. 2024 May 24:15:1384984.

doi: 10.3389/fendo.2024.1384984. eCollection 2024.

Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats

Marwa Matboli¹, Hiba S Al-Amodi², Abdelrahman Khaled³, Radwa Khaled^{4

5}, Marian M S Roushdy¹, Marwa Ali¹, Gouda Ibrahim Diab⁶, Mahmoud Fawzy Elnagar⁷, Rasha A Elmansy^{8

9}, Hagir H TAhmed¹⁰, Enshrah M E Ahmed¹¹, Doaa M A Elzoghby¹², Hala F M Kamel^{1

2}, Mohamed F Farag¹³, Hind A ELsawi¹⁴, Laila M Farid¹⁵, Mariam B Abouelkhair¹⁵, Eman K Habib¹⁶, Heba Fikry¹⁷, Lobna A Saleh¹⁸, Ibrahim H Aboughaleb⁶

Affiliations

¹ Medical Biochemistry and Molecular Biology Department, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
² Biochemistry Department, Faculty of Medicine, Umm Al-Qura University, Makkah, Saudi Arabia.
³ Bioinformatics Group, Center of Informatics Sciences (CIS), School of Information Technology and Computer Sciences, Nile University, Giza, Egypt.
⁴ Biotechnology/Biomolecular Chemistry Department, Faculty of Science, Cairo University, Cairo, Egypt.
⁵ Medicinal Biochemistry and Molecular Biology Department, Modern University for Technology and Information, Cairo, Egypt.
⁶ Biomedical Engineering Department, Egyptian Armed Forces, Cairo, Egypt.
⁷ Zoology Department, Faculty of Science, Ain Shams University, Cairo, Egypt.
⁸ Anatomy Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, Qassim University, Buraydah, Saudi Arabia.
⁹ Department of Anatomy and Cell Biology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁰ Anatomy Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, AlNeelain University, Khartoum, Sudan.
¹¹ Pathology Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, Gassim University, Buraydah, Saudi Arabia.
¹² Clinical Pathology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹³ Medical Physiology Department, Armed Forces College of Medicine, Cairo, Egypt.
¹⁴ Department of Internal Medicine, Badr University in Cairo, Badr, Egypt.
¹⁵ Pathology Department, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁶ Department of Anatomy and Cell Biology, Faculty of Medicine, Galala University, Attaka, Suez Governorate, Egypt.
¹⁷ Department of Histology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁸ Department of Clinical Pharmacology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.

PMID: 38854687
PMCID: PMC11157016
DOI: 10.3389/fendo.2024.1384984

Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats

Marwa Matboli et al. Front Endocrinol (Lausanne). 2024.

. 2024 May 24:15:1384984.

doi: 10.3389/fendo.2024.1384984. eCollection 2024.

Authors

Affiliations

¹ Medical Biochemistry and Molecular Biology Department, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
² Biochemistry Department, Faculty of Medicine, Umm Al-Qura University, Makkah, Saudi Arabia.
³ Bioinformatics Group, Center of Informatics Sciences (CIS), School of Information Technology and Computer Sciences, Nile University, Giza, Egypt.
⁴ Biotechnology/Biomolecular Chemistry Department, Faculty of Science, Cairo University, Cairo, Egypt.
⁵ Medicinal Biochemistry and Molecular Biology Department, Modern University for Technology and Information, Cairo, Egypt.
⁶ Biomedical Engineering Department, Egyptian Armed Forces, Cairo, Egypt.
⁷ Zoology Department, Faculty of Science, Ain Shams University, Cairo, Egypt.
⁸ Anatomy Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, Qassim University, Buraydah, Saudi Arabia.
⁹ Department of Anatomy and Cell Biology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁰ Anatomy Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, AlNeelain University, Khartoum, Sudan.
¹¹ Pathology Unit, Department of Basic Medical Sciences, College of Medicine and Medical Sciences, Gassim University, Buraydah, Saudi Arabia.
¹² Clinical Pathology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹³ Medical Physiology Department, Armed Forces College of Medicine, Cairo, Egypt.
¹⁴ Department of Internal Medicine, Badr University in Cairo, Badr, Egypt.
¹⁵ Pathology Department, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁶ Department of Anatomy and Cell Biology, Faculty of Medicine, Galala University, Attaka, Suez Governorate, Egypt.
¹⁷ Department of Histology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.
¹⁸ Department of Clinical Pharmacology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.

PMID: 38854687
PMCID: PMC11157016
DOI: 10.3389/fendo.2024.1384984

Abstract

Introduction: With the increasing prevalence of type 2 diabetes mellitus (T2DM), there is an urgent need to discover effective therapeutic targets for this complex condition. Coding and non-coding RNAs, with traditional biochemical parameters, have shown promise as viable targets for therapy. Machine learning (ML) techniques have emerged as powerful tools for predicting drug responses.

Method: In this study, we developed an ML-based model to identify the most influential features for drug response in the treatment of type 2 diabetes using three medicinal plant-based drugs (Rosavin, Caffeic acid, and Isorhamnetin), and a probiotics drug (Z-biotic), at different doses. A hundred rats were randomly assigned to ten groups, including a normal group, a streptozotocin-induced diabetic group, and eight treated groups. Serum samples were collected for biochemical analysis, while liver tissues (L) and adipose tissues (A) underwent histopathological examination and molecular biomarker extraction using quantitative PCR. Utilizing five machine learning algorithms, we integrated 32 molecular features and 12 biochemical features to select the most predictive targets for each model and the combined model.

Results and discussion: Our results indicated that high doses of the selected drugs effectively mitigated liver inflammation, reduced insulin resistance, and improved lipid profiles and renal function biomarkers. The machine learning model identified 13 molecular features, 10 biochemical features, and 20 combined features with an accuracy of 80% and AUC (0.894, 0.93, and 0.896), respectively. This study presents an ML model that accurately identifies effective therapeutic targets implicated in the molecular pathways associated with T2DM pathogenesis.

Keywords: drug response; machine learning; rats; therapeutic targets; type 2 diabetes.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

**Figure 1**
Workflow describing the animal groups subjected to molecular and biochemical analysis for ML-model building identify signatures associated with drug response.T2DM, Type 2 Diabetes Mellitus; (L) extracted from the Liver tissues; (A) extracted from the Adipose tissues; HOMA-IR, Homeostatic Model Assessment of Insulin Resistance; LDL-C, low-density lipoprotein cholesterol; HDL-C, high-density lipoprotein cholesterol; AST, aspartate transaminase; ALT, alanine transaminase; BUN, Blood Urea Nitrogen; ACR, urine albumin to creatinine ratio; MLA, Machine learning Algorithm.

**Figure 2**
Show the number of improved (48) and not improved (29) samples.

**Figure 3**
Histopathology examination of liver tissue in experimental animals. **(A)** the Normal group, **(B)** the T2DM group, **(C)** Rosavin-10 group, **(D)** Rosavin-30, **(E)** Z-Biotic 0.5, **(F)** Z-Biotic 1, **(G)** Isorhamnetin-10, **(H)** Isorhamnetin-40, **(I)** Caffeic acid-10, **(J)** Caffeic acid-50. Microvesicular steatosis (Arrow), Inflammatory cells infiltrate (asterisks), Necrotic cells (Arrowhead), Pyknotic hepatocytes (Curved arrow), Sinusoids (S), Central vein (CV), Portal vein (PV), Bile duct (BD). Hepatocytes (h) (10X magnifications).

**Figure 4**
Histopathology examination of adipose tissue in the experimental animals. **(A)** the Normal group, **(B)** the T2DM group, **(C)** the Rosavin-10 group, **(D)** Rosavin-30, **(E)** Z-Biotic 0.5, **(F)** Z-Biotic 1, **(G)** Isorhamnetin-10, **(H)** Isorhamnetin-40, **(I)** Caffeic acid-10, **(J)** Caffeic acid-50. (40X magnifications).

**Figure 5**
Number and accuracy scores for each feature set and both of them combined.

**Figure 6**
Confusion matrix for the best-performing classifiers for each feature group. **(A)** Molecular, **(B)** Biochemical, **(C)** Molecular+Biochemical.

**Figure 7**
Roc curve for the best-performing classifiers for each feature group for the prediction of drug response. **(A)** Molecular, **(B)** Biochemical, **(C)** Molecular+Biochemical.

See this image and copyright information in PMC

References

1. Watkins DA, Ali MK. Measuring the global burden of diabetes: implications for health policy, practice, and research. Lancet. (2023) 402(10397):163–16. doi: 10.1016/S0140-6736(23)01287-4 - DOI - PubMed
1. American Diabetes Association . Standards of medical care in diabetes—2022 abridged for primary care providers. Clin Diabetes. (2022) 40:10–38. doi: 10.2337/cd22-as01 - DOI - PMC - PubMed
1. Ray KK, Nicholls SJ, Li N, Louie MJ, Brennan D, Lincoff AM, et al. . Efficacy and safety of bempedoic acid among patients with and without diabetes: prespecified analysis of the CLEAR Outcomes randomised trial. Lancet Diabetes Endocrinology. (2024) 12:19–28. doi: 10.1016/S2213-8587(23)00316-9 - DOI - PubMed
1. Antonio-Villa NE, Fernández-Chirino L, Vargas-Vazquez A, Bahena-López JP, Bello-Chavolla OY. Trends in diabetes subgroups and their risk for all-cause, cardiovascular disease and diabetes-specific mortality in the US: A data-driven reproducible machine learning approach. J Endocrine Soc. (2021) 5:A423. doi: 10.1210/jendso/bvab048.863 - DOI
1. Buse JB, Wexler DJ, Tsapas A, Rossing P, Mingrone G, Mathieu C, et al. . 2019 update to: management of hyperglycemia in type 2 diabetes, 2018. A consensus report by the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). Diabetes Care. (2020) 43:487–93. doi: 10.2337/dci19-0066 - DOI - PMC - PubMed

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Substances

Actions
Actions
Actions
Actions
Actions

LinkOut - more resources

Full Text Sources
Medical
- MedlinePlus Health Information

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats

Affiliations

Comprehensive machine learning models for predicting therapeutic targets in type 2 diabetes utilizing molecular and biochemical features in rats

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

MeSH terms

Substances

LinkOut - more resources

Full Text Sources

Medical