EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Longitudinal Transcriptomic Remodeling of Adipose Tissue After Bariatric Surgery Revealed by Differential Expression and Explainable Machine Learning

Soumaya Allouch iD, Md Shaheenur Islam Sumon, Aisha Naeem, Claus Vinter Bødker Hviid iD, Zumin Shi iD, Muhammad E H Chowdhury iD, Shona Pedersen iD

Genes · 19.08.2026 · 17 (8) · 974

DOI: 10.3390/genes17080974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genes, online erschienen am 19.08.2026. Verfasst von Soumaya Allouch und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Basic Medical Science, College of Medicine, QU Health, Qatar University, Doha 2713, Qatar. Hauptthemen laut MEDLINE: Machine Learning, Transcriptome, Bariatric Surgery, Adipose Tissue, White. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qatar Research, Development and Innovation (QRDI) Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Bariatric surgery improves metabolic health, but long-term transcriptomic remodeling of white adipose tissue (WAT) after Roux-en-Y gastric bypass (RYGB) remains incompletely defined. This study aimed to characterize longitudinal WAT gene-expression patterns after RYGB and prioritize candidate signatures of post-surgical adaptation using a publicly available dataset.

Methods

We analyzed subcutaneous WAT transcriptomic data from women with obesity who underwent RYGB, with samples collected before surgery and at 2 and 5 years after surgery. Differential expression analysis was integrated with pathway enrichment, supervised machine-learning-based feature prioritization and classification, and SHAP-based model interpretation.

Results

Differential expression and machine-learning analyses showed clear separation between baseline and post-surgery transcriptomic states. Pathway-level findings indicated reduced inflammatory and immune-related signaling, particularly across pathways related to phagosome function, lysosomal activity, antigen presentation, and host-defense responses after surgery. Gene-level analyses additionally suggested extracellular-matrix and metabolic remodeling. Machine-learning models distinguished baseline from post-surgery samples, while SHAP analysis identified genes with the strongest contributions to model predictions. Importantly, several statistically prioritized genes also showed high SHAP attribution, demonstrating concordance between univariate statistical significance and multivariate predictive relevance. This convergence suggests that the models captured biologically meaningful surgery-associated signals rather than purely data-driven classification artifacts.

Conclusions

This study advances the interpretation of longitudinal adipose-tissue transcriptomic remodeling after RYGB by combining differential expression, pathway enrichment, supervised machine learning, and explainable AI within a unified framework. The integrated workflow prioritized candidate long-term remodeling genes, particularly immune/inflammatory and extracellular-matrix-related transcriptomic signatures, that warrant validation in independent cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTranscriptomeBariatric SurgeryAdipose Tissue, WhiteObesityHumansFemaleGene Expression ProfilingGastric BypassAdultLongitudinal Studies

Stichwörter der Autor:innen

bariatric surgeryexplainable artificial intelligencelongitudinal transcriptomicsmachine learningmetabolic remodelingwhite adipose tissue

Autor:innen und Institutionen

  • Department of Basic Medical Science, College of Medicine, QU Health, Qatar University, Doha 2713, Qatar.
  • Department of Clinical Medicine, College of Medicine, Aalborg University, 9260 Aalborg, Denmark.
  • Department of Electrical Engineering, Qatar University, Doha 2713, Qatar.
  • Health Sector, Qatar University, Doha 2713, Qatar.
  • Department of Clinical Biochemistry, Aalborg University Hospital, 9000 Aalborg, Denmark.
  • College of Health Sciences, QU Health, Qatar University, Doha 2713, Qatar.

ORCID-Profile: Soumaya Allouch, Claus Vinter Bødker Hviid, Zumin Shi, Muhammad E H Chowdhury, Shona Pedersen

Förderung

  • Qatar Research, Development and Innovation (QRDI) Council

Zitieren

APA

Allouch, S., Sumon, M. S. I., Naeem, A., Hviid, C. V. B., Shi, Z., Chowdhury, M. E. H., & Pedersen, S. (2026). Longitudinal Transcriptomic Remodeling of Adipose Tissue After Bariatric Surgery Revealed by Differential Expression and Explainable Machine Learning. Genes, 17(8), 974. https://doi.org/10.3390/genes17080974

Vancouver

Allouch S, Sumon MSI, Naeem A, Hviid CVB, Shi Z, Chowdhury MEH, et al. Longitudinal Transcriptomic Remodeling of Adipose Tissue After Bariatric Surgery Revealed by Differential Expression and Explainable Machine Learning. Genes. 2026;17(8):974. doi:10.3390/genes17080974

BibTeX
@article{Allouch2026,
  author = {Allouch, Soumaya and Sumon, Md Shaheenur Islam and Naeem, Aisha and Hviid, Claus Vinter Bødker and Shi, Zumin and Chowdhury, Muhammad E H and Pedersen, Shona},
  title = {Longitudinal Transcriptomic Remodeling of Adipose Tissue After Bariatric Surgery Revealed by Differential Expression and Explainable Machine Learning},
  journal = {Genes},
  year = {2026},
  volume = {17},
  number = {8},
  pages = {974},
  doi = {10.3390/genes17080974}
}
Kostenlos starten →