Update README
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ license: mit
|
|
| 21 |
# Model Card
|
| 22 |
|
| 23 |
[](https://protonmodel.ai/)
|
| 24 |
-
[](https://github.com/mims-harvard/PROTON)
|
| 26 |
[](https://huggingface.co/mims-harvard/PROTON)
|
| 27 |
|
|
@@ -30,6 +30,8 @@ license: mit
|
|
| 30 |
|
| 31 |
Neurological diseases are the leading global cause of disability, yet most lack disease-modifying treatments. We present PROTON, a heterogeneous graph transformer that generates testable hypotheses across molecular, organoid, and clinical systems. To evaluate PROTON, we apply it to Parkinson's disease (PD), bipolar disorder (BD), and Alzheimer's disease (AD). In PD, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons, including the insecticide endosulfan, which ranked within the top 1.29\% of predictions. *In silico* PROTON screens reproduced six genome-wide $\alpha$-synuclein experiments, including a split-ubiquitin yeast two-hybrid system (normalized enrichment score [NES] = 2.30, FDR-adjusted $p < 1 \times 10^{-4}$), an ascorbate peroxidase proximity labeling assay (NES = 2.16, FDR $< 1 \times 10^{-4}$), and a high-depth targeted exome sequencing study in 496 synucleinopathy patients (NES = 2.13, FDR $< 1 \times 10^{-4}$). In BD, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients. In AD, we evaluated PROTON predictions in health records from $n$ = 610,524 patients at Mass General Brigham, confirming that five PROTON-predicted drugs were associated with reduced seven-year dementia risk (minimum hazard ratio = 0.63, 95% CI: 0.53–0.75, $p < 1 \times 10^{-7}$). PROTON generated neurological hypotheses that were evaluated across molecular, organoid, and clinical systems, defining a path for AI-driven discovery in neurological disease.
|
| 32 |
|
|
|
|
|
|
|
| 33 |
## Training Data
|
| 34 |
|
| 35 |
PROTON was trained on NeuroKG, a heterogeneous, undirected biomedical knowledge graph contextualized to the human brain. NeuroKG unifies 36 human datasets and ontologies, and integrates single-nucleus RNA-sequencing atlases comprising 3,756,702 cells from the adult human brain. The knowledge graph contains 147,020 nodes across 16 entity types and 7,366,745 edges across 47 relation types. NeuroKG is available via Harvard Dataverse at DOI: [10.7910/DVN/ZDLS3K](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://protonmodel.ai/).
|
|
|
|
| 21 |
# Model Card
|
| 22 |
|
| 23 |
[](https://protonmodel.ai/)
|
| 24 |
+
[](https://arxiv.org)
|
| 25 |
[](https://github.com/mims-harvard/PROTON)
|
| 26 |
[](https://huggingface.co/mims-harvard/PROTON)
|
| 27 |
|
|
|
|
| 30 |
|
| 31 |
Neurological diseases are the leading global cause of disability, yet most lack disease-modifying treatments. We present PROTON, a heterogeneous graph transformer that generates testable hypotheses across molecular, organoid, and clinical systems. To evaluate PROTON, we apply it to Parkinson's disease (PD), bipolar disorder (BD), and Alzheimer's disease (AD). In PD, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons, including the insecticide endosulfan, which ranked within the top 1.29\% of predictions. *In silico* PROTON screens reproduced six genome-wide $\alpha$-synuclein experiments, including a split-ubiquitin yeast two-hybrid system (normalized enrichment score [NES] = 2.30, FDR-adjusted $p < 1 \times 10^{-4}$), an ascorbate peroxidase proximity labeling assay (NES = 2.16, FDR $< 1 \times 10^{-4}$), and a high-depth targeted exome sequencing study in 496 synucleinopathy patients (NES = 2.13, FDR $< 1 \times 10^{-4}$). In BD, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients. In AD, we evaluated PROTON predictions in health records from $n$ = 610,524 patients at Mass General Brigham, confirming that five PROTON-predicted drugs were associated with reduced seven-year dementia risk (minimum hazard ratio = 0.63, 95% CI: 0.53–0.75, $p < 1 \times 10^{-7}$). PROTON generated neurological hypotheses that were evaluated across molecular, organoid, and clinical systems, defining a path for AI-driven discovery in neurological disease.
|
| 32 |
|
| 33 |
+
|
| 34 |
+
|
| 35 |
## Training Data
|
| 36 |
|
| 37 |
PROTON was trained on NeuroKG, a heterogeneous, undirected biomedical knowledge graph contextualized to the human brain. NeuroKG unifies 36 human datasets and ontologies, and integrates single-nucleus RNA-sequencing atlases comprising 3,756,702 cells from the adult human brain. The knowledge graph contains 147,020 nodes across 16 entity types and 7,366,745 edges across 47 relation types. NeuroKG is available via Harvard Dataverse at DOI: [10.7910/DVN/ZDLS3K](https://doi.org/10.7910/DVN/ZDLS3K). For more details, please refer to our [project website](https://protonmodel.ai/).
|