Related Experiment Video
Updated: Jun 13, 2026

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
Published on: March 1, 2024
Integrating transcriptomics and gene-level interpretable probabilistic Tsetlin Machine reveals elevated pancreatic
Subhradyuti Basu1, Abhipsa Dash1, Deepjyoti Kalita1
1Department of Biotechnology and Medical Engineering, National Institute of Technology, Rourkela, 769008, Odisha, India.
This study introduces an interpretable AI platform to estimate pancreatic cancer risk in type 2 diabetes patients using gene expression data. It aids early cancer detection and personalized treatments by analyzing transcriptomic crosstalk.
Area of Science:
- Oncology
- Metabolic Diseases
- Artificial Intelligence
Background:
- Type 2 diabetes (T2D) is a known risk factor for pancreatic cancer.
- The transcriptomic links between T2D and pancreatic cancer are not fully understood.
- Patient-level risk stratification for pancreatic cancer in T2D patients requires better tools.
Purpose of the Study:
- To develop a novel, interpretable AI platform for cross-disease risk estimation.
- To utilize transcriptomic crosstalk data from diabetic patients for pancreatic adenocarcinoma risk assessment.
- To enable early cancer detection and personalized therapeutics.
Main Methods:
- Development of an interpretable risk estimation platform using probabilistic Tsetlin machines.
- Analysis of transcriptomic crosstalk data from diabetic patients.
- Gene importance identification through Tsetlin machine clause support counts.
Main Results:
- Introduction of the first interpretable AI platform for cross-disease risk estimation between T2D and pancreatic adenocarcinoma.
- Demonstration of Tsetlin machines' ability to highlight crucial genes.
- Potential for improved patient-level risk stratification.
Conclusions:
- The developed AI platform offers a novel approach to understanding transcriptomic crosstalk between T2D and pancreatic cancer.
- Interpretability of the Tsetlin machine facilitates identification of key genes for risk assessment.
- This approach can enhance early cancer detection and personalized treatment strategies for patients.
Related Concept Videos
Type II Diabetes I: Introduction
Type II Diabetes II: Pathophysiology
Type I Diabetes II: Pathophysiology
Carbohydrate Metabolism
Starch accounts for approximately 60% of the carbohydrates consumed by humans. Since amylase enzymes cannot function in the stomach's acidic environment, starch can only be digested in the mouth and small intestine. Simple sugars are found naturally in milk and fruits in the...
Diabetes Mellitus: Type 2 and Gestational
Type I Diabetes I: Introduction

