Ensemble learning based assessment of the role of transcription factors in gene expression

Area of Science:

• Genomics and Computational Biology
• Molecular Biology
• Cancer Research

Background:

• Gene expression regulation is crucial for cell function and growth.
• Dysfunctional genes contribute to cancer development, including Acute Myeloid Leukaemia (AML).
• Understanding the combinatorial patterns of regulatory elements is key to deciphering gene expression control.

Purpose of the Study:

• To develop a computational model for predicting the functional roles of transcriptional factors (TFs).
• To analyze TF binding patterns between divergent gene pairs.
• To gain insights into cell function and gene regulation mechanisms.

Main Methods:

• Utilizing gene expression data from the Gene Expression Omnibus (GEO) for AML.
• Employing TF binding data for EP300 and CTCF from the ENCODE consortium in K562 cells.
• Developing and applying a computational model to analyze regulatory element patterns.

Main Results:

• The study focuses on developing a predictive computational model.
• Analysis of TF binding data in specific cellular contexts (K562 cell line).
• Case study approach using AML gene expression data.

Conclusions:

• Identifying regulatory patterns provides a better understanding of cell function.
• The computational model aims to predict the functional impact of TFs.
• This approach can elucidate mechanisms underlying diseases like AML.