import pandas as pd

# List of your desired features
#LAB features 
# features_to_keep = [
#     "P78417|GSTO1_Acetyl_LEEVLTNKK_1",
#     "O75326|SEM7A_Glyco_NPEAPLNVSR",
#     "P01133|EGF_Glyco_VFLNGSR",
#     "P01137|TGFB1_Glyco_YSNNSWR",
#     "P10646|TFPI1_Glyco_YFYNNQTK_1",
#     "P78324|SHPS1_Glyco_GTANLSETIR",
#     "Q14517|FAT1_Glyco_TGALTVQNTTQLR",
#     "Q8NBL1|PGLT1_Glyco_FLSYNVTR",
#     "O95772|STR3N_Phospho_LLIVQDASER",
#     "P04792|HSPB1_Phospho_QLSSGVSEIR_1",
#     "P04792|HSPB1_Phospho_QLSSGVSEIR_2",
#     "P11171|41_Phospho_SLDGAAAVDSADR",
#     "P13224|GP1BB_Phospho_LSLTDPLVAER_2",
#     "P16949|STMN1_Phospho_ESVPEFPLSPPK",
#     "P23588|IF4B_Phospho_SLENETLNK",
#     "P37802|TAGL2_Phospho_NFSDNQLQEGK",
#     "P42566|EPS15_Phospho_LNDPFQPFPGNDSPK",
#     "P50851|LRBA_Phospho_SPVDIVTGGISPVR",
#     "P51149|RAB7A_Phospho_FQSLGVAFYR",
#     "P61006|RAB8A_Phospho_LEGNSPQGSNQGVK_1",
#     "P61006|RAB8A_Phospho_LEGNSPQGSNQGVK_2",
#     "Q06187|BTK_Phospho_STGDPQGVIR_1",
#     "Q15942|ZYX_Phospho_FSPVTPK",
#     "Q15942|ZYX_Phospho_SPGAPGPLTLK",
#     "Q6WCQ1|MPRIP_Phospho_SNPDFLK",
#     "Q8TD16|BICD2_Phospho_SPILLPK",
#     "Q99501|GA2L1_Phospho_VSPTTSPRPASPVPGSER_1",
#     "Q9UDY2|ZO2_Phospho_SPSPEPR",
#     "Q9UDY2|ZO2_Phospho_SFSPEER",
#     "Q9Y490|TLN1_Phospho_VLVQNAAGSQEK"
# ]

#TN features 
features_to_keep = [
    "P62805|H4_Acetyl_GLGKGGAKR",
    "O75326|SEM7A_Glyco_NPEAPLNVSR",
    "P01133|EGF_Glyco_VFLNGSR",
    "P01137|TGFB1_Glyco_YSNNSWR",
    "P04114|APOB_Glyco_FNSSYLQGTNQITGR",
    "P31997|CEAM8_Glyco_LFIPNITTK",
    "P78324|SHPS1_Glyco_GTANLSETIR",
    "Q13201|MMRN1_Glyco_LQNLTLPTNASIK",
    "Q14517|FAT1_Glyco_TGALTVQNTTQLR",
    "O95772|STR3N_Phospho_LLIVQDASER",
    "P04792|HSPB1_Phospho_QLSSGVSEIR_2",
    "P05556|ITB1_Phospho_WDTGENPIYK",
    "P13224|GP1BB_Phospho_LSLTDPLVAER_1",
    "P16949|STMN1_Phospho_ESVPEFPLSPPK",
    "P42331|RHG25_Phospho_DIPLSPPAQK",
    "P51149|RAB7A_Phospho_FQSLGVAFYR",
    "P61006|RAB8A_Phospho_LEGNSPQGSNQGVK_1",
    "Q06187|BTK_Phospho_STGDPQGVIR_1",
    "Q06187|BTK_Phospho_STGDPQGVIR_2",
    "Q15942|ZYX_Phospho_GPPASSPAPAPK_1",
    "Q15942|ZYX_Phospho_GPPASSPAPAPK_2",
    "Q15942|ZYX_Phospho_FSPVTPK",
    "Q6WCQ1|MPRIP_Phospho_SNPDFLK",
    "Q99501|GA2L1_Phospho_VSPTTSPRPASPVPGSER_1",
    "Q99501|GA2L1_Phospho_VSPTTSPRPASPVPGSER_2",
    "Q9NQ75|CASS4_Phospho_QQLYDIPASPK",
    "Q9NZQ3|SPN90_Phospho_AAPTTPPPPVK_1",
    "Q9Y3Q8|T22D4_Phospho_SPDPFGAVAAQK"
]


# Load the spreadsheet (update 'your_file.xlsx' to your actual filename)
df = pd.read_excel('../datasets/Adjusted_062223_MH_Data_For_Training.xlsx')

# Ensure 'Type' is the first column and keep only relevant features
columns_to_keep = ["Type"] + [f for f in features_to_keep if f in df.columns]
filtered_df = df[columns_to_keep]

# Save the filtered dataframe to a new Excel file
filtered_df.to_excel('../datasets/TN_30.xlsx', index=False)