Instructions to use opentargets/locus_to_gene_26.06.0-dev2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use opentargets/locus_to_gene_26.06.0-dev2 with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("opentargets/locus_to_gene_26.06.0-dev2", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
chore: update model base model for 26.06.0-dev2 run
Browse files- .gitattributes +1 -0
- README.md +70 -0
- classifier.skops +3 -0
- config.json +42 -0
- requirements.txt +2 -0
- test.parquet +3 -0
- train.parquet +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
classifier.skops filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
library_name: sklearn
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- sklearn
|
| 7 |
+
- tabular-classification
|
| 8 |
+
- genomics
|
| 9 |
+
- gwas
|
| 10 |
+
- gene-prioritization
|
| 11 |
+
---
|
| 12 |
+
# Locus-to-Gene (L2G) Model
|
| 13 |
+
|
| 14 |
+
The locus-to-gene (L2G) model prioritises likely causal genes at each GWAS locus based on genetic and functional genomics features.
|
| 15 |
+
|
| 16 |
+
## Model Description
|
| 17 |
+
|
| 18 |
+
This is a **Gradient Boosting Classifier** (XGBoost) trained to predict causal genes at GWAS loci.
|
| 19 |
+
|
| 20 |
+
Limited to protein-coding genes with available feature data.
|
| 21 |
+
|
| 22 |
+
**Key Features:**
|
| 23 |
+
- **Distance**: proximity from credible set variants to gene
|
| 24 |
+
- **Molecular QTL Colocalization**: evidence from expression/protein QTL studies
|
| 25 |
+
- **Variant Pathogenicity**: VEP (Variant Effect Predictor) scores
|
| 26 |
+
|
| 27 |
+
## Usage
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from gentropy.method.l2g.model import LocusToGeneModel
|
| 31 |
+
from gentropy.common.session import Session
|
| 32 |
+
|
| 33 |
+
# Load model from Hugging Face Hub
|
| 34 |
+
session = Session()
|
| 35 |
+
model = LocusToGeneModel.load_from_hub(
|
| 36 |
+
session=session,
|
| 37 |
+
hf_model_id="opentargets/locus_to_gene"
|
| 38 |
+
)
|
| 39 |
+
|
| 40 |
+
# Make predictions on your L2G feature matrix
|
| 41 |
+
predictions = model.predict(your_feature_matrix, session)
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## Training
|
| 45 |
+
|
| 46 |
+
- **Architecture**: XGBoost Gradient Boosting Classifier
|
| 47 |
+
- **Training Data**: Curated positive/negative gene-locus pairs from Open Targets
|
| 48 |
+
- **Evaluation Metric**: Area under precision-recall curve (AUCPR)
|
| 49 |
+
|
| 50 |
+
## Citation
|
| 51 |
+
|
| 52 |
+
If you use this model, please cite:
|
| 53 |
+
|
| 54 |
+
```bibtex
|
| 55 |
+
@article{ghoussaini2021open,
|
| 56 |
+
title={Open Targets Genetics: systematic identification of trait-associated genes using large-scale genetics and functional genomics},
|
| 57 |
+
author={Ghoussaini, Maya and Mountjoy, Edward and Carmona, Maria and others},
|
| 58 |
+
journal={Nature Genetics},
|
| 59 |
+
volume={53},
|
| 60 |
+
pages={1527--1533},
|
| 61 |
+
year={2021},
|
| 62 |
+
doi={10.1038/s41588-021-00945-5}
|
| 63 |
+
}
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
## More Information
|
| 67 |
+
|
| 68 |
+
- **Repository**: [opentargets/gentropy](https://github.com/opentargets/gentropy)
|
| 69 |
+
- **Documentation**: [L2G Method Docs](https://opentargets.github.io/gentropy/python_api/methods/l2g/_l2g/)
|
| 70 |
+
- **Developer**: Open Targets
|
classifier.skops
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:754b9258155d42e744486e0ae172f59fd4e188ab6e78a4189654728998dbfa5e
|
| 3 |
+
size 229078
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sklearn": {
|
| 3 |
+
"columns": [
|
| 4 |
+
"studyLocusId",
|
| 5 |
+
"geneId",
|
| 6 |
+
"goldStandardSet",
|
| 7 |
+
"eQtlColocClppMaximum",
|
| 8 |
+
"pQtlColocClppMaximum",
|
| 9 |
+
"sQtlColocClppMaximum",
|
| 10 |
+
"eQtlColocH4Maximum",
|
| 11 |
+
"pQtlColocH4Maximum",
|
| 12 |
+
"sQtlColocH4Maximum",
|
| 13 |
+
"eQtlColocClppMaximumNeighbourhood",
|
| 14 |
+
"pQtlColocClppMaximumNeighbourhood",
|
| 15 |
+
"sQtlColocClppMaximumNeighbourhood",
|
| 16 |
+
"eQtlColocH4MaximumNeighbourhood",
|
| 17 |
+
"pQtlColocH4MaximumNeighbourhood",
|
| 18 |
+
"sQtlColocH4MaximumNeighbourhood",
|
| 19 |
+
"distanceSentinelFootprint",
|
| 20 |
+
"distanceSentinelFootprintNeighbourhood",
|
| 21 |
+
"distanceFootprintMean",
|
| 22 |
+
"distanceFootprintMeanNeighbourhood",
|
| 23 |
+
"distanceTssMean",
|
| 24 |
+
"distanceTssMeanNeighbourhood",
|
| 25 |
+
"distanceSentinelTss",
|
| 26 |
+
"distanceSentinelTssNeighbourhood",
|
| 27 |
+
"vepMaximum",
|
| 28 |
+
"vepMaximumNeighbourhood",
|
| 29 |
+
"vepMean",
|
| 30 |
+
"vepMeanNeighbourhood",
|
| 31 |
+
"e2gMean",
|
| 32 |
+
"e2gMeanNeighbourhood",
|
| 33 |
+
"geneCount500kb",
|
| 34 |
+
"proteinGeneCount500kb",
|
| 35 |
+
"credibleSetConfidence",
|
| 36 |
+
"transPQtlColocH4Maximum",
|
| 37 |
+
"transPQtlColocH4MaximumNeighbourhood"
|
| 38 |
+
],
|
| 39 |
+
"sklearn_version": "1.7.2"
|
| 40 |
+
},
|
| 41 |
+
"task": "tabular-classification"
|
| 42 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
scikit-learn==1.7.2
|
| 2 |
+
skops
|
test.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f6bad02336095ebac5c87dd59f3e5daae6ff637fa3b502d6b404c0ab5e09d9
|
| 3 |
+
size 801932
|
train.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0dbeb6d1139a07de77ea8522656d780ee1f337c2eb2651c7cb8001e42b60664
|
| 3 |
+
size 4714932
|