A Computational Framework for Genome-wide Characterization of the Human Disease Landscape

Young suk Lee, Arjun Krishnan, Rose Oughtred, Jennifer Rust, Christie S. Chang, Joseph Ryu, Vessela N. Kristensen, Kara Dolinski, Chandra L. Theesfeld, Olga G. Troyanskaya

Research output: Contribution to journalArticle

Abstract

A key challenge for the diagnosis and treatment of complex human diseases is identifying their molecular basis. Here, we developed a unified computational framework, URSA HD (Unveiling RNA Sample Annotation for Human Diseases), that leverages machine learning and the hierarchy of anatomical relationships present among diseases to integrate thousands of clinical gene expression profiles and identify molecular characteristics specific to each of the hundreds of complex diseases. URSA HD can distinguish between closely related diseases more accurately than literature-validated genes or traditional differential-expression-based computational approaches and is applicable to any disease, including rare and understudied ones. We demonstrate the utility of URSA HD in classifying related nervous system cancers and experimentally verifying novel neuroblastoma-associated genes identified by URSA HD . We highlight the applications for potential targeted drug-repurposing and for quantitatively assessing the molecular response to clinical therapies. URSA HD is freely available for public use, including the use of underlying models, at ursahd.princeton.edu. Discovering unique properties among diseases is needed to develop targeted treatments, especially for related disorders. To address this, we developed a unified framework, URSA HD , which leverages physiological relationships between diseases and integrates thousands of clinical samples across >300 diseases to identify distinct characteristics that can be used to guide biomedical research. We demonstrate applications of URSA HD , including guiding hypothesis generation and experiments, drug repurposing, and quantitatively tracking drug response.

Original languageEnglish (US)
Pages (from-to)152-162.e6
JournalCell Systems
Volume8
Issue number2
DOIs
StatePublished - Feb 27 2019

Fingerprint

Genome
Drug Repositioning
Rare Diseases
Neuroblastoma
Transcriptome
Nervous System
Genes
Biomedical Research
RNA
Pharmaceutical Preparations
Neoplasms

All Science Journal Classification (ASJC) codes

  • Pathology and Forensic Medicine
  • Cell Biology
  • Histology

Cite this

Lee, Young suk ; Krishnan, Arjun ; Oughtred, Rose ; Rust, Jennifer ; Chang, Christie S. ; Ryu, Joseph ; Kristensen, Vessela N. ; Dolinski, Kara ; Theesfeld, Chandra L. ; Troyanskaya, Olga G. / A Computational Framework for Genome-wide Characterization of the Human Disease Landscape. In: Cell Systems. 2019 ; Vol. 8, No. 2. pp. 152-162.e6.
@article{cdb486784652461c88da438346ef68c8,
title = "A Computational Framework for Genome-wide Characterization of the Human Disease Landscape",
abstract = "A key challenge for the diagnosis and treatment of complex human diseases is identifying their molecular basis. Here, we developed a unified computational framework, URSA HD (Unveiling RNA Sample Annotation for Human Diseases), that leverages machine learning and the hierarchy of anatomical relationships present among diseases to integrate thousands of clinical gene expression profiles and identify molecular characteristics specific to each of the hundreds of complex diseases. URSA HD can distinguish between closely related diseases more accurately than literature-validated genes or traditional differential-expression-based computational approaches and is applicable to any disease, including rare and understudied ones. We demonstrate the utility of URSA HD in classifying related nervous system cancers and experimentally verifying novel neuroblastoma-associated genes identified by URSA HD . We highlight the applications for potential targeted drug-repurposing and for quantitatively assessing the molecular response to clinical therapies. URSA HD is freely available for public use, including the use of underlying models, at ursahd.princeton.edu. Discovering unique properties among diseases is needed to develop targeted treatments, especially for related disorders. To address this, we developed a unified framework, URSA HD , which leverages physiological relationships between diseases and integrates thousands of clinical samples across >300 diseases to identify distinct characteristics that can be used to guide biomedical research. We demonstrate applications of URSA HD , including guiding hypothesis generation and experiments, drug repurposing, and quantitatively tracking drug response.",
author = "Lee, {Young suk} and Arjun Krishnan and Rose Oughtred and Jennifer Rust and Chang, {Christie S.} and Joseph Ryu and Kristensen, {Vessela N.} and Kara Dolinski and Theesfeld, {Chandra L.} and Troyanskaya, {Olga G.}",
year = "2019",
month = "2",
day = "27",
doi = "https://doi.org/10.1016/j.cels.2018.12.010",
language = "English (US)",
volume = "8",
pages = "152--162.e6",
journal = "Cell Systems",
issn = "2405-4712",
publisher = "Cell Press",
number = "2",

}

Lee, YS, Krishnan, A, Oughtred, R, Rust, J, Chang, CS, Ryu, J, Kristensen, VN, Dolinski, K, Theesfeld, CL & Troyanskaya, OG 2019, 'A Computational Framework for Genome-wide Characterization of the Human Disease Landscape', Cell Systems, vol. 8, no. 2, pp. 152-162.e6. https://doi.org/10.1016/j.cels.2018.12.010

A Computational Framework for Genome-wide Characterization of the Human Disease Landscape. / Lee, Young suk; Krishnan, Arjun; Oughtred, Rose; Rust, Jennifer; Chang, Christie S.; Ryu, Joseph; Kristensen, Vessela N.; Dolinski, Kara; Theesfeld, Chandra L.; Troyanskaya, Olga G.

In: Cell Systems, Vol. 8, No. 2, 27.02.2019, p. 152-162.e6.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Computational Framework for Genome-wide Characterization of the Human Disease Landscape

AU - Lee, Young suk

AU - Krishnan, Arjun

AU - Oughtred, Rose

AU - Rust, Jennifer

AU - Chang, Christie S.

AU - Ryu, Joseph

AU - Kristensen, Vessela N.

AU - Dolinski, Kara

AU - Theesfeld, Chandra L.

AU - Troyanskaya, Olga G.

PY - 2019/2/27

Y1 - 2019/2/27

N2 - A key challenge for the diagnosis and treatment of complex human diseases is identifying their molecular basis. Here, we developed a unified computational framework, URSA HD (Unveiling RNA Sample Annotation for Human Diseases), that leverages machine learning and the hierarchy of anatomical relationships present among diseases to integrate thousands of clinical gene expression profiles and identify molecular characteristics specific to each of the hundreds of complex diseases. URSA HD can distinguish between closely related diseases more accurately than literature-validated genes or traditional differential-expression-based computational approaches and is applicable to any disease, including rare and understudied ones. We demonstrate the utility of URSA HD in classifying related nervous system cancers and experimentally verifying novel neuroblastoma-associated genes identified by URSA HD . We highlight the applications for potential targeted drug-repurposing and for quantitatively assessing the molecular response to clinical therapies. URSA HD is freely available for public use, including the use of underlying models, at ursahd.princeton.edu. Discovering unique properties among diseases is needed to develop targeted treatments, especially for related disorders. To address this, we developed a unified framework, URSA HD , which leverages physiological relationships between diseases and integrates thousands of clinical samples across >300 diseases to identify distinct characteristics that can be used to guide biomedical research. We demonstrate applications of URSA HD , including guiding hypothesis generation and experiments, drug repurposing, and quantitatively tracking drug response.

AB - A key challenge for the diagnosis and treatment of complex human diseases is identifying their molecular basis. Here, we developed a unified computational framework, URSA HD (Unveiling RNA Sample Annotation for Human Diseases), that leverages machine learning and the hierarchy of anatomical relationships present among diseases to integrate thousands of clinical gene expression profiles and identify molecular characteristics specific to each of the hundreds of complex diseases. URSA HD can distinguish between closely related diseases more accurately than literature-validated genes or traditional differential-expression-based computational approaches and is applicable to any disease, including rare and understudied ones. We demonstrate the utility of URSA HD in classifying related nervous system cancers and experimentally verifying novel neuroblastoma-associated genes identified by URSA HD . We highlight the applications for potential targeted drug-repurposing and for quantitatively assessing the molecular response to clinical therapies. URSA HD is freely available for public use, including the use of underlying models, at ursahd.princeton.edu. Discovering unique properties among diseases is needed to develop targeted treatments, especially for related disorders. To address this, we developed a unified framework, URSA HD , which leverages physiological relationships between diseases and integrates thousands of clinical samples across >300 diseases to identify distinct characteristics that can be used to guide biomedical research. We demonstrate applications of URSA HD , including guiding hypothesis generation and experiments, drug repurposing, and quantitatively tracking drug response.

UR - http://www.scopus.com/inward/record.url?scp=85061808799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061808799&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.cels.2018.12.010

DO - https://doi.org/10.1016/j.cels.2018.12.010

M3 - Article

VL - 8

SP - 152-162.e6

JO - Cell Systems

JF - Cell Systems

SN - 2405-4712

IS - 2

ER -

Lee YS, Krishnan A, Oughtred R, Rust J, Chang CS, Ryu J et al. A Computational Framework for Genome-wide Characterization of the Human Disease Landscape. Cell Systems. 2019 Feb 27;8(2):152-162.e6. https://doi.org/10.1016/j.cels.2018.12.010