popV version: 0.6.0
Browse files- OnClass.data-00000-of-00001 +1 -1
- OnClass.index +0 -0
- OnClass.meta +0 -0
- OnClass.npz +2 -2
- README.md +0 -56
- accuracies.json +2 -2
- celltypist.pkl +1 -1
- faiss_index.index +1 -1
- harmony_knn_classifier.index +1 -1
- metadata.json +0 -33
- minified_ref_adata.h5ad +0 -3
- popv_output/predictions.csv +0 -0
- preprocessing.json +0 -0
- pynndescent_index.joblib +0 -3
- ref_labels.csv +0 -0
- scanvi/model.pt +1 -1
- scvi/model.pt +1 -1
- scvi_knn_classifier.index +1 -1
- svm_classifier.joblib +1 -1
- xgboost_classifier.model +2 -2
OnClass.data-00000-of-00001
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27239224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d7b27a347598a59e82ff7137cb77157daaa082e07e4f3b755c7d7c19222f42
|
| 3 |
size 27239224
|
OnClass.index
CHANGED
|
Binary files a/OnClass.index and b/OnClass.index differ
|
|
|
OnClass.meta
CHANGED
|
Binary files a/OnClass.meta and b/OnClass.meta differ
|
|
|
OnClass.npz
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b70e36ecee04f773a507f79263adf8f98ef55bb3e2d6a3f5918b4177e20ccd04
|
| 3 |
+
size 144112689
|
README.md
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: popV
|
| 3 |
-
license: cc-by-4.0
|
| 4 |
-
tags:
|
| 5 |
-
- biology
|
| 6 |
-
- genomics
|
| 7 |
-
- single-cell
|
| 8 |
-
- AnnData:0.12.2
|
| 9 |
-
- scikit_learn:1.7.2
|
| 10 |
-
- organism:Homo sapiens
|
| 11 |
-
- Python:3.12.8
|
| 12 |
-
- popV:0.6.0
|
| 13 |
-
- 'tissue: diverse'
|
| 14 |
-
---
|
| 15 |
-
|
| 16 |
-
Popular Vote (popV) model for automated cell type annotation of single-cell RNA-seq data. We provide here pretrained models
|
| 17 |
-
for plug-in use in your own analysis.
|
| 18 |
-
Follow our [tutorial](https://github.com/YosefLab/popV/blob/main/tabula_sapiens_tutorial.ipynb) to learn how to use the model for cell type annotation.
|
| 19 |
-
|
| 20 |
-
# Model description
|
| 21 |
-
|
| 22 |
-
Tabula Sapiens is a benchmark, first-draft human cell atlas of over 1.1M cells from 28 organs of 24 normal human subjects. This work is the product of the Tabula Sapiens Consortium. Taking the organs from the same individual controls for genetic background, age, environment, and epigenetic effects, and allows detailed analysis and comparison of cell types that are shared between tissues.
|
| 23 |
-
|
| 24 |
-
**Link to CELLxGENE**:
|
| 25 |
-
Link to the [data](https://cellxgene.cziscience.com/e/b806712d-18b0-454c-a0fe-9909159e07c7.cxg/) in the CELLxGENE browser for interactive exploration of the data and download of the source data.
|
| 26 |
-
|
| 27 |
-
**Training Code URL**:
|
| 28 |
-
Not provided by uploader.
|
| 29 |
-
|
| 30 |
-
# Metrics
|
| 31 |
-
|
| 32 |
-
We provide here accuracies for each of the experts and the ensemble model. The validation set accuracies are
|
| 33 |
-
computed on a 10% random subset of the data that was not used for training.
|
| 34 |
-
|
| 35 |
-
| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |
|
| 36 |
-
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 37 |
-
| spermatid | 402 | 0.98 | 0.99 | 0.99 | 0.98 | 0.00 | 0.98 | 1.00 | 0.98 | 1.00 |
|
| 38 |
-
| spermatocyte | 308 | 0.97 | 0.98 | 0.98 | 0.97 | 0.00 | 0.97 | 0.99 | 0.96 | 0.99 |
|
| 39 |
-
| male germ cell | 8 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 1.00 | 1.00 | 1.00 | 1.00 |
|
| 40 |
-
| spermatogonium | 9 | 0.80 | 0.71 | 0.62 | 0.62 | 0.00 | 0.75 | 0.84 | 0.63 | 0.71 |
|
| 41 |
-
|
| 42 |
-
The train accuracies are computed on the training data.
|
| 43 |
-
|
| 44 |
-
| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |
|
| 45 |
-
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
| 46 |
-
| spermatid | 3607 | 0.98 | 0.99 | 0.99 | 0.99 | 0.00 | 0.98 | 0.99 | 0.98 | 0.99 |
|
| 47 |
-
| spermatocyte | 2762 | 0.97 | 0.99 | 0.99 | 0.98 | 0.00 | 0.97 | 0.98 | 0.97 | 0.99 |
|
| 48 |
-
| male germ cell | 108 | 0.95 | 0.99 | 0.96 | 0.96 | 0.00 | 0.96 | 1.00 | 0.98 | 0.99 |
|
| 49 |
-
| spermatogonium | 55 | 0.80 | 0.95 | 0.83 | 0.87 | 0.00 | 0.81 | 0.96 | 0.87 | 0.94 |
|
| 50 |
-
|
| 51 |
-
</details>
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
# References
|
| 55 |
-
|
| 56 |
-
Tabula Sapiens reveals transcription factor expression, senescence effects, and sex-specific features in cell types from 28 human organs and tissues, The Tabula Sapiens Consortium; bioRxiv, doi: https://doi.org/10.1101/2024.12.03.626516
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
accuracies.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"query_accuracy": "| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| spermatid |
|
| 3 |
-
"ref_accuracy": "| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| spermatid |
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"query_accuracy": "| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| spermatid | 389 | 0.98 | 0.98 | 0.99 | 0.99 | 0.00 | 0.99 | 0.99 | 0.97 | 0.99 |\n| spermatocyte | 319 | 0.97 | 0.97 | 0.98 | 0.98 | 0.00 | 0.97 | 0.98 | 0.96 | 0.98 |\n| male germ cell | 10 | 0.95 | 0.95 | 0.87 | 0.95 | 0.00 | 0.83 | 1.00 | 0.95 | 0.91 |\n| spermatogonium | 9 | 0.80 | 0.82 | 0.67 | 0.75 | 0.00 | 0.57 | 0.82 | 0.70 | 0.82 |",
|
| 3 |
+
"ref_accuracy": "| Cell Type | N cells | celltypist | knn bbknn | knn harmony | knn on scvi | onclass | scanvi | svm | xgboost | Consensus Prediction |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| spermatid | 3620 | 0.98 | 0.99 | 0.99 | 0.99 | 0.00 | 0.99 | 0.99 | 0.98 | 0.99 |\n| spermatocyte | 2751 | 0.98 | 0.99 | 0.98 | 0.98 | 0.00 | 0.98 | 0.98 | 0.97 | 0.99 |\n| male germ cell | 106 | 0.97 | 0.99 | 0.97 | 0.98 | 0.00 | 0.93 | 1.00 | 1.00 | 0.99 |\n| spermatogonium | 55 | 0.85 | 0.91 | 0.82 | 0.85 | 0.00 | 0.78 | 0.96 | 0.90 | 0.92 |"
|
| 4 |
}
|
celltypist.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 233270
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f428e8da4c3cc59267f6ac9fbb290c80645e8867171ba3cf679d6cf4e8c52264
|
| 3 |
size 233270
|
faiss_index.index
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1309645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f59bb0a8960a919af1c502266db4473de09a2c9a43e1ca46e38eacbff22c3a
|
| 3 |
size 1309645
|
harmony_knn_classifier.index
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1306445
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1059357c965d1ba044057ca2b84f2f29cd6fff982aba09b4eb262bd9c702f5c4
|
| 3 |
size 1306445
|
metadata.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"popv_version": "0.6.0",
|
| 3 |
-
"anndata_version": "0.12.2",
|
| 4 |
-
"scikit_learn_version": "1.7.2",
|
| 5 |
-
"setup_dict": {
|
| 6 |
-
"ref_labels_key": "popv_labels",
|
| 7 |
-
"ref_batch_key": "batch_key",
|
| 8 |
-
"unknown_celltype_label": "unassigned"
|
| 9 |
-
},
|
| 10 |
-
"prediction_keys": [
|
| 11 |
-
"popv_celltypist_prediction",
|
| 12 |
-
"popv_knn_bbknn_prediction",
|
| 13 |
-
"popv_knn_harmony_prediction",
|
| 14 |
-
"popv_knn_on_scvi_prediction",
|
| 15 |
-
"popv_onclass_prediction",
|
| 16 |
-
"popv_scanvi_prediction",
|
| 17 |
-
"popv_svm_prediction",
|
| 18 |
-
"popv_xgboost_prediction"
|
| 19 |
-
],
|
| 20 |
-
"method_kwargs": {},
|
| 21 |
-
"methods": [
|
| 22 |
-
"CELLTYPIST",
|
| 23 |
-
"KNN_BBKNN",
|
| 24 |
-
"KNN_HARMONY",
|
| 25 |
-
"KNN_SCVI",
|
| 26 |
-
"ONCLASS",
|
| 27 |
-
"SCANVI_POPV",
|
| 28 |
-
"Support_Vector",
|
| 29 |
-
"XGboost"
|
| 30 |
-
],
|
| 31 |
-
"cellxgene_url": "https://cellxgene.cziscience.com/e/b806712d-18b0-454c-a0fe-9909159e07c7.cxg/",
|
| 32 |
-
"organism": "Homo sapiens"
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
minified_ref_adata.h5ad
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8fd5e846f6189ed84a901082acb53e7bc6fd55806c38bc04e6c04e39ee1bc927
|
| 3 |
-
size 18859164
|
|
|
|
|
|
|
|
|
|
|
|
popv_output/predictions.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessing.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pynndescent_index.joblib
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8fdb6eee18d2def4333b46bcff537e0759bc814efcd5613767182939946764b1
|
| 3 |
-
size 5358348
|
|
|
|
|
|
|
|
|
|
|
|
ref_labels.csv
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
scanvi/model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11344629
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2f59956af272469870211b96d91a29056bddb53854479b80e2bf4bf2979ece6
|
| 3 |
size 11344629
|
scvi/model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10828742
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2740f8fadf16587fe4d5327490867f31b79e8be3985cfbd84f0b159714dccf9
|
| 3 |
size 10828742
|
scvi_knn_classifier.index
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 522605
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39bc933391075b16061cd9dae766092faaa83bfb481b7a7ba78cdc6841b63946
|
| 3 |
size 522605
|
svm_classifier.joblib
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 65376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c46db8ad4f5b0bf5014c4a0701b2d7195b3fe190ef18fabad6ac897197aa7b5
|
| 3 |
size 65376
|
xgboost_classifier.model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29cb4202398024f165cd1973110a8c3007e4808c337ef7df7ef46fbe57103fa4
|
| 3 |
+
size 927074
|