Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort

Ikhlak Ahmed; Ajaz A. Bhat; Sujitha Padma Jeya; Wilson K.M. Wong; Hana Q. Sadida; Mya Polkamp; Hrishikesh P. Hardikar; Jyothi Lakshmi; Sura Ahmed Hussain; Evonne Chin-Smith; Amaresh K. Ranjan; Mugdha V. Joglekar; Anandwardhan A. Hardikar; Khalid Fakhro; Ammira Al Shabeeb Akil

doi:10.1186/s12967-025-07113-x

Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort

Ikhlak Ahmed
, Ajaz A. Bhat
, Sujitha Padma Jeya
, Wilson K.M. Wong
, Hana Q. Sadida
, Mya Polkamp
, Hrishikesh P. Hardikar
, Jyothi Lakshmi
, Sura Ahmed Hussain
, Evonne Chin-Smith
, Amaresh K. Ranjan
, Mugdha V. Joglekar
, Anandwardhan A. Hardikar
, Khalid Fakhro
, Ammira Al Shabeeb Akil

School of Medicine

Research output: Contribution to journal › Article › peer-review

7 Downloads (Pure)

Abstract

Background: Type 2 diabetes (T2D) and its vascular complications, including diabetic retinopathy (DR), are escalating in prevalence globally, with disproportionately high prevalence in Middle Eastern populations, where genetic predispositions and lifestyle factors intersect. Early detection and precise risk stratification remain critical challenges in this region. We hypothesised that an integrated plasma multi-omics profile; comprising microRNA, mRNA, and protein biomarkers, could accurately distinguish individuals with T2D and its complications in a Middle Eastern cohort. Methods: A candidate panel of mRNA and protein biomarkers identified from in vitro hyperglycaemia models, along with a vascular microRNA signature previously defined in an Australian cohort, was evaluated. These multiomic biomarkers were profiled in 962 individuals (492 controls, 434 T2D and 36 T2D with DR) from the Qatar Biobank (QBB). Random Forest machine learning workflow was used for risk stratification, with model performance assessed by accuracy and area under the receiver operating characteristic curve. SHAP analysis and penalised regression were used to identify key discriminative biomarkers. Results: The Random Forest classifier achieved robust performance, with an AUC of 0.83, F1 score of 0.78, and overall accuracy of 0.76 in distinguishing T2D cases from controls. A regulatory axis involving miR-29c (protective) and PROM1 (risk-promoting) was identified as a central driver for T2D and DR progression. Protein biomarkers, including ANGPT2 (fold change = 1.64, p-value = 3.8e−03) and PlGF (fold change = 0.66, p-value = 3.7e−02), were significantly associated with vascular complications. Conclusions: Integrating multi-omics data with machine learning enables accurate risk stratification for T2D and DR in Middle Eastern populations. The miR-29c–PROM1 axis and associated proteins represent promising biomarkers for early detection and targeted intervention. Leveraging QBB resources, this study lays the groundwork for precision health initiatives aimed at mitigating diabetes-related complications in a high-risk Middle Eastern cohort.

Original language	English
Article number	1159
Number of pages	15
Journal	Journal of Translational Medicine
Volume	23
Issue number	1
DOIs	https://doi.org/10.1186/s12967-025-07113-x
Publication status	Published - Oct 2025

Open Access - Access Right Statement

This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation orexceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit h t t p : / / c r e a t iv e c o m m o n s . o r g / l i c e n s e s / b y - n c - n d / 4 . 0 /.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Biomarkers
Diabetic retinopathy
Gene expression
Machine learning
Middle east
miR-29c
Multi-omics
PROM1
Random forest
Type 2 diabetes

Access to Document

10.1186/s12967-025-07113-xLicence: CC BY-NC-ND

Full textFinal published version, 3.24 MBLicence: CC BY-NC-ND

Cite this

Ahmed, I., Bhat, A. A., Jeya, S. P., Wong, W. K. M., Sadida, H. Q., Polkamp, M., Hardikar, H. P., Lakshmi, J., Hussain, S. A., Chin-Smith, E., Ranjan, A. K., Joglekar, M. V., Hardikar, A. A., Fakhro, K., & Akil, A. A. S. (2025). Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort. Journal of Translational Medicine, 23(1), Article 1159. https://doi.org/10.1186/s12967-025-07113-x

@article{d86c714fd6204bdb9fc97f7dd960c148,

title = "Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort",

abstract = "Background: Type 2 diabetes (T2D) and its vascular complications, including diabetic retinopathy (DR), are escalating in prevalence globally, with disproportionately high prevalence in Middle Eastern populations, where genetic predispositions and lifestyle factors intersect. Early detection and precise risk stratification remain critical challenges in this region. We hypothesised that an integrated plasma multi-omics profile; comprising microRNA, mRNA, and protein biomarkers, could accurately distinguish individuals with T2D and its complications in a Middle Eastern cohort. Methods: A candidate panel of mRNA and protein biomarkers identified from in vitro hyperglycaemia models, along with a vascular microRNA signature previously defined in an Australian cohort, was evaluated. These multiomic biomarkers were profiled in 962 individuals (492 controls, 434 T2D and 36 T2D with DR) from the Qatar Biobank (QBB). Random Forest machine learning workflow was used for risk stratification, with model performance assessed by accuracy and area under the receiver operating characteristic curve. SHAP analysis and penalised regression were used to identify key discriminative biomarkers. Results: The Random Forest classifier achieved robust performance, with an AUC of 0.83, F1 score of 0.78, and overall accuracy of 0.76 in distinguishing T2D cases from controls. A regulatory axis involving miR-29c (protective) and PROM1 (risk-promoting) was identified as a central driver for T2D and DR progression. Protein biomarkers, including ANGPT2 (fold change = 1.64, p-value = 3.8e−03) and PlGF (fold change = 0.66, p-value = 3.7e−02), were significantly associated with vascular complications. Conclusions: Integrating multi-omics data with machine learning enables accurate risk stratification for T2D and DR in Middle Eastern populations. The miR-29c–PROM1 axis and associated proteins represent promising biomarkers for early detection and targeted intervention. Leveraging QBB resources, this study lays the groundwork for precision health initiatives aimed at mitigating diabetes-related complications in a high-risk Middle Eastern cohort.",

keywords = "Biomarkers, Diabetic retinopathy, Gene expression, Machine learning, Middle east, miR-29c, Multi-omics, PROM1, Random forest, Type 2 diabetes",

author = "Ikhlak Ahmed and Bhat, \{Ajaz A.\} and Jeya, \{Sujitha Padma\} and Wong, \{Wilson K.M.\} and Sadida, \{Hana Q.\} and Mya Polkamp and Hardikar, \{Hrishikesh P.\} and Jyothi Lakshmi and Hussain, \{Sura Ahmed\} and Evonne Chin-Smith and Ranjan, \{Amaresh K.\} and Joglekar, \{Mugdha V.\} and Hardikar, \{Anandwardhan A.\} and Khalid Fakhro and Akil, \{Ammira Al Shabeeb\}",

year = "2025",

month = oct,

doi = "10.1186/s12967-025-07113-x",

language = "English",

volume = "23",

journal = "Journal of Translational Medicine",

issn = "1479-5876",

publisher = "BioMed Central Ltd.",

number = "1",

}

Ahmed, I, Bhat, AA, Jeya, SP, Wong, WKM, Sadida, HQ, Polkamp, M, Hardikar, HP, Lakshmi, J, Hussain, SA, Chin-Smith, E, Ranjan, AK, Joglekar, MV , Hardikar, AA, Fakhro, K & Akil, AAS 2025, 'Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort', Journal of Translational Medicine, vol. 23, no. 1, 1159. https://doi.org/10.1186/s12967-025-07113-x

TY - JOUR

T1 - Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort

AU - Ahmed, Ikhlak

AU - Bhat, Ajaz A.

AU - Jeya, Sujitha Padma

AU - Wong, Wilson K.M.

AU - Sadida, Hana Q.

AU - Polkamp, Mya

AU - Hardikar, Hrishikesh P.

AU - Lakshmi, Jyothi

AU - Hussain, Sura Ahmed

AU - Chin-Smith, Evonne

AU - Ranjan, Amaresh K.

AU - Joglekar, Mugdha V.

AU - Hardikar, Anandwardhan A.

AU - Fakhro, Khalid

AU - Akil, Ammira Al Shabeeb

PY - 2025/10

Y1 - 2025/10

N2 - Background: Type 2 diabetes (T2D) and its vascular complications, including diabetic retinopathy (DR), are escalating in prevalence globally, with disproportionately high prevalence in Middle Eastern populations, where genetic predispositions and lifestyle factors intersect. Early detection and precise risk stratification remain critical challenges in this region. We hypothesised that an integrated plasma multi-omics profile; comprising microRNA, mRNA, and protein biomarkers, could accurately distinguish individuals with T2D and its complications in a Middle Eastern cohort. Methods: A candidate panel of mRNA and protein biomarkers identified from in vitro hyperglycaemia models, along with a vascular microRNA signature previously defined in an Australian cohort, was evaluated. These multiomic biomarkers were profiled in 962 individuals (492 controls, 434 T2D and 36 T2D with DR) from the Qatar Biobank (QBB). Random Forest machine learning workflow was used for risk stratification, with model performance assessed by accuracy and area under the receiver operating characteristic curve. SHAP analysis and penalised regression were used to identify key discriminative biomarkers. Results: The Random Forest classifier achieved robust performance, with an AUC of 0.83, F1 score of 0.78, and overall accuracy of 0.76 in distinguishing T2D cases from controls. A regulatory axis involving miR-29c (protective) and PROM1 (risk-promoting) was identified as a central driver for T2D and DR progression. Protein biomarkers, including ANGPT2 (fold change = 1.64, p-value = 3.8e−03) and PlGF (fold change = 0.66, p-value = 3.7e−02), were significantly associated with vascular complications. Conclusions: Integrating multi-omics data with machine learning enables accurate risk stratification for T2D and DR in Middle Eastern populations. The miR-29c–PROM1 axis and associated proteins represent promising biomarkers for early detection and targeted intervention. Leveraging QBB resources, this study lays the groundwork for precision health initiatives aimed at mitigating diabetes-related complications in a high-risk Middle Eastern cohort.

AB - Background: Type 2 diabetes (T2D) and its vascular complications, including diabetic retinopathy (DR), are escalating in prevalence globally, with disproportionately high prevalence in Middle Eastern populations, where genetic predispositions and lifestyle factors intersect. Early detection and precise risk stratification remain critical challenges in this region. We hypothesised that an integrated plasma multi-omics profile; comprising microRNA, mRNA, and protein biomarkers, could accurately distinguish individuals with T2D and its complications in a Middle Eastern cohort. Methods: A candidate panel of mRNA and protein biomarkers identified from in vitro hyperglycaemia models, along with a vascular microRNA signature previously defined in an Australian cohort, was evaluated. These multiomic biomarkers were profiled in 962 individuals (492 controls, 434 T2D and 36 T2D with DR) from the Qatar Biobank (QBB). Random Forest machine learning workflow was used for risk stratification, with model performance assessed by accuracy and area under the receiver operating characteristic curve. SHAP analysis and penalised regression were used to identify key discriminative biomarkers. Results: The Random Forest classifier achieved robust performance, with an AUC of 0.83, F1 score of 0.78, and overall accuracy of 0.76 in distinguishing T2D cases from controls. A regulatory axis involving miR-29c (protective) and PROM1 (risk-promoting) was identified as a central driver for T2D and DR progression. Protein biomarkers, including ANGPT2 (fold change = 1.64, p-value = 3.8e−03) and PlGF (fold change = 0.66, p-value = 3.7e−02), were significantly associated with vascular complications. Conclusions: Integrating multi-omics data with machine learning enables accurate risk stratification for T2D and DR in Middle Eastern populations. The miR-29c–PROM1 axis and associated proteins represent promising biomarkers for early detection and targeted intervention. Leveraging QBB resources, this study lays the groundwork for precision health initiatives aimed at mitigating diabetes-related complications in a high-risk Middle Eastern cohort.

KW - Biomarkers

KW - Diabetic retinopathy

KW - Gene expression

KW - Machine learning

KW - Middle east

KW - miR-29c

KW - Multi-omics

KW - PROM1

KW - Random forest

KW - Type 2 diabetes

UR - https://www.scopus.com/pages/publications/105019604669

U2 - 10.1186/s12967-025-07113-x

DO - 10.1186/s12967-025-07113-x

M3 - Article

C2 - 41126335

AN - SCOPUS:105019604669

SN - 1479-5876

VL - 23

JO - Journal of Translational Medicine

JF - Journal of Translational Medicine

IS - 1

M1 - 1159

ER -

Plasma multi-omics and machine learning reveal predictive biomarkers for type 2 diabetes and retinopathy in Qatar biobank cohort

Abstract

Open Access - Access Right Statement

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this