{
  "case_id": "host-microbe",
  "record_kind": "computational_reproduction",
  "new_wet_lab_experiment": false,
  "llm_used": false,
  "question": "How do ten prespecified transcripts compare descriptively between F. nucleatum-exposed and medium-control HT-29 samples in GSE90944?",
  "dataset": {
    "accession": "GSE90944",
    "title": "F. nucleatum exposure in HT-29 colorectal cancer cells",
    "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE90944",
    "archive_url": "https://ftp.ncbi.nlm.nih.gov/geo/series/GSE90nnn/GSE90944/suppl/GSE90944_RAW.tar",
    "publication_url": "https://pubmed.ncbi.nlm.nih.gov/28753429/",
    "doi": "10.1016/j.cell.2017.07.008",
    "assay": "Bulk RNA sequencing",
    "model": "HT-29 colorectal cancer cells",
    "organism": "Homo sapiens",
    "instrument": "Illumina HiSeq 3000",
    "reference_genome": "Ensembl GRCh37 / hg19",
    "processing": "Submitters: TopHat 2.0.11 alignment; HTSeq union-mode gene counts. Predome: selected-gene extraction and descriptive library-size CPM conversion.",
    "units": {
      "raw_count": "HTSeq gene counts",
      "cpm": "counts per million assigned gene reads"
    },
    "sample_count": 6,
    "group_count": 2,
    "gene_count": 10,
    "measurement_count": 60,
    "groups": [
      {
        "id": "control",
        "label": "Medium control",
        "sample_count": 3
      },
      {
        "id": "exposed",
        "label": "F. nucleatum",
        "sample_count": 3
      }
    ],
    "notice": "Published public experimental data, reprocessed for display. These experiments were performed by the original investigators, not Predome. This RNA-seq subset is not a drug-response or viability assay.",
    "limitations": [
      "Three submitted RNA-seq samples per condition from one cell line; the metadata does not establish that these represent independent biological replicates.",
      "This subset compares bacterial exposure with medium control. It contains no chemotherapy-treated arm or patient response measurement.",
      "Counts are submitter-provided processed sequencing outputs, not raw FASTQ reads. Predome has not repeated alignment or independently validated the experiment.",
      "CPM adjusts for library size only; it does not correct composition effects, batch effects, gene length or other confounders.",
      "The displayed log2 ratio is log2(mean exposed CPM / mean control CPM), a descriptive value, not a differential-expression test. No p-values or significance claims are provided.",
      "The ten genes are a mechanism-oriented display selection, not an unbiased genome-wide screen, validated biomarker signature, or proof of autophagic flux.",
      "RNA abundance alone does not establish protein activity, autophagy, chemoresistance, patient benefit or causality. GAPDH and ACTB are displayed as context genes and do not normalize the other genes."
    ],
    "download_csv": "/case-data/gse90944-selected-genes.csv",
    "download_json": "/case-data/gse90944-selected-genes.json",
    "download_archive": "/case-data/GSE90944_RAW.tar",
    "source_sha256": "e4c78d89055b94cf18730e098aa8326ad5a7ae8468b0bb3392102d4085eb1459",
    "checked_at": "2026-10-26",
    "publication_date": "2017-07-27",
    "geo_release_date": "2017-07-28",
    "geo_last_update": "2019-05-15",
    "bioproject": "PRJNA356417",
    "sra_study": "SRP094643",
    "reanalysis_formula": "CPM = gene count / sum of all non-summary gene counts × 1,000,000. Exclude HTSeq rows beginning __ from the denominator."
  },
  "samples": [
    {
      "sample_id": "GSM2417930",
      "label": "NC1",
      "group": "control",
      "replicate": 1,
      "library_size": 18618711,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417930"
    },
    {
      "sample_id": "GSM2417931",
      "label": "NC2",
      "group": "control",
      "replicate": 2,
      "library_size": 17041899,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417931"
    },
    {
      "sample_id": "GSM2417932",
      "label": "NC3",
      "group": "control",
      "replicate": 3,
      "library_size": 16278512,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417932"
    },
    {
      "sample_id": "GSM2417927",
      "label": "Fn1",
      "group": "exposed",
      "replicate": 1,
      "library_size": 15330313,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417927"
    },
    {
      "sample_id": "GSM2417928",
      "label": "Fn2",
      "group": "exposed",
      "replicate": 2,
      "library_size": 18457238,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417928"
    },
    {
      "sample_id": "GSM2417929",
      "label": "Fn3",
      "group": "exposed",
      "replicate": 3,
      "library_size": 15633744,
      "source_url": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2417929"
    }
  ],
  "results": [
    {
      "symbol": "ULK1",
      "pathway": "Autophagy initiation",
      "control_mean_cpm": 55.022103384,
      "exposed_mean_cpm": 76.59805655,
      "ratio": 1.392132467,
      "log2_ratio": 0.477296496,
      "samples": [
        {
          "gene": "ULK1",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 1022,
          "library_size": 18618711,
          "cpm": 54.891017966
        },
        {
          "gene": "ULK1",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 949,
          "library_size": 17041899,
          "cpm": 55.68628238
        },
        {
          "gene": "ULK1",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 887,
          "library_size": 16278512,
          "cpm": 54.489009806
        },
        {
          "gene": "ULK1",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 918,
          "library_size": 15330313,
          "cpm": 59.881360544
        },
        {
          "gene": "ULK1",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 1488,
          "library_size": 18457238,
          "cpm": 80.618779473
        },
        {
          "gene": "ULK1",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 1396,
          "library_size": 15633744,
          "cpm": 89.294029632
        }
      ]
    },
    {
      "symbol": "ATG7",
      "pathway": "Autophagy machinery",
      "control_mean_cpm": 37.328814391,
      "exposed_mean_cpm": 39.095128209,
      "ratio": 1.047317705,
      "log2_ratio": 0.066699151,
      "samples": [
        {
          "gene": "ATG7",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 667,
          "library_size": 18618711,
          "cpm": 35.824177087
        },
        {
          "gene": "ATG7",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 674,
          "library_size": 17041899,
          "cpm": 39.54958306
        },
        {
          "gene": "ATG7",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 596,
          "library_size": 16278512,
          "cpm": 36.612683027
        },
        {
          "gene": "ATG7",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 586,
          "library_size": 15330313,
          "cpm": 38.224920783
        },
        {
          "gene": "ATG7",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 719,
          "library_size": 18457238,
          "cpm": 38.954907554
        },
        {
          "gene": "ATG7",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 627,
          "library_size": 15633744,
          "cpm": 40.105556289
        }
      ]
    },
    {
      "symbol": "BECN1",
      "pathway": "Autophagy-associated panel",
      "control_mean_cpm": 49.428843109,
      "exposed_mean_cpm": 52.40639235,
      "ratio": 1.060239104,
      "log2_ratio": 0.084389657,
      "samples": [
        {
          "gene": "BECN1",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 906,
          "library_size": 18618711,
          "cpm": 48.660726298
        },
        {
          "gene": "BECN1",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 876,
          "library_size": 17041899,
          "cpm": 51.402722197
        },
        {
          "gene": "BECN1",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 785,
          "library_size": 16278512,
          "cpm": 48.223080832
        },
        {
          "gene": "BECN1",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 729,
          "library_size": 15330313,
          "cpm": 47.552845138
        },
        {
          "gene": "BECN1",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 1010,
          "library_size": 18457238,
          "cpm": 54.721080153
        },
        {
          "gene": "BECN1",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 859,
          "library_size": 15633744,
          "cpm": 54.945251758
        }
      ]
    },
    {
      "symbol": "ATG5",
      "pathway": "Autophagy-associated panel",
      "control_mean_cpm": 42.928537557,
      "exposed_mean_cpm": 46.990123834,
      "ratio": 1.094612733,
      "log2_ratio": 0.130420544,
      "samples": [
        {
          "gene": "ATG5",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 809,
          "library_size": 18618711,
          "cpm": 43.450913439
        },
        {
          "gene": "ATG5",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 667,
          "library_size": 17041899,
          "cpm": 39.138830714
        },
        {
          "gene": "ATG5",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 752,
          "library_size": 16278512,
          "cpm": 46.195868517
        },
        {
          "gene": "ATG5",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 767,
          "library_size": 15330313,
          "cpm": 50.031594267
        },
        {
          "gene": "ATG5",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 819,
          "library_size": 18457238,
          "cpm": 44.372836282
        },
        {
          "gene": "ATG5",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 728,
          "library_size": 15633744,
          "cpm": 46.565940954
        }
      ]
    },
    {
      "symbol": "MAP1LC3B",
      "pathway": "Autophagy-associated panel",
      "control_mean_cpm": 43.217551109,
      "exposed_mean_cpm": 67.673269349,
      "ratio": 1.565874688,
      "log2_ratio": 0.646968763,
      "samples": [
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 755,
          "library_size": 18618711,
          "cpm": 40.550605249
        },
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 749,
          "library_size": 17041899,
          "cpm": 43.950501056
        },
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 735,
          "library_size": 16278512,
          "cpm": 45.151547021
        },
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 918,
          "library_size": 15330313,
          "cpm": 59.881360544
        },
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 1348,
          "library_size": 18457238,
          "cpm": 73.033679254
        },
        {
          "gene": "MAP1LC3B",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 1096,
          "library_size": 15633744,
          "cpm": 70.10476825
        }
      ]
    },
    {
      "symbol": "SQSTM1",
      "pathway": "Autophagy-associated panel",
      "control_mean_cpm": 155.105678334,
      "exposed_mean_cpm": 215.721352701,
      "ratio": 1.390802419,
      "log2_ratio": 0.475917482,
      "samples": [
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 2929,
          "library_size": 18618711,
          "cpm": 157.3148646
        },
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 2616,
          "library_size": 17041899,
          "cpm": 153.50401971
        },
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 2515,
          "library_size": 16278512,
          "cpm": 154.498150691
        },
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 3327,
          "library_size": 15330313,
          "cpm": 217.021009291
        },
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 4035,
          "library_size": 18457238,
          "cpm": 218.613424175
        },
        {
          "gene": "SQSTM1",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 3307,
          "library_size": 15633744,
          "cpm": 211.529624638
        }
      ]
    },
    {
      "symbol": "TLR4",
      "pathway": "Innate immune signaling",
      "control_mean_cpm": 8.045638631,
      "exposed_mean_cpm": 7.611641974,
      "ratio": 0.946058147,
      "log2_ratio": -0.079999237,
      "samples": [
        {
          "gene": "TLR4",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 163,
          "library_size": 18618711,
          "cpm": 8.754633981
        },
        {
          "gene": "TLR4",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 125,
          "library_size": 17041899,
          "cpm": 7.334863327
        },
        {
          "gene": "TLR4",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 131,
          "library_size": 16278512,
          "cpm": 8.047418585
        },
        {
          "gene": "TLR4",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 123,
          "library_size": 15330313,
          "cpm": 8.02331955
        },
        {
          "gene": "TLR4",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 114,
          "library_size": 18457238,
          "cpm": 6.17643875
        },
        {
          "gene": "TLR4",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 135,
          "library_size": 15633744,
          "cpm": 8.635167622
        }
      ]
    },
    {
      "symbol": "MYD88",
      "pathway": "Innate immune signaling",
      "control_mean_cpm": 45.049088655,
      "exposed_mean_cpm": 38.823013653,
      "ratio": 0.861793541,
      "log2_ratio": -0.214585808,
      "samples": [
        {
          "gene": "MYD88",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 860,
          "library_size": 18618711,
          "cpm": 46.190093396
        },
        {
          "gene": "MYD88",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 757,
          "library_size": 17041899,
          "cpm": 44.419932309
        },
        {
          "gene": "MYD88",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 725,
          "library_size": 16278512,
          "cpm": 44.537240259
        },
        {
          "gene": "MYD88",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 523,
          "library_size": 15330313,
          "cpm": 34.115415647
        },
        {
          "gene": "MYD88",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 657,
          "library_size": 18457238,
          "cpm": 35.595791743
        },
        {
          "gene": "MYD88",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 731,
          "library_size": 15633744,
          "cpm": 46.757833568
        }
      ]
    },
    {
      "symbol": "GAPDH",
      "pathway": "Context gene; not a normalization control",
      "control_mean_cpm": 1143.621917776,
      "exposed_mean_cpm": 1165.242607937,
      "ratio": 1.018905453,
      "log2_ratio": 0.027020186,
      "samples": [
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 21343,
          "library_size": 18618711,
          "cpm": 1146.319957381
        },
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 20538,
          "library_size": 17041899,
          "cpm": 1205.147384103
        },
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 17571,
          "library_size": 16278512,
          "cpm": 1079.398411845
        },
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 17640,
          "library_size": 15330313,
          "cpm": 1150.661437898
        },
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 20852,
          "library_size": 18457238,
          "cpm": 1129.746498366
        },
        {
          "gene": "GAPDH",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 19000,
          "library_size": 15633744,
          "cpm": 1215.319887546
        }
      ]
    },
    {
      "symbol": "ACTB",
      "pathway": "Context gene; not a normalization control",
      "control_mean_cpm": 2369.062306084,
      "exposed_mean_cpm": 2020.322439608,
      "ratio": 0.852794135,
      "log2_ratio": -0.229730579,
      "samples": [
        {
          "gene": "ACTB",
          "sample_id": "GSM2417930",
          "sample_label": "NC1",
          "group": "control",
          "raw_count": 43841,
          "library_size": 18618711,
          "cpm": 2354.67428438
        },
        {
          "gene": "ACTB",
          "sample_id": "GSM2417931",
          "sample_label": "NC2",
          "group": "control",
          "raw_count": 41839,
          "library_size": 17041899,
          "cpm": 2455.066773955
        },
        {
          "gene": "ACTB",
          "sample_id": "GSM2417932",
          "sample_label": "NC3",
          "group": "control",
          "raw_count": 37399,
          "library_size": 16278512,
          "cpm": 2297.445859916
        },
        {
          "gene": "ACTB",
          "sample_id": "GSM2417927",
          "sample_label": "Fn1",
          "group": "exposed",
          "raw_count": 31875,
          "library_size": 15330313,
          "cpm": 2079.213907766
        },
        {
          "gene": "ACTB",
          "sample_id": "GSM2417928",
          "sample_label": "Fn2",
          "group": "exposed",
          "raw_count": 37459,
          "library_size": 18457238,
          "cpm": 2029.501922227
        },
        {
          "gene": "ACTB",
          "sample_id": "GSM2417929",
          "sample_label": "Fn3",
          "group": "exposed",
          "raw_count": 30521,
          "library_size": 15633744,
          "cpm": 1952.251488831
        }
      ]
    }
  ],
  "trace": [
    {
      "name": "Source verification",
      "engine": "deterministic Python",
      "status": "completed",
      "started_at": "2026-11-02T06:00:05.167Z",
      "completed_at": "2026-11-02T06:00:05.314Z",
      "elapsed_ms": 147.035,
      "output": {
        "archive_sha256": "e4c78d89055b94cf18730e098aa8326ad5a7ae8468b0bb3392102d4085eb1459",
        "tables": 6,
        "table_rows": {
          "GSM2417927": 56643,
          "GSM2417928": 56643,
          "GSM2417929": 56643,
          "GSM2417930": 56643,
          "GSM2417931": 56643,
          "GSM2417932": 56643
        },
        "source_date": "2017",
        "source_kind": "submitter-provided processed HTSeq counts; not FASTQ"
      }
    },
    {
      "name": "Numeric and provenance checks",
      "engine": "deterministic Python",
      "status": "completed",
      "started_at": "2026-11-02T06:00:05.314Z",
      "completed_at": "2026-11-02T06:00:05.340Z",
      "elapsed_ms": 26.303,
      "output": {
        "matched_counts": 60,
        "matched_library_denominators": 6,
        "selected_genes": 10,
        "missing_values": 0,
        "negative_counts": 0,
        "biological_independence": "not established by source metadata"
      }
    },
    {
      "name": "Descriptive calculation",
      "engine": "deterministic Python",
      "status": "completed",
      "started_at": "2026-11-02T06:00:05.340Z",
      "completed_at": "2026-11-02T06:00:05.340Z",
      "elapsed_ms": 0.227,
      "output": {
        "formula": "CPM=count/sum(non-summary gene counts)*1000000; ratio=mean(exposed CPM)/mean(control CPM)",
        "samples": 6,
        "counts": 60,
        "derived_values": 60,
        "genes": 10,
        "no_pseudocount": true,
        "inferential_test": "not performed",
        "result_sha256": "2275357f2ef27fcb8abe0b3c6fc6bd9f7b53bb88231e6b048f7f7b2c12852ee1"
      }
    }
  ],
  "input_sha256": {
    "original_archive": "e4c78d89055b94cf18730e098aa8326ad5a7ae8468b0bb3392102d4085eb1459",
    "selected_json": "374b57dac0d820ca15f2dfeea0a0e63da042fc64f3e2c932d272fbb1b99b0cd8"
  },
  "result_sha256": "2275357f2ef27fcb8abe0b3c6fc6bd9f7b53bb88231e6b048f7f7b2c12852ee1",
  "run": {
    "started_at": "2026-11-02T06:00:05.165Z",
    "completed_at": "2026-11-02T06:00:05.341Z",
    "elapsed_ms": 175.823
  },
  "interpretation": "Transcript abundance differences in this selected public-data subset are descriptive. They do not establish autophagic activity, a causal mechanism, chemotherapy resistance or clinical efficacy.",
  "next_validation": {
    "status": "proposed_not_executed",
    "tasks": [
      "Review sample independence and batch metadata.",
      "Repeat a prespecified analysis on an independent dataset.",
      "Use an appropriate experimental assay before claiming protein function or drug response."
    ]
  }
}