From 59f89159055f69a9ddf88817d5de5a330b631e56 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:44:22 -0700
Subject: [PATCH 01/37] refactor phenoscore module

---
 screenpro/{phenoscore.py => phenoscore/__init__.py} | 0
 screenpro/{ => phenoscore}/phenostat.py             | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 rename screenpro/{phenoscore.py => phenoscore/__init__.py} (100%)
 rename screenpro/{ => phenoscore}/phenostat.py (100%)

diff --git a/screenpro/phenoscore.py b/screenpro/phenoscore/__init__.py
similarity index 100%
rename from screenpro/phenoscore.py
rename to screenpro/phenoscore/__init__.py
diff --git a/screenpro/phenostat.py b/screenpro/phenoscore/phenostat.py
similarity index 100%
rename from screenpro/phenostat.py
rename to screenpro/phenoscore/phenostat.py

From 20b53a06ee8d8850b17e57ec99d707be2c8e479f Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:44:34 -0700
Subject: [PATCH 02/37] draft deseq script

---
 screenpro/phenoscore/deseq.py | 37 +++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100644 screenpro/phenoscore/deseq.py

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
new file mode 100644
index 0000000..de60824
--- /dev/null
+++ b/screenpro/phenoscore/deseq.py
@@ -0,0 +1,37 @@
+"""
+deseq module: adapt pyDESeq2 for use in ScreenPro2 package
+"""
+
+import numpy as np
+import pandas as pd
+import anndata as ad
+
+from pydeseq2.dds import DeseqDataSet
+from pydeseq2.default_inference import DefaultInference
+from pydeseq2.ds import DeseqStats
+
+
+def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
+
+    inference = DefaultInference(n_cpus=n_cpus)
+    
+    dds = DeseqDataSet(
+        counts=adata.to_df().astype(int),
+        metadata=adata.obs,
+        design_factors=design,  # compare samples based on the "condition"
+        refit_cooks=True,
+        inference=inference,
+    )
+
+    dds.deseq2()
+
+    stat_res = DeseqStats(
+        dds, 
+        contrast=[design, tested_level, ref_level], 
+        inference=inference
+    )
+    stat_res.summary()
+
+    df = stat_res.results_df
+
+    return df

From cafd6a9287d89593c36969c0689cf0e112e633cc Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:47:10 -0700
Subject: [PATCH 03/37] import `runDESeq`

---
 screenpro/phenoscore/__init__.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/screenpro/phenoscore/__init__.py b/screenpro/phenoscore/__init__.py
index a06384b..4b6941b 100644
--- a/screenpro/phenoscore/__init__.py
+++ b/screenpro/phenoscore/__init__.py
@@ -5,6 +5,8 @@
 import numpy as np
 import anndata as ad
 import pandas as pd
+
+from deseq import runDESeq
 from .phenostat import matrixStat, getFDR
 
 

From 83e29bb194ee9830f7533f2dfe0ea1ed2742188b Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:48:51 -0700
Subject: [PATCH 04/37] mend

---
 screenpro/phenoscore/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/__init__.py b/screenpro/phenoscore/__init__.py
index 4b6941b..77c5bfe 100644
--- a/screenpro/phenoscore/__init__.py
+++ b/screenpro/phenoscore/__init__.py
@@ -6,7 +6,7 @@
 import anndata as ad
 import pandas as pd
 
-from deseq import runDESeq
+from .deseq import runDESeq
 from .phenostat import matrixStat, getFDR
 
 

From 079632122d786cbf3c6b51c9e4a98846f05eef9f Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:53:56 -0700
Subject: [PATCH 05/37] add `quiet=True`

---
 screenpro/phenoscore/deseq.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index de60824..c6d8694 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -21,6 +21,7 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
         design_factors=design,  # compare samples based on the "condition"
         refit_cooks=True,
         inference=inference,
+        quiet=True
     )
 
     dds.deseq2()
@@ -28,7 +29,7 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
     stat_res = DeseqStats(
         dds, 
         contrast=[design, tested_level, ref_level], 
-        inference=inference
+        inference=inference,
     )
     stat_res.summary()
 

From 03cdd9b55785edb76b0223c5946a67f71beaaec0 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 14:56:31 -0700
Subject: [PATCH 06/37] add `quiet=True`

---
 screenpro/phenoscore/deseq.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index c6d8694..01e725f 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -30,6 +30,7 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
         dds, 
         contrast=[design, tested_level, ref_level], 
         inference=inference,
+        quiet=True
     )
     stat_res.summary()
 

From d557f1e991f6149355ab0627ed230fe04c024bab Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 15:01:03 -0700
Subject: [PATCH 07/37] avoid print

---
 screenpro/phenoscore/deseq.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 01e725f..d0bb52b 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -2,6 +2,7 @@
 deseq module: adapt pyDESeq2 for use in ScreenPro2 package
 """
 
+import sys 
 import numpy as np
 import pandas as pd
 import anndata as ad
@@ -32,7 +33,8 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
         inference=inference,
         quiet=True
     )
-    stat_res.summary()
+    
+    sys.stdout = open(stat_res.summary(), 'w')
 
     df = stat_res.results_df
 

From 27b44ed85f9f8669a9b335d39c6b78dba71bcffd Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 15:01:54 -0700
Subject: [PATCH 08/37] mend

---
 screenpro/phenoscore/deseq.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index d0bb52b..77f3b68 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -12,7 +12,7 @@
 from pydeseq2.ds import DeseqStats
 
 
-def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
+def runDESeq(adata, design, tested_level, ref_level, n_cpus=8,quiet=False):
 
     inference = DefaultInference(n_cpus=n_cpus)
     
@@ -22,7 +22,7 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
         design_factors=design,  # compare samples based on the "condition"
         refit_cooks=True,
         inference=inference,
-        quiet=True
+        quiet=quiet
     )
 
     dds.deseq2()
@@ -31,7 +31,7 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8):
         dds, 
         contrast=[design, tested_level, ref_level], 
         inference=inference,
-        quiet=True
+        quiet=quiet
     )
     
     sys.stdout = open(stat_res.summary(), 'w')

From 92d8741ac1bcd622314a6a416b319f6cb41b5006 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Sat, 29 Jun 2024 15:06:29 -0700
Subject: [PATCH 09/37] mend

---
 screenpro/phenoscore/deseq.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 77f3b68..7bb2c62 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -2,10 +2,10 @@
 deseq module: adapt pyDESeq2 for use in ScreenPro2 package
 """
 
-import sys 
 import numpy as np
 import pandas as pd
 import anndata as ad
+import os, contextlib
 
 from pydeseq2.dds import DeseqDataSet
 from pydeseq2.default_inference import DefaultInference
@@ -34,7 +34,10 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8,quiet=False):
         quiet=quiet
     )
     
-    sys.stdout = open(stat_res.summary(), 'w')
+
+    with open(os.devnull, 'w') as devnull:
+        with contextlib.redirect_stdout(devnull):
+            stat_res.summary()
 
     df = stat_res.results_df
 

From 58efc393f85f0d092590d610ae20882e3947d152 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 01:45:22 -0700
Subject: [PATCH 10/37] update log scale

---
 screenpro/plotting.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/screenpro/plotting.py b/screenpro/plotting.py
index 84cccb0..8d75b58 100644
--- a/screenpro/plotting.py
+++ b/screenpro/plotting.py
@@ -65,14 +65,17 @@ def draw_threshold(x, threshold, pseudo_sd):
 
 ## Scatter plot of replicates
 
-def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform=True, **args):
+def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform='log10(x+1)', **args):
     adat = adat_in[[x, y], :].copy()
 
     adat.obs.index = [f'Replicate {str(r)}' for r in adat.obs.replicate.to_list()]
     x_lab, y_lab = [f'Replicate {str(r)}' for r in adat.obs.replicate.to_list()]
 
     if log_transform:
-        sc.pp.log1p(adat)
+        if log_transform == 'log1p':
+            adat = sc.pp.log1p(adat)
+        elif log_transform == 'log10(x+1)':
+            adat.X = np.log10(adat.X+1)
     
     if min_val is None:
         min_val = min([adat.to_df().loc[x_lab,:].min(), adat.to_df().loc[y_lab,:].min()])

From c0ef0f51a8c209a18cd5ce27d7a896f3f9f73be9 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 01:47:51 -0700
Subject: [PATCH 11/37] add a ` adata.copy()` line

---
 screenpro/assays.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/assays.py b/screenpro/assays.py
index 0f11ed4..a6e6970 100644
--- a/screenpro/assays.py
+++ b/screenpro/assays.py
@@ -25,7 +25,7 @@ def __init__(self, adata, fc_transformation='log2(x+1)', test='ttest', n_reps=3)
             fc_transformation (str): fold change transformation to apply for calculating phenotype scores
             test (str): statistical test to use for calculating phenotype scores
         """
-        self.adata = adata
+        self.adata = adata.copy()
         self.pdata = None
         self.fc_transformation = fc_transformation
         self.test = test

From 132e6e4b020c6ad066ac52138f8e403b24675835 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:29:18 -0700
Subject: [PATCH 12/37] split function

---
 screenpro/phenoscore/deseq.py | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 7bb2c62..0d7be39 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -12,7 +12,7 @@
 from pydeseq2.ds import DeseqStats
 
 
-def runDESeq(adata, design, tested_level, ref_level, n_cpus=8,quiet=False):
+def runDESeq(adata, design, n_cpus=8,quiet=False):
 
     inference = DefaultInference(n_cpus=n_cpus)
     
@@ -27,6 +27,13 @@ def runDESeq(adata, design, tested_level, ref_level, n_cpus=8,quiet=False):
 
     dds.deseq2()
 
+    return dds
+
+
+def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=False):
+
+    inference = DefaultInference(n_cpus=n_cpus)
+
     stat_res = DeseqStats(
         dds, 
         contrast=[design, tested_level, ref_level], 

From eb160c683b4410971973b4bfb673bff365f3f2e2 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:42:06 -0700
Subject: [PATCH 13/37] mend

---
 screenpro/phenoscore/deseq.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 0d7be39..3702ea1 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -34,6 +34,8 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
 
     inference = DefaultInference(n_cpus=n_cpus)
 
+    name = f'{tested_level}_vs_{ref_level}'
+
     stat_res = DeseqStats(
         dds, 
         contrast=[design, tested_level, ref_level], 
@@ -48,4 +50,4 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
 
     df = stat_res.results_df
 
-    return df
+    return name, df
\ No newline at end of file

From 668c88c340712c384c3fd206a352c5d6e5d44ec0 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:42:27 -0700
Subject: [PATCH 14/37] add `calculateDrugScreenDESeq` function

---
 screenpro/assays.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/screenpro/assays.py b/screenpro/assays.py
index a6e6970..7482e3c 100644
--- a/screenpro/assays.py
+++ b/screenpro/assays.py
@@ -8,6 +8,7 @@
 import scanpy as sc
 
 from pydeseq2 import preprocessing
+from .phenoscore.deseq import runDESeq, extractDESeqResults
 from .phenoscore import runPhenoScore, runPhenoScoreForReplicate
 from .utils import ann_score_df
 from copy import copy
@@ -90,6 +91,36 @@ def countNormalization(self):
         self.adata.layers['seq_depth_norm'] = norm_counts
         self.adata.X = self.adata.layers['seq_depth_norm']
     
+    def calculateDrugScreenDESeq(self, t0, untreated, treated, run_name=None, **kwargs):
+        """
+        Calculate DESeq2 results for a given drug screen dataset.
+
+        Args:
+            design (str): design matrix for DESeq2
+            run_name (str): name for the DESeq2 calculation run
+            **kwargs: additional arguments to pass to runDESeq
+        """
+        dds = runDESeq(self.adata, 'condition', **kwargs)
+        
+        # Calculate `gamma`, `rho`, and `tau` phenotype scores
+        gamma_name, gamma = extractDESeqResults(
+            dds, 'condition', t0, untreated, **kwargs
+        )
+
+        tau_name, tau = extractDESeqResults(
+            dds, 'condition', t0, treated, **kwargs
+        )
+
+        rho_name, rho = extractDESeqResults(
+            dds, 'condition', untreated, treated, **kwargs
+        )
+
+        if not run_name: run_name = 'pyDESeq2'
+
+        self.phenotypes[run_name] = pd.concat({
+            f'gamma:{gamma_name}': gamma, f'tau:{tau_name}': tau, f'rho:{rho_name}': rho
+        }, axis=1)        
+
     def calculateDrugScreen(self, t0, untreated, treated, db_untreated, db_treated, score_level, db_rate_col='pop_doublings', run_name=None, **kwargs):
         """
         Calculate `gamma`, `rho`, and `tau` phenotype scores for a drug screen dataset in a given `score_level`.

From 4682bfc5b34cfb1cd98632e80021214b54eaf2f4 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:49:53 -0700
Subject: [PATCH 15/37] add a print line

---
 screenpro/phenoscore/deseq.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 3702ea1..7ba3ae1 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -34,7 +34,9 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
 
     inference = DefaultInference(n_cpus=n_cpus)
 
-    name = f'{tested_level}_vs_{ref_level}'
+    result_name = f'{tested_level}_vs_{ref_level}'
+
+    print(f'\t{tested_level}_vs_{ref_level}')
 
     stat_res = DeseqStats(
         dds, 
@@ -48,6 +50,6 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
         with contextlib.redirect_stdout(devnull):
             stat_res.summary()
 
-    df = stat_res.results_df
+    results = stat_res.results_df
 
-    return name, df
\ No newline at end of file
+    return result_name, results

From b39113252bb3f49f04dd8c2ee8bed6f656fcae2d Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:54:00 -0700
Subject: [PATCH 16/37] mend

---
 screenpro/phenoscore/deseq.py | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index 7ba3ae1..ff7be3a 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -15,7 +15,7 @@
 def runDESeq(adata, design, n_cpus=8,quiet=False):
 
     inference = DefaultInference(n_cpus=n_cpus)
-    
+
     dds = DeseqDataSet(
         counts=adata.to_df().astype(int),
         metadata=adata.obs,
@@ -36,8 +36,6 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
 
     result_name = f'{tested_level}_vs_{ref_level}'
 
-    print(f'\t{tested_level}_vs_{ref_level}')
-
     stat_res = DeseqStats(
         dds, 
         contrast=[design, tested_level, ref_level], 
@@ -45,7 +43,6 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
         quiet=quiet
     )
     
-
     with open(os.devnull, 'w') as devnull:
         with contextlib.redirect_stdout(devnull):
             stat_res.summary()

From 30e3b289d5008efa7531f9b193d437a7ca086329 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:54:58 -0700
Subject: [PATCH 17/37] mend

---
 screenpro/phenoscore/deseq.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index ff7be3a..c8f5600 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -16,6 +16,8 @@ def runDESeq(adata, design, n_cpus=8,quiet=False):
 
     inference = DefaultInference(n_cpus=n_cpus)
 
+    print(f'\tcreating `dds` object...')
+    
     dds = DeseqDataSet(
         counts=adata.to_df().astype(int),
         metadata=adata.obs,
@@ -36,6 +38,8 @@ def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=Fa
 
     result_name = f'{tested_level}_vs_{ref_level}'
 
+    print(f'\t{tested_level}_vs_{ref_level}')
+
     stat_res = DeseqStats(
         dds, 
         contrast=[design, tested_level, ref_level], 

From fdcc519993ded790ac8a12c92f44b34aa3620e9c Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Thu, 4 Jul 2024 03:57:12 -0700
Subject: [PATCH 18/37] mend

---
 screenpro/phenoscore/deseq.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/phenoscore/deseq.py b/screenpro/phenoscore/deseq.py
index c8f5600..8399633 100644
--- a/screenpro/phenoscore/deseq.py
+++ b/screenpro/phenoscore/deseq.py
@@ -32,7 +32,7 @@ def runDESeq(adata, design, n_cpus=8,quiet=False):
     return dds
 
 
-def extractDESeqResults(dds, design, tested_level, ref_level, n_cpus=8, quiet=False):
+def extractDESeqResults(dds, design, ref_level, tested_level, n_cpus=8, quiet=False):
 
     inference = DefaultInference(n_cpus=n_cpus)
 

From 6f0a7a612e458f8346efe288aa2f095788b4a376 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Wed, 10 Jul 2024 01:21:17 -0700
Subject: [PATCH 19/37] mend

---
 screenpro/plotting.py | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/screenpro/plotting.py b/screenpro/plotting.py
index 8d75b58..5393a94 100644
--- a/screenpro/plotting.py
+++ b/screenpro/plotting.py
@@ -65,17 +65,14 @@ def draw_threshold(x, threshold, pseudo_sd):
 
 ## Scatter plot of replicates
 
-def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform='log10(x+1)', **args):
+def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform=False, **args):
     adat = adat_in[[x, y], :].copy()
 
     adat.obs.index = [f'Replicate {str(r)}' for r in adat.obs.replicate.to_list()]
     x_lab, y_lab = [f'Replicate {str(r)}' for r in adat.obs.replicate.to_list()]
 
     if log_transform:
-        if log_transform == 'log1p':
-            adat = sc.pp.log1p(adat)
-        elif log_transform == 'log10(x+1)':
-            adat.X = np.log10(adat.X+1)
+        adat.X = np.log10(adat.X+1)
     
     if min_val is None:
         min_val = min([adat.to_df().loc[x_lab,:].min(), adat.to_df().loc[y_lab,:].min()])

From 1c42c5cf926f4cffc890df901e60f12a98210a56 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Wed, 10 Jul 2024 01:24:13 -0700
Subject: [PATCH 20/37] mend

---
 screenpro/plotting.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/plotting.py b/screenpro/plotting.py
index 5393a94..0cd958e 100644
--- a/screenpro/plotting.py
+++ b/screenpro/plotting.py
@@ -65,7 +65,7 @@ def draw_threshold(x, threshold, pseudo_sd):
 
 ## Scatter plot of replicates
 
-def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform=False, **args):
+def plotReplicateScatter(ax, adat_in, x, y, title, min_val=None, max_val=None, log_transform=True, **args):
     adat = adat_in[[x, y], :].copy()
 
     adat.obs.index = [f'Replicate {str(r)}' for r in adat.obs.replicate.to_list()]

From e527eca1b243d1f596fa283ce55ebbc7910b3ab5 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:10:46 -0700
Subject: [PATCH 21/37] add and update files `visualize` module

---
 .../{plotting.py => visualize/__init__.py}    | 65 ++-------------
 screenpro/{ => visualize}/dashboard.py        |  5 --
 screenpro/visualize/utils.py                  | 80 +++++++++++++++++++
 3 files changed, 87 insertions(+), 63 deletions(-)
 rename screenpro/{plotting.py => visualize/__init__.py} (85%)
 rename screenpro/{ => visualize}/dashboard.py (98%)
 create mode 100644 screenpro/visualize/utils.py

diff --git a/screenpro/plotting.py b/screenpro/visualize/__init__.py
similarity index 85%
rename from screenpro/plotting.py
rename to screenpro/visualize/__init__.py
index 0cd958e..7dd300e 100644
--- a/screenpro/plotting.py
+++ b/screenpro/visualize/__init__.py
@@ -1,67 +1,16 @@
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib
-from .utils import ann_score_df
+from ..ngs.utils import ann_score_df
+from .utils import almost_black
 import scanpy as sc
 
-# variables
-almost_black = '#111111'
-dark2 = ['#1b9e77',
-         '#d95f02',
-         '#7570b3',
-         '#e7298a',
-         '#66a61e',
-         '#e6ab02',
-         '#a6761d',
-         '#666666']
-blue_yellow = matplotlib.colors.LinearSegmentedColormap.from_list(
-    'BuYl', [(0, '#ffff00'), (.49, '#000000'), (.51, '#000000'), (1, '#0000ff')])
-blue_yellow.set_bad('#999999', 1)
-yellow_blue = matplotlib.colors.LinearSegmentedColormap.from_list(
-    'YlBu', [(0, '#0000ff'), (.49, '#000000'), (.51, '#000000'), (1, '#ffff00')])
-yellow_blue.set_bad('#999999', 1)
-
-# plt.rcParams['font.sans-serif'] = [
-#     'Helvetica', 'Arial', 'Verdana', 'Bitstream Vera Sans'
-# ]
-# plt.rcParams['font.size'] = 8
-# plt.rcParams['font.weight'] = 'regular'
-# plt.rcParams['text.color'] = almost_black
-#
-# axisLineWidth = .5
-# plt.rcParams['axes.linewidth'] = axisLineWidth
-# plt.rcParams['lines.linewidth'] = 1.5
-#
-# plt.rcParams['axes.facecolor'] = 'white'
-# plt.rcParams['axes.edgecolor'] = almost_black
-# plt.rcParams['axes.labelcolor'] = almost_black
-# # plt.rcParams['axes.color_cycle'] = dark2_all
-#
-# plt.rcParams['patch.edgecolor'] = 'none'
-# plt.rcParams['patch.linewidth'] = .25
-# # plt.rcParams['patch.facecolor'] = dark2_all[0]
-#
-# plt.rcParams['savefig.dpi'] = 1000
-# plt.rcParams['savefig.format'] = 'svg'
-#
-# plt.rcParams['legend.frameon'] = False
-# plt.rcParams['legend.handletextpad'] = .25
-# plt.rcParams['legend.fontsize'] = 8
-# plt.rcParams['legend.numpoints'] = 1
-# plt.rcParams['legend.scatterpoints'] = 1
-#
-# plt.rcParams['ytick.direction'] = 'out'
-# plt.rcParams['ytick.color'] = almost_black
-# plt.rcParams['ytick.major.width'] = axisLineWidth
-# plt.rcParams['xtick.direction'] = 'out'
-# plt.rcParams['xtick.color'] = almost_black
-# plt.rcParams['xtick.major.width'] = axisLineWidth
-
-
-def draw_threshold(x, threshold, pseudo_sd):
-    return threshold * pseudo_sd * (1 if x > 0 else -1) / abs(x)
-
 
 ## Scatter plot of replicates
 
diff --git a/screenpro/dashboard.py b/screenpro/visualize/dashboard.py
similarity index 98%
rename from screenpro/dashboard.py
rename to screenpro/visualize/dashboard.py
index d709e37..44f1c62 100644
--- a/screenpro/dashboard.py
+++ b/screenpro/visualize/dashboard.py
@@ -1,8 +1,3 @@
-## Copyright (c) 2022-2024 ScreenPro2 Development Team.
-## All rights reserved.
-## Gilbart Lab, UCSF / Arc Institute.
-## Multi-Omics Tech Center, Arc Insititue.
-
 import numpy as np
 import pandas as pd
 import bokeh
diff --git a/screenpro/visualize/utils.py b/screenpro/visualize/utils.py
new file mode 100644
index 0000000..84b9c7e
--- /dev/null
+++ b/screenpro/visualize/utils.py
@@ -0,0 +1,80 @@
+import matplotlib.pyplot as plt
+import matplotlib
+import numpy as np
+import pandas as pd
+
+# variables
+almost_black = '#111111'
+dark2 = ['#1b9e77',
+         '#d95f02',
+         '#7570b3',
+         '#e7298a',
+         '#66a61e',
+         '#e6ab02',
+         '#a6761d',
+         '#666666']
+blue_yellow = matplotlib.colors.LinearSegmentedColormap.from_list(
+    'BuYl', [(0, '#ffff00'), (.49, '#000000'), (.51, '#000000'), (1, '#0000ff')])
+blue_yellow.set_bad('#999999', 1)
+yellow_blue = matplotlib.colors.LinearSegmentedColormap.from_list(
+    'YlBu', [(0, '#0000ff'), (.49, '#000000'), (.51, '#000000'), (1, '#ffff00')])
+yellow_blue.set_bad('#999999', 1)
+
+# plt.rcParams['font.sans-serif'] = [
+#     'Helvetica', 'Arial', 'Verdana', 'Bitstream Vera Sans'
+# ]
+# plt.rcParams['font.size'] = 8
+# plt.rcParams['font.weight'] = 'regular'
+# plt.rcParams['text.color'] = almost_black
+#
+# axisLineWidth = .5
+# plt.rcParams['axes.linewidth'] = axisLineWidth
+# plt.rcParams['lines.linewidth'] = 1.5
+#
+# plt.rcParams['axes.facecolor'] = 'white'
+# plt.rcParams['axes.edgecolor'] = almost_black
+# plt.rcParams['axes.labelcolor'] = almost_black
+# # plt.rcParams['axes.color_cycle'] = dark2_all
+#
+# plt.rcParams['patch.edgecolor'] = 'none'
+# plt.rcParams['patch.linewidth'] = .25
+# # plt.rcParams['patch.facecolor'] = dark2_all[0]
+#
+# plt.rcParams['savefig.dpi'] = 1000
+# plt.rcParams['savefig.format'] = 'svg'
+#
+# plt.rcParams['legend.frameon'] = False
+# plt.rcParams['legend.handletextpad'] = .25
+# plt.rcParams['legend.fontsize'] = 8
+# plt.rcParams['legend.numpoints'] = 1
+# plt.rcParams['legend.scatterpoints'] = 1
+#
+# plt.rcParams['ytick.direction'] = 'out'
+# plt.rcParams['ytick.color'] = almost_black
+# plt.rcParams['ytick.major.width'] = axisLineWidth
+# plt.rcParams['xtick.direction'] = 'out'
+# plt.rcParams['xtick.color'] = almost_black
+# plt.rcParams['xtick.major.width'] = axisLineWidth
+
+
+def cleanAxes(ax, top=False, right=False, bottom=True, left=True):
+    ax.grid('off')
+    ax.spines['top'].set_visible(top)
+    ax.spines['right'].set_visible(right)
+    ax.spines['left'].set_visible(left)
+    ax.spines['bottom'].set_visible(bottom)
+
+    #turn off all ticks
+    ax.yaxis.set_ticks_position('none')
+    ax.xaxis.set_ticks_position('none')
+
+    #now re-enable visibles
+    if top:
+        ax.xaxis.tick_top()
+    if bottom:
+        ax.xaxis.tick_bottom()
+    if left:
+        ax.yaxis.tick_left()
+    if right:
+        ax.yaxis.tick_right()
+

From e69c8bb984b27f50d286c1de18d81e089e0371f3 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:12:23 -0700
Subject: [PATCH 22/37] update files `ngs` module

---
 screenpro/ngs/__init__.py |  6 ++++
 screenpro/ngs/utils.py    | 60 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)
 create mode 100644 screenpro/ngs/utils.py

diff --git a/screenpro/ngs/__init__.py b/screenpro/ngs/__init__.py
index 3e3f052..490148d 100644
--- a/screenpro/ngs/__init__.py
+++ b/screenpro/ngs/__init__.py
@@ -40,6 +40,7 @@
 
 from . import cas9
 from . import cas12
+from .utils import find_low_counts, addPseudoCount
 from ..load import load_cas9_sgRNA_library
 from simple_colors import green
 
@@ -384,3 +385,8 @@ def build_counts_anndata(self, source='library', verbose=False):
             return rdata
         else:
             raise ValueError("Invalid source argument. Please choose from 'mapped', 'recombinant' or 'library'. Note: 'mapped' and 'library' act the same way.")
+
+    def filter_low_counts(self, filter_type='either', minimum_reads=50, verbose=False):
+        '''Filter low counts from count matrix
+        '''
+        raise NotImplementedError("This method is not yet implemented.")
\ No newline at end of file
diff --git a/screenpro/ngs/utils.py b/screenpro/ngs/utils.py
new file mode 100644
index 0000000..2f9e8ce
--- /dev/null
+++ b/screenpro/ngs/utils.py
@@ -0,0 +1,60 @@
+import pandas as pd
+import numpy as np
+
+
+def find_low_counts(adata, filter_type='either', minimum_reads=50):
+    """
+    Label variables with low counts in either or all samples.
+
+    Parameters:
+        adata (AnnData): AnnData object
+        filter_type (str): either or all
+        minimum_reads (int): minimum number of reads
+
+    Returns:
+        None
+    """
+    count_bin = adata.X >= minimum_reads
+    if filter_type == 'either':
+        out = adata[:, ~(~count_bin.all(axis=0))].copy()
+    elif filter_type == 'all':
+        out = adata[:, count_bin.all(axis=0)].copy()
+    elif filter_type == 'sum':
+        out = adata[:, adata.to_df().sum(axis=0) >= minimum_reads].copy()
+    else:
+        raise ValueError(f'filter_type "{filter_type}" not recognized. Use "either", "all", or "sum".')
+    
+    # print the number of removed variables
+    n_removed = adata.shape[1] - out.shape[1]
+    print(
+        f"{n_removed} variables with less than {minimum_reads} reads (filter_type: '{filter_type}')"
+    )
+
+    adata.var['low_count'] = ~adata.var.index.isin(out.var.index.to_list())
+
+
+def addPseudoCount(counts, pseudocountBehavior, pseudocountValue):
+    pass
+
+    ## possible pseudocount behaviors
+    # 1. remove 0
+    # 2. add pseudocount
+    # 3. impute 0 (it's hard)
+
+    # # pseudocount
+    # if pseudocountBehavior == 'default' or pseudocountBehavior == 'zeros only':
+    #     def defaultBehavior(row):
+    #         return row if min(
+    #             row) != 0 else row + pseudocountValue
+    
+    #     combinedCountsPseudo = combinedCounts.apply(defaultBehavior, axis=1)
+    # elif pseudocountBehavior == 'all values':
+    #     combinedCountsPseudo = combinedCounts.apply(
+    #         lambda row: row + pseudocountValue, axis=1)
+    # elif pseudocountBehavior == 'filter out':
+    #     combinedCountsPseudo = combinedCounts.copy()
+    #     zeroRows = combinedCounts.apply(lambda row: min(row) <= 0, axis=1)
+    #     combinedCountsPseudo.loc[zeroRows, :] = np.nan
+    # else:
+    #     raise ValueError(
+    #         'Pseudocount behavior not recognized or not implemented')
\ No newline at end of file

From 73a86bdc2b2f2a24e69b7aeac3aab8d7a5ddf9eb Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:13:01 -0700
Subject: [PATCH 23/37] update files `phenoscore` module

---
 .../{utils.py => phenoscore/annotate.py}      | 52 +------------------
 1 file changed, 1 insertion(+), 51 deletions(-)
 rename screenpro/{utils.py => phenoscore/annotate.py} (50%)

diff --git a/screenpro/utils.py b/screenpro/phenoscore/annotate.py
similarity index 50%
rename from screenpro/utils.py
rename to screenpro/phenoscore/annotate.py
index c86bc95..07e612b 100644
--- a/screenpro/utils.py
+++ b/screenpro/phenoscore/annotate.py
@@ -1,55 +1,5 @@
-import pandas as pd
 import numpy as np
-
-
-def check_protospacer_length(library, protospacer_col):
-    lengths = list(set(library[protospacer_col].str.len()))
-    if len(lengths) > 1:
-        raise ValueError(f"Protospacer lengths are not uniform: {lengths}")
-    else:
-        length = lengths[0]
-        return length
-
-
-def trim_protospacer(library, protospacer_col, trim_side, trim_len):
-    if trim_side == '5prime':
-        library[protospacer_col] = library[protospacer_col].str[trim_len:].str.upper()
-    
-    elif trim_side == '3prime':
-        library[protospacer_col] = library[protospacer_col].str[:-trim_len].str.upper()
-    
-    return library
-
-
-def find_low_counts(adata, filter_type='either', minimum_reads=50):
-    """
-    Label variables with low counts in either or all samples.
-
-    Parameters:
-        adata (AnnData): AnnData object
-        filter_type (str): either or all
-        minimum_reads (int): minimum number of reads
-
-    Returns:
-        None
-    """
-    count_bin = adata.X >= minimum_reads
-    if filter_type == 'either':
-        out = adata[:, ~(~count_bin.all(axis=0))].copy()
-    elif filter_type == 'all':
-        out = adata[:, count_bin.all(axis=0)].copy()
-    elif filter_type == 'sum':
-        out = adata[:, adata.to_df().sum(axis=0) >= minimum_reads].copy()
-    else:
-        raise ValueError(f'filter_type "{filter_type}" not recognized. Use "either", "all", or "sum".')
-    
-    # print the number of removed variables
-    n_removed = adata.shape[1] - out.shape[1]
-    print(
-        f"{n_removed} variables with less than {minimum_reads} reads (filter_type: '{filter_type}')"
-    )
-
-    adata.var['low_count'] = ~adata.var.index.isin(out.var.index.to_list())
+import pandas as pd
 
 
 def ann_score_df(df_in, up_hit='resistance_hit', down_hit='sensitivity_hit', ctrl_label='control', threshold=10):

From 6b9ba7d56e77429d5c508bc19ae02251c952118b Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:16:00 -0700
Subject: [PATCH 24/37] mend

---
 screenpro/visualize/__init__.py | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/screenpro/visualize/__init__.py b/screenpro/visualize/__init__.py
index 7dd300e..3a0e9d7 100644
--- a/screenpro/visualize/__init__.py
+++ b/screenpro/visualize/__init__.py
@@ -3,13 +3,9 @@
 ## Gilbart Lab, UCSF / Arc Institute.
 ## Multi-Omics Tech Center, Arc Insititue.
 
-import pandas as pd
 import numpy as np
-import matplotlib.pyplot as plt
-import matplotlib
-from ..ngs.utils import ann_score_df
-from .utils import almost_black
 import scanpy as sc
+from .utils import almost_black
 
 
 ## Scatter plot of replicates

From 1630e44c4c6d61db5864ebff2b00c947e9a44df0 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:42:58 -0700
Subject: [PATCH 25/37] update docs files

---
 docs/source/history.rst   |  3 +-
 docs/source/index.rst     |  1 -
 docs/source/phenotype.md  | 55 ++++++++++++++++++++++++++++++++++
 docs/source/phenotype.rst | 62 ---------------------------------------
 docs/source/plotting.rst  |  9 ------
 5 files changed, 57 insertions(+), 73 deletions(-)
 create mode 100644 docs/source/phenotype.md
 delete mode 100644 docs/source/phenotype.rst
 delete mode 100644 docs/source/plotting.rst

diff --git a/docs/source/history.rst b/docs/source/history.rst
index a3149e4..a58a937 100644
--- a/docs/source/history.rst
+++ b/docs/source/history.rst
@@ -2,9 +2,10 @@
 History
 =======
 
-0.4.0 (coming soon)
+0.3.1 - 0.4.0 (June 2024 - July 2024)
 ~~~~~~~~~~~~~~~~~~~
 * add command line interface
+* major bug fixes and improvements in code formatting
 
 0.2.11 - 0.3.0 (Apr 2024 - May 2024)
 ~~~~~~~~~~~~~~~~~
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 4d9dd0f..d188efb 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -15,7 +15,6 @@ Welcome to ScreenPro2's documentation!
    assays
    ngs
    phenotype
-   plotting
    load
 
 .. toctree::
diff --git a/docs/source/phenotype.md b/docs/source/phenotype.md
new file mode 100644
index 0000000..eac5e98
--- /dev/null
+++ b/docs/source/phenotype.md
@@ -0,0 +1,55 @@
+# Phenotype calculation modules
+
+Log ratio of $y$ vs $x$:
+
+$$\Delta=\log(\frac{\begin{bmatrix}{N_{y}}\end{bmatrix}_{(a,b)} + 1}{\begin{bmatrix}{N_{x}}\end{bmatrix}_{(a,b)} + 1})$$
+
+-   $y \rightarrow$ condition $x$ (e.g. treated samples)
+-   $x \rightarrow$ condition $y$ (e.g. $t_{0}$ samples)
+-   $a \rightarrow$ number of library elements with sgRNAs targeting $T$
+-   $b \rightarrow$ number of biological replicates, $R$ (e.g. 2 or 3)
+-   $N_{x}$ \| $N_{y} \rightarrow$ read counts normalized for sequencing
+    depth in condition $x$ or $y$
+
+Here is a formula for V3 library with single library element per gene
+(i.e. dual sgRNAs in one construct targeting same gene).
+
+Phenotype score for each $T$ comparing $y$ vs $x$:
+
+$$\text{PhenoScore}(T,x,y) =
+\left(
+\frac{
+\overline{\Delta_{(x,y)}}
+}{
+\text{median}( {\overline{\Delta_{(x_{ctrl},y_{ctrl})}}} )
+}
+\right)
+\times \frac{ 1 }{d_{growth}}$$
+
+-   $\overline{\Delta(x,y)} \rightarrow$ log ratio averaged across
+    replicates
+-   $T \rightarrow$ library elements with sgRNAs targeting $T$
+-   $d_{growth} \rightarrow$ growth factor to normalize the phenotype
+    score.
+
+Statistical test comparing $y$ vs $x$ per each target, $T$:
+
+$$\text{p-value}(T,x,y) = \text{t-test} \left(
+\begin{bmatrix}{N_{x}}\end{bmatrix}_{(a,b)},
+\begin{bmatrix}{N_{y}}\end{bmatrix}_{(a,b)}
+\right)$$
+
+(see this wikipedia page: [Dependent t-test for paired
+samples](https://en.wikipedia.org/wiki/Student%27s_t-test#Dependent_t-test_for_paired_samples))
+
+(see the link to the implemented tool: [ttest_rel, a scipy
+module](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.ttest_rel.html))
+
+> This is a test for the null hypothesis that two related or repeated
+> samples have identical average (expected) values.
+
+------------------------------------------------------------------------
+
+::: {.automodule members="" show-inheritance=""}
+screenpro.phenoscore
+:::
diff --git a/docs/source/phenotype.rst b/docs/source/phenotype.rst
deleted file mode 100644
index c462937..0000000
--- a/docs/source/phenotype.rst
+++ /dev/null
@@ -1,62 +0,0 @@
-Phenotype calculation modules
-=======================
-
-Log ratio of :math:`y` vs :math:`x`:
-
-.. math:: \Delta=\log(\frac{\begin{bmatrix}{N_{y}}\end{bmatrix}_{(a,b)} + 1}{\begin{bmatrix}{N_{x}}\end{bmatrix}_{(a,b)} + 1})
-
-- :math:`y \rightarrow` condition :math:`x` (e.g. treated samples)
-- :math:`x \rightarrow` condition :math:`y` (e.g. :math:`t_{0}` samples)
-- :math:`a \rightarrow` number of library elements with sgRNAs targeting :math:`T`
-- :math:`b \rightarrow` number of biological replicates, :math:`R` (e.g. 2 or 3)
-- :math:`N_{x}` | :math:`N_{y} \rightarrow` read counts normalized for sequencing depth in condition :math:`x` or :math:`y`
-
-
-Here is a formula for V3 library with single library element per gene (i.e. dual sgRNAs in one construct targeting same gene).
-
-Phenotype score for each :math:`T` comparing :math:`y` vs :math:`x`:
-
-.. math::
-    \text{PhenoScore}(T,x,y) =
-    \left(
-    \frac{
-        \overline{\Delta_{(x,y)}}
-    }{
-        \text{median}( {\overline{\Delta_{(x_{ctrl},y_{ctrl})}}} )
-    }
-    \right)
-    \times \frac{ 1 }{d_{growth}}
-
-- :math:`\overline{\Delta(x,y)} \rightarrow` log ratio averaged across replicates
-- :math:`T \rightarrow` library elements with sgRNAs targeting :math:`T`
-- :math:`d_{growth} \rightarrow` growth factor to normalize the phenotype score.
-
-Statistical test comparing :math:`y` vs :math:`x` per each target, :math:`T`:
-
-.. math::
-    \text{p-value}(T,x,y) = \text{t-test} \left(
-    \begin{bmatrix}{N_{x}}\end{bmatrix}_{(a,b)},
-    \begin{bmatrix}{N_{y}}\end{bmatrix}_{(a,b)}
-    \right)
-
-
-(see this wikipedia page: `Dependent t-test for paired samples`_)
-
-(see the link to the implemented tool: `ttest_rel, a scipy module`_)
-
-    This is a test for the null hypothesis that two related or repeated samples have identical average (expected) values.
-
------------------------
-
-.. automodule:: screenpro.phenoscore
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. automodule:: screenpro.phenostats
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. _`Dependent t-test for paired samples`: https://en.wikipedia.org/wiki/Student%27s_t-test#Dependent_t-test_for_paired_samples
-.. _`ttest_rel, a scipy module`: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.ttest_rel.html
diff --git a/docs/source/plotting.rst b/docs/source/plotting.rst
deleted file mode 100644
index 98d85e3..0000000
--- a/docs/source/plotting.rst
+++ /dev/null
@@ -1,9 +0,0 @@
-Plotting and visualization modules
-=======================
-
-
-.. automodule:: screenpro.plotting
-   :members:
-   :undoc-members:
-   :show-inheritance:
-

From 00988262d11f960a6ae56c27ec020c337fba7052 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:43:13 -0700
Subject: [PATCH 26/37] mend

---
 screenpro/phenoscore/__init__.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/screenpro/phenoscore/__init__.py b/screenpro/phenoscore/__init__.py
index 77c5bfe..696ba9f 100644
--- a/screenpro/phenoscore/__init__.py
+++ b/screenpro/phenoscore/__init__.py
@@ -1,5 +1,12 @@
-"""
-phenoscore module
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
+"""phenoscore module
+
+This module contains functions for calculating relative phenotypes from CRISPR screens
+datasets.
 """
 
 import numpy as np

From 67989e0ac83a4c6b7ec3175111b05212f73cf551 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:43:34 -0700
Subject: [PATCH 27/37] update files main modules

---
 screenpro/__init__.py | 25 ++++++++++++++++++++++---
 screenpro/__main__.py |  5 +++++
 screenpro/assays.py   | 11 ++++++++---
 screenpro/load.py     | 43 +++++++++++++++++++++++++++++++++----------
 screenpro/main.py     |  1 +
 5 files changed, 69 insertions(+), 16 deletions(-)

diff --git a/screenpro/__init__.py b/screenpro/__init__.py
index 036f773..1c2da6f 100644
--- a/screenpro/__init__.py
+++ b/screenpro/__init__.py
@@ -1,10 +1,29 @@
-from . import plotting as pl
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
+'''ScreenPro2: A Python package for pooled CRISPR screens analysis
+
+This package contains several modules, including:
+
+**Main modules:**
+- ngs: tools for generating counts from NGS data
+- phenoscore: tools for calculating phenoscores
+- assays: wrappers for analyzing CRISPR screens data from standard assays
+
+**Additional modules:**
+- load: tools for loading and saving data
+- visualize: tools for visualizing data
+- datasets: API for accessing pre-processed datasets
+'''
+
 from . import phenoscore as ps
 
-from . import utils
 from . import ngs
+from . import assays
 from . import load
-from . import dashboard
+from . import visualize as viz
 
 from .ngs import GuideCounter
 from .assays import PooledScreens, GImaps
diff --git a/screenpro/__main__.py b/screenpro/__main__.py
index 5d6a810..a0fad73 100644
--- a/screenpro/__main__.py
+++ b/screenpro/__main__.py
@@ -1,3 +1,8 @@
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
 from .main import main
 
 main()
diff --git a/screenpro/assays.py b/screenpro/assays.py
index 7482e3c..42b6b2d 100644
--- a/screenpro/assays.py
+++ b/screenpro/assays.py
@@ -1,5 +1,10 @@
-"""
-Assays module
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
+"""Assays module
+
 """
 
 import numpy as np
@@ -10,7 +15,7 @@
 from pydeseq2 import preprocessing
 from .phenoscore.deseq import runDESeq, extractDESeqResults
 from .phenoscore import runPhenoScore, runPhenoScoreForReplicate
-from .utils import ann_score_df
+from .ngs.utils import ann_score_df
 from copy import copy
 
 
diff --git a/screenpro/load.py b/screenpro/load.py
index 4eb629d..0ded2e6 100644
--- a/screenpro/load.py
+++ b/screenpro/load.py
@@ -1,12 +1,16 @@
-"""
-Module for loading screen datasets
+## Copyright (c) 2022-2024 ScreenPro2 Development Team.
+## All rights reserved.
+## Gilbart Lab, UCSF / Arc Institute.
+## Multi-Omics Tech Center, Arc Insititue.
+
+"""Load module
+
+Functions to load screen datasets and sgRNA library tables.
 """
 
 import pickle
 import pandas as pd
 
-from .utils import check_protospacer_length, trim_protospacer
-
 
 def load_cas9_sgRNA_library(library_path, library_type, sep='\t', index_col=0, protospacer_length=19, verbose=True, **args):
     '''Load Cas9 sgRNA library table for single or dual guide design.
@@ -38,12 +42,12 @@ def load_cas9_sgRNA_library(library_path, library_type, sep='\t', index_col=0, p
         library['protospacer'] = library['protospacer'].str.upper()
 
         protospacer_col = 'protospacer'
-        in_length = check_protospacer_length(library, 'protospacer')
+        in_length = _check_protospacer_length(library, 'protospacer')
         if in_length == protospacer_length:
             pass
         elif in_length > protospacer_length:
             if verbose: print(f"Trimming protospacer sequences in '{protospacer_col}' column.")
-            library = trim_protospacer(
+            library = _trim_protospacer(
                 library, protospacer_col, 
                 '5prime', 
                 in_length - protospacer_length
@@ -82,12 +86,12 @@ def load_cas9_sgRNA_library(library_path, library_type, sep='\t', index_col=0, p
 
         # # TODO: Enable trimming of protospacer sequences through command line arguments.
         for protospacer_col in ['protospacer_A', 'protospacer_B']:
-            in_length = check_protospacer_length(library, protospacer_col) 
+            in_length = _check_protospacer_length(library, protospacer_col) 
             if in_length == protospacer_length:
                 pass
             elif in_length > protospacer_length:
                 if verbose: print(f"Trimming protospacer sequences in '{protospacer_col}' column.")
-                library = trim_protospacer(
+                library = _trim_protospacer(
                     library, protospacer_col, 
                     '5prime', 
                     in_length - protospacer_length
@@ -189,7 +193,26 @@ def loadScreenProcessingData(experimentName, collapsedToTranscripts=True, premer
     return dataDict
 
 
-def write_screen_pkl(screen, name):
+def _check_protospacer_length(library, protospacer_col):
+    lengths = list(set(library[protospacer_col].str.len()))
+    if len(lengths) > 1:
+        raise ValueError(f"Protospacer lengths are not uniform: {lengths}")
+    else:
+        length = lengths[0]
+        return length
+
+
+def _trim_protospacer(library, protospacer_col, trim_side, trim_len):
+    if trim_side == '5prime':
+        library[protospacer_col] = library[protospacer_col].str[trim_len:].str.upper()
+    
+    elif trim_side == '3prime':
+        library[protospacer_col] = library[protospacer_col].str[:-trim_len].str.upper()
+    
+    return library
+
+
+def _write_screen_pkl(screen, name):
     """
     Write AnnData object to a pickle file
     
@@ -203,7 +226,7 @@ def write_screen_pkl(screen, name):
         print(f'Object successfully saved to "{file_name}"')
 
 
-def read_screen_pkl(name):
+def _read_screen_pkl(name):
     """
     Read ScreenPro object from a pickle file
     
diff --git a/screenpro/main.py b/screenpro/main.py
index 0eb34c2..66d6c43 100644
--- a/screenpro/main.py
+++ b/screenpro/main.py
@@ -8,6 +8,7 @@
 from .__init__ import __version__
 from . import ngs
 
+
 def add_counter_parser(parent_subparsers, parent):
     name = "guidecounter"
     desc = "Process FASTQ files to count sgRNA sequences."

From 593a4795748a24009537a62f4946399a564728a5 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:50:52 -0700
Subject: [PATCH 28/37] change file format

---
 docs/source/ngs.md  | 27 +++++++++++++++++++++++++++
 docs/source/ngs.rst | 30 ------------------------------
 2 files changed, 27 insertions(+), 30 deletions(-)
 create mode 100644 docs/source/ngs.md
 delete mode 100644 docs/source/ngs.rst

diff --git a/docs/source/ngs.md b/docs/source/ngs.md
new file mode 100644
index 0000000..5e22e9e
--- /dev/null
+++ b/docs/source/ngs.md
@@ -0,0 +1,27 @@
+# NGS screen processing module
+
+`GuideCounter` class is a wrapper to run the functions for a
+CRISPR screen experiment.
+
+This module contains a set of python functions to process and analyze
+NGS files from CRISPR screens. Based on the type of CRISPR-Cas system
+used for the screen, the functions are divided into two classes:
+`Cas9` and `Cas12`.
+
+------------------------------------------------------------------------
+
+::: {.automodule members="" undoc-members="" show-inheritance=""}
+screenpro.ngs
+:::
+
+::: {.automodule members="" undoc-members="" show-inheritance=""}
+screenpro.ngs.GuideCounter
+:::
+
+::: {.automodule members="" undoc-members="" show-inheritance=""}
+screenpro.ngs.cas9
+:::
+
+::: {.automodule members="" undoc-members="" show-inheritance=""}
+screenpro.ngs.cas12
+:::
diff --git a/docs/source/ngs.rst b/docs/source/ngs.rst
deleted file mode 100644
index 148c29a..0000000
--- a/docs/source/ngs.rst
+++ /dev/null
@@ -1,30 +0,0 @@
-NGS screen processing module
-=======================
-
-`Counter` class is a wrapper to run the functions for a CRISPR screen experiment.
-
-This module contains a set of python functions to process and analyze NGS files from CRISPR screens.
-Based on the type of CRISPR-Cas system used for the screen, the functions are divided into 
-two classes: `Cas9` and `Cas12`.
-
------------------------
-
-.. automodule:: screenpro.ngs
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. automodule:: screenpro.ngs.counter
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. automodule:: screenpro.ngs.cas9
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. automodule:: screenpro.ngs.cas12
-   :members:
-   :undoc-members:
-   :show-inheritance:

From 5bf67efa4bed58d85e4f8814e18b3f012c91ebd5 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 00:51:40 -0700
Subject: [PATCH 29/37] fix import

---
 screenpro/assays.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/assays.py b/screenpro/assays.py
index 42b6b2d..c292fed 100644
--- a/screenpro/assays.py
+++ b/screenpro/assays.py
@@ -15,7 +15,7 @@
 from pydeseq2 import preprocessing
 from .phenoscore.deseq import runDESeq, extractDESeqResults
 from .phenoscore import runPhenoScore, runPhenoScoreForReplicate
-from .ngs.utils import ann_score_df
+from .phenoscore.annotate import ann_score_df
 from copy import copy
 
 

From 7b0aa65a4be76294560ead09c751a05685826e97 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 01:57:33 -0700
Subject: [PATCH 30/37] fix format
 https://stackoverflow.com/questions/58945322/how-can-i-use-automodule-or-autoclass-for-sphinx-in-a-markdown-file

---
 docs/source/ngs.md | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/docs/source/ngs.md b/docs/source/ngs.md
index 5e22e9e..37764f6 100644
--- a/docs/source/ngs.md
+++ b/docs/source/ngs.md
@@ -9,19 +9,8 @@ used for the screen, the functions are divided into two classes:
 `Cas9` and `Cas12`.
 
 ------------------------------------------------------------------------
-
-::: {.automodule members="" undoc-members="" show-inheritance=""}
-screenpro.ngs
-:::
-
-::: {.automodule members="" undoc-members="" show-inheritance=""}
-screenpro.ngs.GuideCounter
-:::
-
-::: {.automodule members="" undoc-members="" show-inheritance=""}
-screenpro.ngs.cas9
-:::
-
-::: {.automodule members="" undoc-members="" show-inheritance=""}
-screenpro.ngs.cas12
-:::
+```{eval-rst}  
+.. automodule:: screenpro.ngs
+   :members:
+   :show-inheritance:
+```
\ No newline at end of file

From bc485b4fbb25e7e40f3452b24213e3a55d137835 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 02:26:00 -0700
Subject: [PATCH 31/37] mend

---
 docs/source/ngs.md | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/docs/source/ngs.md b/docs/source/ngs.md
index 37764f6..df58ec4 100644
--- a/docs/source/ngs.md
+++ b/docs/source/ngs.md
@@ -13,4 +13,18 @@ used for the screen, the functions are divided into two classes:
 .. automodule:: screenpro.ngs
    :members:
    :show-inheritance:
-```
\ No newline at end of file
+```
+
+### Cas9 CRISPR-Cas system (single or dual sgRNA libraries)
+```{eval-rst}  
+.. automodule:: screenpro.cas9
+   :members:
+   :show-inheritance:
+```
+
+### Cas12 CRISPR-Cas system (multiplexed crRNA libraries)
+```{eval-rst}  
+.. automodule:: screenpro.cas12
+   :members:
+   :show-inheritance:
+```

From 24499ec20609f6998600ea8bfb04bb705a7faa4e Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 02:42:25 -0700
Subject: [PATCH 32/37] mend

---
 docs/source/assays.md      |  8 ++++++++
 docs/source/phenotype.md   | 18 +++++++++++++-----
 docs/source/references.md  | 20 ++++++++++++++++++++
 docs/source/references.rst | 27 ---------------------------
 4 files changed, 41 insertions(+), 32 deletions(-)
 create mode 100644 docs/source/assays.md
 create mode 100644 docs/source/references.md
 delete mode 100644 docs/source/references.rst

diff --git a/docs/source/assays.md b/docs/source/assays.md
new file mode 100644
index 0000000..5524eff
--- /dev/null
+++ b/docs/source/assays.md
@@ -0,0 +1,8 @@
+# CRISPR Screen Assays
+
+```{eval-rst}  
+.. automodule:: screenpro.assays
+   :members:
+   :undoc-members:
+   :show-inheritance:
+```
\ No newline at end of file
diff --git a/docs/source/phenotype.md b/docs/source/phenotype.md
index eac5e98..f50aacd 100644
--- a/docs/source/phenotype.md
+++ b/docs/source/phenotype.md
@@ -48,8 +48,16 @@ module](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.ttest_r
 > This is a test for the null hypothesis that two related or repeated
 > samples have identical average (expected) values.
 
-------------------------------------------------------------------------
-
-::: {.automodule members="" show-inheritance=""}
-screenpro.phenoscore
-:::
+___
+
+```{eval-rst}  
+.. automodule:: screenpro.phenoscore
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+.. automodule:: screenpro.phenostats
+   :members:
+   :undoc-members:
+   :show-inheritance:
+```
\ No newline at end of file
diff --git a/docs/source/references.md b/docs/source/references.md
new file mode 100644
index 0000000..63a27cc
--- /dev/null
+++ b/docs/source/references.md
@@ -0,0 +1,20 @@
+# References
+
+-   @Herken2023 *bioRxiv* - Gilbert Lab
+-   @Hsiung2023 *bioRxiv* - Gilbert Lab
+-   @Han2020 *Nature* - Bassik Lab
+-   @Han2017 *Nature Biotechnology* - Bassik Lab
+-   @Tian2019 *Neuron* - Kampmann Lab
+-   @Horlbeck2016 *eLife* - Weissman Lab
+-   @Gilbert2014 *Cell* - Weissman Lab
+-   @Kampmann2014 *Nature Protocols* - Weissman Lab
+-   @Kampmann2013 *PNAS* - Weissman Lab
+-   @Bassik2013 *Cell* - Weissman Lab
+
+___
+
+```{eval-rst}  
+.. bibliography::
+    :all:
+
+```
diff --git a/docs/source/references.rst b/docs/source/references.rst
deleted file mode 100644
index 14fc766..0000000
--- a/docs/source/references.rst
+++ /dev/null
@@ -1,27 +0,0 @@
-References
-----------
-* :cite:t:`Herken2023` *bioRxiv* - Gilbert Lab
-
-* :cite:t:`Hsiung2023` *bioRxiv* - Gilbert Lab
-
-* :cite:t:`Han2020` *Nature* - Bassik Lab
-
-* :cite:t:`Han2017` *Nature Biotechnology* - Bassik Lab
-
-* :cite:t:`Tian2019` *Neuron* - Kampmann Lab
-
-* :cite:t:`Horlbeck2016` *eLife* - Weissman Lab
-
-* :cite:t:`Gilbert2014` *Cell* - Weissman Lab
-
-* :cite:t:`Kampmann2014` *Nature Protocols* - Weissman Lab
-
-* :cite:t:`Kampmann2013` *PNAS* - Weissman Lab
-
-* :cite:t:`Bassik2013` *Cell* - Weissman Lab
-
-
-=============
-
-.. bibliography::
-    :all:

From 5bf65e484fb0fb3a3759439840c28995c93fe091 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 03:21:43 -0700
Subject: [PATCH 33/37] clear

---
 docs/source/assays.rst | 7 -------
 1 file changed, 7 deletions(-)
 delete mode 100644 docs/source/assays.rst

diff --git a/docs/source/assays.rst b/docs/source/assays.rst
deleted file mode 100644
index 0de12cb..0000000
--- a/docs/source/assays.rst
+++ /dev/null
@@ -1,7 +0,0 @@
-CRISPR Screen Assays
-======================
-
-.. automodule:: screenpro.assays
-   :members:
-   :undoc-members:
-   :show-inheritance:
\ No newline at end of file

From 3ec885eb1d4c2e9e4696fb12fce12f88f79fe983 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 03:38:15 -0700
Subject: [PATCH 34/37] update docs files

---
 docs/source/history.rst  | 11 ++++++++---
 docs/source/index.rst    |  1 +
 docs/source/load.md      | 13 +++++++++++++
 docs/source/load.rst     | 14 --------------
 docs/source/visualize.md | 12 ++++++++++++
 5 files changed, 34 insertions(+), 17 deletions(-)
 create mode 100644 docs/source/load.md
 delete mode 100644 docs/source/load.rst
 create mode 100644 docs/source/visualize.md

diff --git a/docs/source/history.rst b/docs/source/history.rst
index a58a937..7277db6 100644
--- a/docs/source/history.rst
+++ b/docs/source/history.rst
@@ -2,12 +2,17 @@
 History
 =======
 
-0.3.1 - 0.4.0 (June 2024 - July 2024)
+1.0.0
+~~~~~
+* coming soon!
+
+0.4.0 - after (June 2024 - July 2024)
 ~~~~~~~~~~~~~~~~~~~
-* add command line interface
+* add command line interface, i.e. `screenpro --help`
+* rename `Counter` class to `GuideCounter` for code clarity
 * major bug fixes and improvements in code formatting
 
-0.2.11 - 0.3.0 (Apr 2024 - May 2024)
+0.2.11 - 0.3.5 (Apr 2024 - June 2024)
 ~~~~~~~~~~~~~~~~~
 * introduce `Counter` class as wrapper for `ngs` module
 * improve core functionalities for CLI
diff --git a/docs/source/index.rst b/docs/source/index.rst
index d188efb..ed19189 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -15,6 +15,7 @@ Welcome to ScreenPro2's documentation!
    assays
    ngs
    phenotype
+   visulize
    load
 
 .. toctree::
diff --git a/docs/source/load.md b/docs/source/load.md
new file mode 100644
index 0000000..bc73d89
--- /dev/null
+++ b/docs/source/load.md
@@ -0,0 +1,13 @@
+# Load module
+
+Set of python functions to read, write, and integrate CRISPR screening
+datasets from different platforms. 
+
+___
+
+```{eval-rst}  
+.. automodule:: screenpro.load
+   :members:
+   :undoc-members:
+   :show-inheritance:
+```
\ No newline at end of file
diff --git a/docs/source/load.rst b/docs/source/load.rst
deleted file mode 100644
index acda05e..0000000
--- a/docs/source/load.rst
+++ /dev/null
@@ -1,14 +0,0 @@
-Load module
-=======================
-
-Set of python functions to read, write, and integrate CRISPR screening datasets from different platforms.
-Notably, `loadScreenProcessingData` function can load `ScreenProcessing`_ outputs.
-
------------------------
-
-.. automodule:: screenpro.load
-   :members:
-   :undoc-members:
-   :show-inheritance:
-
-.. _`ScreenProcessing`: https://github.com/mhorlbeck/ScreenProcessing
diff --git a/docs/source/visualize.md b/docs/source/visualize.md
new file mode 100644
index 0000000..c2febe3
--- /dev/null
+++ b/docs/source/visualize.md
@@ -0,0 +1,12 @@
+# Visualize module
+
+Set of python classes and functions to enable visualizing CRISPR screening datasets.
+
+___
+
+```{eval-rst}  
+.. automodule:: screenpro.visualize
+   :members:
+   :undoc-members:
+   :show-inheritance:
+```
\ No newline at end of file

From cd59d95f35917494240af681568642c9b54e023f Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 17:10:14 -0700
Subject: [PATCH 35/37] update default `fc_transformation` parameter

---
 screenpro/assays.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/assays.py b/screenpro/assays.py
index c292fed..ece57ce 100644
--- a/screenpro/assays.py
+++ b/screenpro/assays.py
@@ -24,7 +24,7 @@ class PooledScreens(object):
     pooledScreens class for processing CRISPR screen datasets
     """
 
-    def __init__(self, adata, fc_transformation='log2(x+1)', test='ttest', n_reps=3):
+    def __init__(self, adata, fc_transformation='log2', test='ttest', n_reps=3):
         """
         Args:
             adata (AnnData): AnnData object with adata.X as a matrix of sgRNA counts

From 52769e8737dd2e952411a5e5ddb0af6b2eff6bfe Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 19:48:09 -0700
Subject: [PATCH 36/37] update docs

---
 docs/source/load.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/docs/source/load.md b/docs/source/load.md
index bc73d89..569e11f 100644
--- a/docs/source/load.md
+++ b/docs/source/load.md
@@ -1,7 +1,8 @@
-# Load module
+# Data loading module
 
 Set of python functions to read, write, and integrate CRISPR screening
-datasets from different platforms. 
+resources (e.g. guide RNA libraries) and datasets from different platforms 
+and analysis tools.
 
 ___
 

From 6fe2cf266aef28355d53bbaae1df519cbab56938 Mon Sep 17 00:00:00 2001
From: abearab <abea@arcinstitute.org>
Date: Fri, 12 Jul 2024 19:50:37 -0700
Subject: [PATCH 37/37] bump version 0.4.1

---
 screenpro/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/screenpro/__init__.py b/screenpro/__init__.py
index 1c2da6f..96f91f5 100644
--- a/screenpro/__init__.py
+++ b/screenpro/__init__.py
@@ -28,6 +28,6 @@
 from .ngs import GuideCounter
 from .assays import PooledScreens, GImaps
 
-__version__ = "0.4.0"
+__version__ = "0.4.1"
 __author__ = "Abe Arab"
 __email__ = 'abea@arcinstitute.org' # "abarbiology@gmail.com"