tpcav 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

tpcav/cavs.py

@@ -205,8 +205,8 @@ class CavTrainer:
                     c, num_samples=num_samples
                 )
                 fscore, weight = _train(
-                    concept_embeddings,
-                    self.control_embeddings,
+                    concept_embeddings.cpu(),
+                    self.control_embeddings.cpu(),
                     Path(output_dir) / c.name,
                     self.penalty,
                 )
@@ -223,8 +223,8 @@ class CavTrainer:
                 res = pool.apply_async(
                     _train,
                     args=(
-                        concept_embeddings,
-                        self.control_embeddings,
+                        concept_embeddings.cpu(),
+                        self.control_embeddings.cpu(),
                         Path(output_dir) / c.name,
                         self.penalty,
                     ),
@@ -409,8 +409,12 @@ def run_tpcav(
     output_dir: str = "tpcav/",
     num_samples_for_pca=10,
     num_samples_for_cav=1000,
+    input_window_length=1024,
+    batch_size=8,
     bws=None,
     input_transform_func=helper.fasta_chrom_to_one_hot_seq,
+    fit_pca=True,
+    p=4
 ):
     """
     One-stop function to compute CAVs on motif concepts and bed concepts, compute AUC of motif concept f-scores after correction
@@ -427,12 +431,12 @@ def run_tpcav(
     for nm in num_motif_insertions:
         builder = ConceptBuilder(
             genome_fasta=genome_fasta,
-            input_window_length=1024,
+            input_window_length=input_window_length,
             bws=bws,
             num_motifs=nm,
             include_reverse_complement=True,
             min_samples=num_samples_for_cav,
-            batch_size=8,
+            batch_size=batch_size,
         )
         # use random regions as control
         builder.build_control()
@@ -449,12 +453,12 @@ def run_tpcav(
     if bed_seq_file is not None or bed_chrom_file is not None:
         bed_builder = ConceptBuilder(
             genome_fasta=genome_fasta,
-            input_window_length=1024,
+            input_window_length=input_window_length,
             bws=bws,
             num_motifs=0,
             include_reverse_complement=True,
             min_samples=num_samples_for_cav,
-            batch_size=8,
+            batch_size=batch_size,
         )
         # use random regions as control
         bed_builder.build_control()
@@ -472,11 +476,12 @@ def run_tpcav(
     # create TPCAV model on top of the given model
     tpcav_model = TPCAV(model, layer_name=layer_name)
     # fit PCA on sampled all concept activations of the last builder (should have the most motifs)
-    tpcav_model.fit_pca(
-        concepts=motif_concept_builders[-1].all_concepts() + bed_builder.concepts if  bed_builder is not None else motif_concept_builders[-1].all_concepts(),
-        num_samples_per_concept=num_samples_for_pca,
-        num_pc="full",
-    )
+    if fit_pca:
+        tpcav_model.fit_pca(
+            concepts=motif_concept_builders[-1].all_concepts() + bed_builder.concepts if  bed_builder is not None else motif_concept_builders[-1].all_concepts(),
+            num_samples_per_concept=num_samples_for_pca,
+            num_pc="full",
+        )
     #torch.save(tpcav_model, output_path / "tpcav_model.pt")
 
     # create trainer for computing CAVs
@@ -493,7 +498,7 @@ def run_tpcav(
                 [motif_concept,],
                 num_samples_for_cav,
                 output_dir=str(output_path / f"cavs_{nm}_motifs/"),
-                num_processes=4,
+                num_processes=p,
             )
         motif_cav_trainers[nm] = cav_trainer
     if bed_builder is not None:
@@ -505,7 +510,7 @@ def run_tpcav(
             bed_builder.concepts,
             num_samples_for_cav,
             output_dir=str(output_path / f"cavs_bed_concepts/"),
-            num_processes=4,
+            num_processes=p,
         )
     else:
         bed_cav_trainer = None

tpcav/tpcav_model.py

@@ -140,7 +140,7 @@ class TPCAV(torch.nn.Module):
         residual, projected = self.project_activations(avs)
         if projected is not None:
             return torch.cat((projected, residual), dim=1)
-        return residual
+        return residual.detach()
 
     def forward_from_embeddings_at_layer(
         self,

{tpcav-0.2.0.dist-info → tpcav-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tpcav
-Version: 0.2.0
+Version: 0.2.2
 Summary: Testing with PCA projected Concept Activation Vectors
 Author-email: Jianyu Yang <yztxwd@gmail.com>
 License-Expression: MIT AND (Apache-2.0 OR BSD-2-Clause)

tpcav-0.2.2.dist-info/RECORD

@@ -0,0 +1,12 @@
+tpcav/__init__.py,sha256=CpHijSyE1HMy8dlvdSaYrwN9gYMGDEJGDdsneNWnqdA,996
+tpcav/cavs.py,sha256=m4Uhur5LwxdDfSpcznjoKCeqg4-UFjDEicpNglQ_7ss,19377
+tpcav/concepts.py,sha256=_ht4UTu2EVJh52JGnKT3PEgDHk4Q-JCpNuHfFOVmzCw,12884
+tpcav/helper.py,sha256=CcNFJEFG00pujUrthBoMInpIBz1mWIG3y5fztaiHO-c,9917
+tpcav/logging_utils.py,sha256=wug7O_5IjxjhOpQr-aq90qKMEUp1EgcPkrv26d8li6Q,281
+tpcav/tpcav_model.py,sha256=N6YmwqeBR8-QVxkV2uoqhYb3WGGMXo0ND6N8V3dIYug,16573
+tpcav/utils.py,sha256=s2TfC-YoH_xa73WuMqvtpuqzx6g3ne12hE90Yg9hToY,21502
+tpcav-0.2.2.dist-info/licenses/LICENSE,sha256=uC-2s0ObLnQzWFKH5aokHXo6CzxlJgeI0P3bIUCZgfU,1064
+tpcav-0.2.2.dist-info/METADATA,sha256=lnI4YDN09v7vOcrc5a1qKfb_t-XNuKjRb31a1yILioY,3502
+tpcav-0.2.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+tpcav-0.2.2.dist-info/top_level.txt,sha256=I9veSE_WsuFYrXlcfRevqtatDyWWZNsWA3dV0CeBXVg,6
+tpcav-0.2.2.dist-info/RECORD,,

tpcav-0.2.0.dist-info/RECORD

@@ -1,12 +0,0 @@
-tpcav/__init__.py,sha256=CpHijSyE1HMy8dlvdSaYrwN9gYMGDEJGDdsneNWnqdA,996
-tpcav/cavs.py,sha256=lqw-V45FCiCNUC8w7payuSPsbMBFy_qcOZaqPGA68js,19195
-tpcav/concepts.py,sha256=_ht4UTu2EVJh52JGnKT3PEgDHk4Q-JCpNuHfFOVmzCw,12884
-tpcav/helper.py,sha256=CcNFJEFG00pujUrthBoMInpIBz1mWIG3y5fztaiHO-c,9917
-tpcav/logging_utils.py,sha256=wug7O_5IjxjhOpQr-aq90qKMEUp1EgcPkrv26d8li6Q,281
-tpcav/tpcav_model.py,sha256=XgNLPXr6_B-Dyb7RdgsUsFnrSK6oNjqqFPOjpz1wXmM,16564
-tpcav/utils.py,sha256=s2TfC-YoH_xa73WuMqvtpuqzx6g3ne12hE90Yg9hToY,21502
-tpcav-0.2.0.dist-info/licenses/LICENSE,sha256=uC-2s0ObLnQzWFKH5aokHXo6CzxlJgeI0P3bIUCZgfU,1064
-tpcav-0.2.0.dist-info/METADATA,sha256=tz5MWTr_-veczwEOPDGUzLEwy3XU9WLlSw4IPOzddc0,3502
-tpcav-0.2.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-tpcav-0.2.0.dist-info/top_level.txt,sha256=I9veSE_WsuFYrXlcfRevqtatDyWWZNsWA3dV0CeBXVg,6
-tpcav-0.2.0.dist-info/RECORD,,