compute_for_clases.py

import pandas as pd
import time
import ast
import csv
import math
from interfazGrafica import interfaz
from descarteProteinas import ejecutar,remplazar_ID_for_sequence
from generate_tha_excel import substitute_or_remove_prot_id
import metricas
from graficas import grafica
import os
import json
import ast
import re
from patrones_similares_aa import remplazar_sequence_for_ID as remplazar_s
from patrones_similares_aa import buscar_patrones_simAA
from collections import defaultdict
from pathlib import Path



def substitute_or_remove_prot_id2(data,sub_rem):
    print("inside the problem")
    with open("nombres_sust.txt") as prottosubs:
          index=prottosubs.readline()
          acept=index.split()
          listtosubs={}
          for i in range(0,len(acept)):
            listtosubs[acept[i]]=[]
          while line := prottosubs.readline():
              newline=line.split()
              #print(len(newline))
              for i in range(0,len(newline)):
                  
                  listtosubs[list(listtosubs.keys())[i]].append(newline[i].strip())  
    resub=1
    if re.search("Primary",list(listtosubs.keys())[0]):
           resub=0
    print((resub+1)%2)
    #print(data)
    #data2=data.copy()
    if(sub_rem == "s"):
       data["Proteina"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
    #datacp=data.copy()
    #print(pd.concat([data2,datacp]).drop_duplicates())
    else: 
        global globi
        datas= data[data["Proteina"].isin(list(listtosubs.values())[(resub+1)%2])==True]
        data = data[data["Proteina"].isin(list(listtosubs.values())[(resub+1)%2])==False]
        
        #datas.to_csv('resultados/proteinasDescartadas_'+ str(globi) +'.csv', index=False) 

        globi=globi+1 
    return data 

def readData(archivoEntrada, enfermedad, archivoTarget):
    """
    Reads data from an Excel file, filters it based on disease (if specified),
    and returns protein sequences along with the number of rows.

    Parameters:
    - archivoEntrada: str, path to the input Excel file.
    - enfermedad: str, disease ID for filtering (empty string for no filtering).
    - archivoTarget: str, path to the target Excel file (not currently in use).

    Returns:
    - sequences: pandas Series, protein sequences column.
    - num_filas: int, number of rows in the filtered data.
    """
    data = pd.read_excel(archivoEntrada)
    dataC = pd.read_csv("resultados/proteinasDescartadas2.csv")
    #data=substitute_or_remove_prot_id(data,"r")
    #dataC=substitute_or_remove_prot_id(dataC,"r")
    #Descarte de proteinas
    data = data[~data['protein_id'].isin(dataC['ProteinasDescartadas'])]
    print("Se ha realizado el descarte de proteínas")

    # "C0002395"
    if(enfermedad != ''):
        data = data.loc[data["disease_id"] == enfermedad]
        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
        #print("Se han seleccionado las proteínas de la enfermedad elegida")
        #dataB=substitute_or_remove_prot_id(dataB,"r")
    #if(archivoTarget != ''):
    #    dataB=substitute_or_remove_prot_id(dataB,"r")
        #Eliminar las proteinas target
    #    data = data[~((data["disease_id"] == enfermedad) &
    #                  (data["protein_id"].isin(dataB["protein_id"])))]
    #    print("Se han descartado las proteínas del archivo target")

    sequences = data["protein_sequence"]
    print(sequences)
    num_filas = sequences.shape[0]

    return sequences, num_filas

def guardar_patrones_len1(sequences, pattern_freqMin):
    """
    Processes protein sequences to find patterns of length 1 and their positions,
    filters patterns based on minimum occurrence, and saves results to a CSV file.

    Parameters:
    - sequences: pandas Series, protein sequences.
    - pattern_freqMin: dict, dictionary to store patterns and their occurrences.

    Returns:
    - pattern_freqMin: dict, updated dictionary of patterns.
    - posicionPatterns: dict, positions of each character in the sequences.
    - longitud_max: int, maximum length of protein sequences.
    """
    all_patterns = dict()
    longitud_max = 0
    # Each pattern associated to the proteins the pattern is in
    pattern_proteins = {}
    for protein in sequences:
        longitud = len(protein)
        if longitud > longitud_max:
            longitud_max = longitud

        all_patterns[protein] = []
        # En cada iteración guarda los patrones que aparecen en la secuencia con sus posiciones asociadas a la proteina
        posicionPatterns = dict()
        for index, letter in enumerate(protein):
            posicionPatterns[letter] = posicionPatterns.get(letter, []) + [index]

        all_patterns[protein] = posicionPatterns


    for protein, patterns in all_patterns.items():
        for pattern, positions in patterns.items():
            if pattern not in pattern_proteins:
                pattern_proteins[pattern] = {}
            if protein not in pattern_proteins[pattern]:
                pattern_proteins[pattern][protein] = []
            pattern_proteins[pattern][protein].extend(positions)


    for pattern, proteins in pattern_proteins.items():
        if len(proteins) >= min_ocurrence:
            pattern_freqMin[pattern] = proteins

    df = pd.DataFrame(pattern_freqMin.items(), columns=['pattern', 'proteins'])
    df.to_csv('prueba2.csv', index=False)
    return pattern_freqMin, posicionPatterns, longitud_max

def buscar_patrones_identicos(sequences):
    """
    Searches for identical patterns of different lengths in protein sequences
    and stores them along with their positions in a dictionary.

    Parameters:
    - sequences: pandas Series, protein sequences.

    Returns:
    - pattern_freqMin: dict, dictionary of patterns and their positions.
    - num_patrones: int, number of unique patterns found.
    """
    pattern_freqMin = {}
    pattern_freqMin, posicionPatterns, longitud_max = guardar_patrones_len1(sequences, pattern_freqMin)

    if bool(pattern_freqMin):
        for pattern_length in range(2, longitud_max + 1):
            # Si se intenta acceder a una clave que no existe se creara una lista vacia
            auxPos = {}
            sub_seqs = []
            for pattern, proteins in pattern_freqMin.items():
                if len(pattern) == pattern_length - 1:
                    for prot, positions in proteins.items():
                        protein_len = len(prot)
                        if protein_len < pattern_length - 1:
                            continue
                        for position in positions:
                            if (protein_len < position + pattern_length):
                                continue
                            sub_seq = prot[position:position + pattern_length]
                            if sub_seq in pattern_freqMin:
                                continue
                            # Si la ultima letra que es la nueva del patron ya esta min_freq, el patron es posible
                            # min freq tb
                            ultima_letra = sub_seq[-1]
                            pos_ultima_letra = position + pattern_length - 1
                            if ultima_letra in pattern_freqMin and pos_ultima_letra in pattern_freqMin[ultima_letra][prot]:
                                if sub_seq not in auxPos:
                                    auxPos[sub_seq] = {}
                                if prot not in auxPos[sub_seq]:
                                    auxPos[sub_seq][prot] = []
                                auxPos[sub_seq][prot].append(position)
                                if sub_seq not in sub_seqs:
                                    sub_seqs.append(sub_seq)
                print(pattern_length)
                sub_seqs_copy = sub_seqs.copy()
                for p in sub_seqs_copy:
                      if len(auxPos[p]) < min_ocurrence:
                          del auxPos[p]
                          sub_seqs.remove(p)

            # Si no se encuentra ningun patron de longitud pattern_length se sale del bucle. No hay mas patrones posible a encontrar
            if not bool(auxPos):
                break

            for pattern, proteins in auxPos.items():
                for prot, pos in proteins.items():
                    if pattern not in pattern_freqMin:
                        pattern_freqMin[pattern] = {}
                    if prot not in pattern_freqMin[pattern]:
                        pattern_freqMin[pattern][prot] = []
                    found=list(filter(lambda x: pos-len(pattern) <= x <= pos+len(pattern), pattern_freqMin[pattern][prot]))
                    print(found)
                    print(len(found))
                    if(len(found)<=0):        
                       pattern_freqMin[pattern][prot].extend(pos)
                       if len(pattern) > 2:
                         if pattern[:-1] in pattern_freqMin:
                            del pattern_freqMin[pattern[:-1]]
                         if pattern[1:] in pattern_freqMin:
                            del pattern_freqMin[pattern[1:]]



        # Ordenar de mayor a menor tamaño. Las subcadenas del mismo tamaño se ordenan por orden alfabetico
        
        dict_ordered_patterns = dict(sorted(pattern_freqMin.items(), key=lambda x: (-len(x[0]), x[0])))
        dict_ordered_patterns = {k: v for k, v in dict_ordered_patterns.items() if len(k) >= 4}
        df = pd.DataFrame(dict_ordered_patterns.items(), columns=['pattern', 'proteins'])
        num_patrones = df.shape[0]
    pattern_freqMin = {k: v for k, v in pattern_freqMin.items() if len(k) >= 4}
    return pattern_freqMin, num_patrones

def remplazar_sequence_for_ID(pattern_freqMin,name,archivoEntrada,ocurrencia,archivoClases=None):
    """
    Replaces identified patterns in the original data with their corresponding IDs,
    saves the results to a CSV file, and prints a success message.

    Parameters:
    - pattern_freqMin: dict, dictionary of patterns and their positions.
    - name: str name of the class
    - archivoEntrada: str, path to the input Excel file.
    - ocurrencia: float, occurrence parameter.
    - archivoClases (Optional): str, path to the classes Excel file.
    """
    df_b = pd.read_excel(archivoEntrada)
    #df_b=pd.read_excel("proteinasClase_PC00060.xlsx")
    #df_b=substitute_or_remove_prot_id(df_b,'r')
    cl=pd.read_excel(archivoClase)
    #cl=substitute_or_remove_prot_id(cl,"r")
    #data2=data.copy()
    cli=cl.groupby('protein_id')
    di=[]
    do={}
    for k,v in cli:
      for index,row in v.iterrows():
         di.append(row['class_name'])
      do[k]=di
      di=[]
    class_dict=do
    output = []

    for key, value in pattern_freqMin.items():
        for proteina, posiciones in value.items():
            output.append([key, proteina, posiciones])

    output = [sublista for sublista in output if len(sublista[0]) != 1]

    # Ordenar de mayor a menor tamaño. Las subcadenas del mismo tamaño se ordenan por orden alfabetico
    output_ordered = sorted(output, key=lambda x: (-len(x[0]), x[0]))


    proteinas_dict = dict(df_b[['protein_sequence', 'protein_id']].values)
    for item in output_ordered:
        protein_sequence = item[1]
        if protein_sequence in proteinas_dict:
            item[1] = proteinas_dict[protein_sequence]
        item.append(class_dict[item[1]] if item[1] in class_dict else "N/A")    
    df_a = pd.DataFrame(output_ordered, columns=['Patron', 'Proteina', 'Posiciones','classesProt'])

    # Guardar el DataFrame actualizado en un archivo CSV
    
    df_a.to_csv('clases/'+ name +'/patronesIdenticos'+str(int((ocurrencia%1)*100))+'.csv', index=False)
    print("Se ha generado el .csv con los patrones idénticos encontrados")
def compute_pattern_ocurrence(df,name):
    """
    Computes the occurrence of patterns in the data and saves the results to a CSV file.

    Parameters:
    - df: pandas DataFrame, DataFrame containing pattern information.
    - name: str name of the class
    
    Note: saves the patterns, the amount of times a pattern appears in proteins of the dataset and the number of proteins that have that pattern.
    """
    df2=df.groupby('Patron')
    compl=0
    comp=0
    first=True
    res=set()
    for k,v in df2:
         res=set()  
         for index,row in v.iterrows():
             Posic=[oo for oo in ast.literal_eval(row['Posiciones']) if oo is not '[' and oo is not ']']
             rem=[]
             if(len(Posic)>2):
              u=0
              while u+1<len(Posic):
                 if(Posic[u]+len(k)<=Posic[u+1]):
                    del Posic[u+1]
                 else:
                   u+=1
             res|=set(Posic)      
             compl+=1
         comp+=len(res)
         
    for k,v in df2:
         dicta={'Patron':[] ,'total_Patrones_por_prot':[],'numero_prot':[]}
         dicta[k]=0
         dox=0
         dix=0
         co=0
         res=0
         Posic=set()
         for index,row in v.iterrows():
             
             Posic|=set([oo for oo in ast.literal_eval(row['Posiciones']) if oo is not '[' and oo is not ']'])
             Poss=[oo for oo in ast.literal_eval(row['Posiciones']) if oo is not '[' and oo is not ']']
             co+=1
             rem=[]
             if(len(Poss)>2):
              u=0
              while u+1<len(Poss):
                 if(Poss[u]+len(k)<=Poss[u+1]):
                    del Poss[u+1]
                 else:
                   u+=1
             res+=len(Poss)   
         dix+=len(Posic)   
         dox+=len(Posic)*len(str(k))
         dox/=seq_len
         #dicta['%Ocurrencia_caracter'].append(dox*100)
         #dicta['longitud_Apariciones'].append(co)
         #dicta['longitud_Apariciones_Proteina'].append(dix)
         #dicta['%Patron'].append(co/compl*100)
         #dicta['%Patron_proteina'].append(dix/comp*100)
         dicta['Patron'].append(str(k))
         #dicta['total_Patrones'].append(compl)
         dicta['total_Patrones_por_prot'].append(res)
         dicta['numero_prot'].append(co)
         do=pd.DataFrame(dicta)
         if not first:
            do.to_csv('clases/'+fil.name.split('.')[0]+'/patronesOcurrencia.csv',index=False,header=False,mode='a' )
         else:
            do.to_csv('clases/'+fil.name.split('.')[0]+'/patronesOcurrencia.csv',index=False )
            first=False
    del df2                 
    
    del do    
def compute_proteinas_ocurrencia(df,name):
    """
    Computes the occurrence of proteins in the data and saves the results to a CSV file.

    Parameters:
    - df: pandas DataFrame, DataFrame containing protein information.
    - name: str name of the class
    
    Note: Saves four values the protein id, the so called global ocurrence, the classes it has each protein. Global ocurrence is the percentage of Aminoacids in the sequence that belong to a pattern vs the total of aminoacids in the sequence of a specific protein.
    """
    df3=df.groupby('Proteina')
    first=True
    df_b = pd.read_excel(archivoEntrada)
    #df_b = pd.read_excel("proteinasClase_PC00060.xlsx")
    #df_b=substitute_or_remove_prot_id(df_b,"r")
    proteinas_dict = dict(df_b[['protein_id','protein_sequence']].values)
    positions_visited=[]
    for k,v in df3:
        di={'proteinas':[],'global_ocurrence':[],"classesProt":[]}
        seq=proteinas_dict[k]
        #di['maximum_ocurrence'].append(len(seq))
        di['proteinas'].append(k)
        pato=[]
        glob_ocurrence=0
        Acum=[]
        
        
        
        for index,row in v.iterrows():
            print(row)
            pat={}
            pat['patron']=str(row['Patron'])
            Posit=[oo for oo in ast.literal_eval(row['Posiciones']) if oo is not '[' and oo is not ']']
            print(Posit)
            Add=[]
            for i in Posit:
               for kaa in range(0,len(str(row['Patron']))):
                   print(i)
                   Add.append(int(i)+kaa)
            lex=len(list(set(Acum) & set(Add)))       
                    
            Posic=Posit
            pat['loc_ocurren']=(len(Posic)*len(str(row['Patron'])))/len(seq)
            glob_ocurrence+=len(Posic)*len(str(row['Patron']))-lex
            pato.append(pat)
            Acum=list(set(Acum) | set(Add))
        #di['patrones'].append(pato)    
        di['global_ocurrence'].append(glob_ocurrence/len(seq))
        di['classesProt'].append(class_dict[k] if k in class_dict else "N/A")
        do=pd.DataFrame(di)
        if not first:
            do.to_csv('clases/'+fil.name.split('.')[0]+'/proteinasOcurrencia.csv',index=False,header=False,mode='a' )
         else:
            do.to_csv('clases/'+fil.name.split('.')[0]+'/proteinasOcurrencia.csv',index=False )   
           first=False 
    del do        
if __name__ == "__main__":
    if not os.path.exists("resultados"):
        # Si no existe, crearla
        os.makedirs("resultados")
        print(f"La carpeta resultados se ha creado correctamente.")
    else:
        print(f"La carpeta resultados ya existe.")


    inicio = time.time()
    jsonfile=open("param_file.conf","r")
    datosInterfaz=json.load(jsonfile)
    #datosInterfaz = interfaz()
    print(datosInterfaz)

    archivoEntrada = datosInterfaz["NombreArchivoEntrada"]
    enfermedad = datosInterfaz["CodigoEnfermedad"]
    archivoTarget = datosInterfaz["NombreArchivoTarget"]
    similitud = float(datosInterfaz["Similitud"])
    archivoClase=datosIntefaz["NombreArchivoClase"]
    cl=pd.read_excel("alzheimer_protein_class 2.xlsx")
    #cl=substitute_or_remove_prot_id(cl,"r")
    #data2=data.copy()
    cli=cl.groupby('protein_id')
    di=[]
    do={}
    for k,v in cli:
      for index,row in v.iterrows():
         di.append(row['class_name'])
      do[k]=di
      di=[]  
    class_dict=do
         
    for fil in Path("clases").rglob("*.xlsx"):
       if not os.path.exists("clases/"+fil.name.split('.')[0]+"/"):
        # Si no existe, crearla
         os.makedirs("clases/"+fil.name.split('.')[0]+"/")
         print(f"La carpeta resultados se ha creado correctamente.")
       else:
          print(f"La carpeta resultados ya existe.")
       #ejecutar("clases/"+fil.name, enfermedad, similitud)
       pattern_freqMin = dict()
       sequences, num_filas = readData("clases/"+fil.name, enfermedad, archivoTarget)
       df_b = pd.read_excel("clases/"+fil.name)
       #df_b=pd.read_excel("proteinasClase_PC00060.xlsx")
       proteinas_dict = dict(df_b[['protein_sequence', 'protein_id']].values)
       ka=""
       for item in sequences:
            ka=proteinas_dict[item]        
       min_ocurrence = math.floor(num_filas * float(datosInterfaz["OcurrenciaMin"]))
       seq_len=0
       for i in sequences:
         seq_len+=len(i)  
       print(min_ocurrence)
       pattern_freqMin, num_patrones = buscar_patrones_identicos(sequences)
       remplazar_sequence_for_ID(pattern_freqMin,fil.name.split('.')[0],archivoEntrada,datosInterfaz["OcurrenciaMin"],archivoClase)
   
       df=pd.read_csv('clases/'+fil.name.split('.')[0]+'/patronesIdenticos.csv', usecols=['Patron', 'Proteina', 'Posiciones',"classesProt"],index_col=False)
       #df=substitute_or_remove_prot_id2(df,"s")
       df.to_csv('clases/'+fil.name.split('.')[0]+'/patronesIdenticos.csv', index=False)
    
       #dfx=df.copy()
       compute_pattern_ocurrence(df,name)
                         
    
       
       compute_proteinas_ocurrencia(df,name)
              
    #metricas.metrica_distanciaProteinas()
       archivo = 'resultados/Metrica_distanciaProteinasMismoPatron.csv'
       nombreOutput = 'resultados/Figura_DistanciaProteinasMismoPatron'
    #grafica(archivo, nombreOutput)
    
       print("Se han obtenido los resultados de la métrica para la distancia entre dos proteínas que poseen el mismo patrón")

       metrica = math.floor(num_patrones * float(datosInterfaz["Metrica"]))

       metricas.patronesComunClas(metrica,fil.name.split('.')[0])
    
       archivo = 'resultados/Metrica_patronesComunes.csv'
       nombreOutput = 'resultados/Figura_distanciaProteinasPatronesComunes'
    #grafica(archivo, nombreOutput)
       print("Se han obtenido los resultados de la métrica para la distancia entre dos proteínas que poseen mas de un patrón en común")
       
       fin = time.time()
    
       tiempo_total = fin - inicio
       print(tiempo_total, "segundos")