Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique
IntroductionVarious sequencing based approaches are used to identify and characterize the activities of cis-regulatory elements in a genome-wide fashion. Some of these techniques rely on indirect markers such as histone modifications (ChIP-seq with histone antibodies) or chromatin accessibility (ATA...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-08-01
|
| Series: | Frontiers in Cellular and Infection Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcimb.2023.1182567/full |
| _version_ | 1797756355818291200 |
|---|---|
| author | Ronald J. Nowling Kimani Njoya John G. Peters Michelle M. Riehle |
| author_facet | Ronald J. Nowling Kimani Njoya John G. Peters Michelle M. Riehle |
| author_sort | Ronald J. Nowling |
| collection | DOAJ |
| description | IntroductionVarious sequencing based approaches are used to identify and characterize the activities of cis-regulatory elements in a genome-wide fashion. Some of these techniques rely on indirect markers such as histone modifications (ChIP-seq with histone antibodies) or chromatin accessibility (ATAC-seq, DNase-seq, FAIRE-seq), while other techniques use direct measures such as episomal assays measuring the enhancer properties of DNA sequences (STARR-seq) and direct measurement of the binding of transcription factors (ChIP-seq with transcription factor-specific antibodies). The activities of cis-regulatory elements such as enhancers, promoters, and repressors are determined by their sequence and secondary processes such as chromatin accessibility, DNA methylation, and bound histone markers.MethodsHere, machine learning models are employed to evaluate the accuracy with which cis-regulatory elements identified by various commonly used sequencing techniques can be predicted by their underlying sequence alone to distinguish between cis-regulatory activity that is reflective of sequence content versus secondary processes.Results and discussionModels trained and evaluated on D. melanogaster sequences identified through DNase-seq and STARR-seq are significantly more accurate than models trained on sequences identified by H3K4me1, H3K4me3, and H3K27ac ChIP-seq, FAIRE-seq, and ATAC-seq. These results suggest that the activity detected by DNase-seq and STARR-seq can be largely explained by underlying DNA sequence, independent of secondary processes. Experimentally, a subset of DNase-seq and H3K4me1 ChIP-seq sequences were tested for enhancer activity using luciferase assays and compared with previous tests performed on STARR-seq sequences. The experimental data indicated that STARR-seq sequences are substantially enriched for enhancer-specific activity, while the DNase-seq and H3K4me1 ChIP-seq sequences are not. Taken together, these results indicate that the DNase-seq approach identifies a broad class of regulatory elements of which enhancers are a subset and the associated data are appropriate for training models for detecting regulatory activity from sequence alone, STARR-seq data are best for training enhancer-specific sequence models, and H3K4me1 ChIP-seq data are not well suited for training and evaluating sequence-based models for cis-regulatory element prediction. |
| first_indexed | 2024-03-12T18:00:12Z |
| format | Article |
| id | doaj.art-3016afc463ad4fa3ba1dc6222152a5fb |
| institution | Directory Open Access Journal |
| issn | 2235-2988 |
| language | English |
| last_indexed | 2024-03-12T18:00:12Z |
| publishDate | 2023-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cellular and Infection Microbiology |
| spelling | doaj.art-3016afc463ad4fa3ba1dc6222152a5fb2023-08-02T11:58:19ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882023-08-011310.3389/fcimb.2023.11825671182567Prediction accuracy of regulatory elements from sequence varies by functional sequencing techniqueRonald J. Nowling0Kimani Njoya1John G. Peters2Michelle M. Riehle3Electrical Engineering and Computer Science, Milwaukee School of Engineering, Milwaukee, WI, United StatesDepartment of Microbiology and Immunology, Medical College of Wisconsin, Milwaukee, WI, United StatesElectrical Engineering and Computer Science, Milwaukee School of Engineering, Milwaukee, WI, United StatesDepartment of Microbiology and Immunology, Medical College of Wisconsin, Milwaukee, WI, United StatesIntroductionVarious sequencing based approaches are used to identify and characterize the activities of cis-regulatory elements in a genome-wide fashion. Some of these techniques rely on indirect markers such as histone modifications (ChIP-seq with histone antibodies) or chromatin accessibility (ATAC-seq, DNase-seq, FAIRE-seq), while other techniques use direct measures such as episomal assays measuring the enhancer properties of DNA sequences (STARR-seq) and direct measurement of the binding of transcription factors (ChIP-seq with transcription factor-specific antibodies). The activities of cis-regulatory elements such as enhancers, promoters, and repressors are determined by their sequence and secondary processes such as chromatin accessibility, DNA methylation, and bound histone markers.MethodsHere, machine learning models are employed to evaluate the accuracy with which cis-regulatory elements identified by various commonly used sequencing techniques can be predicted by their underlying sequence alone to distinguish between cis-regulatory activity that is reflective of sequence content versus secondary processes.Results and discussionModels trained and evaluated on D. melanogaster sequences identified through DNase-seq and STARR-seq are significantly more accurate than models trained on sequences identified by H3K4me1, H3K4me3, and H3K27ac ChIP-seq, FAIRE-seq, and ATAC-seq. These results suggest that the activity detected by DNase-seq and STARR-seq can be largely explained by underlying DNA sequence, independent of secondary processes. Experimentally, a subset of DNase-seq and H3K4me1 ChIP-seq sequences were tested for enhancer activity using luciferase assays and compared with previous tests performed on STARR-seq sequences. The experimental data indicated that STARR-seq sequences are substantially enriched for enhancer-specific activity, while the DNase-seq and H3K4me1 ChIP-seq sequences are not. Taken together, these results indicate that the DNase-seq approach identifies a broad class of regulatory elements of which enhancers are a subset and the associated data are appropriate for training models for detecting regulatory activity from sequence alone, STARR-seq data are best for training enhancer-specific sequence models, and H3K4me1 ChIP-seq data are not well suited for training and evaluating sequence-based models for cis-regulatory element prediction.https://www.frontiersin.org/articles/10.3389/fcimb.2023.1182567/fullenhancersfunctional sequencingmachine learningsequence modelsDNase-seqSTARR-seq |
| spellingShingle | Ronald J. Nowling Kimani Njoya John G. Peters Michelle M. Riehle Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique Frontiers in Cellular and Infection Microbiology enhancers functional sequencing machine learning sequence models DNase-seq STARR-seq |
| title | Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| title_full | Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| title_fullStr | Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| title_full_unstemmed | Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| title_short | Prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| title_sort | prediction accuracy of regulatory elements from sequence varies by functional sequencing technique |
| topic | enhancers functional sequencing machine learning sequence models DNase-seq STARR-seq |
| url | https://www.frontiersin.org/articles/10.3389/fcimb.2023.1182567/full |
| work_keys_str_mv | AT ronaldjnowling predictionaccuracyofregulatoryelementsfromsequencevariesbyfunctionalsequencingtechnique AT kimaninjoya predictionaccuracyofregulatoryelementsfromsequencevariesbyfunctionalsequencingtechnique AT johngpeters predictionaccuracyofregulatoryelementsfromsequencevariesbyfunctionalsequencingtechnique AT michellemriehle predictionaccuracyofregulatoryelementsfromsequencevariesbyfunctionalsequencingtechnique |