Medical News Observer

Key Points:

• IntelliGenes integrates advanced machine learning and traditional statistical methods, using multi-genomic, clinical, and demographic data for disease prediction.
• The software features a unique I-Gene score for assessing individual biomarkers’ significance in complex trait prediction.
• Validated with high accuracy in cardiovascular disease prediction, IntelliGenes offers a new frontier in personalized medicine and treatment discovery.

Overview

IntelliGenes software, developed at Rutgers Health, integrates artificial intelligence (AI) and machine-learning techniques to evaluate the importance of specific genomic biomarkers. This innovative machine learning (ML) pipeline is designed for multi-genomics exploration to identify biomarkers crucial for accurate disease prediction.

IntelliGenes 

This tool integrates a unique blend of traditional statistical techniques and advanced machine learning algorithms, utilizing multi-genomic, clinical, and demographic data. A key feature is the Intelligent Gene (I-Gene) score, a novel metric developed to evaluate the significance of individual biomarkers in predicting complex traits. These I-Gene scores enable the creation of individualized I-Gene profiles, helping to understand the complexities of machine learning in disease prediction. 

According to its developers, this software has significant potential for merging various datasets with the rapid advancements in AI and machine learning. It is user-friendly, versatile, and a cross-platform application. 

Validation

The software’s performance was validated using Amarel, a high-performance computing cluster managed by the Rutgers Office of Advanced Research Computing.  IntelliGenes was used to identify 18 key transcriptomic biomarkers, enabling early cardiovascular disease prediction with up to 96% accuracy, corroborated by clinical records.

Implications

IntelliGenes has the potential for broader research employing novel machine learning methods, paving the way for personalized medical interventions and discovering new treatment targets. 

References

• DeGroat, William, Dinesh Mendhe, Atharva Bhusari, Habiba Abdelhalim, Saman Zeeshan, and Zeeshan Ahmed. 2023a. “IntelliGenes: A Novel Machine Learning Pipeline for Biomarker Discovery and Predictive Analysis Using Multi-Genomic Profiles.” Bioinformatics 39 (12): btad755. https://doi.org/10.1093/bioinformatics/btad755.
• DeGroat, William, Habiba Abdelhalim, Kush Patel, Dinesh Mendhe, Saman Zeeshan, and Zeeshan Ahmed. 2024. “Discovering Biomarkers Associated and Predicting Cardiovascular Disease with High Accuracy Using a Novel Nexus of Machine Learning Techniques for Precision Medicine.” Scientific Reports 14 (1): 1. https://doi.org/10.1038/s41598-023-50600-8.
• “IntelliGenes Github Repository.”Ahmed, Zeeshan. n.d.              https://github.com/ drzeeshanahmed/intelligenes
• “IntelliGenes: AI/ML Pipeline for Predictive Analyses Using Multi-Genomic Profiles.” n.d. Accessed January 24, 2024. https://codeocean.com/explore/6ce8fb31-0995-480f-9ec0-80fb59c44052.