{"@context":{"@language":"en","@vocab":"https://schema.org/","citeAs":"cr:citeAs","column":"cr:column","conformsTo":"dct:conformsTo","cr":"http://mlcommons.org/croissant/","data":{"@id":"cr:data","@type":"@json"},"dataBiases":"cr:dataBiases","dataCollection":"cr:dataCollection","dataType":{"@id":"cr:dataType","@type":"@vocab"},"dct":"http://purl.org/dc/terms/","extract":"cr:extract","field":"cr:field","fileProperty":"cr:fileProperty","fileObject":"cr:fileObject","fileSet":"cr:fileSet","format":"cr:format","includes":"cr:includes","isEnumeration":"cr:isEnumeration","isLiveDataset":"cr:isLiveDataset","jsonPath":"cr:jsonPath","key":"cr:key","md5":"cr:md5","parentField":"cr:parentField","path":"cr:path","personalSensitiveInformation":"cr:personalSensitiveInformation","recordSet":"cr:recordSet","references":"cr:references","regex":"cr:regex","repeated":"cr:repeated","replace":"cr:replace","sc":"https://schema.org/","separator":"cr:separator","source":"cr:source","subField":"cr:subField","transform":"cr:transform","wd":"https://www.wikidata.org/wiki/"},"alternateName":"RNAscope Dataset v1.0","conformsTo":"http://mlcommons.org/croissant/1.0","license":{"@type":"sc:CreativeWork","name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-sa/4.0/"},"distribution":[{"contentUrl":"https://www.kaggle.com/api/v1/datasets/download/rnascopedata/release?datasetVersionNumber=1","contentSize":"474.23 MB","md5":"ijg4IGmrhoGRMCiumsOuUg==","encodingFormat":"application/zip","@id":"archive.zip","@type":"cr:FileObject","name":"archive.zip","description":"Archive containing all the contents of the RNAscope-All-Datasets dataset"},{"includes":"*.json","containedIn":{"@id":"archive.zip"},"encodingFormat":"application/json","@id":"application-json_fileset","@type":"cr:FileSet","name":"application/json files","description":"application/json files contained in archive.zip"},{"includes":"*.mdb","containedIn":{"@id":"archive.zip"},"encodingFormat":"application/x-msaccess","@id":"application-x-msaccess_fileset","@type":"cr:FileSet","name":"application/x-msaccess files","description":"application/x-msaccess files contained in archive.zip"}],"version":1,"keywords":["subject \u003E earth and nature \u003E biology","subject \u003E science and technology \u003E computer science \u003E artificial intelligence","subject \u003E earth and nature"],"isAccessibleForFree":true,"includedInDataCatalog":{"@type":"sc:DataCatalog","name":"Kaggle","url":"https://www.kaggle.com"},"creator":{"@type":"sc:Person","name":"RNAscopeData","url":"/rnascopedata","image":"https://storage.googleapis.com/kaggle-avatars/thumbnails/26865900-kg.png?t=2025-05-15-07-00-27"},"publisher":{"@type":"sc:Organization","name":"Kaggle","url":"https://www.kaggle.com/organizations/kaggle","image":"https://storage.googleapis.com/kaggle-organizations/4/thumbnail.png"},"thumbnailUrl":"https://storage.googleapis.com/kaggle-datasets-images/7426236/11822316/c6e3a82a8228d04d6944a751b5d28684/dataset-card.png?t=2025-05-15-12-11-21","dateModified":"2025-05-15T11:05:48.543","@type":"sc:Dataset","name":"RNAscope-All-Datasets","url":"https://www.kaggle.com/datasets/rnascopedata/release/versions/1","description":"# RNAscope Dataset Repository\n\n**RNAscope** is a unified benchmarking suite for evaluating RNA pre-trained language models (pLMs) on three hierarchical dimensions of RNA biology: **structure**, **interaction**, and **function**. It comprises 15 tasks derived from rigorously curated experimental datasets, spanning pre-mRNA, mRNA, and ncRNA contexts. All tasks use consistent train/validation/test partitions and domain-appropriate evaluation metrics to ensure reproducibility and fairness.\n\nRNAscope enables systematic, multi-scale assessment of RNA pLMs\u2014from nucleotide-level base-pairing and chemical reactivity to molecular binding and transcript-level function. Its modular design supports direct comparison across diverse biological tasks and promotes transparent model benchmarking.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F26865900%2Fc352a071ab1cdd326b11039d090c9757%2Fe25780669852f546dafed779acea2b8.png?generation=1747312125993660\u0026alt=media)\n\n# **Version:** \n\nRNAscope Dataset v1.0  \n\n# **Future Directions:** \n\nWe envision ongoing expansion of this resource through incorporation of emerging datasets, additional species and cell types, and new task modalities. Community contributions and feedback are welcome to maintain RNAscope as a living benchmark that evolves with advances in RNA biology and machine learning methodologies.  \n"}