# Evo 2 (Arc Institute / NVIDIA / Stanford)
Evo 2 is relevant to Atlas because genomic foundation models can score noncoding and coding sequence contexts around neurodegeneration genes. 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 (@evo2024; @jun2015; @tau_review2018) and connects the page to relevant SciDEX artifacts.
## Neurodegeneration Context
... # Evo 2 (Arc Institute / NVIDIA / Stanford)
Evo 2 is relevant to Atlas because genomic foundation models can score noncoding and coding sequence contexts around neurodegeneration genes. 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 (@evo2024; @jun2015; @tau_review2018) and connects the page to relevant SciDEX artifacts.
## Neurodegeneration Context
For MAPT, APOE, LRRK2, SNCA, GBA, C9orf72, and TREM2, disease risk is not reducible to one protein-coding variant. Regulatory haplotypes, splicing, repeat structure, ancestry-specific linkage disequilibrium, and cell-type-specific expression all shape interpretation. A long-context sequence model gives SciDEX a way to ask whether a variant or haplotype sits in a sequence environment that the model treats as constrained, unusual, or functionally coupled to nearby genes [@evo2024]. MAPT is a useful example because tau biology has direct disease relevance and genetic studies have implicated loci near the tau gene in Alzheimer's disease and other tauopathies [@jun2015; @tau_review2018]. 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
- prioritizing MAPT regulatory variants for follow-up in tau-propagation hypotheses
- comparing human risk loci with model-organism sequence context before proposing experiments
- generating candidate perturbations for Forge notebooks that test splicing, enhancer, or promoter hypotheses
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/MAPT](/entity/MAPT), a hypothesis, an analysis, or a knowledge-graph edge.
## Interpretation and Limits
A genomic language model is not a clinical variant classifier, and model-derived plausibility must be separated from validated disease association. 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-BIOMNI-CAS13_PR-d6f415f0](/analysis/SDA-BIOMNI-CAS13_PR-d6f415f0)
- [h-var-95b0f9a6bc](/hypothesis/h-var-95b0f9a6bc)
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
- [@evo2024] Sequence modeling and design from molecular to genome scale with Evo
- [@jun2015] A novel Alzheimer disease locus located near the gene encoding tau protein
- [@tau_review2018] Tau protein and neurodegenerative disease
Pathway Diagram
The following diagram shows the key molecular relationships involving Evo 2 (Arc Institute / NVIDIA / Stanford) discovered through SciDEX knowledge graph analysis:
Mermaid diagram (expand to render)