Abstract
Background: Enhancers are short DNA regions that improve transcription efficiency by recruiting transcription factors. Identifying enhancer regions is important to understand the process of gene expression. As enhancers are independent of their distances and orientations to the target genes, it is difficult to locate enhancers accurately. Recently, with the development of highthroughput ChIP-seq (Chromatin Immunoprecipitation sequencing) technologies, several computational methods were developed to predict enhancers. However, most of these methods rely on p300 binding sites and/or DNase I hypersensitive sites (DHSs) for selecting positive training samples, which is imprecise and subsequently leads to unsatisfactory prediction performance. Besides, in the literature, there is no work that predicts enhancers from tissues across different developmental stages.
Methods: In this paper, we proposed a method based on support vector machines (SVMs) to investigate enhancer prediction on cell lines and tissues from EnhancerAtlas. Specifically, we focused on predicting enhancers on different developmental stages of heart and lung tissues.
Results and Conclusion: Our results show that 1) the proposed method achieves good performance on most cell lines and tissues, especially it outperforms several state of the art methods on heart and lung. 2) It is easier to predict enhancers from tissues of adult stage than from tissues of fetal stage, which is proven on both heart and lung tissues.
Keywords: Enhancer prediction, ChIP-seq, support vector machines, heart, lung, developmental stages.
Graphical Abstract
Call for Papers in Thematic Issues
AI-Based Prediction of Functional Proteins
Functional proteins are vital molecules involved in a variety of physiological and pathological processes within the body. Understanding the relationship between protein structure and function is key to unraveling the mechanisms of life sciences, disease processes, and drug discovery. However, traditional experimental methods are often time-consuming, costly, and constrained by ...read more
Application of Large Language Models in Bioinformatics
Large language models (LLMs) are increasingly transforming the field of bioinformatics by enabling scalable, data-driven solutions to complex biological and biomedical challenges. Recent advances in domain-specific foundation models have shown strong performance across a wide range of applications, including protein structure and function prediction, gene annotation, drug discovery, multi-omics data ...read more
Hot Topics in Computational Genomics
Computational genomics has emerged since the beginning of the 21st century. Recently, along with the sequencing technology at single-cell level, computational genomics step forward to the level of singe-cell resolution. Several topics are well studied in this area. Several other topics are still challenging tasks for bioinformatics. This thematic issue ...read more
Related Books
Microbial Insights into Wastewater Treatment and Environmental Sustainability
Biological Control for Plant Protection: Recent Advances in Research and Sustainability
From Genes to Algorithms: Navigating the Biotechnology Data Revolution
Phytochemical Arsenal: Understanding Plant Defense Mechanisms Against Nematodes
Controlled Environment Horticulture: Where Plant Biotechnology Meets Sustainable Future
Genetic Diversity of Coronaviruses: From SARSCoV to SARS-CoV-2 – (Part 2)
Wild Vegetables: Morphology, Phytochemistry and Utility - (Part 2)
A Practical Approach to Molecular Cloning
Organoid Technology: Disease Modelling, Drug Discovery, and Personalized Medicine
Arid and Semi-Arid Zones of Mexico: A Comprehensive Exploration of Biodiversity, Ecology, and Conservation
24
8