Commit
•
66fb4bf
1
Parent(s):
9c77234
chore: update model
Browse files- README.md +113 -10
- l2g_model_1006.pkl +1 -1
README.md
CHANGED
|
@@ -1,15 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
# Model description
|
| 3 |
|
| 4 |
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:
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
|
| 11 |
-
|
| 12 |
-
|
| 13 |
|
| 14 |
## Intended uses & limitations
|
| 15 |
|
|
@@ -52,10 +155,10 @@ Gradient Boosting Classifier
|
|
| 52 |
# How to Get Started with the Model
|
| 53 |
|
| 54 |
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.
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
|
| 60 |
# Citation
|
| 61 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: sklearn
|
| 3 |
+
tags:
|
| 4 |
+
- sklearn
|
| 5 |
+
- skops
|
| 6 |
+
- tabular-classification
|
| 7 |
+
model_format: pickle
|
| 8 |
+
model_file: l2g_model_1006.pkl
|
| 9 |
+
widget:
|
| 10 |
+
- structuredData:
|
| 11 |
+
distanceTssMean:
|
| 12 |
+
- 0.1378757804632187
|
| 13 |
+
- 0.004574988503009081
|
| 14 |
+
- 0.01267080195248127
|
| 15 |
+
distanceTssMinimum:
|
| 16 |
+
- 0.02554949000477791
|
| 17 |
+
- 9.566087828716263e-05
|
| 18 |
+
- 0.00206877407617867
|
| 19 |
+
eqtlColocClppMaximum:
|
| 20 |
+
- 0.0
|
| 21 |
+
- 0.0
|
| 22 |
+
- 0.0
|
| 23 |
+
eqtlColocClppMaximumNeighborhood:
|
| 24 |
+
- 0.0
|
| 25 |
+
- 0.0
|
| 26 |
+
- 0.0
|
| 27 |
+
eqtlColocLlrMaximum:
|
| 28 |
+
- 0.0
|
| 29 |
+
- 0.0
|
| 30 |
+
- 0.0
|
| 31 |
+
eqtlColocLlrMaximumNeighborhood:
|
| 32 |
+
- 0.0
|
| 33 |
+
- 0.0
|
| 34 |
+
- 0.0
|
| 35 |
+
pqtlColocClppMaximum:
|
| 36 |
+
- 0.0
|
| 37 |
+
- 0.0
|
| 38 |
+
- 0.0
|
| 39 |
+
pqtlColocClppMaximumNeighborhood:
|
| 40 |
+
- 0.0
|
| 41 |
+
- 0.0
|
| 42 |
+
- 0.0
|
| 43 |
+
pqtlColocLlrMaximum:
|
| 44 |
+
- 0.0
|
| 45 |
+
- 0.0
|
| 46 |
+
- 0.0
|
| 47 |
+
pqtlColocLlrMaximumNeighborhood:
|
| 48 |
+
- 0.0
|
| 49 |
+
- 0.0
|
| 50 |
+
- 0.0
|
| 51 |
+
sqtlColocClppMaximum:
|
| 52 |
+
- 0.0
|
| 53 |
+
- 0.0
|
| 54 |
+
- 0.0
|
| 55 |
+
sqtlColocClppMaximumNeighborhood:
|
| 56 |
+
- 0.0
|
| 57 |
+
- 0.0
|
| 58 |
+
- 0.0
|
| 59 |
+
sqtlColocLlrMaximum:
|
| 60 |
+
- 0.0
|
| 61 |
+
- 0.0
|
| 62 |
+
- 0.0
|
| 63 |
+
sqtlColocLlrMaximumNeighborhood:
|
| 64 |
+
- 0.0
|
| 65 |
+
- 0.0
|
| 66 |
+
- 0.0
|
| 67 |
+
studyLocusId:
|
| 68 |
+
- -6454334657549107000
|
| 69 |
+
- 6087706114048421000
|
| 70 |
+
- -744015116205320800
|
| 71 |
+
tuqtlColocClppMaximum:
|
| 72 |
+
- 0.0
|
| 73 |
+
- 0.0
|
| 74 |
+
- 0.0
|
| 75 |
+
tuqtlColocClppMaximumNeighborhood:
|
| 76 |
+
- 0.0
|
| 77 |
+
- 0.0
|
| 78 |
+
- 0.0
|
| 79 |
+
tuqtlColocLlrMaximum:
|
| 80 |
+
- 0.0
|
| 81 |
+
- 0.0
|
| 82 |
+
- 0.0
|
| 83 |
+
tuqtlColocLlrMaximumNeighborhood:
|
| 84 |
+
- 0.0
|
| 85 |
+
- 0.0
|
| 86 |
+
- 0.0
|
| 87 |
+
vepMaximum:
|
| 88 |
+
- 0.0
|
| 89 |
+
- 0.0
|
| 90 |
+
- 0.0
|
| 91 |
+
vepMaximumNeighborhood:
|
| 92 |
+
- 0.0
|
| 93 |
+
- 0.0
|
| 94 |
+
- 0.0
|
| 95 |
+
vepMean:
|
| 96 |
+
- 0.0
|
| 97 |
+
- 0.0
|
| 98 |
+
- 0.0
|
| 99 |
+
vepMeanNeighborhood:
|
| 100 |
+
- 0.0
|
| 101 |
+
- 0.0
|
| 102 |
+
- 0.0
|
| 103 |
+
---
|
| 104 |
|
| 105 |
# Model description
|
| 106 |
|
| 107 |
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:
|
| 108 |
|
| 109 |
+
- Distance: (from credible set variants to gene)
|
| 110 |
+
- Molecular QTL Colocalization
|
| 111 |
+
- Chromatin Interaction: (e.g., promoter-capture Hi-C)
|
| 112 |
+
- Variant Pathogenicity: (from VEP)
|
| 113 |
|
| 114 |
+
More information at: https://opentargets.github.io/gentropy/python_api/methods/l2g/_l2g/
|
| 115 |
+
|
| 116 |
|
| 117 |
## Intended uses & limitations
|
| 118 |
|
|
|
|
| 155 |
# How to Get Started with the Model
|
| 156 |
|
| 157 |
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.
|
| 158 |
+
The model can then be used to make predictions using the `predict` method.
|
| 159 |
+
|
| 160 |
+
More information can be found at: https://opentargets.github.io/gentropy/python_api/methods/l2g/model/
|
| 161 |
+
|
| 162 |
|
| 163 |
# Citation
|
| 164 |
|
l2g_model_1006.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2796518
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f4889d855574c1f2db1b64e09a322c8f30374df432b8faa780a98a8bf487158
|
| 3 |
size 2796518
|