import json as json
import pandas as pd

DATA = []
HUMAN = []
with open("ReactomePathways.txt",'r') as f1:
    for line in f1:
        #print(line.split("\t"))
        sl = line.split("\t")
        RID = sl[0]
        name = sl[1]
        specis= sl[2]
        if specis[-1] == "\n":
            specis = specis[0:-1]

        DATA.append({"RID":RID, "name":name, "specis":specis})
        if specis == "Homo sapiens":
            HUMAN.append({"RID":RID, "name":name, "specis":specis})          

len(DATA)

20751

len(HUMAN)

2255

HDF = pd.DataFrame(HUMAN)

HDF.head(50)

HDF.to_csv("Allpathways_HomoSpiens.csv")

with open("pathways.txt", 'w')as file:
    for item in HDF["name"]:
        file.write(item)
        file.write("\n")

import json as json
import pandas as pd

DATA = []
HUMAN = []
with open("UniProt2Reactome_All_Levels.txt",'r') as f1:
    for line in f1:

        #print(line.split("\t"))
        sl = line.split("\t")
        #print(sl)
        UID = sl[0]
        RID = sl[1]
        WAD = sl[2]
        name = sl[3]
        GEN = sl[4]
        specis= sl[5]

        if specis[-1] == "\n":
            specis = specis[0:-1]

        DATA.append({"UID": UID,\
                     "RID":RID,\
                     "WAD":WAD,\
                     "name":name,\
                     "GEN": GEN,\
                     "specis":specis\
                    })

        if specis == "Homo sapiens":
            HUMAN.append({"UID": UID,\
                         "RID":RID,\
                         "WAD":WAD,\
                         "name":name,\
                         "GEN":GEN,\
                         "specis":specis\
                    })

len(DATA)

784328

len(HUMAN)

125359

HDF = pd.DataFrame(HUMAN)

HDF.head(50)

HDF.to_csv("Uniprot2Pathways_HomoSpiens.csv")

unames = list(set(HDF['name']))
len(unames)

2229

Name2uniprot = []
for name in unames:
    alluniprot = []
    for ID,nm in zip(HDF['UID'],HDF['name']):
        if nm == name:
            alluniprot.append(ID)
    Name2uniprot.append({"Pathway": name,"UIDs":alluniprot, "count": len(alluniprot)})

NUP = pd.DataFrame(Name2uniprot)

NUP.to_csv("Pathways2Uniprot.csv")