SomaScan → Alzheimer's-phenotype models — regression (distilled TabM students, TabPFN v2)
69 lightweight, standalone models that predict continuous Alzheimer's-disease–related phenotypes (cognition, neuropathology burden, motor/functional measures, demographics, a genetic risk score, and longitudinal change) from SomaScan plasma proteomics.
These accompany the manuscript "Fusing depth and breadth: Plasma proteomics scales deep
Alzheimer's phenotyping to global cohorts." Discrete phenotypes (e.g. medication
use, APOE genotype) live in the companion repo somascan-ad-classification-tabpfn-v2.
- Task: 69 regression phenotypes.
- Input: SomaScan plasma proteomics — aptamers named by SeqId (e.g.
seq.10001.7); seeinput_schema.csv(7,287 aptamers). Each model uses its own ~500 selected aptamers. - Artifact: one
meta/<id>.json+ one TabM.pt(~22 MB) per phenotype. - Pipeline:
st-tabpfn-pipeline(not needed at inference).
Quickstart
pip install torch tabm rtdl_num_embeddings numpy pandas
# predict ALL 69 phenotypes (wide output: sample_id + one column per phenotype)
python predict.py --input plasma_somascan.tsv --output predictions.csv
# specific phenotypes (name or target_id; comma-separated)
python predict.py --input plasma.tsv --output out.csv --target age_at_visit,cogn_global
# list what's available
python predict.py --list
predict.py depends on public packages only. Input is a CSV/TSV with a sample-id column
(sample_id / SAMPLE.ID, optional) plus SomaScan aptamer columns matched by name; column
order is irrelevant and extra columns are ignored. The models were trained on complete data and
ship no imputer — provide complete aptamer values (NaN cells are rejected).
Repo layout
| path | what |
|---|---|
predict.py |
standalone loader / CLI |
phenotypes.tsv |
index: target_id, name, paper category + description, metric, CV teacher/student R² |
meta/<id>.json |
per-model: selected feature names, arch, y-scaler, weights path |
models/<id>_student_tabm.pt |
TabM student weights (+ embedding bins) |
input_schema.csv |
the 7,287 SomaScan SeqIds the panel can supply |
parity_table.csv |
per-phenotype teacher-vs-student CV detail |
How the models were built
- Feature pre-filter (capacity reduction, not selection): CatBoost ranks aptamers and the top 500 are passed to the teacher — solely to fit TabPFN's input limit (matches the manuscript:
--method CatBoost,--selected_k 500). - Teacher: TabPFN v2 regressor (
tabpfn-v2-regressor.ckpt), a foundation model. - Distillation → student: a TabM network (parameter-efficient MLP ensemble + piecewise-linear embeddings) is trained to reproduce the teacher's predictions on a GMM-augmented transfer set (
gmm:10000), with a 5-quantile pinball loss; the released point estimate is the quantile-integral mean. - Deployable model: the teacher is dropped; only the student + preprocessing metadata ship. No feature scaling (models trained on unscaled data).
Performance (held-out cross-validation)
Evaluated on the manuscript's exact per-phenotype, person-grouped 10-fold partition (recovered and re-applied), so these numbers are directly comparable to the paper. The student is distilled separately within each fold.
| n | teacher R² (mean) | student R² (mean) | mean gap (teacher−student) | student ≥ teacher | |
|---|---|---|---|---|---|
| All regression | 69 | 0.097 | 0.109 | −0.012 | 87% |
Per-phenotype numbers are in parity_table.csv.
Intended use & limitations
- Research use only. Not a diagnostic device; predictions are population-level estimates.
- Platform-specific: trained on SomaScan aptamer measurements; not transferable to other proteomic platforms without recalibration.
License
Student weights are distilled derivatives of a TabPFN v2 teacher. The teacher
(Prior-Labs/TabPFN-v2-reg) is released under the Prior Labs License — Apache 2.0 with an
additional attribution requirement (https://priorlabs.ai/tabpfn-license/). As an
Apache-2.0-based license, these derivative students may be redistributed and used provided the
Prior Labs / TabPFN attribution is preserved.
Citation
If you use these models, cite the manuscript (citation TBD), TabPFN (Hollmann et al., Nature 2025), and TabM (Gorishniy et al., 2024).