Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins

Omics technologies have led to the discovery of a vast number of proteins that are expressed but have no functional annotation - so called hypothetical proteins (HPs). Even in the best-studied model organism Escherichia coli K-12, over 2 % of the proteome remains uncharacterized. This knowledge gap...

Full description

Saved in:
Bibliographic Details
Main Authors: Sagarika Chakraborty, Zachary Ardern, Habibu Aliyu, Anne-Kristin Kaster
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Computational and Structural Biotechnology Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2001037025003009
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849236243198509056
author Sagarika Chakraborty
Zachary Ardern
Habibu Aliyu
Anne-Kristin Kaster
author_facet Sagarika Chakraborty
Zachary Ardern
Habibu Aliyu
Anne-Kristin Kaster
author_sort Sagarika Chakraborty
collection DOAJ
description Omics technologies have led to the discovery of a vast number of proteins that are expressed but have no functional annotation - so called hypothetical proteins (HPs). Even in the best-studied model organism Escherichia coli K-12, over 2 % of the proteome remains uncharacterized. This knowledge gap becomes even worse when looking at microbial dark matter. However, knowing the functions of proteins is crucial for elucidating cellular and metabolic processes and harnessing biotechnological potentials. Here, we employed machine learning to decipher the transcriptional regulatory network of E. coli K-12, as well as other in silico tools to assign functions to uncharacterized HPs. We further provide experimental validation of in silico predicted functions for three HP-encoding genes (yhdN, yeaC and ydgH) as proof of concept, by analyzing growth patterns of deletion mutants compared to the wild type, as well as their transcriptional responses to specific conditions. This study demonstrates that the use of Big Omics Data in combination with Artificial Intelligence and experimental controls is a powerful approach to illuminate functional dark matter.
format Article
id doaj-art-072f7fe0576b4685a43eaeb1ea177e61
institution Kabale University
issn 2001-0370
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Computational and Structural Biotechnology Journal
spelling doaj-art-072f7fe0576b4685a43eaeb1ea177e612025-08-20T04:02:23ZengElsevierComputational and Structural Biotechnology Journal2001-03702025-01-01273565357810.1016/j.csbj.2025.07.036Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteinsSagarika Chakraborty0Zachary Ardern1Habibu Aliyu2Anne-Kristin Kaster3Institute for Biological Interfaces 5 (IBG-5), Biotechnology and Microbial Genetics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, GermanyInstitute for Biological Interfaces 5 (IBG-5), Biotechnology and Microbial Genetics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany; Wellcome Trust Sanger Institute, Hinxton, Saffron Walden CB10 1RQ, United KingdomInstitute for Biological Interfaces 5 (IBG-5), Biotechnology and Microbial Genetics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, GermanyInstitute for Biological Interfaces 5 (IBG-5), Biotechnology and Microbial Genetics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany; Institute for Applied Biosciences (IAB), Karlsruhe Institute of Technology (KIT), Kaiserstraße 12, Karlsruhe 76131, Germany; Corresponding author at: Institute for Biological Interfaces 5 (IBG-5), Biotechnology and Microbial Genetics, Karlsruhe Institute of Technology (KIT), Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany.Omics technologies have led to the discovery of a vast number of proteins that are expressed but have no functional annotation - so called hypothetical proteins (HPs). Even in the best-studied model organism Escherichia coli K-12, over 2 % of the proteome remains uncharacterized. This knowledge gap becomes even worse when looking at microbial dark matter. However, knowing the functions of proteins is crucial for elucidating cellular and metabolic processes and harnessing biotechnological potentials. Here, we employed machine learning to decipher the transcriptional regulatory network of E. coli K-12, as well as other in silico tools to assign functions to uncharacterized HPs. We further provide experimental validation of in silico predicted functions for three HP-encoding genes (yhdN, yeaC and ydgH) as proof of concept, by analyzing growth patterns of deletion mutants compared to the wild type, as well as their transcriptional responses to specific conditions. This study demonstrates that the use of Big Omics Data in combination with Artificial Intelligence and experimental controls is a powerful approach to illuminate functional dark matter.http://www.sciencedirect.com/science/article/pii/S2001037025003009Artificial intelligenceBig omics dataFunctional annotation of proteinsFunctional dark matterIndependent Component Analysis (ICA)
spellingShingle Sagarika Chakraborty
Zachary Ardern
Habibu Aliyu
Anne-Kristin Kaster
Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
Computational and Structural Biotechnology Journal
Artificial intelligence
Big omics data
Functional annotation of proteins
Functional dark matter
Independent Component Analysis (ICA)
title Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
title_full Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
title_fullStr Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
title_full_unstemmed Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
title_short Deciphering the proteome of Escherichia coli K-12: Integrating transcriptomics and machine learning to annotate hypothetical proteins
title_sort deciphering the proteome of escherichia coli k 12 integrating transcriptomics and machine learning to annotate hypothetical proteins
topic Artificial intelligence
Big omics data
Functional annotation of proteins
Functional dark matter
Independent Component Analysis (ICA)
url http://www.sciencedirect.com/science/article/pii/S2001037025003009
work_keys_str_mv AT sagarikachakraborty decipheringtheproteomeofescherichiacolik12integratingtranscriptomicsandmachinelearningtoannotatehypotheticalproteins
AT zacharyardern decipheringtheproteomeofescherichiacolik12integratingtranscriptomicsandmachinelearningtoannotatehypotheticalproteins
AT habibualiyu decipheringtheproteomeofescherichiacolik12integratingtranscriptomicsandmachinelearningtoannotatehypotheticalproteins
AT annekristinkaster decipheringtheproteomeofescherichiacolik12integratingtranscriptomicsandmachinelearningtoannotatehypotheticalproteins