Added all lung data aside from umaps

app.py

@@ -14,8 +14,8 @@ from shiny.express import input, ui
 # Constants #
 #############
 
-all_datasets = ['MCF7', 'T47D', 'lymphoma', 'prostate_rna', 'prostate_atac']
-rna_datasets = ['MCF7', 'T47D', 'lymphoma', 'prostate_rna']
+all_datasets = ['MCF7', 'T47D', 'lymphoma', 'prostate_rna', 'prostate_atac', 'LUAD', 'LUSC']
+rna_datasets = ['MCF7', 'T47D', 'lymphoma', 'prostate_rna', 'LUAD', 'LUSC']
 atac_datasets = ['MCF7', 'T47D', 'lymphoma', 'prostate_atac']
 
 MCF7_T47D_mg_options = [
@@ -42,10 +42,18 @@ prostate_rna_mg_options = [
 prostate_atac_mg_options = [
     'ATAC - Hallmark', 'ATAC_TFIDF - Hallmark', 'GAS - Hallmark',
     "ATAC - Motifs", "ATAC_TFIDF - Motifs", "ATAC_TFIDF - Motifs",
-    "GAS - Neuronal",
-    'GAS+ATAC - Hallmark', 'GAS+ATAC_TFIDF - Hallmark', 'GAS+ATAC - Hallmark+Motifs', 'GAS+ATAC_TFIDF - Hallmark+Motifs', 'GAS+ATAC - Neuronal+Motifs'
+    'GAS+ATAC - Hallmark', 'GAS+ATAC_TFIDF - Hallmark', 'GAS+ATAC - Hallmark+Motifs', 'GAS+ATAC_TFIDF - Hallmark+Motifs'
 ]
 
+luad_rna_mg_options = [
+    'RNA - Hallmark'
+]
+
+lusc_rna_mg_options = [
+    'RNA - Hallmark'
+]
+
+
 mg_colors = {'RNA - hallmark' : "#cf1322", 'ATAC - hallmark' : "#1c13cf", 'ATAC_TFIDF - hallmark' : "#3329f0",
             'ATAC - cistrome' : "#2968f0", 'ATAC_TFIDF - cistrome' : "#437dfa",
             'ATAC - motifs' : "#6e43fa", 'ATAC_TFIDF - motifs' : "#5b3ac7",
@@ -70,7 +78,8 @@ dar_df = pd.concat([pd.read_csv(f'data/differentially_accessible_regions/{datase
 subset_groupings = np.load("data/subset_all_groupings.pkl", allow_pickle = True)
 umap_dict = np.load("data/umap_embeddings.pkl", allow_pickle = True)
 hallmark_geneset_df = pd.read_csv("data/hallmark_enrichment_selection_overlap.tsv", sep = "\t")
-GO_BP_df = pd.read_csv("data/GO_BP_geneset_enrichment.tsv", sep = "\t")
+GO_BP_df = pd.read_csv("data/geneset_enrichment.tsv", sep = "\t")
+GO_BP_df = GO_BP_df[GO_BP_df['Gene Set'] == 'GO Biological Processes RNA']
 gene_group_frequency_df = pd.read_csv("data/gene-group_distribution.tsv", sep = "\t")
 
 # Reading in dataset info
@@ -129,7 +138,7 @@ with ui.nav_panel("Overview"):
                 '''
                 # Experimental Design
 
-                Five single-cell datasets were used to evaluate the performance of scMKL and compare to other methods of single-cell analysis as shown below. 
+                Seven single-cell datasets were used to evaluate the performance of scMKL and compare to other methods of single-cell analysis as shown below. 
                 scMKL was used to predict cell labels for each data set.
                 '''
                 )
@@ -410,7 +419,7 @@ with ui.nav_panel("scMKL Performance"):
             # Data set selection
             ui.input_radio_buttons("dataset_selection_MP",
                                 "Datasets",
-                                {"MCF7": "MCF7", "T47D": "T47D", "lymphoma": "Lymphoma", "prostate_rna" : "Prostate RNA", "prostate_atac" : "Prostate ATAC"},
+                                {"MCF7": "MCF7", "T47D": "T47D", "lymphoma": "Lymphoma", "prostate_rna" : "Prostate RNA", "prostate_atac" : "Prostate ATAC", 'LUSC' : 'LUSC', 'LUAD' : 'LUAD'},
                                 selected = "MCF7"
                             )
 
@@ -448,7 +457,9 @@ with ui.nav_panel("scMKL Performance"):
                                 "T47D" : MCF7_T47D_mg_options,
                                 "lymphoma" : lymphoma_mg_options,
                                 "prostate_rna" : prostate_rna_mg_options,
-                                "prostate_atac": prostate_atac_mg_options
+                                "prostate_atac": prostate_atac_mg_options,
+                                'LUAD' : luad_rna_mg_options,
+                                'LUSC' : lusc_rna_mg_options
                                 }
 
                 user_choice = input.dataset_selection_MP()
@@ -503,6 +514,8 @@ with ui.nav_panel("Model Comparison"):
                                 {"MCF7": "MCF7",
                                 "T47D": "T47D",
                                 "lymphoma": "Lymphoma",
+                                'LUAD' : 'LUAD',
+                                'LUSC' : 'LUSC',
                                 "prostate_rna" : "Prostate_RNA",
                                 "prostate_atac" : "Prostate_ATAC"},
                                 selected = "MCF7"
@@ -554,7 +567,9 @@ with ui.nav_panel("scMKL Results"):
                                 "T47D": "T47D",
                                 "lymphoma": "Lymphoma",
                                 "prostate_rna" : "Prostate RNA",
-                                "prostate_atac" : "Prostate ATAC"},
+                                "prostate_atac" : "Prostate ATAC",
+                                'LUAD' : 'LUAD',
+                                'LUSC' : 'LUSC'},
                                 selected = "MCF7"
                             )
 
@@ -572,7 +587,9 @@ with ui.nav_panel("scMKL Results"):
                                     "T47D" : MCF7_T47D_mg_options,
                                     "lymphoma" : lymphoma_mg_options,
                                     "prostate_rna" : prostate_rna_mg_options,
-                                    "prostate_atac": prostate_atac_mg_options
+                                    "prostate_atac": prostate_atac_mg_options,
+                                    'LUAD' : luad_rna_mg_options,
+                                    'LUSC' : lusc_rna_mg_options
                                     }
 
                 ui.update_radio_buttons("modality_selections_SR",
@@ -628,9 +645,9 @@ with ui.nav_panel("scMKL Results"):
 
 
 
-# ##################
-# # scanpy Results #
-# ##################
+##################
+# scanpy Results #
+##################
 with ui.nav_panel("scanpy Results"):
 
     ui.markdown("# Single-cell Analysis with scanpy")
@@ -644,7 +661,14 @@ with ui.nav_panel("scanpy Results"):
             # Data set selection
             ui.input_radio_buttons("dataset_selection_sA",
                                 "Datasets",
-                                {"MCF7": "MCF7", "T47D": "T47D", "lymphoma": "Lymphoma", "prostate_rna" : "Prostate_RNA", "prostate_atac" : "Prostate_ATAC"},
+                                {"MCF7": "MCF7", 
+                                 "T47D": "T47D", 
+                                 "lymphoma": "Lymphoma", 
+                                 "prostate_rna" : "Prostate_RNA", 
+                                 "prostate_atac" : "Prostate_ATAC",
+                                #  'LUAD' : 'LUAD',
+                                #  'LUSC' : 'LUSC'
+                                },
                                 selected = "MCF7"
                             )
 
@@ -663,7 +687,9 @@ with ui.nav_panel("scanpy Results"):
                                     "T47D" : multimodal,
                                     "lymphoma" : multimodal,
                                     "prostate_rna" : ["RNA"],
-                                    "prostate_atac" : ["ATAC"]
+                                    "prostate_atac" : ["ATAC"],
+                                    'LUAD' : ["RNA"],
+                                    'LUSC' : ["RNA"]
                                     }
 
                 ui.update_radio_buttons("modality_selection_sA",
@@ -774,7 +800,12 @@ with ui.nav_panel("GSEApy Results"):
             '''
             )
 
-            ui.input_radio_buttons("dataset_selection_GR", "Dataset Selection", {"MCF7" : "MCF7", "T47D" : "T47D", "lymphoma" : "Lymphoma", "prostate_rna" : "Prostate_RNA"},
+            ui.input_radio_buttons("dataset_selection_GR", "Dataset Selection", {"MCF7" : "MCF7", 
+                                                                                 "T47D" : "T47D", 
+                                                                                 "lymphoma" : "Lymphoma", 
+                                                                                 "prostate_rna" : "Prostate_RNA",
+                                                                                 'LUAD' : 'LUAD',
+                                                                                 'LUSC' : 'LUSC'},
                                         selected = "MCF7"
                                     )
 

data/{figures/heatmaps/prostate_atac_GAS_neuronal_selection_heatmap.png → differentially_expressed_genes/LUAD_DEGs.tsv.gz}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c03c434bfed6f302cb5a61ccb4d6be86bddf301335a62681c1626ecb09f5e7
-size 552895
+oid sha256:15c911d68e229a2b72827cccaa86cb3825da8c36266bbddb2c8a05c6be5fc974
+size 941258

data/{figures/heatmaps/prostate_atac_GAS+ATAC_neuronal+motifs_selection_heatmap.png → differentially_expressed_genes/LUSC_DEGs.tsv.gz}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:816e8c38009c65affbe3e13db8c9ba74689d3ded0bb29b83c978128f733f1318
-size 1633608
+oid sha256:e7ff7d552476c8cae16f63024b8e636f9def91596db9b8765a09c72bfb003294
+size 839098

data/feature_selections/LUAD_feature_selections.tsv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3abf431de45082798d7162cfb44a6410a095abd035853832b1f5056edfbe9c
+size 4479

data/feature_selections/LUSC_feature_selections.tsv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b922e4d57a610a34b9961bcfe1e29e1db4cbd53a31af4f4463f98a0e7ff809
+size 3515

data/feature_selections/MCF7_feature_selections.tsv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15cd69fc3dccdd7f81e53254251d13aaf42cff1cdcc8d423fe1cd8a21fa7b4f1
-size 638323
+oid sha256:7ede33b57f9f4238fba8a7ac6ea13baed3060259522eb7677ba353d75a560e22
+size 651002

data/feature_selections/T47D_feature_selections.tsv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4dd1063499fd800b469d749a0057eef4b8aa45e38b5e3c80983ed707ad57ff9
-size 610567
+oid sha256:a47cebd2a5280537d6e3445b9e5a5c31fb00f39bd62a7496fb0301dcdf853187
+size 624280

data/feature_selections/lymphoma_feature_selections.tsv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c529f0d686b664820aaeeddfac68a79d4b4f69d604f835c1e2cbd79c21f5ff
-size 49260
+oid sha256:6e6902e8f94c27fc6ff81fc994e0458c06499b272f39b220dbb5bb071b716fdd
+size 50793

data/feature_selections/prostate_atac_feature_selections.tsv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a94974f21678dac4b6e6da013f24cbfc1fddb92f9a463b84238702c115a6441
-size 92252
+oid sha256:86c85bbbf224b970d14bb1d5f4f12d2263bedec1456af9eb3045a5eff85d63e0
+size 94637

data/feature_selections/prostate_rna_feature_selections.tsv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c31d67447bdb21f91645261d25e1e41000335993f32ecbddd66ba878d24baf3
-size 6926
+oid sha256:0fc996e319b2d587c6c0b8cfb3d8b367e84b8cf8852677ee79059e69391b731d
+size 7097