AutoTransOP: translating omics signatures without orthologue requirements using deep learning

Abstract The development of therapeutics and vaccines for human diseases requires a systematic understanding of human biology. Although animal and in vitro culture models can elucidate some disease mechanisms, they typically fail to adequately recapitulate human biology as evidenced by the predomina...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikolaos Meimetis, Krista M. Pullen, Daniel Y. Zhu, Avlant Nilsson, Trong Nghia Hoang, Sara Magliacane, Douglas A. Lauffenburger
Format: Article
Language:English
Published: Nature Portfolio 2024-01-01
Series:npj Systems Biology and Applications
Online Access:https://doi.org/10.1038/s41540-024-00341-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121823795675136
author Nikolaos Meimetis
Krista M. Pullen
Daniel Y. Zhu
Avlant Nilsson
Trong Nghia Hoang
Sara Magliacane
Douglas A. Lauffenburger
author_facet Nikolaos Meimetis
Krista M. Pullen
Daniel Y. Zhu
Avlant Nilsson
Trong Nghia Hoang
Sara Magliacane
Douglas A. Lauffenburger
author_sort Nikolaos Meimetis
collection DOAJ
description Abstract The development of therapeutics and vaccines for human diseases requires a systematic understanding of human biology. Although animal and in vitro culture models can elucidate some disease mechanisms, they typically fail to adequately recapitulate human biology as evidenced by the predominant likelihood of clinical trial failure. To address this problem, we developed AutoTransOP, a neural network autoencoder framework, to map omics profiles from designated species or cellular contexts into a global latent space, from which germane information for different contexts can be identified without the typically imposed requirement of matched orthologues. This approach was found in general to perform at least as well as current alternative methods in identifying animal/culture-specific molecular features predictive of other contexts—most importantly without requiring homology matching. For an especially challenging test case, we successfully applied our framework to a set of inter-species vaccine serology studies, where 1-to-1 mapping between human and non-human primate features does not exist.
format Article
id doaj-art-d709836e3f53497f9d22e8848afa7d5b
institution Kabale University
issn 2056-7189
language English
publishDate 2024-01-01
publisher Nature Portfolio
record_format Article
series npj Systems Biology and Applications
spelling doaj-art-d709836e3f53497f9d22e8848afa7d5b2024-12-15T12:09:51ZengNature Portfolionpj Systems Biology and Applications2056-71892024-01-0110111910.1038/s41540-024-00341-9AutoTransOP: translating omics signatures without orthologue requirements using deep learningNikolaos Meimetis0Krista M. Pullen1Daniel Y. Zhu2Avlant Nilsson3Trong Nghia Hoang4Sara Magliacane5Douglas A. Lauffenburger6Department of Biological Engineering, Massachusetts Institute of TechnologyDepartment of Biological Engineering, Massachusetts Institute of TechnologyDepartment of Biological Engineering, Massachusetts Institute of TechnologyDepartment of Biological Engineering, Massachusetts Institute of TechnologySchool of Electrical Engineering and Computer Science, Washington State UniversityInstitute of Informatics, University of AmsterdamDepartment of Biological Engineering, Massachusetts Institute of TechnologyAbstract The development of therapeutics and vaccines for human diseases requires a systematic understanding of human biology. Although animal and in vitro culture models can elucidate some disease mechanisms, they typically fail to adequately recapitulate human biology as evidenced by the predominant likelihood of clinical trial failure. To address this problem, we developed AutoTransOP, a neural network autoencoder framework, to map omics profiles from designated species or cellular contexts into a global latent space, from which germane information for different contexts can be identified without the typically imposed requirement of matched orthologues. This approach was found in general to perform at least as well as current alternative methods in identifying animal/culture-specific molecular features predictive of other contexts—most importantly without requiring homology matching. For an especially challenging test case, we successfully applied our framework to a set of inter-species vaccine serology studies, where 1-to-1 mapping between human and non-human primate features does not exist.https://doi.org/10.1038/s41540-024-00341-9
spellingShingle Nikolaos Meimetis
Krista M. Pullen
Daniel Y. Zhu
Avlant Nilsson
Trong Nghia Hoang
Sara Magliacane
Douglas A. Lauffenburger
AutoTransOP: translating omics signatures without orthologue requirements using deep learning
npj Systems Biology and Applications
title AutoTransOP: translating omics signatures without orthologue requirements using deep learning
title_full AutoTransOP: translating omics signatures without orthologue requirements using deep learning
title_fullStr AutoTransOP: translating omics signatures without orthologue requirements using deep learning
title_full_unstemmed AutoTransOP: translating omics signatures without orthologue requirements using deep learning
title_short AutoTransOP: translating omics signatures without orthologue requirements using deep learning
title_sort autotransop translating omics signatures without orthologue requirements using deep learning
url https://doi.org/10.1038/s41540-024-00341-9
work_keys_str_mv AT nikolaosmeimetis autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT kristampullen autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT danielyzhu autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT avlantnilsson autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT trongnghiahoang autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT saramagliacane autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning
AT douglasalauffenburger autotransoptranslatingomicssignatureswithoutorthologuerequirementsusingdeeplearning