CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers
Abstract Background Epigenetic modifications established in mammalian gametes are largely reprogrammed during early development, however, are partly inherited by the embryo to support its development. In this study, we examine CpG island (CGI) sequences to predict whether a mouse blastocyst CGI inhe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-04916-3 |
| _version_ | 1798036353276968960 |
|---|---|
| author | Osamu Maruyama Yinuo Li Hiroki Narita Hidehiro Toh Wan Kin Au Yeung Hiroyuki Sasaki |
| author_facet | Osamu Maruyama Yinuo Li Hiroki Narita Hidehiro Toh Wan Kin Au Yeung Hiroyuki Sasaki |
| author_sort | Osamu Maruyama |
| collection | DOAJ |
| description | Abstract Background Epigenetic modifications established in mammalian gametes are largely reprogrammed during early development, however, are partly inherited by the embryo to support its development. In this study, we examine CpG island (CGI) sequences to predict whether a mouse blastocyst CGI inherits oocyte-derived DNA methylation from the maternal genome. Recurrent neural networks (RNNs), including that based on gated recurrent units (GRUs), have recently been employed for variable-length inputs in classification and regression analyses. One advantage of this strategy is the ability of RNNs to automatically learn latent features embedded in inputs by learning their model parameters. However, the available CGI dataset applied for the prediction of oocyte-derived DNA methylation inheritance are not large enough to train the neural networks. Results We propose a GRU-based model called CMIC (CGI Methylation Inheritance Classifier) to augment CGI sequence by converting it into variable-length k-mers, where the length k is randomly selected from the range $$k_{\min }$$ k min to $$k_{\max }$$ k max , N times, which were then used as neural network input. N was set to 1000 in the default setting. In addition, we proposed a new embedding vector generator for k-mers called splitDNA2vec. The randomness of this procedure was higher than the previous work, dna2vec. Conclusions We found that CMIC can predict the inheritance of oocyte-derived DNA methylation at CGIs in the maternal genome of blastocysts with a high F-measure (0.93). We also show that the F-measure can be improved by increasing the parameter N, that is, the number of sequences of variable-length k-mers derived from a single CGI sequence. This implies the effectiveness of augmenting input data by converting a DNA sequence to N sequences of variable-length k-mers. This approach can be applied to different DNA sequence classification and regression analyses, particularly those involving a small amount of data. |
| first_indexed | 2024-04-11T21:11:41Z |
| format | Article |
| id | doaj.art-2368566fd5e84a869956acc7c60ac72e |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-11T21:11:41Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-2368566fd5e84a869956acc7c60ac72e2022-12-22T04:02:59ZengBMCBMC Bioinformatics1471-21052022-09-0123112010.1186/s12859-022-04916-3CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mersOsamu Maruyama0Yinuo Li1Hiroki Narita2Hidehiro Toh3Wan Kin Au Yeung4Hiroyuki Sasaki5Faculty of Design, Kyushu UniversityGraduate School of Design, Kyushu UniversitySchool of Design, Kyushu UniversityDivision of Epigenomics and Development, Medical Institute of Bioregulation, Kyushu UniversityDivision of Epigenomics and Development, Medical Institute of Bioregulation, Kyushu UniversityDivision of Epigenomics and Development, Medical Institute of Bioregulation, Kyushu UniversityAbstract Background Epigenetic modifications established in mammalian gametes are largely reprogrammed during early development, however, are partly inherited by the embryo to support its development. In this study, we examine CpG island (CGI) sequences to predict whether a mouse blastocyst CGI inherits oocyte-derived DNA methylation from the maternal genome. Recurrent neural networks (RNNs), including that based on gated recurrent units (GRUs), have recently been employed for variable-length inputs in classification and regression analyses. One advantage of this strategy is the ability of RNNs to automatically learn latent features embedded in inputs by learning their model parameters. However, the available CGI dataset applied for the prediction of oocyte-derived DNA methylation inheritance are not large enough to train the neural networks. Results We propose a GRU-based model called CMIC (CGI Methylation Inheritance Classifier) to augment CGI sequence by converting it into variable-length k-mers, where the length k is randomly selected from the range $$k_{\min }$$ k min to $$k_{\max }$$ k max , N times, which were then used as neural network input. N was set to 1000 in the default setting. In addition, we proposed a new embedding vector generator for k-mers called splitDNA2vec. The randomness of this procedure was higher than the previous work, dna2vec. Conclusions We found that CMIC can predict the inheritance of oocyte-derived DNA methylation at CGIs in the maternal genome of blastocysts with a high F-measure (0.93). We also show that the F-measure can be improved by increasing the parameter N, that is, the number of sequences of variable-length k-mers derived from a single CGI sequence. This implies the effectiveness of augmenting input data by converting a DNA sequence to N sequences of variable-length k-mers. This approach can be applied to different DNA sequence classification and regression analyses, particularly those involving a small amount of data.https://doi.org/10.1186/s12859-022-04916-3Recurrent neural networkGated recurrent unitClassificationOocyteBlastocystEmbryo |
| spellingShingle | Osamu Maruyama Yinuo Li Hiroki Narita Hidehiro Toh Wan Kin Au Yeung Hiroyuki Sasaki CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers BMC Bioinformatics Recurrent neural network Gated recurrent unit Classification Oocyte Blastocyst Embryo |
| title | CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers |
| title_full | CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers |
| title_fullStr | CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers |
| title_full_unstemmed | CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers |
| title_short | CMIC: predicting DNA methylation inheritance of CpG islands with embedding vectors of variable-length k-mers |
| title_sort | cmic predicting dna methylation inheritance of cpg islands with embedding vectors of variable length k mers |
| topic | Recurrent neural network Gated recurrent unit Classification Oocyte Blastocyst Embryo |
| url | https://doi.org/10.1186/s12859-022-04916-3 |
| work_keys_str_mv | AT osamumaruyama cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers AT yinuoli cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers AT hirokinarita cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers AT hidehirotoh cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers AT wankinauyeung cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers AT hiroyukisasaki cmicpredictingdnamethylationinheritanceofcpgislandswithembeddingvectorsofvariablelengthkmers |