PsychGNN All-Tested-Pairs Model
Model summary
This repository contains a heterogeneous graph neural network trained on all tested SNP-disorder pairs on the published psychiatric graph panel.
The model predicts whether a tested SNP-disorder pair is:
null, ornon-null (suggestive or genome-wide significant)
This is a variant-level research model. It is not a clinical model.
Intended task
The training target is all-tested-pairs cross-disorder association prediction:
- take the fixed SNP panel used in the graph artifact
- collect every tested SNP-disorder pair on that panel from the harmonized dataset
- label pairs as positive if
sig_tier ∈ {suggestive, gws}
- label pairs as negative if
sig_tier == null
- train the graph model to distinguish non-null from null tested pairs across all 11 disorders
Held-out GWS edges are removed from message passing so the graph encoder does not see the target edge directly.
Data provenance
The checkpoint was trained on:
The harmonized dataset was derived from public OpenMed / PGC Hugging Face repositories, including:
Scope
The modeled disorder panel contains 11 disorder groups:
- ADHD
- Anxiety
- Autism
- Bipolar disorder
- Borderline personality disorder
- Eating disorders
- Major depressive disorder
- Obsessive-compulsive disorder
- Post-traumatic stress disorder
- Schizophrenia
- Substance use
This evaluation covers all 11 disorders.
Architecture
The encoder is a heterogeneous GraphSAGE-style architecture over:
- SNP nodes
- gene nodes
- disorder nodes
This release uses:
- hidden dimension:
128
- layers:
2
- dropout:
0.15
Decoder heads:
- bilinear SNP-disorder link decoder for binary classification
- auxiliary effect-size regression head for non-null edges
No disorder-disorder edges are used in the graph for this release.
Training configuration
Best hyperparameters:
- hidden dimension:
128
- layers:
2
- dropout:
0.15
- learning rate:
5e-4
- weight decay:
1e-5
Checkpoint metadata:
- SNP feature dimension:
7
- gene feature dimension:
4
- disorder feature dimension:
5
The positive class is defined as suggestive ∪ gws, so this model is trained as a binary tested-pair classifier rather than an ordinal multi-tier model.
Graph context
Graph metadata for this release:
- variants:
18,979
- genes:
1,205
- disorders:
11
- SNP-disorder edges:
22,687
- SNP-gene edges:
65,634
- disorder-disorder edges:
0
- GWS threshold for graph construction:
5e-8
- SNP-gene positional window:
100,000 bp
Evaluation
Primary all-tested-pairs benchmark:
- test AUROC:
0.9817
- test AP:
0.9276
- macro AUROC:
0.9814
- macro AP:
0.8647
- effect-size Pearson r on non-null test edges:
0.9883
- best validation AP:
0.9223
Per-disorder results:
| Disorder | AUROC | AP | Test pairs | Positive test pairs |
|---|
| ADHD | 0.9860 | 0.9109 | 2188 | 239 |
| Anxiety | 0.9665 | 0.9250 | 2146 | 632 |
| Autism | 0.9978 | 0.9043 | 2473 | 53 |
| Bipolar | 0.9605 | 0.9309 | 2240 | 675 |
| BPD | 0.9830 | 0.6608 | 1921 | 49 |
| Eating disorders | 0.9985 | 0.8026 | 2483 | 4 |
| MDD | 0.9754 | 0.8904 | 2569 | 336 |
| OCD | 0.9427 | 0.6659 | 2148 | 80 |
| PTSD | 0.9998 | 0.8333 | 2491 | 2 |
| Schizophrenia | 0.9866 | 0.9957 | 2732 | 2086 |
| Substance use | 0.9982 | 0.9916 | 679 | 100 |
Some disorders still have very small positive test counts, so their AP values should be interpreted cautiously.
Baseline comparison
| Baseline | Test AUROC | Test AP |
|---|
| Disorder prevalence | 0.8852 | 0.6022 |
| Variant prevalence | 0.3740 | 0.1616 |
| Additive prior | 0.8170 | 0.5460 |
| Low-rank SVD | 0.5099 | 0.2408 |
Class balance on the graph SNP panel
- ADHD:
1,428 gws, 168 suggestive, 12,994 null
- Anxiety:
2,729 gws, 1,486 suggestive, 10,097 null
- Autism:
93 gws, 262 suggestive, 16,138 null
- Bipolar:
3,091 gws, 1,412 suggestive, 10,437 null
- BPD:
135 gws, 193 suggestive, 12,484 null
- Eating disorders:
7 gws, 25 suggestive, 16,533 null
- MDD:
1,019 gws, 1,225 suggestive, 14,888 null
- OCD:
35 gws, 501 suggestive, 13,793 null
- PTSD:
15 gws, 16,599 null
- Schizophrenia:
13,474 gws, 436 suggestive, 4,307 null
- Substance use:
661 gws, 11 suggestive, 3,862 null
Inputs and outputs
Inputs
The checkpoint expects:
- SNP feature matrix
- gene feature matrix
- disorder feature matrix
- SNP-gene edge index
- SNP-disorder edge index
- variant and disorder mappings
These are provided by the associated public graph artifact.
Outputs
For a scored (variant, disorder) pair, the model produces:
- a binary link score for
non-null vs null
- an auxiliary effect-size estimate for non-null edges
The binary link score is the primary output of this release.
How to use
Minimal checkpoint loading:
1import torch
2from huggingface_hub import hf_hub_download
3
4ckpt_path = hf_hub_download(
5 "lighteternal/psychgnn-all-tested-pairs-model",
6 "model.pt",
7 repo_type="model",
8)
9checkpoint = torch.load(ckpt_path, map_location="cpu", weights_only=False)
10
11print(checkpoint["hyperparams"])
12print(checkpoint["feature_dims"])
13print(checkpoint["report"]["all_tested_split"]["macro_ap"])
To run inference, instantiate a heterogeneous GraphSAGE-style model matching the architecture above, load the checkpoint state dict, and score variant-disorder pairs against
lighteternal/psychgnn-psychiatric-graph.
Files in this repository
model.ptevaluation_report.json
Limitations
- Positive class combines suggestive and genome-wide significant associations into one label.
- Several disorders have very small positive test counts even though all 11 are represented.
- The graph is built from GWS SNP-disorder edges, so encoder context is narrower than the full harmonized dataset.
- This release does not address zero-shot generalization to unseen disorders.
- The auxiliary effect head is not a causal estimate.
Appropriate use
Reasonable uses:
- broad cross-disorder variant scoring across the 11 modeled disorders
- ranking tested variant-disorder pairs for follow-up
- exploratory psychiatric genetics analysis
- comparison against simpler non-graph baselines
Inappropriate uses:
- patient-level prediction
- clinical interpretation
- screening or diagnosis
- treatment selection
