Gene filtering

README.md

@@ -1,2 +1,15 @@
 # SingleCellWebApp
 Bioinformatic technique team project  
+Here are the outputs we got from running our codes. 
+
+![PHOTO-2025-05-23-22-18-02](https://github.com/user-attachments/assets/052b7fae-295a-41b5-8f4c-9efb99e6365b)
+Above is the output from rank genes function
+
+![PHOTO-2025-05-23-22-32-16](https://github.com/user-attachments/assets/f7fe0897-e9b4-4412-be4a-c63479aa43b9)
+This one is the violin plot output.
+
+![PHOTO-2025-05-23-22-52-52](https://github.com/user-attachments/assets/62fcd331-dd72-4e4a-930a-e8698a6f8d01)
+This one is from marker genes code.
+
+![PHOTO-2025-05-23-21-32-06](https://github.com/user-attachments/assets/30361fa4-fdc4-43cf-83a1-15c57454cbc1)
+Lastly, this is the output we got from the get scores p-values function.

rank_genes_violin_demo.py

@@ -0,0 +1,17 @@
+from rank_genes_violin import get_rank_genes_groups_violin
+import scanpy as sc
+
+#sample dataset
+adata = sc.datasets.pbmc3k()
+
+# calculating neighborhoods
+sc.pp.neighbors(adata)
+
+sc.tl.leiden(adata, resolution=1.0)
+
+# Differential expression analysis (with t-test)
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='t-test')
+
+
+# calling the function and visualizing
+get_rank_genes_groups_violin(adata, groups='0', n_genes=8)

src/modules/get_marker_genes_demo.py

@@ -0,0 +1,18 @@
+import scanpy as sc
+import pandas as pd
+from markedgenes import get_marker_genes  # defined function in main code
+
+# Demo dataset
+adata = sc.datasets.pbmc3k()
+
+#preprocessing and clustering (same with the main code)
+sc.pp.pca(adata, svd_solver='arpack')
+sc.pp.neighbors(adata)
+sc.tl.leiden(adata)  # Leiden clustering yap
+
+# ranking genes between groups
+sc.tl.rank_genes_groups(adata, 'leiden', method='t-test')
+
+# recalling the function
+scores_and_pvals = get_scores_and_pvals(adata)
+print(scores_and_pvals)

src/modules/get_rank_genes_demo.py

@@ -0,0 +1,23 @@
+from rank_genes_group import rank_genes_groups_custom
+import scanpy as sc
+
+sc.datasets.pbmc3k()
+sc.pp.normalize_total(adata, target_sum=1e4)
+sc.pp.log1p(adata)
+sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+adata = adata[:, adata.var.highly_variable]
+sc.pp.scale(adata, max_value=10)
+
+# PCA and neighborhoods
+sc.pp.pca(adata, svd_solver='arpack')  # Bu satır uyarıyı çözer
+sc.pp.neighbors(adata, n_pcs=40)
+
+# Clustering (Leiden)
+sc.tl.leiden(adata, resolution=1.0)
+
+sc.settings.verbosity = 2
+
+#to save results
+results_file = "pbmc3k_rank_genes.h5ad"
+rank_genes_groups_custom(adata, groupby='leiden' , method='t-test' , n_genes=25 , sharey=False)
+adata.write(results_file)

src/modules/get_scors_and_pvals.py

@@ -0,0 +1,36 @@
+import scanpy as sc
+import pandas as pd
+from rank_genes_group import rank_genes_groups
+
+# Load the dataset
+adata = sc.datasets.pbmc3k()
+
+# Apply PCA to reduce dimensionality (to avoid high-dimension warning)
+sc.pp.pca(adata, svd_solver='arpack')
+
+# Calculate neighbors on PCA-reduced data
+sc.pp.neighbors(adata)
+
+# Run Leiden algorithm (with future-proofing for 'igraph' backend)
+sc.tl.leiden(adata, resolution=1.0, flavor='igraph', directed=False, n_iterations=2)
+
+# Run differential expression analysis to rank genes
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='t-test')
+
+
+# Reduce verbosity for cleaner output
+sc.settings.verbosity = 2
+
+# Define a function to get gene names and p-values from rank_genes_groups
+def get_scores_and_pvals(adata):
+    result = adata.uns['rank_genes_groups']
+    groups = result['names'].dtype.names
+    df = pd.DataFrame(
+        {group + '_' + key[:1]: result[key][group]
+         for group in groups for key in ['names', 'pvals']}).head(5)
+    return df
+
+# Run the function to get the results
+scores_and_pvals = get_scores_and_pvals(adata)
+print(scores_and_pvals)
+

src/modules/get_scors_and_pvals_demo.py

@@ -0,0 +1,17 @@
+from get_scors_and_pvals import get_scores_and_pvals
+import scanpy as sc
+import pandas as pd
+
+# Demo dataset
+adata = sc.datasets.pbmc3k() 
+
+# ranking genes between groups
+sc.pp.pca(adata, svd_solver='arpack')
+sc.pp.neighbors(adata)
+sc.tl.leiden(adata)
+sc.tl.rank_genes_groups(adata, 'leiden', method='t-test')
+
+# recalling the function
+scores_and_pvals = get_scores_and_pvals(adata)
+print(scores_and_pvals)
+

src/modules/pvals_demo.py

@@ -0,0 +1,16 @@
+from get_scors_and_pvals import get_scores_and_pvals
+import scanpy as sc
+import pandas as pd
+
+# Demo dataset
+adata = sc.datasets.pbmc3k() 
+
+# ranking genes between groups
+sc.pp.pca(adata, svd_solver='arpack')
+sc.pp.neighbors(adata)
+sc.tl.leiden(adata)
+sc.tl.rank_genes_groups(adata, 'leiden', method='t-test')
+
+# recalling the function
+scores_and_pvals = get_scores_and_pvals(adata)
+print(scores_and_pvals)

src/modules/rank_genes_group_demo.py

@@ -0,0 +1,24 @@
+from rankgenesgroup import rank_genes_groups
+import scanpy as sc
+
+adata = sc.datasets.pbmc3k()
+
+sc.pp.normalize_total(adata, target_sum=1e4)
+sc.pp.log1p(adata)
+sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+adata = adata[:, adata.var.highly_variable]
+sc.pp.scale(adata, max_value=10)
+
+# PCA and neighborhoods
+sc.pp.pca(adata, svd_solver='arpack')  # Bu satır uyarıyı çözer
+sc.pp.neighbors(adata, n_pcs=40)
+
+# Clustering (Leiden)
+sc.tl.leiden(adata, resolution=1.0)
+
+sc.settings.verbosity = 2
+
+#to save results
+results_file = "pbmc3k_rank_genes.h5ad"
+sc.tl.rank_genes_groups(adata, groupby='leiden' , method='t-test' , n_genes=25 , sharey=False)
+adata.write(results_file)

src/modules/rank_genes_violin.py

@@ -0,0 +1,18 @@
+import scanpy as sc
+adata = sc.datasets.pbmc3k()
+sc.pp.neighbors(adata)
+sc.tl.leiden(adata, resolution=1.0)
+sc.settings.verbosity = 2  # reduce the verbosity
+
+def get_rank_genes_groups_violin(adata, groups='0', n_genes=8):
+   """
+   -Plots a violin plot for the top ranked genes in specified groups (clusters).
+
+    Parameters:
+    - adata: AnnData object with results from rank_genes_groups
+    - groups: List or string specifying the groups (clusters) to plot (default is all groups)
+    - n_genes: Number of top genes to display in the plot (default is 8)
+
+   """
+   sc.pl.rank_genes_groups_violin(adata, groups=groups, n_genes=n_genes)
+   return adata

src/modules/rank_genes_violin_demo.py

@@ -0,0 +1,17 @@
+from rank_genes_violin import get_rank_genes_groups_violin
+import scanpy as sc
+
+#sample dataset
+adata = sc.datasets.pbmc3k()
+
+# calculating neighborhoods
+sc.pp.neighbors(adata)
+
+sc.tl.leiden(adata, resolution=1.0)
+
+# Differential expression analysis (with t-test)
+sc.tl.rank_genes_groups(adata, groupby='leiden', method='t-test')
+
+
+# calling the function and visualizing
+get_rank_genes_groups_violin(adata, groups='0', n_genes=8)

src/modules/rankgenesgroup.py

@@ -0,0 +1,36 @@
+import scanpy as sc
+
+# Örnek veri setini yükle
+adata = sc.datasets.pbmc3k()
+
+# Temel ön işleme
+sc.pp.normalize_total(adata, target_sum=1e4)
+sc.pp.log1p(adata)
+sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+adata = adata[:, adata.var.highly_variable]
+sc.pp.scale(adata, max_value=10)
+
+# PCA ve komşuluk hesaplama
+sc.pp.pca(adata, svd_solver='arpack')  # Bu satır uyarıyı çözer
+sc.pp.neighbors(adata, n_pcs=40)
+
+# Clustering (Leiden)
+sc.tl.leiden(adata, resolution=1.0)
+
+# Verbosity ayarı
+sc.settings.verbosity = 2
+
+# Sonuçları kaydetmek için bir dosya ismi belirle
+results_file = "pbmc3k_rank_genes.h5ad"
+
+# Gen sıralama ve görselleştirme fonksiyonu
+def rank_genes_groups(adata, method='t-test', n_genes=25, sharey=False):
+    """
+    - Perform differential expression analysis and plot top marker genes.
+    """
+    sc.tl.rank_genes_groups(adata, groupby='leiden', method=method)
+    sc.pl.rank_genes_groups(adata, n_genes=n_genes, sharey=sharey)
+    adata.write(results_file)
+
+# Fonksiyonu çağır
+rank_genes_groups(adata)