{"snapshot":{"version":"cathedral-malaria-input-audit-v1","recordedAt":"2026-10-15T22:08:28.283Z","mainPaperDoi":"10.1038/s41591-026-04590-5","scope":"Public source metadata and workbook structure. Not a model execution, joined analysis cohort, clinical inference or independent validation.","modelReproduced":false,"dataJoinEstablished":false,"rawReadsDownloaded":false,"sources":{"workbook":{"sourceDoi":"10.1038/s41467-025-62810-x","sourcePage":"https://www.nature.com/articles/s41467-025-62810-x","receipt":{"url":"https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41467-025-62810-x/MediaObjects/41467_2025_62810_MOESM4_ESM.xlsx","retrievedAt":"2026-10-15T22:02:28.678Z","bytes":711085,"sha256":"6f3fc32b1271b80f1f8947e52fd3493f2d94728804d2a8ba522639bfd5bdf29b","providerChecksum":null,"providerChecksumMatched":null,"etag":"\"96bdd9df0053aa250f2c7c884485a737\"","lastModified":"Sat, 09 Aug 2025 13:44:56 GMT"},"sheets":[{"name":"Data Set Assignment","physicalRowCount":15,"keyInspections":[]},{"name":"Data dictionary","physicalRowCount":63,"keyInspections":[]},{"name":"Data Set 1","physicalRowCount":1114,"keyInspections":[{"column":"A","headerRow":1,"header":"UID","nonemptyKeyCells":1113,"distinctKeys":1113,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":32,"keyTransformation":"none","biologicalJoinEstablished":false}]},{"name":"Data Set 2","physicalRowCount":1616,"keyInspections":[{"column":"A","headerRow":1,"header":"UID","nonemptyKeyCells":1615,"distinctKeys":1615,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":35,"keyTransformation":"none","biologicalJoinEstablished":false}]},{"name":"Data Set 3","physicalRowCount":1777,"keyInspections":[{"column":"A","headerRow":1,"header":"UID","nonemptyKeyCells":1776,"distinctKeys":1776,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":40,"keyTransformation":"none","biologicalJoinEstablished":false}]},{"name":"Data Set 4","physicalRowCount":666,"keyInspections":[{"column":"A","headerRow":1,"header":"UID","nonemptyKeyCells":665,"distinctKeys":665,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":23,"keyTransformation":"none","biologicalJoinEstablished":false}]},{"name":"Data Set 5","physicalRowCount":1569,"keyInspections":[{"column":"C","headerRow":1,"header":"UID","nonemptyKeyCells":1568,"distinctKeys":1568,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":35,"keyTransformation":"none","biologicalJoinEstablished":false}]}],"observedFields":[{"sheet":"Data Set 1","cell":"A1","value":"UID"},{"sheet":"Data Set 1","cell":"E1","value":"parasitemia"},{"sheet":"Data dictionary","cell":"C6","value":"numeric (%)"},{"sheet":"Data Set 5","cell":"C1","value":"UID"}],"formulasExecuted":false,"licence":"Article CC-BY-4.0; check third-party exceptions and data-specific terms before reuse","joinStatus":"No verified mapping to the PX1 model's phenotype/genotype/COI cohort","comparisonReceipt":{"url":"https://raw.githubusercontent.com/Karaniare/PfWGS-DRscanner/8ef861e27f93d95859113003dc01d24747fb28c7/Examples%20(selection)/px1_genotypes_metadata_combined.tsv","retrievedAt":"2026-10-15T22:02:29.259Z","bytes":2981,"sha256":"944218a9bd6be5f77e8d1ec913ea75a10480412021b67478c4370000a87ddaf6","providerChecksum":"sha256:944218a9bd6be5f77e8d1ec913ea75a10480412021b67478c4370000a87ddaf6","providerChecksumMatched":true,"etag":"W/\"f83d6bf1239f0875c48c13be2aab7e9653e35f6a07780499053fe6fbc70b17cb\"","lastModified":null}},"ena":[{"receipt":{"url":"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA1298911&result=read_run&format=json&fields=run_accession%2Csample_accession%2Cstudy_accession%2Cscientific_name%2Clibrary_strategy%2Cfastq_bytes%2Cfastq_md5%2Cfastq_ftp","retrievedAt":"2026-10-15T21:58:58.840Z","bytes":70972,"sha256":"05f41353c840a390fbc64540fed6819b6d1efd618496c05d3805a24e5379bff8","providerChecksum":null,"providerChecksumMatched":null,"etag":null,"lastModified":null},"project":"PRJNA1298911","runCount":158,"sampleCount":158,"fileCount":316,"knownFastqBytes":"465882029469","completeFileCoverage":true,"runsWithoutListedFastq":0,"species":["Plasmodium falciparum"],"runsWithUnknownSpecies":0,"libraryStrategies":["WGS"],"downloadedReads":false,"analysisCohortEstablished":false,"clinicalInference":false},{"receipt":{"url":"https://www.ebi.ac.uk/ena/portal/api/filereport?accession=PRJNA1450510&result=read_run&format=json&fields=run_accession%2Csample_accession%2Cstudy_accession%2Cscientific_name%2Clibrary_strategy%2Cfastq_bytes%2Cfastq_md5%2Cfastq_ftp","retrievedAt":"2026-10-15T21:59:17.123Z","bytes":438073,"sha256":"729b785463558cda7fb50a5089e8bde26d246eaf6fc5438d087aa36cc4c9075c","providerChecksum":null,"providerChecksumMatched":null,"etag":null,"lastModified":null},"project":"PRJNA1450510","runCount":1375,"sampleCount":1375,"fileCount":1304,"knownFastqBytes":"6124279733","completeFileCoverage":false,"runsWithoutListedFastq":71,"species":["Plasmodium falciparum"],"runsWithUnknownSpecies":546,"libraryStrategies":["AMPLICON"],"downloadedReads":false,"analysisCohortEstablished":false,"clinicalInference":false}],"pf7":{"doi":"10.5281/zenodo.18711720","licence":"cc-by-4.0","recordReceipt":{"url":"https://zenodo.org/api/records/18711720","retrievedAt":"2026-10-15T21:57:12.694Z","bytes":15961,"sha256":"93e7035abc55264c999fa05be6524714db0d10a457d7bcb3613e1959753b44d2","providerChecksum":null,"providerChecksumMatched":null,"etag":"W/\"8\"","lastModified":null},"receipt":{"url":"https://zenodo.org/api/records/18711720/files/Pf7_samples.txt/content","retrievedAt":"2026-10-15T21:57:13.916Z","bytes":3950451,"sha256":"826c188c7d8173b32f8243eb33339b00d95630488c0a1fbba9b360afcc32f767","providerChecksum":"md5:d0d5c002984e95a71cf9aaa670f9c23b","providerChecksumMatched":true,"etag":null,"lastModified":null},"sampleCount":20864,"knownCountryCount":33,"missingCountryCount":160,"knownYearRange":[1984,2018],"missingOrUnparsedYearCount":160,"qcValues":{"True":16203,"False":4661},"metadataOnly":true,"genotypesDownloaded":false,"analysisCohortEstablished":false},"code":{"commit":"8ef861e27f93d95859113003dc01d24747fb28c7","repository":"https://github.com/Karaniare/PfWGS-DRscanner","treeComplete":true,"treeSha":"dd161c3b143c9f69ead622fcdc9b6aaf99c451fc","treeReceipt":{"url":"https://api.github.com/repos/Karaniare/PfWGS-DRscanner/git/trees/dd161c3b143c9f69ead622fcdc9b6aaf99c451fc?recursive=1","retrievedAt":"2026-10-15T21:57:14.049Z","bytes":7240,"sha256":"16bbfa059574a981029d7e7967d0f73aeb0fe01d6a16c897d661ad3b33b18e02","providerChecksum":null,"providerChecksumMatched":null,"etag":"W/\"f548024d191a6dfcd14897ca3fa58c286dc875f6fd912abf97085d59455fece6\"","lastModified":"Mon, 08 Jun 2026 15:05:13 GMT"},"model":{"path":"main/MIxed-Effects_Model.R","gitBlob":"8928efe989a20220222dbbb18584f20b18077451","sha256":"3c4a48ed01e380189b7f1ee129d24636e87c7b86ee6182929124c8b87e3e21c3","retrievedAt":"2026-10-15T21:57:14.773Z","bytes":10030},"example":{"path":"Examples (selection)/px1_genotypes_metadata_combined.tsv","gitBlob":"172b614ad5c063bcceb4669946faa224da270a17","sha256":"944218a9bd6be5f77e8d1ec913ea75a10480412021b67478c4370000a87ddaf6","retrievedAt":"2026-10-15T21:57:14.789Z","bytes":2981,"physicalDataRows":211,"headers":["sample_name","major_genotype"]},"requiredFiles":[{"name":"ex_vivo_phenotype_data_long_table_current.csv","presentInPinnedTree":false},{"name":"parasitemia.csv","presentInPinnedTree":false},{"name":"COI_calls_all_uganda_samples.csv","presentInPinnedTree":false}],"archive":{"doi":"10.5281/zenodo.21283869","licence":"mit-license","name":"Karaniare/PfWGS-DRscanner-v1.0.0.zip","bytes":365388863,"checksum":"md5:0885c651b2723d7bfb66049ee994807f","downloaded":false},"authorCodeExecuted":false},"mainWorkbook":{"sourceDoi":"10.1038/s41591-026-04590-5","sourcePage":"https://www.nature.com/articles/s41591-026-04590-5","receipt":{"url":"https://media.springernature.com/original/springer-static/esm/art%3A10.1038%2Fs41591-026-04590-5/MediaObjects/41591_2026_4590_MOESM5_ESM.xlsx","retrievedAt":"2026-10-15T22:08:27.452Z","bytes":106432,"sha256":"7f08b7218fe7c0eb4741a003fd298b6656598030a0165653d9f736ce364b9c31","providerChecksum":null,"providerChecksumMatched":null,"etag":"\"af8210d3e6f582b489a8e0b078620863\"","lastModified":"Tue, 11 Aug 2026 10:11:48 GMT"},"comparisonReceipt":{"url":"https://raw.githubusercontent.com/Karaniare/PfWGS-DRscanner/8ef861e27f93d95859113003dc01d24747fb28c7/Examples%20(selection)/px1_genotypes_metadata_combined.tsv","retrievedAt":"2026-10-15T22:08:27.789Z","bytes":2981,"sha256":"944218a9bd6be5f77e8d1ec913ea75a10480412021b67478c4370000a87ddaf6","providerChecksum":"sha256:944218a9bd6be5f77e8d1ec913ea75a10480412021b67478c4370000a87ddaf6","providerChecksumMatched":true,"etag":"W/\"f83d6bf1239f0875c48c13be2aab7e9653e35f6a07780499053fe6fbc70b17cb\"","lastModified":null},"articleLicence":"CC-BY-NC-ND-4.0","dataSpecificReusePermission":"not-established","sheets":[{"name":"Source_dataset1","physicalRowCount":1347,"formulaCount":0,"headers":[{"cell":"A1","text":"sample_name"},{"cell":"B1","text":"site"},{"cell":"C1","text":"region"},{"cell":"D1","text":"study"},{"cell":"E1","text":"year"},{"cell":"F1","text":"parasitemia"},{"cell":"G1","text":"px1_haplotype"},{"cell":"H1","text":"wsaf"},{"cell":"I1","text":"k13_genotype"},{"cell":"J1","text":"Pyronaridine"},{"cell":"K1","text":"Pyrimethamine"},{"cell":"L1","text":"Chloroquine"},{"cell":"M1","text":"Piperaquine"},{"cell":"N1","text":"DHA"},{"cell":"O1","text":"Mefloquine"},{"cell":"P1","text":"Lumefantrine"},{"cell":"Q1","text":"RSA"},{"cell":"R1","text":"px1_coverage"}],"keyInspections":[{"column":"A","headerRow":1,"header":"sample_name","nonemptyKeyCells":1345,"distinctKeys":1345,"duplicateKeyCells":0,"comparisonDistinctKeys":211,"exactTextMatches":161,"keyTransformation":"none","biologicalJoinEstablished":false,"nonTextKeyCells":1,"formulaKeyCells":0,"keyColumnFullyText":false,"comparisonScope":"Text cells only; numeric and formula cells are excluded without conversion."}]}],"sourceDataRedistributed":false,"analysisCohortEstablished":false}},"failures":[{"stage":"ena","recordedAt":"2026-10-15T21:57:40.179Z","error":"The operation was aborted due to timeout","recovery":"The two studies were inspected separately. Successful receipts are retained above."},{"stage":"main-workbook-key-check","recordedAt":"2026-10-15T22:07:53.497Z","error":"Selected workbook key has wrong header, formulas or non-text values","recovery":"Explicit mixed-type schema inspection retained the one numeric key as unmapped; no type conversion or completed biological join."}],"remainingInputs":["Verify the exact per-isolate join between the published phenotype source and PX1 genotypes; do not join by row order or collection year.","Recover and qualify COI calls and the exact parasitemia transformation expected by the pinned model.","Validate full PIN/deletion/phase definitions and cohort inclusion, not only the three example SNPs.","Confirm data-specific reuse/access terms and preregister a bounded input bundle before isolated execution."]},"sha256":"3db6cde36b028ce17404c3d9a09ecb1156457a0d899d1bdcb2a70adf59315013","verification":"SHA-256 of JSON.stringify(snapshot), UTF-8. Verifies these exported bytes, not an externally witnessed timestamp or scientific conclusion."}