immucellai2 2.1.24__tar.gz → 2.1.25__tar.gz

{immucellai2-2.1.24 → immucellai2-2.1.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: immucellai2
-Version: 2.1.24
+Version: 2.1.25
 Summary: A tool for immune cell type deconvolution
 Home-page: https://github.com/VyvyanYjm/ImmuCellAI2.0
 Author: YangJingmin

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/Deconvolution.py

@@ -8,13 +8,9 @@ from immucellai2.myclasses import CLASS_FOR_RUN, CLASS_FOR_RUNRESULT, CLASS_FOR_
 import scipy
 import os
 import tqdm
-import joblib
-import dask
-import dask.delayed
-import dask.multiprocessing
-from dask.distributed import Client, LocalCluster
 from concurrent.futures import ProcessPoolExecutor, as_completed
 from itertools import chain
+import joblib
 import multiprocessing
 from copy import deepcopy
 
@@ -26,6 +22,7 @@ class Move:
         raise NotImplementedError
     def propose(self, state, random_state):
         raise NotImplementedError
+        
 class GibbsMHMove(Move):
     def __init__(self, phi, alpha, sp):
         self.phi = phi
@@ -37,12 +34,13 @@ class GibbsMHMove(Move):
         q, _ = self.get_proposal(state.coords, random_state)
         new_state = State(q)
         return new_state, np.ones(state.coords.shape[0], dtype=bool)
+        
 def gibbs_proposal_function(coords, random, phi, alpha, sp):
     min_threshold = 1e-6
     updated_coords = np.copy(coords) 
     column_sums = np.sum(phi, axis=0)
     normalized_matrix = phi / column_sums
-    G, K = normalized_matrix.shape  # ʹ�� normalized_matrix ����״
+    G, K = normalized_matrix.shape  
     for n in range(len(coords)):
         theta_n = updated_coords[n, :]
         prob_mat = np.multiply(normalized_matrix, theta_n)
@@ -50,7 +48,7 @@ def gibbs_proposal_function(coords, random, phi, alpha, sp):
         for g in range(G):
             row_sum = np.sum(prob_mat[g, :])  # ʹ�� NumPy ���������к�
             pvals = np.full(K, 1/K) if row_sum < min_threshold else prob_mat[g, :] / row_sum
-            Z_n.append(np.random.multinomial(n=round(sp[g]), pvals=pvals))
+            Z_n.append(random_state.multinomial(n=round(sp[g]), pvals=pvals))
         Z_nk = np.sum(Z_n, axis=0)
         alpha_param = Z_nk + alpha
         updated_coords[n, :] = np.random.dirichlet(alpha=alpha_param)
@@ -66,7 +64,7 @@ class EnsembleSampler:
         self.alpha_value = alpha_value
         self.sp_value = sp_value
         self.backend = Backend(nwalkers=nwalkers, ndim=ndim, iterations=iterations)
-        self._random = np.random.mtrand.RandomState()
+        self.random_state = np.random.mtrand.RandomState() 
     def sample(self, initial_state, iterations=1, progress=False, progress_kwargs=None):
         if progress_kwargs is None: 
             progress_kwargs = {} 
@@ -128,36 +126,101 @@ def get_progress_bar(display, total, **kwargs):
                 return getattr(tqdm, "tqdm_" + display)(total=total, **kwargs)
     return _NoOpPBar()
 
+'''
+def mcse_python(samples):
+    n_iter, n_dim = samples.shape
+    mcse_vec = np.empty(n_dim)
+    for k in range(n_dim):
+        x = samples[:, k]
+        rho = np.correlate(x - x.mean(), x - x.mean(), mode='full')
+        rho = rho[n_iter - 1:] / rho[n_iter - 1]
+        lag = next((i for i, r in enumerate(rho[1:], 1) if r < 0.05), n_iter)
+        ess = n_iter / (1 + 2 * rho[1:lag + 1].sum())
+        mcse_vec[k] = np.std(x, ddof=1) / np.sqrt(ess)
+    return mcse_vec 
+def mcse_python(segment):
+    return np.std(segment, axis=0) / np.sqrt(len(segment))
 def ThreadRunEachSamples( 
-   EmceeParameters = None, referenceMatrix = None, 
-   SampleExpressionData = None, SampleName=None, MAPorMLE = ('MAP','MLE'),  *args): 
+    EmceeParameters = None, 
+    referenceMatrix = None, 
+    SampleExpressionData = None, 
+    SampleName=None, 
+    MAPorMLE = ('MAP','MLE'), 
+    *args): 
+    samplename = SampleName
+    phi_value = referenceMatrix 
+    alpha_value = 1 
+    sp_value = SampleExpressionData 
+    K = EmceeParameters.ndims 
+    rng = np.random.RandomState(seed)
+    max_iter   = EmceeParameters.nsteps
+    nwalkers = EmceeParameters.nwalkers
+    tol_ratio  = 0.01
+    eval_step  = 50
+    theta = EmceeParameters.position
+    if theta.ndim == 1:
+        theta = theta.reshape(nwalkers, K)
+    else:
+        theta = theta[:nwalkers, :K] 
+    full_chain = np.zeros((max_iter, nwalkers, K))
+    converged = False
+    converged_step = None
+    for i in range(max_iter): 
+        gibbs_move = GibbsMHMove(phi_value, alpha_value, sp_value)
+        state, _ = gibbs_move.propose(State(theta), rng)
+        theta = state.coords
+        full_chain[i] = theta
+        if (i + 1) % eval_step == 0 and i + 1 >= eval_step:
+            segment = full_chain[(i + 1 - eval_step): (i + 1)].reshape(-1, K)
+            mcse_vec = mcse_python(segment) 
+            theta_hat = segment.mean(axis=0) 
+            theta_hat_safe = np.where(theta_hat == 0, 1e-10, theta_hat) 
+            ratio = mcse_vec / theta_hat_safe 
+            if np.all(np.abs(ratio) <= tol_ratio):
+                converged = True
+                converged_step = i + 1 
+                break 
+    if converged and converged_step is not None:
+        start_step = max(0, converged_step - 100)
+        truncated_chain = full_chain[start_step:converged_step]
+    else:
+        start_step = max(0, max_iter - 100) 
+        truncated_chain = full_chain[start_step:max_iter]
+    flat_samples = truncated_chain.reshape(-1, K) 
+    return full_chain, flat_samples'''
+
+
+def ThreadRunEachSamples(
+   EmceeParameters = None, referenceMatrix = None,
+   SampleExpressionData = None, SampleName=None, MAPorMLE = ('MAP','MLE'),  *args):
    nwalkers, ndims = EmceeParameters.nwalkers, EmceeParameters.ndims
    position, nsteps = EmceeParameters.position, EmceeParameters.nsteps
-   discard, thin = EmceeParameters.discard, EmceeParameters.thin 
+   discard, thin = EmceeParameters.discard, EmceeParameters.thin
    samplename = SampleName
-   phi_value = referenceMatrix 
-   alpha_value = 1 
-   sp_value = SampleExpressionData 
-   print(" create new threading for sample '%s'"%str(samplename)) 
-   if MAPorMLE == 'MAP': 
+   phi_value = referenceMatrix
+   alpha_value = 1
+   sp_value = SampleExpressionData
+   print(" create new threading for sample '%s'"%str(samplename))
+   if MAPorMLE == 'MAP':
       sampler = EnsembleSampler(nwalkers, ndims, phi_value, alpha_value, sp_value)
    sampler.run_mcmc(position, nsteps, progress=True)
    mcmc_samples, flat_samples = [[[]]], [[]]
    mcmc_samples = sampler.get_chain()
    flat_samples = sampler.get_chain( discard = discard, thin = thin, flat = True)
    print( "Threading for sample '%s' run over, exiting..."%str(samplename))
-   return mcmc_samples, flat_samples 
-
+   return mcmc_samples, flat_samples
+    
 class MultiprocessesResult(object): 
-   def __init__(self, SampleName, SamplingResult, CellType): 
-      self.SampleName = SampleName
-      self.CellTypeList = CellType
-      self.ResultObjectOne = CLASS_FOR_RUNRESULT( 
-         SampleNameList = [ self.SampleName ] , 
-         McmcSamplingResultList = np.array([ SamplingResult[0] ]) , 
-         FlatSamplingResultList = np.array([ SamplingResult[1] ]) , 
-         CellTypeList = CellType
-      ) 
+    def __init__(self, SampleName, SamplingResult, CellType): 
+        self.SampleName = SampleName 
+        self.CellTypeList = CellType 
+        self.ResultObjectOne = CLASS_FOR_RUNRESULT( 
+            SampleNameList = [ self.SampleName ] , 
+            McmcSamplingResultList = np.array([ SamplingResult[0] ]) , 
+            FlatSamplingResultList = np.array([ SamplingResult[1] ]) , 
+            CellTypeList = CellType
+        ) 
+      
 def MergeResultsForAllSample(ThreadList=list(), OtherParams=[], *args):
     print("Merge all results from deconvolution into one ResultObject...")
     if len(ThreadList) < 1: 
@@ -180,60 +243,62 @@ def MergeResultsForAllSample(ThreadList=list(), OtherParams=[], *args):
     FileCellTypeCategory = OtherParams[1]
     # Creating the final merged result object
     MergeResultsObject = CLASS_FOR_RUNRESULT(
-       SampleNameList=SampleNameWhole,
-       CellTypeList=CellTypeWhole,
-       FileCellTypeCategory=FileCellTypeCategory,
-       McmcSamplingResultList=McmcSamplingWhole,
-       FlatSamplingResultList=FlatSamplingWhole,
-       CellTypeRatioResult=CellTypeRatioResultWhole,
-       CellTypeRatioResultFinal=CellTypeRatioResultFinalWhole)
+        SampleNameList=SampleNameWhole,
+        CellTypeList=CellTypeWhole,
+        FileCellTypeCategory=FileCellTypeCategory,
+        McmcSamplingResultList=McmcSamplingWhole,
+        FlatSamplingResultList=FlatSamplingWhole,
+        CellTypeRatioResult=CellTypeRatioResultWhole,
+        CellTypeRatioResultFinal=CellTypeRatioResultFinalWhole)
     return MergeResultsObject
-def MainRun(RunObject, seed = 42, MultithreadModule = 'joblib'): 
-    EnvironmentRun = RunObject.EnvironmentRun
+    
+def MainRun(RunObject, seed=42, MultithreadModule = 'joblib'): 
+    EnvironmentRun = RunObject.EnvironmentRun 
     RecordTime = CLASS_FOR_TIME() 
     nsamples = len(RunObject.SampleList) 
-    EmceeParameterCopy = RunObject.EmceeParameter.mycopy() 
-    CelltypesReferenceMatrix = RunObject.CelltypesReferenceMatrix 
-    SampleNameToIndex = {name: idx for idx, name in enumerate(RunObject.SampleList)}
-    parameterlist = [] 
-    for SampleNameii in range(nsamples):
-        SampleName = RunObject.SampleList[SampleNameii]
-        SampleIndex = SampleNameToIndex[SampleName]  # ��ȡ����
+    parameterlist = []
+    #CelltypesReferenceMatrix = RunObject.CelltypesReferenceMatrix 
+    for sample_index in range(nsamples):
+        SampleName = RunObject.SampleList[sample_index]
         parameterlist.append((
-            EmceeParameterCopy,
-            CelltypesReferenceMatrix,
-            RunObject.SamplesBulkRNAseqExpression[SampleIndex],  # ʹ��������������
-            SampleName,
-            RunObject.MAPorMLE
-        ))
+            (RunObject.EmceeParameter).mycopy(),
+            RunObject.CelltypesReferenceMatrix ,
+            RunObject.SamplesBulkRNAseqExpression[sample_index],
+            RunObject.SampleList[sample_index], 
+            RunObject.MAPorMLE 
+        )) 
+    #EmceeParameterCopy = RunObject.EmceeParameter.mycopy() 
     MultiprocessingReturnValue = [] 
     if MultithreadModule == 'joblib':
-       try: 
-          MultiprocessingReturnValue = joblib.Parallel(n_jobs=int(EnvironmentRun.ThreadNum), backend='loky',verbose=0)(joblib.delayed(ThreadRunEachSamples)(*arg) for arg in parameterlist)
-       except:
-          print('error occurs while paralleling')
-       finally:
-          del parameterlist
-          print('finished all!')
+        try: 
+            results = joblib.Parallel(n_jobs=int(EnvironmentRun.ThreadNum), backend='loky',verbose=0)(joblib.delayed(ThreadRunEachSamples)(*arg) for arg in parameterlist) 
+        except: 
+            print('error occurs while paralleling') 
+        finally: 
+            del parameterlist 
+            print('finished all!') 
     elif MultithreadModule == 'multiprocessing':
         with multiprocessing.Pool(processes=int(EnvironmentRun.ThreadNum)) as pool:
-            try:
-                MultiprocessingReturnValue = pool.starmap(ThreadRunEachSamples, parameterlist)
-            except Exception as e:
-                print(f'Error occurs while paralleling: {e}')
-            finally:
-                pool.close()
-                pool.join()
-                print('Finished all!')
+            results = pool.starmap(
+                ThreadRunEachSamples, 
+                [(EmceeParameterCopy, 
+                  CelltypesReferenceMatrix, 
+                  RunObject.SamplesBulkRNAseqExpression[sample_index], 
+                  RunObject.SampleList[sample_index], 
+                  seed + sample_index, 
+                  RunObject.MAPorMLE
+                  ) for sample_index in range(nsamples)]
+            )   
     MergedResultObject = MergeResultsForAllSample(
-        ThreadList = [MultiprocessesResult( 
-            SampleName = RunObject.SampleList[Sampleii], 
-            SamplingResult = MultiprocessingReturnValue[Sampleii], 
-            CellType=deepcopy(RunObject.CellType),
-        )   for Sampleii in range(len(MultiprocessingReturnValue))],
+        ThreadList=[MultiprocessesResult(
+            RunObject.SampleList[i], 
+            result, 
+            deepcopy(RunObject.CellType)
+        ) for i, result in enumerate(results)],
         OtherParams=[deepcopy(RunObject.CellType), RunObject.FileCellTypeCategory]
-        )
+    ) 
     RecordTime.ShowCostTime()
-    if os.path.exists("TempThread"): os.system("rm -rf TempThread")
+    if os.path.exists("TempThread"): 
+        os.system("rm -rf TempThread")
     print("###<----Main program Run finished...")
     return MergedResultObject 

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/ObtainCategory.py

@@ -49,7 +49,7 @@ def ObtainInformation2(line, SearchString, DictValue):
    else:
       DictValue[SearchString] =  obcontent
 
-def ObtainCellTypeCategory(CellTypeCateogry):
+def ObtainCellTypeCateogry(CellTypeCateogry):
     if CellTypeCateogry is None or not os.path.isfile(CellTypeCateogry):
         try:
             from importlib.resources import files

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/PrepareData.py

@@ -1,38 +1,46 @@
 #!/usr/bin/python3
-from .myclasses import CLASS_FOR_RUN
-from .ObtainCategory import ObtainCellTypeCategory
+from immucellai2.myclasses import CLASS_FOR_RUN
+from immucellai2.ObtainCategory import ObtainCellTypeCateogry
 import pandas
 import os
-import importlib.util
 import re
 import sys
 import multiprocessing as mp
+from importlib_resources import files 
+
+def SelectGeneForDeconvolution(DFReferenceProfile, FileCoveredGenes="", Method="UsedMarker"):
+   print("Select the gene for the following deconvolution...")
+   GeneUsedForDeconvolution = []
+   DFReferenceProfileGenes = DFReferenceProfile.index.values
+   if Method == "UsedMarker":
+      if FileCoveredGenes == "": 
+         try:
+            marker_path = files("immucellai2.myconfig").joinpath("MarkerUsedDeconvolution.txt")
+            FileCoveredGenes = str(marker_path)
+         except Exception as e:
+            script_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
+            FileCoveredGenes = os.path.join(script_dir, "immucellai2/myconfig/MarkerUsedDeconvolution.txt")
+            print(f"[WARNING] Using fallback path: {FileCoveredGenes}")
+      try:
+         GeneUsedForDeconvolution0 = pandas.read_table(FileCoveredGenes, sep="\t", header=None).iloc[1].tolist()
+         print(f"[DEBUG] head:\n list(islice(GeneUsedForDeconvolution0, 3))")
+         GeneUsedForDeconvolution = list(set(GeneUsedForDeconvolution0).intersection(set(DFReferenceProfileGenes)))
+         print(f"Successfully loaded {len(GeneUsedForDeconvolution)} marker genes")
+      except FileNotFoundError:
+         print(f"Error: Marker file not found - {FileCoveredGenes}")
+         print("Please check:")
+         print("1. Package is installed correctly (pip install --upgrade immucellai2)")
+         print("2. Environment variable IMMUCELLAI_CONFIG_DIR is set")
+         return [] 
+      except Exception as e:
+         print(f"Error reading marker file: {str(e)}") 
+         return [] 
+   return GeneUsedForDeconvolution
 
 def Obtainmyconfigpath():
    script_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
    return os.path.join(script_dir, "immucellai2", "myconfig", "")
 
-def get_package_dir(package_name):
-    spec = importlib.util.find_spec(package_name)
-    if spec is None:
-        raise ModuleNotFoundError(f"Package '{package_name}' not found")
-    path = spec.origin or spec.submodule_search_locations[0]
-    return os.path.dirname(path) 
-
-def SelectGeneForDeconvolution(DFReferenceProfile, FileCoveredGenes="", Method="UsedMarker"):
-    print("Select the gene for the following deconvolution...")
-    GeneUsedForDeconvolution = []
-    DFReferenceProfileGenes = DFReferenceProfile.index.values
-    if Method == "UsedMarker":
-        if FileCoveredGenes == "":
-            pkg_marker_path = os.path.join(get_package_dir("immucellai2"), "myconfig/MarkerUsedDeconvolution.txt")
-            if os.path.exists(pkg_marker_path):
-                FileCoveredGenes = pkg_marker_path
-                print(f"[INFO] Found marker file in immucellai2 package: {FileCoveredGenes}")
-            GeneUsedForDeconvolution0 = (pandas.read_table(FileCoveredGenes, sep= "\t")).iloc[0].to_list()
-            GeneUsedForDeconvolution = list(set(GeneUsedForDeconvolution0).intersection(set(DFReferenceProfileGenes)))
-    return GeneUsedForDeconvolution
-
 def CelltypeCategoryCheck(FileCellTypeCategory = "", celltypelist = [] ):
    print("Check the Celltype covered by configfile")
    if FileCellTypeCategory == "":
@@ -67,11 +75,11 @@ def InitialCellTypeRatioCheck(InitialCellTypeRatio, FileInitialCellTypeRatio = "
    elif Expactedcelltypenum in [ ncelltype, ncelltype -1 ]:
       return FileInitialCellTypeRatio
    else:
-      InitialCellTypeRatio = 'randn'     
+      InitialCellTypeRatio = 'randn'    
 
 def PrepareData(FileReferenceProfile , 
    FileSampleExpressionProfile , 
-   EnvironmentConfig = ("", "") ,
+   EnvironmentConfig = "" ,
    FileCoveredGenes = "" ,
    FileCellTypeCategory = "" ,
    FileInitialCellTypeRatio = "" ,
@@ -80,27 +88,26 @@ def PrepareData(FileReferenceProfile ,
    if FileReferenceProfile.shape[1] < 2:
       print("warning: When open Reference File, might sep = ' ' not '\t'")
    print("celltype reference raw matrix:\n", FileReferenceProfile.iloc[0:4, 0:4])
-   ReferenceCelltype = {}
+   ReferenceCelltype = {} 
    for oneCellType in FileReferenceProfile.columns.values.tolist():
       numbertail = re.findall("\.[0-9]*$", oneCellType)
       oneCellType0 = oneCellType
       if numbertail != []: oneCellType = oneCellType[:-len(numbertail)]
-      if oneCellType in ReferenceCelltype.keys():
+      if oneCellType in ReferenceCelltype.keys(): 
          ReferenceCelltype[oneCellType].append(ReferenceCelltype[oneCellType])
       else: ReferenceCelltype[oneCellType] = [oneCellType0]
    DFReferenceProfile = pandas.DataFrame(columns = list(ReferenceCelltype.keys()),
        index = FileReferenceProfile.index.values)
    for celltype in  DFReferenceProfile.columns.values:
-        DFReferenceProfile[celltype] = (
+        DFReferenceProfile[celltype] = (  
            FileReferenceProfile.loc[:, ReferenceCelltype[celltype] ]).mean(axis = 1)
-   print("celltype reference matrix:\n", DFReferenceProfile.iloc[0:4, 0:4]) 
+   print("celltype reference matrix:\n", DFReferenceProfile.iloc[0:4, 0:4])
    DFSampleExpressionProfile = pandas.read_table(FileSampleExpressionProfile, sep = "\t", header = 0, index_col = 0)
-   print(" initialize a Object For running...")  
-   print("environment config(cpus, threads): ", EnvironmentConfig)
+   print(" initialize a Object For running...") 
+   print("environment config(threads): ", EnvironmentConfig)
    GeneUsedForDeconvolution = SelectGeneForDeconvolution(DFReferenceProfile)
    #FileCellTypeCategory = CelltypeCategoryCheck(FileCellTypeCategory, celltypelist = list(ReferenceCelltype.keys()))
-   FileInitialCellTypeRatio = InitialCellTypeRatioCheck(InitialCellTypeRatio, 
-      FileInitialCellTypeRatio, ncelltype = DFReferenceProfile.shape[1]) 
+   FileInitialCellTypeRatio = InitialCellTypeRatioCheck(InitialCellTypeRatio, FileInitialCellTypeRatio, ncelltype = DFReferenceProfile.shape[1]) 
    DFReferenceProfile0 = DFReferenceProfile.loc[GeneUsedForDeconvolution, ]
    DFReferenceProfile0 = DFReferenceProfile0[DFReferenceProfile0.index.isin(DFSampleExpressionProfile.index)]   
    selected_DFSampleExpressionProfile = DFSampleExpressionProfile.loc[DFReferenceProfile0.index]

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/__init__.py

@@ -1,7 +1,7 @@
-from .Deconvolution import MainRun # MainRun
-from .PrepareData import PrepareData # PrepareDate
-from .ObtainCategory import ExtractResult, SummaryCellRatio # ExtractResult()
-from .Drawplot import DrawPlotFunction1, DrawPlotFunction2 # visualization()
+from .myfunction1 import MainRun # MainRun
+from .myfunction2 import PrepareData # PrepareDate
+from .myfunction3 import ExtractResult, SummaryCellRatio # ExtractResult()
+from .myfunction4 import DrawPlotFunction1, DrawPlotFunction2 # visualization()
 import os
 import pandas
 import argparse
@@ -11,12 +11,12 @@ import numpy as np
 import random
 
 def load_tumor_reference_data():
-    from importlib.resources import path
+    from importlib_resources import path
     with path("immucellai2.myconfig", "reference_tumorCelltypes.txt") as file_path:
         return pandas.read_table(file_path, sep="\t", header=0, index_col=0)
         
 def load_normal_reference_data():
-    from importlib.resources import path
+    from importlib_resources import path
     with path("immucellai2.myconfig", "reference_normalCelltypes.txt") as file_path:
         return pandas.read_table(file_path, sep="\t", header=0, index_col=0)
 
@@ -41,7 +41,7 @@ def main():
    mp.set_start_method('fork', force=True) 
    parser = argparse.ArgumentParser(description='ImmuCellAI2 deconvolution tool')
    parser.add_argument('-f', '--reference', dest = 'reference', default="", help = 'celltype reference experession matrix')
-   parser.add_argument('-g', '--genes', dest = 'CoveredGenes', action = 'store_const', help = 'The genes used in the following deconvolution process selected by BayesPrism, temporary variance')
+   parser.add_argument('-g', '--genes', dest = 'CoveredGenes', action = 'store_const', const=True, help = 'The genes used in the following deconvolution process selected by BayesPrism, temporary variance')
    parser.add_argument('-s', '--sample', dest = 'sample', required = True, help = 'the samples gene expression profile')
    parser.add_argument('-t', '--thread', dest = 'thread', type=int, default = 16, help = "threading numbers for deconvolution")
    parser.add_argument('--sample-type', dest="sample_type", default = 'normal', choices=['tumor','normal'], help='Sample type (tumor/normal, default normal)')

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/myclasses.py

@@ -99,19 +99,25 @@ class CLASS_FOR_RUNRESULT(object):
             self.EmceeFunction2( McSamplingResultList[sampleii, :, :, :] )
       return  NewMcSamplingResultList
    def optimized_calculation(self, FlatSamplingResultOne, nCellType):
-       if FlatSamplingResultOne.shape[1] == nCellType:
-           return FlatSamplingResultOne / FlatSamplingResultOne.sum(axis=1)[:, None]
-       elif FlatSamplingResultOne.shape[1] + 1 == nCellType:
-           return numpy.column_stack((FlatSamplingResultOne, 1 - FlatSamplingResultOne.sum(axis=1)))
-   def EmceeFunction2(self, FlatSamplingResultList):
-       fshape = FlatSamplingResultList.shape
-       nCellType = len(self.CellType)
-       NewFlatSamplingResultList = numpy.zeros((fshape[0], fshape[1], nCellType))
-       for sampleii in range(fshape[0]):
-           FlatSamplingResultOne = FlatSamplingResultList[sampleii, :, :]
-           NewFlatSamplingResultOne = self.optimized_calculation(FlatSamplingResultOne, nCellType)
-           NewFlatSamplingResultList[sampleii, :, :] = NewFlatSamplingResultOne
-       return NewFlatSamplingResultList
+      row_sums = FlatSamplingResultOne.sum(axis=1, keepdims=True)
+      row_sums_safe = row_sums + 1e-10 
+      if FlatSamplingResultOne.shape[1] == nCellType:
+         return FlatSamplingResultOne / row_sums_safe
+      elif FlatSamplingResultOne.shape[1] + 1 == nCellType:
+         normalized = FlatSamplingResultOne / row_sums_safe
+         last_col = 1 - normalized.sum(axis=1, keepdims=True)
+         return numpy.column_stack((normalized, last_col))
+      else:
+         raise ValueError(f"Dimension mismatch: input {FlatSamplingResultOne.shape[1]} columns, target {nCellType}columns")
+   def EmceeFunction2(self, FlatSamplingResultList): 
+      fshape = FlatSamplingResultList.shape
+      nCellType = len(self.CellType)
+      NewFlatSamplingResultList = numpy.zeros((fshape[0], fshape[1], nCellType))
+      for sampleii in range(fshape[0]):
+         FlatSamplingResultOne = FlatSamplingResultList[sampleii, :, :]
+         NewFlatSamplingResultOne = self.optimized_calculation(FlatSamplingResultOne, nCellType)
+         NewFlatSamplingResultList[sampleii, :, :] = NewFlatSamplingResultOne
+      return NewFlatSamplingResultList
    def CalculateCellTypeRatio(self):
       CellTypeRatioResult = pandas.DataFrame(numpy.zeros(( len(self.SampleName),
                                                            len(self.CellType) )),
@@ -127,7 +133,7 @@ class CLASS_FOR_RUNRESULT(object):
          CellTypeRatioResult.loc[SampleNameOne, ] = FlatSamplingAverageOne
          FinalSampling = self.McmcSamplingResult[Oneii, -1, :, :]
          CellTypeRatioResultFinal.loc[SampleNameOne, ] = numpy.mean(FinalSampling, axis = 0)
-      return CellTypeRatioResult, CellTypeRatioResultFinal
+      return CellTypeRatioResult, CellTypeRatioResultFinal 
    def CalculateRatioOld(self):
       CellTypeRatioResult = pandas.DataFrame([[]], columns = self.CellType, index = self.SampleName )
       for Oneii in range(len(self.FlatSamplingResult)):
@@ -135,19 +141,19 @@ class CLASS_FOR_RUNRESULT(object):
          SampleNameOne = self.SampleName[Oneii]
          CellTypeRatioOne = list()
          for ii in range(len(self.Celltype)):
-             CellTypeRatioOne.append((FlatSamplingOne[:, :, ii].sum(axis =1))[1])
-         CellTypeRatioResult.loc[SampleNameOne,] = CellTypeRatioOne
+            CellTypeRatioOne.append((FlatSamplingOne[:, :, ii].sum(axis =1))[1])
+         CellTypeRatioResult.loc[SampleNameOne,:] = CellTypeRatioOne
       return CellTypeRatioResult
    def save_result(self, FilenameToSave, ResultIndex = 0):
       DataCelltypeRatio = self.get_result( ResultIndex = ResultIndex )
       (DataCelltypeRatio.T).to_excel(FilenameToSave, index = True, header = True)
    def get_result(self, ResultIndex = 0):
-     if ResultIndex == 0:
-        return self.CellTypeRatioResult
-     elif ResultIndex  == 1:
-        return self.CellTypeRatioResultFinal
-     else:
-        pass
+      if ResultIndex == 0:
+         return self.CellTypeRatioResult
+      elif ResultIndex  == 1:
+         return self.CellTypeRatioResultFinal
+      else:
+         pass
    @property
    def CellTypeCateogryContent(self):
       return self._CellTypeCateogryContent
@@ -156,6 +162,7 @@ class CLASS_FOR_RUNRESULT(object):
       self._CellTypeCateogryContent = CellTypeCateogryContent
       del self.FileCellTypeCategory
 
+
 class CLASS_FOR_EMCEEPARAMETER(object):
    def __init__(self, position, CellType = list(), nsteps = 1000, 
       nwalkers = 1, 
@@ -241,4 +248,6 @@ class CLASS_ENVIRONMENT_CONFIG(object):
    def __init__(self, Environment):
       self.ThreadNum =  Environment
 
+  
 
+#exmaples1 = CLASSONE(111)

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/myconfig/Celltype.category

@@ -58,8 +58,8 @@
    RankedLayer: 3
    RelatedNode: 
       HisParentNode: Lymplhoid Cells 
-      HisChidNode: ['MZB', 'FOB', 'Breg', 'GCB', 'PB']
-      HisChidNode: ['MBC', 'PC', 'Bex', 'Bn']
+      HisChidNode: ['MZB', 'FOB', 'Breg', 'GC_B', 'plasmablast']
+      HisChidNode: ['memoryB', 'plasma', 'exhaustedB', 'Bnaive']
    Description: ...
 
 #[NewNode]
@@ -68,7 +68,7 @@
    RankedLayer: 3
    RelatedNode: 
       HisParentNode: Lymplhoid Cells
-      HisChidNode: ['γδT', 'CD4T', 'CD8T','NKT']
+      HisChidNode: ['gdT', 'CD4T', 'CD8T','NKT']
    Description: ...
 
 #[NewNode]
@@ -95,7 +95,7 @@
    RankedLayer: 3
    RelatedNode:
       HisParentNode: Myeloid Cells
-      HisChidNode: ['Basophil', 'Eosinophil', 'mastcell', 'Neutrophil']
+      HisChidNode: ['basophils', 'eosinophils', 'mast_cell', 'neutrophils']
    Description: ...
 
 #[NewNode]
@@ -113,7 +113,7 @@
    RankedLayer: 3
    RelatedNode:
       HisParentNode: Myeloid Cells
-      HisChidNode: ['cMo', 'intMo', 'ncMo']
+      HisChidNode: ['classical Monocytes', 'intermediate monocytes', 'nonclassical monocytes']
    Description: ...
 
 #[NewNode]
@@ -142,8 +142,8 @@
 
 
 #[NewNode]
-   CellType: γδT
-   AlsoKnownAs: ['gdT', 'gamma delta T']
+   CellType: gdT
+   AlsoKnownAs: ['gd T', 'gamma delta T']
    RankedLayer: 4
    RelatedNode:
       HisParentNode: T cells
@@ -156,9 +156,9 @@
    RankedLayer: 4
    RelatedNode:
       HisParentNode: T cells
-      HisChidNode: ['Th1_17','CD4Tcell', 'CD4Tn', 'Th1', 'Th2','Th0','Th9']
+      HisChidNode: ['Th1/Th17', 'CD4Tnaive', 'Th1','Th', 'Th2','Th0','Th9']
       HisChidNode: ['Treg', 'Th17', 'Th22', 'Tfh','Tfr']
-      HisChidNode: ['CD4Tcm', 'CD4Temra', 'CD4Trm', 'CD4Tem']
+      HisChidNode: ['CD4Tcm', 'CD4Temra', 'CD4Trm', 'CD4Tem','memoryCD4T']
    Description: ...
 
 #[NewNode]
@@ -167,8 +167,8 @@
    RankedLayer: 4
    RelatedNode:
       HisParentNode: T cells
-      HisChidNode: ['CD8Tcell', 'Tc', 'Tex', 'MAIT']
-      HisChidNode: ['CD8Tn', 'CD8Tcm', 'CD8Tem', 'CD8Temra', 'CD8Trm']
+      HisChidNode: ['CD8aa', 'memory T', 'Tc', 'exhausted_T', 'MAIT']
+      HisChidNode: ['CD8Tnaive', 'CD8Tcm', 'CD8Tem', 'CD8Temra', 'CD8Trm','memoryCD8T']
    Description: ...
 
 #[NewNode]
@@ -177,7 +177,7 @@
    RankedLayer: 4
    RelatedNode:
       HisParentNode: ILC
-      HisChidNode: ['cNK', 'NKreg']
+      HisChidNode: ['cytotoxicNK', 'regulatoryNK']
    Description: ...
 
 #[NewNode]
@@ -186,15 +186,15 @@
 
 #[NewNode]
    CellType: classical monocyes
-   AlsoKnownAs: ['cMo']
+   AlsoKnownAs: ['CMonocyte']
 
 #[NewNode]
    CellType: intermediate monocyes
-   AlsoKnownAs: ['intMo']
+   AlsoKnownAs: ['IMonocyte']
 
 #[NewNode]
    CellType: nonclassical monocyes
-   AlsoKnownAs: ['ncMo']
+   AlsoKnownAs: ['NMonocyte']
 
 
 #[NewNode]

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/myconfig/reference_normalCelltypes.txt

@@ -1,4 +1,4 @@
-Bn	Breg	CD4Tcm	CD4Tem	CD4Temra	CD4Tn	CD4Trm	CD8Tcm	CD8Tem	CD8Temra	CD8Tn	CD8Trm	cMo	FOB	GCB	ILC1	ILC2	ILC3	intMo	Langerhans	M0	M2	M1	MAIT	MZB	NKT	ncMo	Tc	Tfh	Th1	Th1_17	Th17	Th2	Tr1	Treg	Basophil	cDC1	cDC2	cNK	Eosinophil	Bex	Tex	γδT	mastcell	MBC	monoDC	Neutrophil	pDC	PC	PB	NKreg
+Bnaive	Breg	CD4Tcm	CD4Tem	CD4Temra	CD4Tnaive	CD4Trm	CD8Tcm	CD8Tem	CD8Temra	CD8Tnaive	CD8Trm	CMonocyte	FOB	GC_B	ILC1	ILC2	ILC3	IMonocyte	Langerhans	M0	M2	M1	MAIT	MZB	NKT	NMonocyte	Tc	Tfh	Th1	Th1/Th17	Th17	Th2	Tr1	Treg	basophils	cDC1	cDC2	cytotoxicNK	eosinophils	exhaustedB	exhausted_T	gdT	mast_cell	memoryB	monoDC	neutrophils	pDC	plasma	plasmablast	regulatoryNK
 5S_rRNA	3.72288814625436	3.9839937277119	1.04242543528017	1.10166388743374	0.262488492500141	2.88442409468091	0	3.30505460913788	1.45668126858648	3.52551723641445	2.33293862772959	0.375938524543258	1.52075220597206	0.53956901678129	1.14602167759865	0.648102507997582	2.07420233648288	3.61611516932655	1.55950430705335	0.467424934673458	0.291947100896851	0.22030068960234	0.134254802991306	0.848662289189787	0.944633890126093	1.53743580579717	1.84858717816614	0.526258168262494	2.42911337811475	2.78786344420041	2.09601566178111	2.07881195299172	1.39542673326364	1.3598615912259	2.87883993797047	2.66510105106112	0.78799772271775	0.594872868455309	2.06158466154722	0	1.347781563304	0.297028643797706	0.749424409087233	1.61335777803813	2.09866985018597	0.734770517655795	1.26902966694485	4.1043228059796	0.184496474993528	0.449509458267856	2.05754437374052
 5_8S_rRNA	101.778179517657	0.0463120820428233	0	0.0496320942187055	0.265334278384527	0.860297885120605	0	6.25571737372557	5.13478501586834	0.415958809032976	0.79772882086214	0	0.0304645464561831	0.334650831196325	0.00921571406148335	0	0	0	0	0	0.0128361639986559	0.0281038018431943	0	0.0543925389724701	0	0	0	0	0.147384211618789	0.262500332744139	0	0.222284293889944	0.269170643471795	0	0.514434164711424	0	0	0.0234670992913785	0.191980797126382	0.0817242103291416	0	0.839573510430039	0.0351727765855236	0.177577371480421	289.739908229461	0.00377841407068054	0.0549230277282921	0	0.00657589261577782	0	0
 7SK	0.412388345004592	0.0663967103450191	0.182523114342318	0.207720273509821	0.514981680258264	0.521358838337904	0.460635430456313	1.00809400229153	1.12585366118991	0.56793244714343	0.2720010973473	0.815221481921778	0.17309616176035	0.0968227096452869	0.0144270543501783	0.204828258784804	0.00988163659248495	0.146042989572289	0.00727501711135191	0	0.00246636867612614	0.0159919858772734	0.00563765152325374	0.127323629110979	0	0.103696656575346	0.0304256600508641	0.0150509509702144	0.908954887880856	0.291518944612427	0	0.0849652097172878	0.0916391005871732	0.0503021990514254	0.705293673449258	0.380813553028531	0.0224173017522048	0.0179368881616202	0.0772749331826404	0.372073616748534	0	0.067085881126663	0.0405615798133645	0.206343302300748	0.00592984431685868	0.0156476955683151	0.349801575252531	0.0373479564796323	0.029113861512623	0.0122842568022437	0.301372936346232

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2/myconfig/reference_tumorCelltypes.txt

@@ -1,4 +1,4 @@
-Bn	Breg	CD4Tcm	CD4Tem	CD4Temra	CD4Tn	CD4Trm	CD8Tcm	CD8Tem	CD8Temra	CD8Tn	CD8Trm	cMo	FOB	GCB	ILC1	ILC2	ILC3	intMo	Langerhans	M0	M2	M1	MAIT	MDSC	MZB	NKT	ncMo	TAM	Tc	Tfh	Th1	Th1_17	Th17	Th2	Tr1	Treg	Basophil	cDC1	cDC2	cNK	Eosinophil	Bex	Tex	γδT	mastcell	MBC	monoDC	Neutrophil	pDC	PC	PB	NKreg
+Bnaive	Breg	CD4Tcm	CD4Tem	CD4Temra	CD4Tnaive	CD4Trm	CD8Tcm	CD8Tem	CD8Temra	CD8Tnaive	CD8Trm	CMonocyte	FOB	GC_B	ILC1	ILC2	ILC3	IMonocyte	Langerhans	M0	M2	M1	MAIT	MDSCs	MZB	NKT	NMonocyte	TAM	Tc	Tfh	Th1	Th1/Th17	Th17	Th2	Tr1	Treg	basophils	cDC1	cDC2	cytotoxicNK	eosinophils	exhaustedB	exhausted_T	gdT	mast_cell	memoryB	monoDC	neutrophils	pDC	plasma	plasmablast	regulatoryNK
 5S_rRNA	3.72288814625436	3.9839937277119	1.04242543528017	1.10166388743374	0.262488492500141	2.88442409468091	0	3.30505460913788	1.45668126858648	3.52551723641445	2.33293862772959	0.375938524543258	1.52075220597206	0.53956901678129	1.14602167759865	0.648102507997582	2.07420233648288	3.61611516932655	1.55950430705335	0.467424934673458	0.291947100896851	0.22030068960234	0.134254802991306	0.848662289189787	3.56282877292757	0.944633890126093	1.53743580579717	1.84858717816614	0.179985792652513	0.526258168262494	2.42911337811475	2.78786344420041	2.09601566178111	2.07881195299172	1.39542673326364	1.3598615912259	2.87883993797047	2.66510105106112	0.78799772271775	0.594872868455309	2.06158466154722	0	1.347781563304	0.297028643797706	0.749424409087233	1.61335777803813	2.09866985018597	0.734770517655795	1.26902966694485	4.1043228059796	0.184496474993528	0.449509458267856	2.05754437374052
 5_8S_rRNA	101.778179517657	0.0463120820428233	0	0.0496320942187055	0.265334278384527	0.860297885120605	0	6.25571737372557	5.13478501586834	0.415958809032976	0.79772882086214	0	0.0304645464561831	0.334650831196325	0.00921571406148335	0	0	0	0	0	0.0128361639986559	0.0281038018431943	0	0.0543925389724701	0.148570234219534	0	0	0	0.00673730545389831	0	0.147384211618789	0.262500332744139	0	0.222284293889944	0.269170643471795	0	0.514434164711424	0	0	0.0234670992913785	0.191980797126382	0.0817242103291416	0	0.839573510430039	0.0351727765855236	0.177577371480421	289.739908229461	0.00377841407068054	0.0549230277282921	0	0.00657589261577782	0	0
 7SK	0.412388345004592	0.0663967103450191	0.182523114342318	0.207720273509821	0.514981680258264	0.521358838337904	0.460635430456313	1.00809400229153	1.12585366118991	0.56793244714343	0.2720010973473	0.815221481921778	0.17309616176035	0.0968227096452869	0.0144270543501783	0.204828258784804	0.00988163659248495	0.146042989572289	0.00727501711135191	0	0.00246636867612614	0.0159919858772734	0.00563765152325374	0.127323629110979	0.285124375928072	0	0.103696656575346	0.0304256600508641	0.00348914401853447	0.0150509509702144	0.908954887880856	0.291518944612427	0	0.0849652097172878	0.0916391005871732	0.0503021990514254	0.705293673449258	0.380813553028531	0.0224173017522048	0.0179368881616202	0.0772749331826404	0.372073616748534	0	0.067085881126663	0.0405615798133645	0.206343302300748	0.00592984431685868	0.0156476955683151	0.349801575252531	0.0373479564796323	0.029113861512623	0.0122842568022437	0.301372936346232

{immucellai2-2.1.24 → immucellai2-2.1.25}/immucellai2.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: immucellai2
-Version: 2.1.24
+Version: 2.1.25
 Summary: A tool for immune cell type deconvolution
 Home-page: https://github.com/VyvyanYjm/ImmuCellAI2.0
 Author: YangJingmin

{immucellai2-2.1.24 → immucellai2-2.1.25}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = immucellai2
-version = 2.1.24
+version = 2.1.25
 author = YangJingmin
 author_email = yangjingmin2021@163.com
 description = A tool for immune cell type deconvolution