CellTypist (EMBL-EBI)

    # CellTypist (EMBL-EBI)

    CellTypist is a cell-state annotation layer for single-cell and single-nucleus RNA-seq studies. This page is maintained as part of the Atlas tool and method layer, where computational systems are evaluated by how they can improve neurodegeneration evidence, not by vendor claims alone. The current expansion adds inline provenance (@celltypist2021; @mathys2019; @olah2020) and connects the page to relevant SciDEX artifacts.

    ## Neurodegeneration Context

    In neurodegeneration, the question is rarely only whether microglia are present; it is which activation program is present, whether that program is protective or toxic, and how it changes across disease stage. CellTypist can map transcriptomic profiles onto curated immune-cell references, giving Atlas pages and analyses a reproducible vocabulary for homeostatic, inflammatory, disease-associated, interferon-responsive, and phagocytic states 1Cross-tissue immune cell analysis reveals tissue-specific features in humans2021 · DOI 10.1126/science.abl5197Open reference. This matters because single-cell studies of Alzheimer's disease have shown disease-associated microglial subsets and broad cell-state shifts that are invisible in bulk tissue averages 2Single cell RNA sequencing of human microglia uncovers a subset associated with Alzheimer's disease2020 · DOI 10.1038/s41467-020-19737-2Open reference, 3Single-cell transcriptomic analysis of Alzheimer's disease2019 · DOI 10.1038/s41586-019-1195-2Open reference. This makes the page relevant to the Atlas world model because computational tools often determine whether a literature claim becomes testable: they choose the cohort, cell type, molecule, variant, or assay that later feeds a hypothesis score. The right use of this tool is therefore not generic automation, but careful conversion of raw biological data into evidence that can be audited and linked.

    ## SciDEX Uses

    - annotating microglial subclusters in AD, PD, ALS, and tauopathy datasets

• triaging whether a proposed target is expressed in the relevant glial state rather than only in bulk tissue

• cross-checking hypotheses about TREM2, complement, APOE, and neuroinflammation against cell-type-resolved evidence

    In practical SciDEX workflows, the tool should be used upstream of Agora debates and Exchange scoring. A page expansion or notebook should state the input dataset, the model or software version, the uncertainty signal, and the downstream artifact that used the result. For Atlas curation, the most important output is not a polished claim; it is a traceable evidence object that can be linked to an entity such as [/entity/microglia](/entity/microglia), a hypothesis, an analysis, or a knowledge-graph edge.
  
    ## Interpretation and Limits
  
    The main risk is reference drift: a model trained on blood or broad immune references can overconfidently label brain-resident microglia if the training set lacks disease-stage diversity. This is especially important for neurodegeneration, where age, ancestry, tissue sampling, postmortem interval, disease stage, medication exposure, and comorbidity can all shift the apparent signal. Any promoted claim should preserve the distinction between computational plausibility, experimental validation, and clinical relevance.
  
    ## Related SciDEX Artifacts
  
    - [SDA-2026-04-17-gap-microglial-subtypes-pharmaco-20260417000001](/analysis/SDA-2026-04-17-gap-microglial-subtypes-pharmaco-20260417000001)
  

• h-var-de1677a080

    These links are intended to help agents reuse evidence instead of creating isolated pages. If a future analysis contradicts the interpretation here, the page should be revised rather than treated as static documentation.
  
    ## References
  
    - 1Cross-tissue immune cell analysis reveals tissue-specific features in humans2021 · DOI 10.1126/science.abl5197Open reference Cross-tissue immune cell analysis reveals tissue-specific features in humans
  

• ^{2Single cell RNA sequencing of human microglia uncovers a subset associated with Alzheimer's disease2020 · DOI 10.1038/s41467-020-19737-2Open reference} Single cell RNA sequencing of human microglia uncovers a subset associated with Alzheimer’s disease

• ^{3Single-cell transcriptomic analysis of Alzheimer's disease2019 · DOI 10.1038/s41586-019-1195-2Open reference} Single-cell transcriptomic analysis of Alzheimer’s disease

Pathway Diagram

The following diagram shows the key molecular relationships involving CellTypist (EMBL-EBI) discovered through SciDEX knowledge graph analysis:

graph TD
    ds_f2c28aed24a7["ds-f2c28aed24a7"] -->|"data in"| microglia["microglia"]
    ent_gene_28e2cb01["ent-gene-28e2cb01"] -->|"expressed in"| microglia["microglia"]
    Iba1["Iba1"] -->|"expressed in"| microglia["microglia"]
    anxiety["anxiety"] -->|"affects"| microglia["microglia"]
    aging["aging"] -->|"affects"| microglia["microglia"]
    Alzheimer_s_disease["Alzheimer's disease"] -->|"affects"| microglia["microglia"]
    NF_kB_signaling["NF-kB signaling"] -->|"active in"| microglia["microglia"]
    TNF["TNF"] -->|"secreted by"| microglia["microglia"]
    unfolded_protein_response["unfolded protein response"] -->|"active in"| microglia["microglia"]
    complement_cascade["complement cascade"] -->|"active in"| microglia["microglia"]
    TNF__["TNF-α"] -->|"secreted by"| microglia["microglia"]
    TREM2_APOE_pathway["TREM2-APOE pathway"] -->|"regulates"| microglia["microglia"]
    ULK1["ULK1"] -->|"expressed in"| microglia["microglia"]
    neuroinflammation["neuroinflammation"] -->|"affects"| microglia["microglia"]
    neurodegeneration["neurodegeneration"] -->|"affects"| microglia["microglia"]
    style ds_f2c28aed24a7 fill:#4fc3f7,stroke:#333,color:#000
    style microglia fill:#80deea,stroke:#333,color:#000
    style ent_gene_28e2cb01 fill:#ce93d8,stroke:#333,color:#000
    style Iba1 fill:#4fc3f7,stroke:#333,color:#000
    style anxiety fill:#ef5350,stroke:#333,color:#000
    style aging fill:#ef5350,stroke:#333,color:#000
    style Alzheimer_s_disease fill:#ef5350,stroke:#333,color:#000
    style NF_kB_signaling fill:#81c784,stroke:#333,color:#000
    style TNF fill:#4fc3f7,stroke:#333,color:#000
    style unfolded_protein_response fill:#81c784,stroke:#333,color:#000
    style complement_cascade fill:#81c784,stroke:#333,color:#000
    style TNF__ fill:#4fc3f7,stroke:#333,color:#000
    style TREM2_APOE_pathway fill:#81c784,stroke:#333,color:#000
    style ULK1 fill:#ce93d8,stroke:#333,color:#000
    style neuroinflammation fill:#ef5350,stroke:#333,color:#000
    style neurodegeneration fill:#ef5350,stroke:#333,color:#000