{ "date": "2026-10-13", "version": 6, "qualifiedFreshStudies": 0, "benchmarkRun": false, "newAccuracyResults": null, "headline": "No fresh human M5 holdout qualified in this expanded search.", "scope": "Metadata-only screen of UPF1, RENT1 and HUPF1 in human SRA records, plus the KnockRBP multi-omics catalogue and a recent GEO lead. Counts describe catalogue records, not independent cohorts; sources overlap.", "counts": { "sraExperiments": 840, "sraStudyAccessions": 80, "knockRbpDatasets": 1453, "knockRbpRiboDatasets": 24, "knockRbpUpf1Datasets": 4 }, "decisions": [ { "name": "KnockRBP multi-omics catalogue", "status": "No UPF1 RPF entry", "detail": "All 1,453 catalogue entries screened. The 24 Ribo-seq entries target other RBPs. UPF1 entries DataSet_212, 338, 975 and 1135 are Poly(A)-seq or Total RNA-seq in CHA15, HeLa, HepG2 and K562. They cannot supply the paired RNA/RPF endpoint.", "source": "https://knockrbp.xu-bioinfo.com/datasets/" }, { "name": "GSE308938 \u00b7 recent UPF1 RNA/RPF lead", "status": "Excluded: yeast, not human", "detail": "GEO metadata lists Saccharomyces cerevisiae for every sample, including WT and upf1-deletion RNA-seq and 80S Ribo-seq. Suitable assay names do not establish a human holdout.", "source": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE308938" }, { "name": "SRP185496 and ERP164400", "status": "Excluded: previously used studies", "detail": "The human RPF matches resolve to Aliouat and NMDRHT data already used in development/evaluation. Another accession or archive release does not make them untouched.", "source": "https://www.ncbi.nlm.nih.gov/sra/?term=SRP185496" }, { "name": "SRA UPF1 aliases and assay screening", "status": "No additional qualifying pair identified", "detail": "Ribosomal RNA depletion (RiboMinus), RIP-seq and ribosome-bound decay intermediates are not automatically ribosome-protected-fragment translation-efficiency measurements. Keyword matches were not treated as assay qualification.", "source": "https://www.ncbi.nlm.nih.gov/sra/?term=%28UPF1+OR+RENT1+OR+HUPF1%29+AND+%22Homo+sapiens%22%5BOrganism%5D" } ], "nextStep": "Obtain an independent human study with UPF1 perturbation and matched controls measured by both RNA-seq and RPF, biological replication, sample-level counts and a clear sample sheet. A lab-held or not-yet-indexed deposit remains a possible route; no author has been contacted.", "benchmarkGate": [ "Verify human origin, perturbation, assay identity, matched conditions, replication and study independence before reading outcome tables.", "Freeze the cohort, feature mapping, target estimator and all three existing pooled v4 checkpoints before evaluation; no tuning on the holdout.", "Compare M5 with ExtraTrees and ridge using identical evaluable genes, paired uncertainty intervals, error metrics and measured runtime. Report negative results and exclusions." ], "limitations": [ "This is a dated search snapshot, not proof that no eligible dataset exists. Unindexed, private or poorly annotated data may be missed.", "The GEO alias query returned 501 sample IDs; these IDs were saved but not independently adjudicated sample by sample in this expansion.", "No new numerical outcome table was opened, no model was fitted and no new superiority or latency result is claimed. Existing v4 development scores remain unchanged." ], "knockRbpUpf1Metadata": [ { "DatasetID": "DataSet_212", "RBP": "UPF1", "DataType": "Poly(A)-seq", "specice": "human", "Biosample_Name": "CHA15", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "apa", "as", "editing", "gene", "isoform", "apa_region", "apa_orf", "apa_lof", "as_region", "as_orf", "as_lof", "editing_region", "editing_orf", "editing_lof" ] }, { "DatasetID": "DataSet_338", "RBP": "UPF1", "DataType": "Total RNA-seq", "specice": "human", "Biosample_Name": "HeLa", "Tissue_Type": "Cervix", "Disease": "Human papillomavirus-related cervical carcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "apa", "as", "editing", "gene", "isoform", "apa_region", "apa_orf", "apa_lof", "editing_region", "editing_orf", "editing_lof" ] }, { "DatasetID": "DataSet_975", "RBP": "UPF1", "DataType": "Total RNA-seq", "specice": "human", "Biosample_Name": "HepG2", "Tissue_Type": "Liver", "Disease": "Hepatocellular carcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "apa", "as", "editing", "gene", "isoform", "apa_region", "apa_orf", "apa_lof", "as_region", "as_orf", "as_lof", "editing_region", "editing_orf", "editing_lof" ] }, { "DatasetID": "DataSet_1135", "RBP": "UPF1", "DataType": "Total RNA-seq", "specice": "human", "Biosample_Name": "K562", "Tissue_Type": "Blood", "Disease": "Chronic myelogenous leukemia", "Extra_Treatment": "-", "AvailableContentTypes": [ "apa", "as", "editing", "gene", "isoform", "apa_region", "apa_orf", "apa_lof", "as_region", "as_orf", "as_lof", "editing_region", "editing_orf", "editing_lof" ] } ], "knockRbpRiboMetadata": [ { "DatasetID": "DataSet_19", "RBP": "Abcf1", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "Mouse embryonic fibroblast", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_20", "RBP": "Mettl3", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "Mouse embryonic fibroblast", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_54", "RBP": "ALKBH5", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "THP-1", "Tissue_Type": "Blood", "Disease": "Childhood acute monocytic leukemia", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_146", "RBP": "Eif4g2", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "NIH3T3", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_147", "RBP": "Eif4g2", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "NIH3T3", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_164", "RBP": "FMR1", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HCT116", "Tissue_Type": "Colon", "Disease": "Colon adenocarcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_166", "RBP": "FMR1", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HCT116", "Tissue_Type": "Colon", "Disease": "Colon adenocarcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_246", "RBP": "Mettl3", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "C57BL/6 neutrophil", "Tissue_Type": "Blood", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_247", "RBP": "METTL3", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HG3", "Tissue_Type": "Blood", "Disease": "Chronic lymphocytic leukemia", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_255", "RBP": "MTIF3", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HEK293T", "Tissue_Type": "Kidney", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_292", "RBP": "EIF1", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HCT116", "Tissue_Type": "Colon", "Disease": "Colon adenocarcinoma", "Extra_Treatment": "lactimidomycin", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_305", "RBP": "Qki", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "mESC", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "t0", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_306", "RBP": "Qki", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "mESC", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "t10", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_307", "RBP": "Khdrbs1", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "mESC", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "t0", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_308", "RBP": "Khdrbs1", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "mESC", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "t10", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_318", "RBP": "Ppie", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "R1 ES cells", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_319", "RBP": "Ppie", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "R1 ES cells", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_320", "RBP": "Ppie", "DataType": "Ribo-seq", "specice": "mouse", "Biosample_Name": "R1 ES cells", "Tissue_Type": "Embryo", "Disease": "Normal", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_328", "RBP": "YTHDF3", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HeLa", "Tissue_Type": "Cervix", "Disease": "Human papillomavirus-related cervical carcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] }, { "DatasetID": "DataSet_387", "RBP": "EIF1", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HCT116", "Tissue_Type": "Colon", "Disease": "Colon adenocarcinoma", "Extra_Treatment": "cycloheximide", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_440", "RBP": "EIF4A2", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HEK293T", "Tissue_Type": "Kidney", "Disease": "Normal", "Extra_Treatment": "", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_443", "RBP": "EIF4E2", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "A549", "Tissue_Type": "Lung", "Disease": "Lung adenocarcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_567", "RBP": "METTL5", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "HepG2", "Tissue_Type": "Liver", "Disease": "Hepatocellular carcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "te", "codon", "metagene" ] }, { "DatasetID": "DataSet_578", "RBP": "RBMS1", "DataType": "Ribo-seq", "specice": "human", "Biosample_Name": "A549", "Tissue_Type": "Lung", "Disease": "Lung adenocarcinoma", "Extra_Treatment": "-", "AvailableContentTypes": [ "codon", "metagene" ] } ], "checkpointSha256": { "backend/models/m5-reconciled-response-v4/ExtraTrees.joblib": "48cc22c7316e546c4a294fc016bceac8b643be47a50139b4066292e59cca00fc", "backend/models/m5-reconciled-response-v4/reconciled_v4.joblib": "8de9d75816d11b17cd03a0988fb4cc1b44cf5958dc01750afa60c05d76db3aee", "backend/models/m5-reconciled-response-v4/ridge.joblib": "65d3ab7c933060c0198ab0388a85915a2dd904f27d56421d35721065b403370e" }, "sourceSha256": { "GSE308938.soft": "5114b05a80b4ce8c59f146d10f3c0afbc4bd73010a17c60ee814b162d9c3d468", "KnockRBP.xml": "a094c77f9bc3d6f4a92504107ec3df2236302bb8eec092b8a7f5f292ed8d471f", "gds-alias-search.json": "86e8744024caccb9d9a3076507a4f41ec23988b58d606a4cdfc8cac5a0ed9205", "knockrbp-catalogue-metadata.json": "ebee5212568a5abd70ca35f169e7013fdba1a741612cdbff2ee0ae5750a56373", "knockrbp-catalogue.html": "5b0da04d005871a36c11bf9578f24198aa33916feea5bee87a6cd530d7128fec", "sra-alias-search.json": "7fe4340664ad1403c3061322ec275e59b7ac131fa8256a84d4ddb1875fc943aa", "sra-screening-records.json": "f0ee89810ee6187433cec02fe11133e6aafd34e7b00f35a4c975f90ac8fad072", "sra-summary-0.json": "afac5234289dc355721daf96c9dc38d702db32278e11dc85f3f28c1dc716d327", "sra-summary-200.json": "aa85f842b09f43ca38ac1c51c029884050b5c4814c6d0c0abc72a9ca7950d774", "sra-summary-400.json": "6cde310e32e3856f9121d9faca9d706af898c6a790b148f015b0893c32a19864", "sra-summary-600.json": "548b9c53ada7af8e82e0d7676fd0dafdbad8151341d814e52efb66c986495af7", "sra-summary-800.json": "e6a5e7f7b049829e793e9fbad0c0f728795fef812c3c9639afa31ba073f9bea4" } }