|
|
--- |
|
|
library_name: sklearn |
|
|
tags: |
|
|
- sklearn |
|
|
- skops |
|
|
- tabular-classification |
|
|
model_format: skops |
|
|
model_file: classifier.skops |
|
|
widget: |
|
|
- structuredData: |
|
|
credibleSetConfidence: |
|
|
- 0.75 |
|
|
- 0.75 |
|
|
- 0.25 |
|
|
distanceFootprintMean: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 0.9948455095291138 |
|
|
distanceFootprintMeanNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
distanceSentinelFootprint: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 0.9999213218688965 |
|
|
distanceSentinelFootprintNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
distanceSentinelTss: |
|
|
- 0.9982281923294067 |
|
|
- 0.9999350309371948 |
|
|
- 0.9999213218688965 |
|
|
distanceSentinelTssNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
distanceTssMean: |
|
|
- 0.9982281923294067 |
|
|
- 0.9999350309371948 |
|
|
- 0.9947366714477539 |
|
|
distanceTssMeanNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
eQtlColocClppMaximum: |
|
|
- 0.949999988079071 |
|
|
- 0.0 |
|
|
- 0.06608512997627258 |
|
|
eQtlColocClppMaximumNeighbourhood: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
eQtlColocH4Maximum: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 0.0 |
|
|
eQtlColocH4MaximumNeighbourhood: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 0.0 |
|
|
geneCount500kb: |
|
|
- 20.0 |
|
|
- 15.0 |
|
|
- 8.0 |
|
|
geneId: |
|
|
- ENSG00000087237 |
|
|
- ENSG00000169174 |
|
|
- ENSG00000084674 |
|
|
goldStandardSet: |
|
|
- 1 |
|
|
- 1 |
|
|
- 1 |
|
|
pQtlColocClppMaximum: |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
pQtlColocClppMaximumNeighbourhood: |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
pQtlColocH4Maximum: |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
pQtlColocH4MaximumNeighbourhood: |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
proteinGeneCount500kb: |
|
|
- 8.0 |
|
|
- 7.0 |
|
|
- 3.0 |
|
|
sQtlColocClppMaximum: |
|
|
- 0.949999988079071 |
|
|
- 0.0 |
|
|
- 0.21970131993293762 |
|
|
sQtlColocClppMaximumNeighbourhood: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 1.0 |
|
|
sQtlColocH4Maximum: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 0.0 |
|
|
sQtlColocH4MaximumNeighbourhood: |
|
|
- 1.0 |
|
|
- 0.0 |
|
|
- 0.0 |
|
|
studyLocusId: |
|
|
- 005bc8624f8dd7f7c7bc63e651e9e59d |
|
|
- 02c442ea4fa5ab80586a6d1ff6afa843 |
|
|
- 235e8ce166619f33e27582fff5bc0c94 |
|
|
vepMaximum: |
|
|
- 0.33000001311302185 |
|
|
- 0.6600000262260437 |
|
|
- 0.6600000262260437 |
|
|
vepMaximumNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
vepMean: |
|
|
- 0.33000001311302185 |
|
|
- 0.6600000262260437 |
|
|
- 0.0039977929554879665 |
|
|
vepMeanNeighbourhood: |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
- 1.0 |
|
|
--- |
|
|
|
|
|
# Model description |
|
|
|
|
|
The locus-to-gene (L2G) model derives features to prioritise likely causal genes at each GWAS locus based on genetic and functional genomics features. The main categories of predictive features are: |
|
|
|
|
|
- Distance: (from credible set variants to gene) |
|
|
- Molecular QTL Colocalization |
|
|
- Variant Pathogenicity: (from VEP) |
|
|
|
|
|
More information at: https://opentargets.github.io/gentropy/python_api/methods/l2g/_l2g/ |
|
|
|
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
[More Information Needed] |
|
|
|
|
|
## Training Procedure |
|
|
|
|
|
Gradient Boosting Classifier |
|
|
|
|
|
### Hyperparameters |
|
|
|
|
|
<details> |
|
|
<summary> Click to expand </summary> |
|
|
|
|
|
| Hyperparameter | Value | |
|
|
|-------------------------|-----------------| |
|
|
| objective | binary:logistic | |
|
|
| base_score | | |
|
|
| booster | | |
|
|
| callbacks | | |
|
|
| colsample_bylevel | | |
|
|
| colsample_bynode | | |
|
|
| colsample_bytree | 0.8 | |
|
|
| device | | |
|
|
| early_stopping_rounds | | |
|
|
| enable_categorical | False | |
|
|
| eval_metric | aucpr | |
|
|
| feature_types | | |
|
|
| feature_weights | | |
|
|
| gamma | | |
|
|
| grow_policy | | |
|
|
| importance_type | | |
|
|
| interaction_constraints | | |
|
|
| learning_rate | | |
|
|
| max_bin | | |
|
|
| max_cat_threshold | | |
|
|
| max_cat_to_onehot | | |
|
|
| max_delta_step | | |
|
|
| max_depth | 5 | |
|
|
| max_leaves | | |
|
|
| min_child_weight | 10 | |
|
|
| missing | nan | |
|
|
| monotone_constraints | | |
|
|
| multi_strategy | | |
|
|
| n_estimators | | |
|
|
| n_jobs | | |
|
|
| num_parallel_tree | | |
|
|
| random_state | 777 | |
|
|
| reg_alpha | 1 | |
|
|
| reg_lambda | 1.0 | |
|
|
| sampling_method | | |
|
|
| scale_pos_weight | 0.8 | |
|
|
| subsample | 0.8 | |
|
|
| tree_method | | |
|
|
| validate_parameters | | |
|
|
| verbosity | | |
|
|
| eta | 0.05 | |
|
|
|
|
|
</details> |
|
|
|
|
|
# How to Get Started with the Model |
|
|
|
|
|
To use the model, you can load it using the `LocusToGeneModel.load_from_hub` method. This will return a `LocusToGeneModel` object that can be used to make predictions on a feature matrix. |
|
|
The model can then be used to make predictions using the `predict` method. |
|
|
|
|
|
More information can be found at: https://opentargets.github.io/gentropy/python_api/methods/l2g/model/ |
|
|
|
|
|
|
|
|
# Citation |
|
|
|
|
|
https://doi.org/10.1038/s41588-021-00945-5 |
|
|
|
|
|
# License |
|
|
|
|
|
MIT |
|
|
|
