Merge commits from main into reviews

eval/zero_shot_classification.py

@@ -1,5 +1,5 @@
 """zero_shot_classification.py evaluates the performance of a pre-trained model
-on an unseen dataset without fine-tuning."""
+at classifying an unseen dataset without fine-tuning."""
 import string
 import random
 from collections import defaultdict
@@ -11,11 +11,18 @@
 import scanpy as sc
 import anndata as ad
 from evaluation_utils import prep_for_evaluation
-from zero_shot_model_evaluators import SSLZeroShotEvaluator, SCVIZeroShotEvaluator
-from zero_shot_model_evaluators import GeneformerZeroShotEvaluator
+
+
 from zero_shot_model_evaluators import VariableGeneZeroShotEvaluator
 from zero_shot_model_evaluators import PrincipalComponentsZeroShotEvaluator
-from model_loaders import load_scvi_model, load_ssl_model
+
+from zero_shot_model_evaluators import SCVIZeroShotEvaluator
+from zero_shot_model_evaluators import SSLZeroShotEvaluator
+from zero_shot_model_evaluators import GeneformerZeroShotEvaluator
+from zero_shot_model_evaluators import PretrainedPrincipalComponentsZeroShotEvaluator
+
+
+from model_loaders import load_scvi_model, load_ssl_model, load_pca_model
 from model_loaders import load_geneformer_model, get_ssl_checkpoint_file
 
 
@@ -59,9 +66,12 @@ def get_classification_metrics_df(train_adata,
         random_string = ''.join(random.choices(
             string.ascii_uppercase + string.digits, k=10))
         tmp_output_dir = Path(
-            f"tmp_zero_shot_integration_geneformer_{random_string}")
+            f"tmp_zero_shot_classification_geneformer_{random_string}")
         zero_shot_evaluator = GeneformerZeroShotEvaluator(
             geneformer_model, var_file, dict_dir, tmp_output_dir)
+    elif method == "PretrainedPCA": # todo test this
+        pca_model = load_pca_model(downsampling_method, percentage, seed, model_directory)
+        zero_shot_evaluator = PretrainedPrincipalComponentsZeroShotEvaluator(pca_model)
 
     classification_metrics = zero_shot_evaluator.evaluate_classification(
         train_adata, test_adata, cell_type_col)
@@ -128,7 +138,7 @@ def main():
 
     new_adata = prep_for_evaluation(adata, formatted_h5ad_file, var_file)
 
-    if method == "SSL":
+    if method == "SSL" or method == "PretrainedPCA":
         print("processing anndata")
         sc.pp.normalize_per_cell(new_adata, counts_per_cell_after=1e4)
         sc.pp.log1p(new_adata)

eval/zero_shot_integration.py

@@ -16,8 +16,11 @@
 from zero_shot_model_evaluators import VariableGeneZeroShotEvaluator
 from zero_shot_model_evaluators import PrincipalComponentsZeroShotEvaluator
 
-from zero_shot_model_evaluators import SSLZeroShotEvaluator, SCVIZeroShotEvaluator
+from zero_shot_model_evaluators import SCVIZeroShotEvaluator
+from zero_shot_model_evaluators import SSLZeroShotEvaluator
 from zero_shot_model_evaluators import GeneformerZeroShotEvaluator
+from zero_shot_model_evaluators import PretrainedPrincipalComponentsZeroShotEvaluator
+
 
 from evaluation_utils import prep_for_evaluation
 
@@ -61,6 +64,9 @@ def get_scib_metrics_df(adata,
             f"tmp_zero_shot_integration_geneformer_{random_string}")
         zero_shot_evaluator = GeneformerZeroShotEvaluator(
             geneformer_model, var_file, dict_dir, tmp_output_dir)
+    elif method == "PretrainedPCA": # todo test this
+        pca_model = load_pca_model(downsampling_method, percentage, seed, model_directory)
+        zero_shot_evaluator = PretrainedPrincipalComponentsZeroShotEvaluator(pca_model)
 
     scib_metrics = zero_shot_evaluator.evaluate_integration(
         adata, batch_col=batch_col, label_col=label_col)

eval/zero_shot_model_evaluators.py

@@ -193,7 +193,7 @@ def __init__(self, model):
         self.embedding_name = "X_Pretrained_PCA"
         self.model = model
     def get_embeddings(self, adata):
-        return adata.X @ model
+        return adata.X @ self.model
 
 
 class SSLZeroShotEvaluator(ZeroShotEvaluator):

requirements.txt

@@ -19,7 +19,7 @@ betterproto==1.2.5
 biothings-client==0.3.1
 bleach==6.1.0
 blosc2==2.5.1
-certifi==2024.2.2
+certifi==2024.7.4
 cffi==1.16.0
 charset-normalizer==3.3.2
 chex==0.1.86
@@ -88,7 +88,7 @@ isoduration==20.11.0
 jax==0.4.28
 jaxlib==0.4.28
 jedi==0.19.1
-Jinja2==3.1.3
+Jinja2==3.1.6
 joblib==1.4.2
 json5==0.9.25
 jsonpointer==2.4
@@ -141,7 +141,7 @@ ndindex==1.8
 nest-asyncio==1.6.0
 networkx==3.4.2
 ninja==1.11.1.1
-notebook==7.1.3
+notebook==7.2.2
 notebook_shim==0.2.4
 npy-append-array==0.9.16
 numba==0.59.1
@@ -212,7 +212,7 @@ pyro-api==0.1.2
 pyro-ppl==1.9.0
 python-dateutil==2.9.0.post0
 python-json-logger==2.0.7
-pytorch-lightning==2.2.4
+pytorch-lightning==2.4.0
 pytorch-tabnet==4.1.0
 pytz==2024.2
 pyudorandom==1.0.0
@@ -221,11 +221,11 @@ pyzmq==26.0.3
 qtconsole==5.5.2
 QtPy==2.4.1
 rapids-dask-dependency==24.2.0
-ray==2.10.0
+ray==2.43.0
 rdkit==2023.9.6
 referencing==0.34.0
 regex==2023.12.25
-requests==2.31.0
+requests==2.32.4
 rfc3339-validator==0.1.4
 rfc3986-validator==0.1.1
 rich==13.7.1
@@ -276,7 +276,7 @@ torchvision==0.15.2
 tornado==6.4
 tqdm==4.66.5
 traitlets==5.14.3
-transformers==4.39.2
+transformers==4.48.0
 triton==2.0.0
 types-python-dateutil==2.9.0.20240316
 typing_extensions==4.10.0