SNPeBoT: a tool for predicting transcription factor allele specific binding

Tallennettuna:
Bibliografiset tiedot
Julkaisussa:BMC Bioinformatics vol. 26 (2025), p. 1
Päätekijä: Oliva, Patrick Gohlldo
Julkaistu:
Springer Nature B.V.
Aiheet:
Linkit:Citation/Abstract
Full Text
Full Text - PDF
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!

MARC

LEADER 00000nab a2200000uu 4500
001 3187545174
003 UK-CbPIL
022 |a 1471-2105 
024 7 |a 10.1186/s12859-025-06094-4  |2 doi 
035 |a 3187545174 
045 2 |b d20250101  |b d20251231 
084 |a 58459  |2 nlm 
100 1 |a Oliva, Patrick Gohlldo 
245 1 |a SNPeBoT: a tool for predicting transcription factor allele specific binding 
260 |b Springer Nature B.V.  |c 2025 
513 |a Journal Article 
520 3 |a BackgroundMutations in non-coding regulatory regions of DNA may lead to disease through the disruption of transcription factor binding. However, our understanding of binding patterns of transcription factors and the effects that changes to their binding sites have on their action remains limited.SummaryTo address this issue we trained a Deep learning model to predict the effects of Single Nucleotide Polymorphisms (SNP) on transcription factor binding. Allele specific binding (ASB) data from Chromatin Immunoprecipitation sequencing (ChIP-seq) experiments were paired with high sequence-identity DNA binding Domains assessed in Protein Binding Microarray (PBM) experiments. For each transcription factor a paired DNA binding Domain was selected from which we derived E-score profiles for reference and alternate DNA sequences of ASB events. A Convolutional Neural Network (CNN) was trained to predict whether these profiles were indicative of ASB gain/loss or no change in binding. 18211 E-score profiles from 113 transcription factors were split into train, validation and test data. We compared the performance of the trained model with other available platforms for predicting the effect of SNP on transcription factor binding. Our model demonstrated increased accuracy and ASB recall in comparison to the best scoring benchmark tools.ConclusionIn this paper we present our model SNPeBoT (Single Nucleotide Polymorphism effect on Binding of Transcription Factors) in its standalone and web server form. The increased recovery and prediction accuracy of allele specific binding events could prove useful in discovering non-coding mutations relevant to disease. 
653 |a Deep learning 
653 |a Mutation 
653 |a Artificial neural networks 
653 |a Chromatin 
653 |a Alleles 
653 |a Data processing 
653 |a Genomes 
653 |a Nucleotide sequence 
653 |a Machine learning 
653 |a Cell cycle 
653 |a Protein arrays 
653 |a Polymorphism 
653 |a Binding sites 
653 |a Gene expression 
653 |a Nucleotides 
653 |a Gene sequencing 
653 |a Experiments 
653 |a Immunoprecipitation 
653 |a Deoxyribonucleic acid--DNA 
653 |a Transcription factors 
653 |a Single-nucleotide polymorphism 
653 |a Gain-Loss 
653 |a Neural networks 
653 |a Regulatory sequences 
653 |a DNA microarrays 
653 |a Environmental 
773 0 |t BMC Bioinformatics  |g vol. 26 (2025), p. 1 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3187545174/abstract/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3187545174/fulltext/embedded/H09TXR3UUZB2ISDL?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3187545174/fulltextPDF/embedded/H09TXR3UUZB2ISDL?source=fedsrch