{"database": "metadata", "table": "run_metadata", "rows": [[9723, "ERR3841996", "ERX3854558", "ERS3556001", "ERP116106", "PRJEB33323", "Deconstructing the individual steps of vertebrate translation initiation", "ena-STUDY-Computational Biology Unit-03-07-2019-10:11:34:314-422", "Other", "In eukaryotes  the number of ribosomes synthesizing a given protein depends on how many are recruited to its mRNA  their success in navigating its five prime untranslated region UTR and whether they recognize its start codon. Initiation of translation is a rate limiting step in protein synthesis and key to gene expression control 1  but despite this centrality it remains poorly understood 2 3. Here we introduce ribosome complex profiling RCP seq to capture the transcriptome wide occupancy of scanning  initiating  elongating and terminating ribosome complexes in a higher eukaryote. We track scanning and elongating ribosomes across all five prime UTRs in zebrafish  which enable us to assess the individual regulatory contributions from the three stages of initiation: ribosome recruitment  scanning of the five prime UTR and recognition of the start codon. Our data sheds light on small subunit recruitment to mRNAs presenting evidence for the threading model and demonstrates that sequence features regulate this recruitment. We estimate the processivity of scanning ribosomes as they traverse the five prime UTR and show that the repressive effects of upstream open reading frames depend on the efficiency of both translation initiation and termination. Finally  we determine the optimal initiation contexts by directly estimating the conversion of scanning to elongating ribosomes and demonstrate specific regulation of translation initiation at the endoplasmic reticulum. Our results open for the possibility of deconvoluting translation initiation into separate stages and provides the first view of global occupancy of ribosomal small subunits in a vertebrate.", "ENA FIRST PUBLIC:2020 03 27|ENA LAST UPDATE:2019 07 03", null, null, "Sphere 3", "SAMEA5752542", "Computational Biology Unit", "ENA FIRST PUBLIC:2020 03 27T17:04:59Z|ENA LAST UPDATE:2019 07 03T10:01:14Z|External Id:SAMEA5752542|INSDC center name:Computational Biology Unit|INSDC first public:2020 03 27T17:04:59Z|INSDC last update:2019 07 03T10:01:14Z|INSDC status:public|Submitter Id:5|common name:zebrafish|dev stage:Sphere|sample name:5|scientific name:Danio rerio", null, null, null, null, null, null, null, null, "NextSeq 500 sequencing", "ena EXPERIMENT Computational Biology Unit 27 01 2020 16:24:36:406 6", "Sphere 3", "OTHER", "RNA Seq", null, "RNA-Seq", "TRANSCRIPTOMIC", "other", "SINGLE", "ILLUMINA", "NextSeq 500", null, "ERP116106", "NextSeq 500 sequencing", "ENA FIRST PUBLIC:2020 03 27|ENA LAST UPDATE:2020 02 14", null, null, 1439954368.0, 18946768.0, "ena RUN Computational Biology Unit 27 01 2020 16:24:36:406 6", "0:76", "A:669362698;C:280496524;G:316727778;T:173353505;N:13863", 76, null, null, null, 669362698, 280496524, 316727778, 173353505, 13863, "ERX3854558", "ERS3556001", "ERA2359305", "Computational Biology Unit|European Nucleotide Archive", "Computational Biology Unit", 1, 0.26155, null, 0.12068, null, 0.96915, null, 0.45719, null, 76, null, "B", null, "usable mapping rate", "illumina", "nextseq", "unknown", "other", "unknown", "bulk", "unknown", "unknown", null, "Unknown", "2019-07-03", "Blastula", "Embryo", "Undetermined", "Embryo Imprecise"]], "columns": ["rowid", "run.accession", "experiment.accession", "sample.accession", "study.accession", "bioproject", "study.title", "study.alias", "study.type", "study.abstract", "study.attributes", "study.PMIDs", "sample.description", "sample.title", "sample.alias", "sample.centername", "sample.attributes", "GEOsample.title", "GEOsample.dataprocessing", "GEOsample.source", "GEOsample.treatmentprotocol", "GEOsample.extractprotocol", "GEOsample.growthprotocol", "GEOsample.characteristics", "GEOsample.accession", "experiment.title", "experiment.alias", "experiment.library_name", "experiment.design_description", "experiment.library_construction_protocol", "experiment.attributes", "experiment.library_strategy", "experiment.library_source", "experiment.library_selection", "experiment.library_layout", "experiment.platform", "experiment.instrument_model", "experiment.spot_descriptor", "experiment.study_ref", "run.title", "run.attributes", "run.filename", "run.semantic_name", "run.total_bases", "run.total_spots", "run.alias", "run.read_lengths", "run.base_counts", "run.r1_length", "run.r2_length", "run.r3_length", "run.r4_length", "run.Acount", "run.Ccount", "run.Gcount", "run.Tcount", "run.Ncount", "run.experiment", "run.pool_member", "submission.accession", "submission.srasource", "submission.bioprojectsource", "seqdetective.n_mates", "seqdetective.mapping_rate.mate1", "seqdetective.mapping_rate.mate2", "seqdetective.nofeature_rate.mate1", "seqdetective.nofeature_rate.mate2", "seqdetective.sparsity.mate1", "seqdetective.sparsity.mate2", "seqdetective.pos_strand_rate.mate1", "seqdetective.pos_strand_rate.mate2", "seqdetective.readlen.mate1", "seqdetective.readlen.mate2", "seqdetective.judgement.mate1", "seqdetective.judgement.mate2", "seqdetective.judgement.reason", "platform_family", "instrument_generation", "read_bias", "selection_class", "prep_kit", "sc_or_bulk", "tech_class", "technology", "tech_variant", "submission.bioprojectsource.country", "earliest_date", "devstage_curation", "devstage_curation_coarse", "tissue_curation", "tissue_curation_coarse"], "primary_keys": ["rowid"], "primary_key_values": ["9723"], "units": {}, "query_ms": 10.496102000615792}