Skip to content

P
ProteinsPatterns
Switch branch/tag
Find file Normal viewHistoryPermalink
generate_tha_excel.py 10.2 KB
Newer Older
Rafael Artinano's avatar
first commit  
Rafael Artinano committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 
import pandas as pd
import Levenshtein
import time
from sklearn.cluster import OPTICS,DBSCAN,AgglomerativeClustering,BisectingKMeans,SpectralClustering
from sklearn.preprocessing import StandardScaler
import numpy as np
from scipy.spatial.distance import pdist, squareform
from pyclustering.cluster.dbscan import dbscan
from pyclustering.utils import timedcall
from Levenshtein import distance
import re
from minineedle import needle, smith, core
from Bio.Blast.Applications import NcbiblastpCommandline
from io import StringIO
from Bio.Blast import NCBIXML
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio import SeqIO
import swalign
import multiprocessing as mp
globi=0
df_b=None

def substitute_or_remove_prot_id(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()
    global globi
    if(sub_rem == "s"):
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
    #datacp=data.copy()
    #print(pd.concat([data2,datacp]).drop_duplicates())
    elif(sub_rem == "p"):
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==False]
        data= data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==True]
        #print(data[data["protein_id"].isin(list(listtosubs.values())[(resub)])==True])
        #print(datas)
        
        #data.drop_duplicates(subset=['disease_id','protein_sequence'],keep='first',inplace=True)
        data=data.drop_duplicates(keep="first", inplace=False)
        did=data.copy()
        data = data.drop_duplicates(subset=['disease_id', 'protein_sequence'], keep="first", inplace=False)
        did=did[~did.isin(data).all(axis=1)]
        did=did.drop_duplicates()
        #print(pd.concat([did,did2]).drop_duplicates(keep=False))
        print(did)
        datas=pd.concat([datas, did], ignore_index=True)
        data.to_excel('data_nervous_genes_principalpurge.xlsx',index=False,columns=data.columns) 
        datas.to_csv('resultados/proteinasDescartadassp_'+ str(globi) +'.csv', index=False) 
    elif(sub_rem == "c"):
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub+1)%2])==True]
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
        print("tamaño original: "+str(len(data)))
        dats=data.drop_duplicates(subset=['protein_id','class_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en id: "+str(len(dats)))
        dats=dats.drop_duplicates(subset=['protein_sequence','class_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en secuencia: "+str(len(dats)))
        dats.to_excel('clases.xlsx',index=False,columns=data.columns)  
        datas.to_csv('resultados/clasesDescartadas_'+ str(globi) +'.csv', index=False) 
        #pd_diff=pd.concat([data,dats]).drop_duplicates(keep=False)
        #pd_diff.to_excel('data_not_valid.xlsx')
        globi=globi+1 
        data=dats
    else: 
        
        datas= data[data["protein_id"].isin(list(listtosubs.values())[(resub+1)%2])==True]
        data["protein_id"].replace(list(listtosubs.values())[(resub+1)%2], list(listtosubs.values())[resub])
        print("tamaño original: "+str(len(data)))
        dats=data.drop_duplicates(subset=['disease_id','protein_id'],keep='first',inplace=False)
        print("Despues de tirar duplicados en id: "+str(len(dats)))
        dats=dats.drop_duplicates(subset=['disease_id','protein_sequence'],keep='first',inplace=False)
        print("Despues de tirar duplicados en secuencia: "+str(len(dats)))
        dats.to_excel('data_nervous_genes_x.xlsx',index=False,columns=data.columns)  
        datas.to_csv('resultados/proteinasDescartadas_'+ str(globi) +'.csv', index=False) 
        #pd_diff=pd.concat([data,dats]).drop_duplicates(keep=False)
        #pd_diff.to_excel('data_not_valid.xlsx')
        globi=globi+1 
        data=dats
        #data.to_excel('data_nervous_genes_2.xlsx')
    return data                


def divide_by_class(data):
    print("inside the problem")
    cl=pd.read_excel("alzheimer_protein_class 1.xlsx")
    cl=substitute_or_remove_prot_id(cl,"c")
    cl.to_excel("alzheimer_protein_class 2.xlsx")
    #data2=data.copy()
    cli=cl.groupby('class_id')
    di=[]
    for k,v in cli:
     
      for index,row in v.iterrows():
         di.append(row['protein_id'])
      do=data[data["protein_id"].isin(di)]
      do.to_excel('proteinasClase_'+k+'.xlsx',index=False,columns=data.columns )
      di=[]
    #datacp=data.copy()
    #print(pd.concat([data2,datacp]).drop_duplicates())
    
    return data

def readData(archivoEntrada, enfermedad):
    data = pd.read_excel(archivoEntrada)
    
    #data.to_excel('data_nervous_genes_2.xlsx')
    
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        print(len(data))
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]
    data=substitute_or_remove_prot_id(data,"r")
    sequences = data["protein_sequence"]

    return sequences
def readOData(archivoEntrada, enfermedad):
    data = pd.read_excel(archivoEntrada)
    #data=substitute_or_remove_prot_id(data,"r")
    
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]

    sequences = data["protein_sequence"]

    return sequences

def readCData(archivoEntrada, enfermedad):
    data = pd.read_excel(archivoEntrada)
    #data=substitute_or_remove_prot_id(data,"r")
    
    if (enfermedad != ''):
        #datar=substitute_or_remove_prot_id(data,"r")
        #sprint("numero de filas de proteinas descartadas totales principal : "+ str(len(data)-len(datar)))
        
        
        data = data.loc[data["disease_id"] == enfermedad]

        #dataB = pd.read_excel("proteinas_en_comun_Alzheimer.xlsx")
                  
        
        
        #data=substitute_or_remove_prot_id(data,"r")
        #dataB=substitute_or_remove_prot_id(dataB,"r")  
        #dataB.to_excel("proteinas_en_comun_Alzeheimer2.xlsx")
        #data.to_excel('data_nervous_genes_2.xlsx')
        #filt_data=len(data)
        #alz_filt_data=len(dataB)
        #print("proteinas descartadas post filtro, principal: " + str(filt_data-len(data)))      
        #print("proteinas descartadas post filtro, comun alz: " + str(alz_filt_data-len(dataB)))
        #data = data[~((data["disease_id"] == enfermedad) &
        #              (data["protein_id"].isin(dataB["protein_id"])) &
        #              (data["gene_id"].isin(dataB["gene_id"])))]

    data=divide_by_class(data)
    sequences = data["protein_sequence"]

    return sequences


if __name__=='__main__':
      #data=readData('data_nervous_genes_1.xlsx','C0002395')
      data2 = readCData('data_nervous_genes_xf.xlsx','C0002395')
      data2=data2.to_list()
      datl=data.to_list() 
      #print(len(datl))
      du=[]
      #print(set(data2) - set(datl))      
      get_index_to_delete=[]
      for u in range(0,len(datl)):
         if datl[u] not in data2:
            du.append(datl[u])
         else:
            get_index_to_delete.append(u)   
            #print(str(u)+" Este no deberia estar: "+str(datl[u]))         
      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
      dia=[]     
      for y in du:
          dia.append(list(listtosubs.values())[(resub+1)%2][list(listtosubs.values())[resub].index(y)])
                
      #print(dia)