DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data
Abstract Background The widespread usage of Cap Analysis of Gene Expression (CAGE) has led to numerous breakthroughs in understanding the transcription mechanisms. Recent evidence in the literature, however, suggests that CAGE suffers from transcriptional and technical noise. Regardless of the sampl...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04945-y |
| _version_ | 1811196636061237248 |
|---|---|
| author | Dimitris Grigoriadis Nikos Perdikopanis Georgios K. Georgakilas Artemis G. Hatzigeorgiou |
| author_facet | Dimitris Grigoriadis Nikos Perdikopanis Georgios K. Georgakilas Artemis G. Hatzigeorgiou |
| author_sort | Dimitris Grigoriadis |
| collection | DOAJ |
| description | Abstract Background The widespread usage of Cap Analysis of Gene Expression (CAGE) has led to numerous breakthroughs in understanding the transcription mechanisms. Recent evidence in the literature, however, suggests that CAGE suffers from transcriptional and technical noise. Regardless of the sample quality, there is a significant number of CAGE peaks that are not associated with transcription initiation events. This type of signal is typically attributed to technical noise and more frequently to random five-prime capping or transcription bioproducts. Thus, the need for computational methods emerges, that can accurately increase the signal-to-noise ratio in CAGE data, resulting in error-free transcription start site (TSS) annotation and quantification of regulatory region usage. In this study, we present DeepTSS, a novel computational method for processing CAGE samples, that combines genomic signal processing (GSP), structural DNA features, evolutionary conservation evidence and raw DNA sequence with Deep Learning (DL) to provide single-nucleotide TSS predictions with unprecedented levels of performance. Results To evaluate DeepTSS, we utilized experimental data, protein-coding gene annotations and computationally-derived genome segmentations by chromatin states. DeepTSS was found to outperform existing algorithms on all benchmarks, achieving 98% precision and 96% sensitivity (accuracy 95.4%) on the protein-coding gene strategy, with 96.66% of its positive predictions overlapping active chromatin, 98.27% and 92.04% co-localized with at least one transcription factor and H3K4me3 peak. Conclusions CAGE is a key protocol in deciphering the language of transcription, however, as every experimental protocol, it suffers from biological and technical noise that can severely affect downstream analyses. DeepTSS is a novel DL-based method for effectively removing noisy CAGE signal. In contrast to existing software, DeepTSS does not require feature selection since the embedded convolutional layers can readily identify patterns and only utilize the important ones for the classification task. This study highlights the key role that DL can play in Molecular Biology, by removing the inherent flaws of experimental protocols, that form the backbone of contemporary research. Here, we show how DeepTSS can unleash the full potential of an already popular and mature method such as CAGE, and push the boundaries of coding and non-coding gene expression regulator research even further. |
| first_indexed | 2024-04-12T01:02:17Z |
| format | Article |
| id | doaj.art-79def2d984ad4e3c8a8be5e9ca87eebf |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-12T01:02:17Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-79def2d984ad4e3c8a8be5e9ca87eebf2022-12-22T03:54:25ZengBMCBMC Bioinformatics1471-21052022-12-0123S211710.1186/s12859-022-04945-yDeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE dataDimitris Grigoriadis0Nikos Perdikopanis1Georgios K. Georgakilas2Artemis G. Hatzigeorgiou3Hellenic Pasteur InstituteHellenic Pasteur InstituteDepartment of Electrical and Computer Engineering, University of ThessalyHellenic Pasteur InstituteAbstract Background The widespread usage of Cap Analysis of Gene Expression (CAGE) has led to numerous breakthroughs in understanding the transcription mechanisms. Recent evidence in the literature, however, suggests that CAGE suffers from transcriptional and technical noise. Regardless of the sample quality, there is a significant number of CAGE peaks that are not associated with transcription initiation events. This type of signal is typically attributed to technical noise and more frequently to random five-prime capping or transcription bioproducts. Thus, the need for computational methods emerges, that can accurately increase the signal-to-noise ratio in CAGE data, resulting in error-free transcription start site (TSS) annotation and quantification of regulatory region usage. In this study, we present DeepTSS, a novel computational method for processing CAGE samples, that combines genomic signal processing (GSP), structural DNA features, evolutionary conservation evidence and raw DNA sequence with Deep Learning (DL) to provide single-nucleotide TSS predictions with unprecedented levels of performance. Results To evaluate DeepTSS, we utilized experimental data, protein-coding gene annotations and computationally-derived genome segmentations by chromatin states. DeepTSS was found to outperform existing algorithms on all benchmarks, achieving 98% precision and 96% sensitivity (accuracy 95.4%) on the protein-coding gene strategy, with 96.66% of its positive predictions overlapping active chromatin, 98.27% and 92.04% co-localized with at least one transcription factor and H3K4me3 peak. Conclusions CAGE is a key protocol in deciphering the language of transcription, however, as every experimental protocol, it suffers from biological and technical noise that can severely affect downstream analyses. DeepTSS is a novel DL-based method for effectively removing noisy CAGE signal. In contrast to existing software, DeepTSS does not require feature selection since the embedded convolutional layers can readily identify patterns and only utilize the important ones for the classification task. This study highlights the key role that DL can play in Molecular Biology, by removing the inherent flaws of experimental protocols, that form the backbone of contemporary research. Here, we show how DeepTSS can unleash the full potential of an already popular and mature method such as CAGE, and push the boundaries of coding and non-coding gene expression regulator research even further.https://doi.org/10.1186/s12859-022-04945-yTSSCAGEBioinformaticsPromoterTranscriptionMachine Learning |
| spellingShingle | Dimitris Grigoriadis Nikos Perdikopanis Georgios K. Georgakilas Artemis G. Hatzigeorgiou DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data BMC Bioinformatics TSS CAGE Bioinformatics Promoter Transcription Machine Learning |
| title | DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data |
| title_full | DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data |
| title_fullStr | DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data |
| title_full_unstemmed | DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data |
| title_short | DeepTSS: multi-branch convolutional neural network for transcription start site identification from CAGE data |
| title_sort | deeptss multi branch convolutional neural network for transcription start site identification from cage data |
| topic | TSS CAGE Bioinformatics Promoter Transcription Machine Learning |
| url | https://doi.org/10.1186/s12859-022-04945-y |
| work_keys_str_mv | AT dimitrisgrigoriadis deeptssmultibranchconvolutionalneuralnetworkfortranscriptionstartsiteidentificationfromcagedata AT nikosperdikopanis deeptssmultibranchconvolutionalneuralnetworkfortranscriptionstartsiteidentificationfromcagedata AT georgioskgeorgakilas deeptssmultibranchconvolutionalneuralnetworkfortranscriptionstartsiteidentificationfromcagedata AT artemisghatzigeorgiou deeptssmultibranchconvolutionalneuralnetworkfortranscriptionstartsiteidentificationfromcagedata |