A Review About Transcription Factor Binding Sites Prediction Based on Deep Learning
TL;DR: In this paper, the authors provide a comprehensively understand the prediction of TF binding sites and to promote further development in this field, including deep learning methods for predicting TFBS, especially deep learning-based approaches.
read more
Abstract: Transcription factors (TFs) recognize and bind to specific DNA sequences, thereby altering the chromatin structure and regulating transcription. TFs aid in the formation of a guide genome that facilitates the expression of genes under complex regulation. Understanding the underlying mechanism that mediates the TF-led regulation of gene expression is a popular topic in current genomic research. However, identifying the precise TF binding site (TFBS) and the specific role of the TFs in transcriptional regulation is challenging. This article summarizes the status of research concerning the prediction of TFBS. First, the experimental methods for identifying TFBS have been summarized by accessing related databases. Second, the machine learning methods for predicting TFBS, especially deep learning, have been summarized. Finally, the study elaborates on the main challenges faced in TFBS prediction. The purpose of this article is to provide researchers with a comprehensively understand the prediction of TFBS and to promote further development in this field.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
PlantBind: an attention-based multi-label neural network for predicting plant transcription factor binding sites
TL;DR: PlantBind is presented, a method for integrated prediction and interpretation of transcription factor binding sites based on DNA sequences and DNA shape profiles that provides an effective solution for identifying plant TFBSs, which will promote greater understanding of transcriptional regulatory mechanisms in plants.
11
RiceTFtarget: A Rice Transcription Factor-Target Prediction Server Based on Co-expression and Machine Learning.
TL;DR: The RiceTFtarget project as mentioned in this paper realized rice transcription factor-target prediction based on co-expression, pattern matching, and machine learning, and achieved a state-of-the-art performance.
6
An Efficient Deep Learning Approach for DNA-Binding Proteins Classification from Primary Sequences
Nosiba Yousif Ahmed,Wafa Alameen Alsanousi,Eman Mohammed Hamid,Murtada Khalafallah Elbashir,Khadija Mohammed Al-Aidarous,Mogtaba Mohammed,Mohamed Elhafiz M Musa +6 more
TL;DR: This study proposes a novel approach to identify DNA-binding proteins by integrating a CNN with bidirectional long-short-term memory (LSTM) and gated recurrent unit (GRU) as (CNN-BiLG), exhibiting commendable classification accuracy based on comparative analysis.
5
Evolution and Comparative Genomics of the Transforming Growth Factor-β-Related Proteins in Nile Tilapia
Muhammad Farhan Khan,Shakeela Parveen,Mehwish Sultana,Peng Zhu,Youhou Xu,Areeba Safdar,Laiba Shafique +6 more
4
References
A decision tree for the genetic diagnosis of deficiency of adenosine deaminase 2 (DADA2): a French reference centres experience
Mélanie Rama,Claire Duflos,Isabelle Melki,Didier Bessis,A. Bonhomme,Hélène Martin,Diane Doummar,Stéphanie Valence,Diana Rodriguez,Emilie Carme,David Geneviève,David Geneviève,Ketil Heimdal,Antonella Insalaco,Nathalie Franck,Viviane Queyrel-Moranne,Nathalie Tieulie,Jonathan London,Florence Uettwiller,Sophie Georgin-Lavialle,Alexandre Belot,Isabelle Koné-Paut,Véronique Hentgen,Guilaine Boursier,Isabelle Touitou,Isabelle Touitou,Guillaume Sarrabay,Guillaume Sarrabay +27 more
TL;DR: The identifying symptoms and genotypes of patients referred to the authors' reference centres and to improve the indications for genetic testing are described to help improve obtaining genetic confirmation of DADA2 in the context of autoinflammatory symptoms.
Reverse-complement parameter sharing improves deep learning models for genomics
TL;DR: It is shown that conventional deep learning models that do not explicitly model this property can produce substantially different predictions on forward and reverse-complement versions of the same DNA sequence, and four new convolutional neural network layers are presented that leverage the reverse- complement property of genomic DNA sequence.
Anti-inflammatory effects of anisalcohol on lipopolysaccharide-stimulated BV2 microglia via selective modulation of microglia polarization and down-regulation of NF-κB p65 and JNK activation.
TL;DR: It is demonstrated that PMBA can inhibit M1 transformation and promote M2 transformation of microglia, thus attenuating the production of inflammatory mediators and cytokines and is a possible therapeutic candidate for diseases such as ischemic stroke, where inflammation is a central hallmark.
72
esATAC: an easy-to-use systematic pipeline for ATAC-seq data analysis.
TL;DR: esATAC is a highly integrated easy‐to‐use R/Bioconductor package, for systematic ATAC‐seq data analysis that covers essential steps for full analyzing procedure, including raw data processing, quality control and downstream statistical analysis such as peak calling, enrichment analysis and transcription factor footprinting.
58
Predicting the effects of SNPs on transcription factor binding affinity.
Sierra S. Nishizaki,Natalie Ng,Shengcheng Dong,Robert S. Porter,Cody Morterud,Colten Williams,Courtney Asman,Jessica A. Switzenberg,Alan P. Boyle +8 more
TL;DR: By cataloging the effects of every possible mutation within the transcription factorbinding site motif, SEMpl can predict the consequences of SNPs to transcription factor binding and can be used to identify potential disease-causing regulatory loci.
57