{"schema":"https://automatedassays.local/schemas/real-data-evidence-bundle/1.0.0","schema_version":"1.0.0","bundle_public_id":"997b6eea-e849-41f3-a597-c3668ff34a8b","generated_at":"2026-11-03T17:43:09.000000Z","mode":"real_data","label":"Count filtering, normalisation and sample quality","record":{"record_id":"pmid:27508061","science_record_content_hash":null,"science_record_source":null},"operation":{"name":"rna_seq_count_filtering_and_normalisation","version":"0.1.0","parameters":{"paper":"pmid:27508061","paper_version":"2","stage":"counts_qc","source_files":{"targets.txt":"sha256:88ae42c0539403073f0bbbd53287dd9c9cf61ddd5b1a42856243d7d99113cb8b","edgeRQL.R":"sha256:3b11478ac314c4456af8b4ba7af7992e938488ffc7bec88d3f73f42aed4c0bba","edgeRQL.Rnw":"sha256:defd3acb73dcbfe885ca02209ac9437b785b4ccf12c7ba09a8a8bb311173902d"},"software":{"edgeR":"3.14.0","limma":"3.28.21","org.Mm.eg.db":"3.3.0","GO.db":"3.3.0","gplots":"3.0.1"},"deviations":{"kegg_transport":"KEGG's REST endpoint now redirects http to https, and the pinned R's url() reader cannot follow a redirect, so the gene-to-pathway table kegga reads is fetched over https and passed to limma::kegga as the gene.pathway and pathway.names arguments that limma documents for supplying those tables directly. The species argument, the gene sets and the analysis are the authors' own.","r_patch_release":"The paper ran on R 3.3.1 and this platform runs on R 3.3.2.","limma_patch_release":"The paper ran on limma 3.28.6 and this platform runs on limma 3.28.21, the last patch of the same Bioconductor 3.3 series.","annotation_dbi_patch_release":"The paper ran on AnnotationDbi 1.34.3 and this platform runs on AnnotationDbi 1.38.0, the last patch of the same Bioconductor 3.3 series.","operating_system":"The paper ran on Windows 7 x64 and this platform runs on Linux."}}},"dataset":{"asset_id":"GEO:GSE60450:Lactation-GenewiseCounts","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE60450","licence":{"state":"open"}},"result":{"stage":"counts_qc","label":"Count filtering, normalisation and sample quality","status":"complete","numbers":{"stage":"counts_filtering_and_normalisation","source_file":"GSE60450_Lactation-GenewiseCounts.txt.gz","samples":12,"groups":{"B.lactating":2,"B.pregnant":2,"B.virgin":2,"L.lactating":2,"L.pregnant":2,"L.virgin":2},"genes_in_source":27179,"genes_after_symbol_drop":26357,"genes_dropped_without_symbol":822,"filter_rule":"cpm > 0.5 in at least 2 libraries","filter_min_cpm":0.5,"filter_min_libraries":2,"genes_kept":15653,"genes_filtered_out":10704,"normalisation":"TMM (edgeR calcNormFactors)","normalisation_method":"TMM","library_sizes":{"MCL1.DG":23139638,"MCL1.DH":21689576,"MCL1.DI":23976634,"MCL1.DJ":22546909,"MCL1.DK":21422164,"MCL1.DL":19918278,"MCL1.LA":20276400,"MCL1.LB":21571124,"MCL1.LC":22120647,"MCL1.LD":21879947,"MCL1.LE":24660577,"MCL1.LF":24602860},"norm_factors":{"MCL1.DG":1.234989,"MCL1.DH":1.213001,"MCL1.DI":1.125787,"MCL1.DJ":1.069287,"MCL1.DK":1.036246,"MCL1.DL":1.087182,"MCL1.LA":1.369976,"MCL1.LB":1.367587,"MCL1.LC":1.005906,"MCL1.LD":0.92398,"MCL1.LE":0.528589,"MCL1.LF":0.534754}},"artefact_sha256":{"sample_qc.tsv":"sha256:9cf12f7783b55a0efdc91b9be2e0a8e02e7ea0e98a23f859a76434733397a993","counts_filtered.tsv":"sha256:cfe96107d3daec2c92b597a21af1105412ed5ef823cd57dea8244f3646e266fe","mds.png":"sha256:365d5d410f6106d157b68836204c4522114f10307009bc40afe9ad51c380de99","md1.png":"sha256:c9c9f1c0385f31e948086fec48431c2e455995b66701e3ea4055430573257376","md11.png":"sha256:770e71a2d9b9adb76939d5d1c2c330ca2263eea5b64e5adfe925f66271276948"},"comparison":{"stage":"counts_qc","label":"Count filtering, normalisation and sample quality","source":"The paper prints the library size and the normalisation factor of every library after filtering and normalisation, and states the filter rule and the normalisation method.","criteria":[{"name":"filter_rule","statement":"Genes are kept when they have a count per million above 0.5 in at least two libraries.","comparison":"exact","published":{"min_cpm":0.5,"min_libraries":2},"verdict":"reproduced","agreements":["the filter rule"],"differences":[],"compared":1,"detail":"1 of 1 agree with the paper"},{"name":"normalisation_method","statement":"Normalisation is the trimmed mean of M values.","comparison":"exact","published":"TMM","verdict":"reproduced","agreements":["the method"],"differences":[],"compared":1,"detail":"1 of 1 agree with the paper"},{"name":"group_sizes","statement":"The twelve libraries fall into six groups of two, and the paper states that the small group size is justified by the low background variability.","comparison":"exact","published":{"B.virgin":2,"B.pregnant":2,"B.lactating":2,"L.virgin":2,"L.pregnant":2,"L.lactating":2},"verdict":"reproduced","agreements":["B.virgin","B.pregnant","B.lactating","L.virgin","L.pregnant","L.lactating"],"differences":[],"compared":6,"detail":"6 of 6 agree with the paper"},{"name":"library_sizes","statement":"The library size of every library equals the number the paper prints, after the filter has been applied and the library sizes recalculated.","comparison":"exact","published":{"MCL1.DG":23139638,"MCL1.DH":21689576,"MCL1.DI":23976634,"MCL1.DJ":22546909,"MCL1.DK":21422164,"MCL1.DL":19918278,"MCL1.LA":20276400,"MCL1.LB":21571124,"MCL1.LC":22120647,"MCL1.LD":21879947,"MCL1.LE":24660577,"MCL1.LF":24602860},"verdict":"reproduced","agreements":["MCL1.DG","MCL1.DH","MCL1.DI","MCL1.DJ","MCL1.DK","MCL1.DL","MCL1.LA","MCL1.LB","MCL1.LC","MCL1.LD","MCL1.LE","MCL1.LF"],"differences":[],"compared":12,"detail":"12 of 12 agree with the paper"},{"name":"normalisation_factors","statement":"The normalisation factor of every library agrees with the number the paper prints to the three decimals it prints.","comparison":"to the printed precision of 0.001","published":{"MCL1.DG":1.235,"MCL1.DH":1.213,"MCL1.DI":1.126,"MCL1.DJ":1.069,"MCL1.DK":1.036,"MCL1.DL":1.087,"MCL1.LA":1.37,"MCL1.LB":1.368,"MCL1.LC":1.006,"MCL1.LD":0.924,"MCL1.LE":0.529,"MCL1.LF":0.535},"verdict":"reproduced","agreements":["MCL1.DG","MCL1.DH","MCL1.DI","MCL1.DJ","MCL1.DK","MCL1.DL","MCL1.LA","MCL1.LB","MCL1.LC","MCL1.LD","MCL1.LE","MCL1.LF"],"differences":[],"compared":12,"detail":"12 of 12 agree with the paper"}],"summary":{"reproduced":5,"not_reproduced":0,"not_scored":0}},"log_sha256":"sha256:2789de33c3e7a108dd604ee761876e00c956ed4e0c573f741b5805ba0c850891","started_at":"2026-11-03T17:42:56.081162Z","completed_at":"2026-11-03T17:43:09.910573Z"},"integrity":{"dataset_sha256":"sha256:46cd415ac9b82853efb608bddc98cddbf8c7a908807877d448d9c73419b615cc","result_sha256":"sha256:a1f4df7f4ba128a759d8da6db62614641875603a7474e4c02572b23b18563976","bundle_hash":"25d0e73c4e732aef23de129367c22fb8c3889275e672ff9c8be9c63fdd553a59"},"replay_contract":{"description":"Re-running the operation on the dataset identified above must reproduce the recorded result hash exactly.","dataset_asset_id":"GEO:GSE60450:Lactation-GenewiseCounts","dataset_source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE60450","expected_dataset_sha256":"sha256:46cd415ac9b82853efb608bddc98cddbf8c7a908807877d448d9c73419b615cc","expected_result_sha256":"sha256:a1f4df7f4ba128a759d8da6db62614641875603a7474e4c02572b23b18563976","operation":"rna_seq_count_filtering_and_normalisation","operation_version":"0.1.0","design":{"paper":"pmid:27508061","paper_version":"2","stage":"counts_qc","source_files":{"targets.txt":"sha256:88ae42c0539403073f0bbbd53287dd9c9cf61ddd5b1a42856243d7d99113cb8b","edgeRQL.R":"sha256:3b11478ac314c4456af8b4ba7af7992e938488ffc7bec88d3f73f42aed4c0bba","edgeRQL.Rnw":"sha256:defd3acb73dcbfe885ca02209ac9437b785b4ccf12c7ba09a8a8bb311173902d"},"software":{"edgeR":"3.14.0","limma":"3.28.21","org.Mm.eg.db":"3.3.0","GO.db":"3.3.0","gplots":"3.0.1"},"deviations":{"kegg_transport":"KEGG's REST endpoint now redirects http to https, and the pinned R's url() reader cannot follow a redirect, so the gene-to-pathway table kegga reads is fetched over https and passed to limma::kegga as the gene.pathway and pathway.names arguments that limma documents for supplying those tables directly. The species argument, the gene sets and the analysis are the authors' own.","r_patch_release":"The paper ran on R 3.3.1 and this platform runs on R 3.3.2.","limma_patch_release":"The paper ran on limma 3.28.6 and this platform runs on limma 3.28.21, the last patch of the same Bioconductor 3.3 series.","annotation_dbi_patch_release":"The paper ran on AnnotationDbi 1.34.3 and this platform runs on AnnotationDbi 1.38.0, the last patch of the same Bioconductor 3.3 series.","operating_system":"The paper ran on Windows 7 x64 and this platform runs on Linux."}},"platform":{"accession":null,"source_url":null,"sha256":null}}}