• Uma Kumari (Corresponding Author)
• Bhavya Ramesh (First Author)
• Prajwal Mahajan (Second Author)
• Jeevan Prakash (Second Author)

Idiopathic Pulmonary Fibrosis (IPF) is a progressive and life-threatening lung disease marked by the accumulation of fibrotic tissue and a steady decline in respiratory function. Despite ongoing research, the molecular drivers of IPF remain poorly understood due to its complex and multifactorial nature, involving genetic, transcriptomic, proteomic, and metabolic alterations. Although high-throughput omics technologies have become increasingly accessible, the integrative analysis of multi-omics datasets for IPF remains underdeveloped. Conventional methods often fail to capture the intricate, non-linear relationships between different molecular layers, limiting the discovery of reliable biomarkers and therapeutic targets. This study explores the application of machine learning techniques for the integrative analysis of multi-omics data in IPF. We employed Integrative Non-negative Matrix Factorization (INMF) and iCluster to uncover shared molecular signatures and stratify patient subgroups. INMF effectively decomposed transcriptomic and epigenomic datasets into joint and unique components, highlighting key cross-omics patterns linked to IPF heterogeneity. Heatmap analyses revealed sparse yet interpretable activation across latent factors, indicating biologically relevant groupings. Parallelly, iCluster enabled joint modelling and unsupervised clustering across data types, with the inclusion of highly variable features significantly improving cluster definition. The resulting subtypes displayed concordant profiles across omics layers, suggesting the presence of distinct molecular endotypes within the IPF population. Collectively, these integrative approaches provide novel insights into the molecular architecture of IPF and demonstrate the potential of machine learning in handling high-dimensional, heterogeneous datasets. This work offers a promising framework for biomarker identification, pathway mapping, and improved patient stratification in fibrotic lung diseases.

Idiopathic Pulmonary Fibrosis; Multi-omics Integration; Machine Learning; Biomarkers; Molecular Subtypes; Data Heterogeneity; INMF; iCluster; Systems Biology; Disease Stratification

"INTEGRATION OF MULTI-OMICS DATA FOR IDIOPATHIC PULMONARY FIBROSIS THROUGH MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.f855-f866, June-2025, Available :http://www.jetir.org/papers/JETIR2506599.pdf

"INTEGRATION OF MULTI-OMICS DATA FOR IDIOPATHIC PULMONARY FIBROSIS THROUGH MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. ppf855-f866, June-2025, Available at : http://www.jetir.org/papers/JETIR2506599.pdf