{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Wayment-Steele HK"],"funding":["Stanford University","U.S. Department of Health & Human Services | National Institutes of Health"],"pagination":["1174-1184"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9771809"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["4(12)"],"pubmed_abstract":["Medicines based on messenger RNA (mRNA) hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydrolysis. Predicting the degradation of an RNA molecule is a key task in designing more stable RNA-based therapeutics. Here, we describe a crowdsourced machine learning competition ('Stanford OpenVaccine') on Kaggle, involving single-nucleotide resolution measurements on 6,043 diverse 102-130-nucleotide RNA constructs that were themselves solicited through crowdsourcing on the RNA design platform Eterna. The entire experiment was completed in less t"],"journal":["Nature machine intelligence"],"pubmed_title":["Deep learning models for predicting RNA degradation via dual crowdsourcing."],"pmcid":["PMC9771809"],"funding_grant_id":["R35 GM122579","RISE"],"pubmed_authors":["Steenwinckel B","Ito T","Das R","Vandewiele G","Gao J","Mao H","Chiu KY","Wayment-Steele HK","Tunguz B","Fujikawa K","Kim DS","Kladwang W","Ishi K","Romano J","Fares M","Wellington-Oguri R","Ozturk F","Tinti M","Ozturk E","Watkins AM","Demkin M","Eterna Participants","He S","Onodera K","Noumi T","Reade W","Lee Y","Nicol JJ","Amer K"],"additional_accession":[]},"is_claimable":false,"name":"Deep learning models for predicting RNA degradation via dual crowdsourcing.","description":"Medicines based on messenger RNA (mRNA) hold immense potential, as evidenced by their rapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNA molecules has been limited by their thermostability, which is fundamentally limited by the intrinsic instability of RNA molecules to a chemical degradation reaction called in-line hydrolysis. Predicting the degradation of an RNA molecule is a key task in designing more stable RNA-based therapeutics. Here, we describe a crowdsourced machine learning competition ('Stanford OpenVaccine') on Kaggle, involving single-nucleotide resolution measurements on 6,043 diverse 102-130-nucleotide RNA constructs that were themselves solicited through crowdsourcing on the RNA design platform Eterna. The entire experiment was completed in less t","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-25T19:59:06.861Z","creation":"2025-02-19T01:08:01.465Z"},"accession":"S-EPMC9771809","cross_references":{"pubmed":["36567960"],"doi":["10.1038/s42256-022-00571-8"]}}