{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Ravi S"],"funding":["UMass Chan Medical School","BRIDGE Fund Award","NIH HHS","The Bassick Family Foundation"],"pagination":["gkaf233"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11954528"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["53(6)"],"pubmed_abstract":["Species-specific differences in protein translation can affect the design of protein-based drugs. Consequently, efficient expression of recombinant proteins often requires codon optimization. Publicly available optimization tools do not always result in higher expression levels and can lead to protein misfolding and reduced expression. Here, we aimed to develop a novel deep learning (DL) tool using a recurrent neural network (RNN) to define cell type-dependent codon biases. Using gene expression data from three different tissue types (brain, liver, and muscle) and all secretory genes, we trained DL models to predict optimal codon usage. Codon-optimized sequences for test reporter genes exhibited enhanced protein expression compared to their original sequences and those optimized using a pu"],"journal":["Nucleic acids research"],"pubmed_title":["A deep learning model trained on expressed transcripts across different tissue types reveals cell-type codon-optimization preferences."],"pmcid":["PMC11954528"],"funding_grant_id":["1R21AI183080-01A1","R01NS076991-01"],"pubmed_authors":["Yang H","Sharma T","Xie J","Tai PWL","Yip M","Gao G","Ravi S"],"additional_accession":[]},"is_claimable":false,"name":"A deep learning model trained on expressed transcripts across different tissue types reveals cell-type codon-optimization preferences.","description":"Species-specific differences in protein translation can affect the design of protein-based drugs. Consequently, efficient expression of recombinant proteins often requires codon optimization. Publicly available optimization tools do not always result in higher expression levels and can lead to protein misfolding and reduced expression. Here, we aimed to develop a novel deep learning (DL) tool using a recurrent neural network (RNN) to define cell type-dependent codon biases. Using gene expression data from three different tissue types (brain, liver, and muscle) and all secretory genes, we trained DL models to predict optimal codon usage. Codon-optimized sequences for test reporter genes exhibited enhanced protein expression compared to their original sequences and those optimized using a pu","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Mar","modification":"2025-07-13T03:04:57.883Z","creation":"2025-07-13T03:04:57.883Z"},"accession":"S-EPMC11954528","cross_references":{"pubmed":["40156867"],"doi":["10.1093/nar/gkaf233"]}}