, Derek Goss, Tanner Wells & many more at https://git.io/v65k6.

Made with Slides.com