Cargando…

Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference

The modeling of gene regulatory networks (GRNs) is limited due to a lack of direct measurements of regulatory features in genome-wide screens. Most GRN inference methods are therefore forced to model relationships between regulatory genes and their targets with expression as a proxy for the upstream...

Descripción completa

Detalles Bibliográficos
Autores principales: Tjärnberg, Andreas, Beheler-Amass, Maggie, Jackson, Christopher A, Christiaen, Lionel A, Gresham, David, Bonneau, Richard
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cold Spring Harbor Laboratory 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9915715/
https://www.ncbi.nlm.nih.gov/pubmed/36778259
http://dx.doi.org/10.1101/2023.02.02.526909
_version_ 1784885956279533568
author Tjärnberg, Andreas
Beheler-Amass, Maggie
Jackson, Christopher A
Christiaen, Lionel A
Gresham, David
Bonneau, Richard
author_facet Tjärnberg, Andreas
Beheler-Amass, Maggie
Jackson, Christopher A
Christiaen, Lionel A
Gresham, David
Bonneau, Richard
author_sort Tjärnberg, Andreas
collection PubMed
description The modeling of gene regulatory networks (GRNs) is limited due to a lack of direct measurements of regulatory features in genome-wide screens. Most GRN inference methods are therefore forced to model relationships between regulatory genes and their targets with expression as a proxy for the upstream independent features, complicating validation and predictions produced by modeling frameworks. Separating covariance and regulatory influence requires aggregation of independent and complementary sets of evidence, such as transcription factor (TF) binding and target gene expression. However, the complete regulatory state of the system, e.g. TF activity (TFA) is unknown due to a lack of experimental feasibility, making regulatory relations difficult to infer. Some methods attempt to account for this by modeling TFA as a latent feature, but these models often use linear frameworks that are unable to account for non-linearities such as saturation, TF-TF interactions, and other higher order features. Deep learning frameworks may offer a solution, as they are capable of modeling complex interactions and capturing higher-order latent features. However, these methods often discard central concepts in biological systems modeling, such as sparsity and latent feature interpretability, in favor of increased model complexity. We propose a novel deep learning autoencoder-based framework, StrUcture Primed Inference of Regulation using latent Factor ACTivity (SupirFactor), that scales to single cell genomic data and maintains interpretability to perform GRN inference and estimate TFA as a latent feature. We demonstrate that SupirFactor outperforms current leading GRN inference methods, predicts biologically relevant TFA and elucidates functional regulatory pathways through aggregation of TFs.
format Online
Article
Text
id pubmed-9915715
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Cold Spring Harbor Laboratory
record_format MEDLINE/PubMed
spelling pubmed-99157152023-02-11 Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference Tjärnberg, Andreas Beheler-Amass, Maggie Jackson, Christopher A Christiaen, Lionel A Gresham, David Bonneau, Richard bioRxiv Article The modeling of gene regulatory networks (GRNs) is limited due to a lack of direct measurements of regulatory features in genome-wide screens. Most GRN inference methods are therefore forced to model relationships between regulatory genes and their targets with expression as a proxy for the upstream independent features, complicating validation and predictions produced by modeling frameworks. Separating covariance and regulatory influence requires aggregation of independent and complementary sets of evidence, such as transcription factor (TF) binding and target gene expression. However, the complete regulatory state of the system, e.g. TF activity (TFA) is unknown due to a lack of experimental feasibility, making regulatory relations difficult to infer. Some methods attempt to account for this by modeling TFA as a latent feature, but these models often use linear frameworks that are unable to account for non-linearities such as saturation, TF-TF interactions, and other higher order features. Deep learning frameworks may offer a solution, as they are capable of modeling complex interactions and capturing higher-order latent features. However, these methods often discard central concepts in biological systems modeling, such as sparsity and latent feature interpretability, in favor of increased model complexity. We propose a novel deep learning autoencoder-based framework, StrUcture Primed Inference of Regulation using latent Factor ACTivity (SupirFactor), that scales to single cell genomic data and maintains interpretability to perform GRN inference and estimate TFA as a latent feature. We demonstrate that SupirFactor outperforms current leading GRN inference methods, predicts biologically relevant TFA and elucidates functional regulatory pathways through aggregation of TFs. Cold Spring Harbor Laboratory 2023-02-03 /pmc/articles/PMC9915715/ /pubmed/36778259 http://dx.doi.org/10.1101/2023.02.02.526909 Text en https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (https://creativecommons.org/licenses/by-nc-nd/4.0/) , which allows reusers to copy and distribute the material in any medium or format in unadapted form only, for noncommercial purposes only, and only so long as attribution is given to the creator.
spellingShingle Article
Tjärnberg, Andreas
Beheler-Amass, Maggie
Jackson, Christopher A
Christiaen, Lionel A
Gresham, David
Bonneau, Richard
Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title_full Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title_fullStr Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title_full_unstemmed Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title_short Structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
title_sort structure primed embedding on the transcription factor manifold enables transparent model architectures for gene regulatory network and latent activity inference
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9915715/
https://www.ncbi.nlm.nih.gov/pubmed/36778259
http://dx.doi.org/10.1101/2023.02.02.526909
work_keys_str_mv AT tjarnbergandreas structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference
AT beheleramassmaggie structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference
AT jacksonchristophera structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference
AT christiaenlionela structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference
AT greshamdavid structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference
AT bonneaurichard structureprimedembeddingonthetranscriptionfactormanifoldenablestransparentmodelarchitecturesforgeneregulatorynetworkandlatentactivityinference