Computational translation of genomic responses from experimental model systems to humans

Douglas K. Brubaker, Elizabeth Anne Proctor, Kevin M. Haigis, Douglas A. Lauffenburger

Research output: Contribution to journalArticle

Abstract

The high failure rate of therapeutics showing promise in mouse models to translate to patients is a pressing challenge in biomedical science. Though retrospective studies have examined the fidelity of mouse models to their respective human conditions, approaches for prospective translation of insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-supervised learning approach for inference of disease-associated human differentially expressed genes and pathways from mouse model experiments. We examined 36 transcriptomic case studies where comparable phenotypes were available for mouse and human inflammatory diseases and assessed multiple computational approaches for inferring human biology from mouse datasets. We found that semi-supervised training of a neural network identified significantly more true human biological associations than interpreting mouse experiments directly. Evaluating the experimental design of mouse experiments where our model was most successful revealed principles of experimental design that may improve translational performance. Our study shows that when prospectively evaluating biological associations in mouse studies, semi-supervised learning approaches, combining mouse and human data for biological inference, provide the most accurate assessment of human in vivo disease processes. Finally, we proffer a delineation of four categories of model system-to-human “Translation Problems" defined by the resolution and coverage of the datasets available for molecular insight translation and suggest that the task of translating insights from model systems to human disease contexts may be better accomplished by a combination of translation-minded experimental design and computational approaches.

Original languageEnglish (US)
Article numbere1006286
JournalPLoS computational biology
Volume15
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

translation (genetics)
Genomics
Mouse
genomics
Theoretical Models
mice
experimental design
Design of experiments
animal models
Supervised learning
Experimental design
Semi-supervised Learning
Research Design
Model
learning
experiment
Experiments
Human
pressing
Experiment

All Science Journal Classification (ASJC) codes

  • Ecology, Evolution, Behavior and Systematics
  • Modeling and Simulation
  • Ecology
  • Molecular Biology
  • Genetics
  • Cellular and Molecular Neuroscience
  • Computational Theory and Mathematics

Cite this

Brubaker, Douglas K. ; Proctor, Elizabeth Anne ; Haigis, Kevin M. ; Lauffenburger, Douglas A. / Computational translation of genomic responses from experimental model systems to humans. In: PLoS computational biology. 2019 ; Vol. 15, No. 1.
@article{d9eb143635604a48b8a0f998c45a8f6a,
title = "Computational translation of genomic responses from experimental model systems to humans",
abstract = "The high failure rate of therapeutics showing promise in mouse models to translate to patients is a pressing challenge in biomedical science. Though retrospective studies have examined the fidelity of mouse models to their respective human conditions, approaches for prospective translation of insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-supervised learning approach for inference of disease-associated human differentially expressed genes and pathways from mouse model experiments. We examined 36 transcriptomic case studies where comparable phenotypes were available for mouse and human inflammatory diseases and assessed multiple computational approaches for inferring human biology from mouse datasets. We found that semi-supervised training of a neural network identified significantly more true human biological associations than interpreting mouse experiments directly. Evaluating the experimental design of mouse experiments where our model was most successful revealed principles of experimental design that may improve translational performance. Our study shows that when prospectively evaluating biological associations in mouse studies, semi-supervised learning approaches, combining mouse and human data for biological inference, provide the most accurate assessment of human in vivo disease processes. Finally, we proffer a delineation of four categories of model system-to-human “Translation Problems{"} defined by the resolution and coverage of the datasets available for molecular insight translation and suggest that the task of translating insights from model systems to human disease contexts may be better accomplished by a combination of translation-minded experimental design and computational approaches.",
author = "Brubaker, {Douglas K.} and Proctor, {Elizabeth Anne} and Haigis, {Kevin M.} and Lauffenburger, {Douglas A.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pcbi.1006286",
language = "English (US)",
volume = "15",
journal = "PLoS Computational Biology",
issn = "1553-734X",
publisher = "Public Library of Science",
number = "1",

}

Computational translation of genomic responses from experimental model systems to humans. / Brubaker, Douglas K.; Proctor, Elizabeth Anne; Haigis, Kevin M.; Lauffenburger, Douglas A.

In: PLoS computational biology, Vol. 15, No. 1, e1006286, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Computational translation of genomic responses from experimental model systems to humans

AU - Brubaker, Douglas K.

AU - Proctor, Elizabeth Anne

AU - Haigis, Kevin M.

AU - Lauffenburger, Douglas A.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The high failure rate of therapeutics showing promise in mouse models to translate to patients is a pressing challenge in biomedical science. Though retrospective studies have examined the fidelity of mouse models to their respective human conditions, approaches for prospective translation of insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-supervised learning approach for inference of disease-associated human differentially expressed genes and pathways from mouse model experiments. We examined 36 transcriptomic case studies where comparable phenotypes were available for mouse and human inflammatory diseases and assessed multiple computational approaches for inferring human biology from mouse datasets. We found that semi-supervised training of a neural network identified significantly more true human biological associations than interpreting mouse experiments directly. Evaluating the experimental design of mouse experiments where our model was most successful revealed principles of experimental design that may improve translational performance. Our study shows that when prospectively evaluating biological associations in mouse studies, semi-supervised learning approaches, combining mouse and human data for biological inference, provide the most accurate assessment of human in vivo disease processes. Finally, we proffer a delineation of four categories of model system-to-human “Translation Problems" defined by the resolution and coverage of the datasets available for molecular insight translation and suggest that the task of translating insights from model systems to human disease contexts may be better accomplished by a combination of translation-minded experimental design and computational approaches.

AB - The high failure rate of therapeutics showing promise in mouse models to translate to patients is a pressing challenge in biomedical science. Though retrospective studies have examined the fidelity of mouse models to their respective human conditions, approaches for prospective translation of insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-supervised learning approach for inference of disease-associated human differentially expressed genes and pathways from mouse model experiments. We examined 36 transcriptomic case studies where comparable phenotypes were available for mouse and human inflammatory diseases and assessed multiple computational approaches for inferring human biology from mouse datasets. We found that semi-supervised training of a neural network identified significantly more true human biological associations than interpreting mouse experiments directly. Evaluating the experimental design of mouse experiments where our model was most successful revealed principles of experimental design that may improve translational performance. Our study shows that when prospectively evaluating biological associations in mouse studies, semi-supervised learning approaches, combining mouse and human data for biological inference, provide the most accurate assessment of human in vivo disease processes. Finally, we proffer a delineation of four categories of model system-to-human “Translation Problems" defined by the resolution and coverage of the datasets available for molecular insight translation and suggest that the task of translating insights from model systems to human disease contexts may be better accomplished by a combination of translation-minded experimental design and computational approaches.

UR - http://www.scopus.com/inward/record.url?scp=85060367530&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060367530&partnerID=8YFLogxK

U2 - 10.1371/journal.pcbi.1006286

DO - 10.1371/journal.pcbi.1006286

M3 - Article

VL - 15

JO - PLoS Computational Biology

JF - PLoS Computational Biology

SN - 1553-734X

IS - 1

M1 - e1006286

ER -