Merge pull request #63 from bigbio/dev

Minor changes in the README

README.md

@@ -193,8 +193,6 @@ Options:
 
 #### Compute TPA
 
-# TODO @PingZheng: Can you confirm that this command works?
-
 ```asciidoc
 python compute_tpa --fasta Homo-sapiens-uniprot-reviewed-contaminants-decoy-202210.fasta --organism 'human' --peptides PXD003947-peptides.csv --ruler --ploidy 2 --cpc 200 --output PXD003947-tpa.tsv --verbose
 ```
@@ -250,3 +248,4 @@ Wang H, Dai C, Pfeuffer J, Sachsenberg T, Sanchez A, Bai M, Perez-Riverol Y. Tis
 - Julianus Pfeuffer
 - Yasset Perez-Riverol
 - Hong Wang
+- Ping Zheng

ibaqpy/ibaq/combiner.py

@@ -29,7 +29,7 @@
 
 class Combiner:
     def __init__(
-        self, data_folder: os.PathLike, covariate: str = None, organism: str = "HUMAN"
+            self, data_folder: os.PathLike, covariate: str = None, organism: str = "HUMAN"
     ):
         """Generate concated IbaqNorm and metadata."""
         self.df_pca = compute_pca(self.df_corrected.T, n_components=5)
@@ -114,11 +114,11 @@ def imputer(self, covariate_to_keep: list = None):
         print(self.df.head)
 
     def outlier_removal(
-        self,
-        n_components: int = None,
-        min_cluster_size: int = None,
-        min_samples_num: int = None,
-        n_iter: int = None,
+            self,
+            n_components: int = None,
+            min_cluster_size: int = None,
+            min_samples_num: int = None,
+            n_iter: int = None,
     ):
         logger.info("Removing outliers from imputed data ...")
         # Apply iterative outlier removal on imputed data
@@ -164,7 +164,7 @@ def outlier_removal(
         )
 
     def batch_correction(
-        self, n_components: int = None, tissue_parts_to_keep: int = None
+            self, n_components: int = None, tissue_parts_to_keep: int = None
     ):
         logger.info("Applying batch effect correction ...")
         # Plot PCA of uncorrected imputed data

ibaqpy/ibaq/peptide_normalization.py

@@ -540,18 +540,18 @@ def peptide_normalization(
         raise FileNotFoundError("The file does not exist.")
 
     print("Loading data..")
-    F = Feature(parquet)
+    feature = Feature(parquet)
     if sdrf:
         technical_repetitions, label, sample_names, choice = analyse_sdrf(sdrf)
     else:
-        technical_repetitions, label, sample_names, choice = F.experimental_inference
-    low_frequency_peptides = F.low_frequency_peptides
+        technical_repetitions, label, sample_names, choice = feature.experimental_inference
+    low_frequency_peptides = feature.low_frequency_peptides
     header = False
     if not skip_normalization and pnmethod == "globalMedian":
-        med_map = F.get_median_map()
+        med_map = feature.get_median_map()
     elif not skip_normalization and pnmethod == "conditionMedian":
-        med_map = F.get_median_map_to_condition()
-    for samples, df in F.iter_samples():
+        med_map = feature.get_median_map_to_condition()
+    for samples, df in feature.iter_samples():
         for sample in samples:
             # Perform data preprocessing on every sample
             print(f"{str(sample).upper()}: Data preprocessing...")
@@ -638,4 +638,4 @@ def peptide_normalization(
                 header = True
 
     if save_parquet:
-        F.csv2parquet(output)
+        feature.csv2parquet(output)