stabilize python versions

2_ReportLimma_wo_GUI/limma_params.yaml

@@ -1,11 +1,14 @@
 
+# Path to report file
 report_infile: D:\ReportAnalysis\2_ReportLimma_wo_GUI\test\test1\NM_qfq_table_pgmfreq.tsv
 
+# Path to .tsv table with sample groups
 sample_table: D:\ReportAnalysis\2_ReportLimma_wo_GUI\limma_sample_table.tsv
 
+# Path to output file
 outfile: D:\ReportAnalysis\2_ReportLimma_wo_GUI\test\test1\LIMMA_NM_qfq_table_pgmfreq.tsv
 
-# Possible types 
+# Statistical tests applied. Possible types:
 # - limma
 # - limma_with_duplicates
 # - t-test
@@ -14,13 +17,15 @@ test_type:
   - limma_with_duplicates
   - t-test
 
+# Integrations used to apply Limma
 integrations:
   - Z_pgm2p
   - Z_pgm2p_dNM
   - Z_p2qf
   - Z_qf2qfq
   - Z_qfq2qfqall
 
+# Groups to be compared (use the group names of sample table)
+# If the value is [Group1, Group2],the mean difference will be calculated as Group1 - Group2
 hypothesis_testing:
-  - [ H, C ]
-  - [ Control, Heteroplasmy ]
+  - [ Heteroplasmy, Control ]

4_qTableReport/qReportMaker.py

@@ -72,6 +72,7 @@ def generateFreqTable(config, sign_i, fdr_i, rep, contrast):
     if rep_i.shape[0] == 0:
         return []
 
+
     bi, biPivot = BSLM({
         'infile': rep_i,
         'outfile': None,
@@ -135,7 +136,7 @@ def qReportPivot(config, fdr_i, sign_i, rep, ptmCol, contrast):
 
     qTableD = {
         'PSMs': qTableD,
-        'Peptides': qTableD.applymap(lambda x: 0 if x==0 else 1)
+        'Peptides': qTableD.map(lambda x: 0 if x==0 else 1)
         }
 
     return qTableD
@@ -162,7 +163,7 @@ def qReportAddData(config, fdr_i, sign_i, quan, qTableD, repNM, rep, contrast):
     pdmCol, qCol, qdCol, pdmFreq, qFreq, sign, signNM, FDRdNM, FDRNM = getColumnNames(config, contrast)
 
     # Collapse PTMs of the same protein
-    qTableD = qTableD.reset_index().drop(pdmCol, axis=1).groupby([qCol]).agg(sum)
+    qTableD = qTableD.reset_index().drop(pdmCol, axis=1).groupby([qCol]).agg("sum")
 
     # Get all PTMs inside each protein 
     qTableD[(quan, 'PTMs')] = qTableD.sum(axis=1)
@@ -176,7 +177,7 @@ def qReportAddData(config, fdr_i, sign_i, quan, qTableD, repNM, rep, contrast):
 
     # Add NM freq considering all pdm
     qTableD = qTableD.join(
-        repNM[[qCol, pdmFreq]].groupby(qCol).agg(sum).fillna(0)\
+        repNM[[qCol, pdmFreq]].groupby(qCol).agg("sum").fillna(0)\
             .rename(columns={pdmFreq[0]: quan, 'REL': 'NM'}),
         how='left'
         )
@@ -189,7 +190,7 @@ def qReportAddData(config, fdr_i, sign_i, quan, qTableD, repNM, rep, contrast):
                 repNM[FDRNM]<fdr_i
                 ]),
             [qCol, pdmFreq]
-            ].groupby(qCol).agg(sum)\
+            ].groupby(qCol).agg("sum")\
             .rename(columns={pdmFreq[0]: quan, 'REL': 'NMsig'}),
         how='left'
         ).fillna(0)

4_qTableReport/utils/BinomialSiteListMaker.py

@@ -44,6 +44,7 @@ def getBinom(wdf, col):
     '''
     '''
     p, d, a, m, x = col
+
 
     # Get aa freq
     afreq = pd.Series(list(zip(*[
@@ -76,8 +77,8 @@ def getBinom(wdf, col):
     # P2 --> p = p(a) & ni = Total pdm with i mod
     fdf['p2'] = [afreq[i] for i in fdf[a]]
 
-    d_size = wdf[d].value_counts().to_frame().reset_index().rename(
-        columns={'index': 'd', 'd': 'n2'})
+    d_size = wdf[d].value_counts().to_frame().reset_index()#.rename(columns={'index': 'd', 'd': 'n2'})
+    d_size.columns = ['d', 'n2']
 
     fdf = pd.merge(
         fdf,
@@ -160,6 +161,7 @@ def main(args):
 
     wdf = pd.DataFrame(wdf, columns=[pdm, p, d, a, m])
 
+
     logging.info("Calculating binomial pvalues at PSM level")
     biS = getBinom(wdf, [p, d, a, m, x])
 

requirements.txt

@@ -0,0 +1,45 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: win-64
+blas=1.0=mkl
+bottleneck=1.3.5=py311h5bb9823_0
+bzip2=1.0.8=he774522_0
+ca-certificates=2023.08.22=haa95532_0
+et_xmlfile=1.1.0=py311haa95532_0
+icc_rt=2022.1.0=h6049295_2
+intel-openmp=2023.1.0=h59b6b97_46319
+libffi=3.4.4=hd77b12b_0
+mkl=2023.1.0=h6b88ed4_46357
+mkl-service=2.4.0=py311h2bbff1b_1
+mkl_fft=1.3.8=py311h2bbff1b_0
+mkl_random=1.2.4=py311h59b6b97_0
+numexpr=2.8.7=py311h1fcbade_0
+numpy=1.26.0=py311hdab7c0b_0
+numpy-base=1.26.0=py311hd01c5d8_0
+openpyxl=3.0.10=py311h2bbff1b_0
+openssl=3.0.11=h2bbff1b_2
+packaging=23.1=py311haa95532_0
+pandas=2.1.1=py311hf62ec03_0
+patsy=0.5.3=py311haa95532_0
+pip=23.3=py311haa95532_0
+plotly=5.18.0=py_0
+python=3.11.5=he1021f5_0
+python-dateutil=2.8.2=pyhd3eb1b0_0
+python-tzdata=2023.3=pyhd3eb1b0_0
+pytz=2023.3.post1=py311haa95532_0
+pyyaml=6.0.1=py311h2bbff1b_0
+scipy=1.11.3=py311hc1ccb85_0
+setuptools=68.0.0=py311haa95532_0
+six=1.16.0=pyhd3eb1b0_1
+sqlite=3.41.2=h2bbff1b_0
+statsmodels=0.14.0=py311hd7041d2_0
+tbb=2021.8.0=h59b6b97_0
+tenacity=8.2.2=py311haa95532_0
+tk=8.6.12=h2bbff1b_0
+tzdata=2023c=h04d1e81_0
+vc=14.2=h21ff451_1
+vs2015_runtime=14.27.29016=h5e58377_2
+wheel=0.41.2=py311haa95532_0
+xz=5.4.2=h8cc25b3_0
+yaml=0.2.5=he774522_0
+zlib=1.2.13=h8cc25b3_0