CacPred: a cascaded convolutional neural network for TF-DNA binding prediction
Abstract Background Transcription factors (TFs) regulate the genes’ expression by binding to DNA sequences. Aligned TFBSs of the same TF are seen as cis-regulatory motifs, and substantial computational efforts have been invested to find motifs. In recent years, convolutional neural networks (CNNs) h...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-03-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12864-025-11399-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849390475883053056 |
|---|---|
| author | Shuangquan Zhang Anjun Ma Xuping Xie Zhichao Lian Yan Wang |
| author_facet | Shuangquan Zhang Anjun Ma Xuping Xie Zhichao Lian Yan Wang |
| author_sort | Shuangquan Zhang |
| collection | DOAJ |
| description | Abstract Background Transcription factors (TFs) regulate the genes’ expression by binding to DNA sequences. Aligned TFBSs of the same TF are seen as cis-regulatory motifs, and substantial computational efforts have been invested to find motifs. In recent years, convolutional neural networks (CNNs) have succeeded in TF-DNA binding prediction, but existing DL methods’ accuracy needs to be improved and convolution function in TF-DNA binding prediction should be further explored. Results We develop a cascaded convolutional neural network model named CacPred to predict TF-DNA binding on 790 Chromatin immunoprecipitation-sequencing (ChIP-seq) datasets and seven ChIP-nexus (chromatin immunoprecipitation experiments with nucleotide resolution through exonuclease, unique barcode, and single ligation) datasets. We compare CacPred to six existing DL models across nine standard evaluation metrics. Our results indicate that CacPred outperforms all comparison models for TF-DNA binding prediction, and the average accuracy (ACC), matthews correlation coefficient (MCC), and the area of eight metrics radar (AEMR) are improved by 3.3%, 9.2%, and 6.4% on 790 ChIP-seq datasets. Meanwhile, CacPred improves the average ACC, MCC, and AEMR of 5.5%, 16.8%, and 12.9% on seven ChIP-nexus datasets. To explain the proposed method, motifs are used to show features CacPred learned. In light of the results, CacPred can find some significant motifs from input sequences. Conclusions This paper indicates that CacPred performs better than existing models on ChIP-seq data. Seven ChIP-nexus datasets are also analyzed, and they coincide with results that our proposed method performs the best on ChIP-seq data. CacPred only is equipped with the convolutional algorithm, demonstrating that pooling processing of the existing models leads to losing some sequence information. Some significant motifs are found, showing that CacPred can learn features from input sequences. In this study, we demonstrate that CacPred is an effective and feasible model for predicting TF-DNA binding. CacPred is freely available at https://github.com/zhangsq06/CacPred . |
| format | Article |
| id | doaj-art-ae467f6ec38d428fb65ffe32d330f3b2 |
| institution | Kabale University |
| issn | 1471-2164 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj-art-ae467f6ec38d428fb65ffe32d330f3b22025-08-20T03:41:39ZengBMCBMC Genomics1471-21642025-03-0126S211110.1186/s12864-025-11399-yCacPred: a cascaded convolutional neural network for TF-DNA binding predictionShuangquan Zhang0Anjun Ma1Xuping Xie2Zhichao Lian3Yan Wang4School of Cyber Science and Engineering, Nanjing University of Science and TechnologyDepartment of Biomedical Informatics, College of Medicine, The Ohio State UniversityKey Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin UniversitySchool of Cyber Science and Engineering, Nanjing University of Science and TechnologyKey Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin UniversityAbstract Background Transcription factors (TFs) regulate the genes’ expression by binding to DNA sequences. Aligned TFBSs of the same TF are seen as cis-regulatory motifs, and substantial computational efforts have been invested to find motifs. In recent years, convolutional neural networks (CNNs) have succeeded in TF-DNA binding prediction, but existing DL methods’ accuracy needs to be improved and convolution function in TF-DNA binding prediction should be further explored. Results We develop a cascaded convolutional neural network model named CacPred to predict TF-DNA binding on 790 Chromatin immunoprecipitation-sequencing (ChIP-seq) datasets and seven ChIP-nexus (chromatin immunoprecipitation experiments with nucleotide resolution through exonuclease, unique barcode, and single ligation) datasets. We compare CacPred to six existing DL models across nine standard evaluation metrics. Our results indicate that CacPred outperforms all comparison models for TF-DNA binding prediction, and the average accuracy (ACC), matthews correlation coefficient (MCC), and the area of eight metrics radar (AEMR) are improved by 3.3%, 9.2%, and 6.4% on 790 ChIP-seq datasets. Meanwhile, CacPred improves the average ACC, MCC, and AEMR of 5.5%, 16.8%, and 12.9% on seven ChIP-nexus datasets. To explain the proposed method, motifs are used to show features CacPred learned. In light of the results, CacPred can find some significant motifs from input sequences. Conclusions This paper indicates that CacPred performs better than existing models on ChIP-seq data. Seven ChIP-nexus datasets are also analyzed, and they coincide with results that our proposed method performs the best on ChIP-seq data. CacPred only is equipped with the convolutional algorithm, demonstrating that pooling processing of the existing models leads to losing some sequence information. Some significant motifs are found, showing that CacPred can learn features from input sequences. In this study, we demonstrate that CacPred is an effective and feasible model for predicting TF-DNA binding. CacPred is freely available at https://github.com/zhangsq06/CacPred .https://doi.org/10.1186/s12864-025-11399-yTranscription factorChIP-seqDeep learningTF-DNA binding prediction |
| spellingShingle | Shuangquan Zhang Anjun Ma Xuping Xie Zhichao Lian Yan Wang CacPred: a cascaded convolutional neural network for TF-DNA binding prediction BMC Genomics Transcription factor ChIP-seq Deep learning TF-DNA binding prediction |
| title | CacPred: a cascaded convolutional neural network for TF-DNA binding prediction |
| title_full | CacPred: a cascaded convolutional neural network for TF-DNA binding prediction |
| title_fullStr | CacPred: a cascaded convolutional neural network for TF-DNA binding prediction |
| title_full_unstemmed | CacPred: a cascaded convolutional neural network for TF-DNA binding prediction |
| title_short | CacPred: a cascaded convolutional neural network for TF-DNA binding prediction |
| title_sort | cacpred a cascaded convolutional neural network for tf dna binding prediction |
| topic | Transcription factor ChIP-seq Deep learning TF-DNA binding prediction |
| url | https://doi.org/10.1186/s12864-025-11399-y |
| work_keys_str_mv | AT shuangquanzhang cacpredacascadedconvolutionalneuralnetworkfortfdnabindingprediction AT anjunma cacpredacascadedconvolutionalneuralnetworkfortfdnabindingprediction AT xupingxie cacpredacascadedconvolutionalneuralnetworkfortfdnabindingprediction AT zhichaolian cacpredacascadedconvolutionalneuralnetworkfortfdnabindingprediction AT yanwang cacpredacascadedconvolutionalneuralnetworkfortfdnabindingprediction |