{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:11:10Z","timestamp":1775578270628,"version":"3.50.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T00:00:00Z","timestamp":1691020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272067"],"award-info":[{"award-number":["62272067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2023NSFSC0499"],"award-info":[{"award-number":["2023NSFSC0499"]}]},{"name":"Scientific Research Foundation of Sichuan Province","award":["2022001"],"award-info":[{"award-number":["2022001"]}]},{"name":"Scientific Research Foundation of Sichuan Province","award":["MZGC20230078"],"award-info":[{"award-number":["MZGC20230078"]}]},{"name":"Scientific Research Foundation of Chengdu University of Information Technology","award":["KYQN202208"],"award-info":[{"award-number":["KYQN202208"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Enhancers are crucial cis-regulatory elements that control gene expression in a cell-type-specific manner. Despite extensive genetic and computational studies, accurately predicting enhancer activity in different cell types remains a challenge, and the grammar of enhancers is still poorly understood. Here, we present HEAP (high-resolution enhancer activity prediction), an explainable deep learning framework for predicting enhancers and exploring enhancer grammar. The framework includes three modules that use grammar-based reasoning for enhancer prediction. The algorithm can incorporate DNA sequences and epigenetic modifications to obtain better accuracy. We use a novel two-step multi-task learning method, task adaptive parameter sharing (TAPS), to efficiently predict enhancers in different cell types. We first train a shared model with all cell-type datasets. Then we adapt to specific tasks by adding several task-specific subset layers. Experiments demonstrate that HEAP outperforms published methods and showcases the effectiveness of the TAPS, especially for those with limited training samples. Notably, the explainable framework HEAP utilizes post-hoc interpretation to provide insights into the prediction mechanisms from three perspectives: data, model architecture and algorithm, leading to a better understanding of model decisions and enhancer grammar. To the best of our knowledge, HEAP will be a valuable tool for insight into the complex mechanisms of enhancer activity.<\/jats:p>","DOI":"10.1093\/bib\/bbad286","type":"journal-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T11:24:32Z","timestamp":1691148272000},"source":"Crossref","is-referenced-by-count":9,"title":["HEAP: a task adaptive-based explainable deep learning framework for enhancer activity prediction"],"prefix":"10.1093","volume":"24","author":[{"given":"Yuhang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Chengdu University of Information Technology , 610225, Chengdu , China"}]},{"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engieering, Sichuan University , 610065, Chengdu , China"}]},{"given":"Hao","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chengdu University of Information Technology , 610225, Chengdu , China"}]},{"given":"Guiquan","family":"Zhu","sequence":"additional","affiliation":[{"name":"West China Hospital of Stomatology, Sichuan University , 610041, Chengdu , China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3422-8305","authenticated-orcid":false,"given":"Yongqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Chengdu University of Information Technology , 610225, Chengdu , China"}]}],"member":"286","published-online":{"date-parts":[[2023,8,3]]},"reference":[{"issue":"3","key":"2023092216533330600_ref1","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.molcel.2019.07.009","article-title":"Enhancer features that drive formation of transcriptional condensates","volume":"75","author":"Shrinivas","year":"2019","journal-title":"Mol Cell"},{"issue":"18","key":"2023092216533330600_ref2","doi-asserted-by":"crossref","first-page":"10309","DOI":"10.1093\/nar\/gkab765","article-title":"Deciphering enhancer sequence using thermodynamics-based models and convolutional neural networks","volume":"49","author":"Dibaeinia","year":"2021","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"2023092216533330600_ref3","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1016\/j.devcel.2021.02.016","article-title":"Enhancer grammar in development, evolution, and disease: dependencies and interplay","volume":"56","author":"Jindal","year":"2021","journal-title":"Dev Cell"},{"issue":"6","key":"2023092216533330600_ref4","doi-asserted-by":"crossref","first-page":"1262","DOI":"10.1016\/j.cell.2020.02.031","article-title":"Comprehensive in vivo interrogation reveals phenotypic impact of human enhancer variants","volume":"180","author":"Kvon","year":"2020","journal-title":"Cell"},{"issue":"1","key":"2023092216533330600_ref5","doi-asserted-by":"crossref","DOI":"10.1002\/cpmb.105","article-title":"Starr-seq and umi-Starr-seq: assessing enhancer activities for genome-wide-, high-, and low-complexity candidate libraries","volume":"128","author":"Neumayr","year":"2019","journal-title":"Curr Protoc Mol Biol"},{"issue":"6","key":"2023092216533330600_ref6","doi-asserted-by":"crossref","first-page":"bbab252","DOI":"10.1093\/bib\/bbab252","article-title":"Integrative machine learning framework for the identification of cell-specific enhancers from the human genome","volume":"22","author":"Shaherin Basith","year":"2021","journal-title":"Brief Bioinform"},{"issue":"8","key":"2023092216533330600_ref7","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1093\/bioinformatics\/btaa914","article-title":"Ienhancer-xg: interpretable sequence-based enhancers and their strength predictor","volume":"37","author":"Cai","year":"2021","journal-title":"Bioinformatics"},{"issue":"3","key":"2023092216533330600_ref8","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1002968","article-title":"Rfecs: a random-forest based algorithm for enhancer identification from chromatin state","volume":"9","author":"Rajagopal","year":"2013","journal-title":"PLoS Comput Biol"},{"issue":"20","key":"2023092216533330600_ref9","doi-asserted-by":"crossref","first-page":"3436","DOI":"10.1093\/bioinformatics\/btab349","article-title":"Crephan: cross-species prediction of enhancers by using hierarchical attention networks","volume":"37","author":"Hong","year":"2021","journal-title":"Bioinformatics"},{"issue":"13","key":"2023092216533330600_ref10","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1093\/bioinformatics\/btx105","article-title":"Biren: predicting enhancers with a deep-learning-based model using the dna sequence alone","volume":"33","author":"Yang","year":"2017","journal-title":"Bioinformatics"},{"issue":"10","key":"2023092216533330600_ref11","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1038\/nmeth.3547","article-title":"Predicting effects of noncoding variants with deep learning\u2013based sequence model","volume":"12","author":"Zhou","year":"2015","journal-title":"Nat Methods"},{"issue":"5","key":"2023092216533330600_ref12","doi-asserted-by":"crossref","first-page":"bbab005","DOI":"10.1093\/bib\/bbab005","article-title":"A transformer architecture based on bert and 2d convolutional neural network to identify dna enhancers from sequence information","volume":"22","author":"Le","year":"2021","journal-title":"Brief Bioinform"},{"issue":"2","key":"2023092216533330600_ref13","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1109\/TCBB.2022.3167090","article-title":"Prediction of enhancers in dna sequence data using a hybrid cnn-dlstm model","volume":"20","author":"Kaur","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"2","key":"2023092216533330600_ref14","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/s12539-022-00503-5","article-title":"Ricenn: prediction of rice enhancers with neural network based on dna sequences","volume":"14","author":"Gao","year":"2022","journal-title":"Interdiscip Sci: Comput Life Sci"},{"issue":"4","key":"2023092216533330600_ref15","doi-asserted-by":"crossref","first-page":"2120","DOI":"10.3390\/app12042120","article-title":"Ienhancer-deep: a computational predictor for enhancer sites and their strength using deep learning","volume":"12","author":"Kamran","year":"2022","journal-title":"Appl Sci"},{"key":"2023092216533330600_ref16","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.3389\/fgene.2019.01305","article-title":"A pretraining-retraining strategy of deep learning improves cell-specific enhancer predictions","volume":"10","author":"Niu","year":"2020","journal-title":"Front Genet"},{"key":"2023092216533330600_ref17","first-page":"264200","article-title":"Enhancer identification using transfer and adversarial deep learning of dna sequences","author":"Cohn","year":"2018","journal-title":"BioRxiv"},{"issue":"6","key":"2023092216533330600_ref18","doi-asserted-by":"crossref","first-page":"967","DOI":"10.1093\/bib\/bbv101","article-title":"Progress and challenges in bioinformatics approaches for enhancer identification","volume":"17","author":"Kleftogiannis","year":"2016","journal-title":"Brief Bioinform"},{"issue":"7","key":"2023092216533330600_ref19","doi-asserted-by":"crossref","first-page":"E1291","DOI":"10.1073\/pnas.1621150114","article-title":"Systematic dissection of genomic features determining transcription factor binding and enhancer function","volume":"114","author":"Grossman","year":"2017","journal-title":"Proc Natl Acad Sci"},{"issue":"6","key":"2023092216533330600_ref20","doi-asserted-by":"crossref","first-page":"bbab273","DOI":"10.1093\/bib\/bbab273","article-title":"High-resolution transcription factor binding sites prediction improved performance and interpretability by deep learning method","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"issue":"3","key":"2023092216533330600_ref21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009941","article-title":"Base-resolution prediction of transcription factor binding signals by a deep learning framework","volume":"18","author":"Zhang","year":"2022","journal-title":"PLoS Comput Biol"},{"issue":"7818","key":"2023092216533330600_ref22","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1038\/s41586-020-2493-4","article-title":"Expanded encyclopaedias of dna elements in the human and mouse genomes","volume":"583","author":"Moore","year":"2020","journal-title":"Nature"},{"key":"2023092216533330600_ref23","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.ymeth.2019.03.014","article-title":"Enhancer prediction with histone modification marks using a hybrid neural network model","volume":"166","author":"Lim","year":"2019","journal-title":"Methods"},{"key":"2023092216533330600_ref24","first-page":"7561","article-title":"Task adaptive parameter sharing for multi-task learning","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wallingford","year":"2022"},{"issue":"2","key":"2023092216533330600_ref25","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s42256-020-00282-y","article-title":"Deep neural networks identify sequence context features predictive of transcription factor binding","volume":"3","author":"Zheng","year":"2021","journal-title":"Nat Mach Intell"},{"issue":"24","key":"2023092216533330600_ref26","doi-asserted-by":"crossref","first-page":"5610","DOI":"10.1093\/bioinformatics\/btaa1075","article-title":"Prediction of histone post-translational modifications using deep learning","volume":"36","author":"Baisya","year":"2020","journal-title":"Bioinformatics"},{"issue":"7414","key":"2023092216533330600_ref27","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of dna elements in the human genome","volume":"489","author":"ENCODE Project Consortium","year":"2012","journal-title":"Nature"},{"issue":"D1","key":"2023092216533330600_ref28","first-page":"D58","article-title":"Enhanceratlas 2.0: an updated resource with enhancer annotation in 586 tissue\/cell types across nine species","volume":"48","author":"Gao","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023092216533330600_ref29","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1093\/bioinformatics\/btw203","article-title":"Gkmsvm: an r package for gapped-kmer svm","volume":"32","author":"Ghandi","year":"2016","journal-title":"Bioinformatics"},{"issue":"8","key":"2023092216533330600_ref30","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of dna-and rna-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat Biotechnol"},{"issue":"W1","key":"2023092216533330600_ref31","doi-asserted-by":"crossref","first-page":"W160","DOI":"10.1093\/nar\/gkw257","article-title":"deeptools2: a next generation web server for deep-sequencing data analysis","volume":"44","author":"Ram\u00edrez","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023092216533330600_ref32","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"5","key":"2023092216533330600_ref33","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1038\/s41588-022-01048-5","article-title":"Deepstarr predicts enhancer activity from dna sequence and enables the de novo design of synthetic enhancers","volume":"54","author":"de Almeida","year":"2022","journal-title":"Nat Genet"},{"key":"2023092216533330600_ref34","first-page":"12321","article-title":"Involution: Inverting the inherence of convolution for visual recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2021"},{"issue":"6","key":"2023092216533330600_ref35","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"Bedtools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"issue":"1","key":"2023092216533330600_ref36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-15-293","article-title":"Jvenn: an interactive venn diagram viewer","volume":"15","author":"Bardou","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023092216533330600_ref37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gb-2007-8-2-r24","article-title":"Quantifying similarity between motifs","volume":"8","author":"Gupta","year":"2007","journal-title":"Genome Biol"},{"key":"2023092216533330600_ref38","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023092216533330600_ref39","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"International conference on machine learning","author":"Shrikumar","year":"2017"},{"key":"2023092216533330600_ref40","article-title":"Technical note on transcription factor motif discovery from importance scores (tf-modisco) version 0.5. 6.5","author":"Shrikumar","year":"2018"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/5\/bbad286\/51710990\/bbad286.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/5\/bbad286\/51710990\/bbad286.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T17:13:04Z","timestamp":1695402784000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbad286\/7236592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,3]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,9,20]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbad286","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,9]]},"published":{"date-parts":[[2023,8,3]]},"article-number":"bbad286"}}