view DPOGALAXY.py @ 6:d811c2f74042 draft

Uploaded

#print('Hello world')
#PS C:\Users\joseduarte\Documents\pythonfiles\phage> python pdpo_test.py
#Hello world

class PDPOPrediction:
    def __init__(self, Folder = 'location', mdl='',seq_file = 'fasta_file.fasta',ttable=11):
        import pickle
        import pandas as pd
        from Bio import SeqIO
        import os
        from pathlib import Path
        self.data = {}
        self.df_output = None
        self.seqfile = seq_file
        self.__location__ = os.path.realpath(os.path.join(os.getcwd(), Folder))

        with open(os.path.join(self.__location__,mdl), 'rb') as m:
            self.model = pickle.load(m)
        if mdl == 'SVM4311':
            with open(os.path.join(__location__,'d4311_SCALER'),'rb') as sl:
                self.scaler = pickle.load(sl)
                self.name = mdl
        elif mdl == 'RF5748':
            with open(os.path.join(__location__,'d5748_SCALER'),'rb') as sc:
                self.scaler = pickle.load(sc)
                self.name = mdl
        elif mdl == 'ANN4311':
            with open(os.path.join(__location__,'d4311_SCALER'),'rb') as sl:
                self.scaler = pickle.load(sl)
                self.name = mdl

        for seq in SeqIO.parse(os.path.join(self.__location__,self.seqfile), 'fasta'):
            #name_seq = seq.id
            DNA_seq = seq.seq
            AA_seq = DNA_seq.translate(table=ttable)
            descr_seq = seq.description.replace(' ','')
            self.data[descr_seq]=[DNA_seq._data,AA_seq._data]
        self.df = pd.DataFrame({'ID':list(self.data.keys()),
                              'DNAseq':[elem[0] for elem in self.data.values()],
                              'AAseq':[elem[1] for elem in self.data.values()]})
        self.df = self.df.set_index('ID')

    def Datastructure(self):
        import pandas as pd
        import pickle
        from Bio.SeqUtils.ProtParam import ProteinAnalysis
        from propy import CTD
        from propy import AAComposition

        def count_orf(orf_seq):
            dic = {'DNA-A': 0, 'DNA-C': 0, 'DNA-T': 0, 'DNA-G': 0, 'DNA-GC': 0}
            for letter in range(len(orf_seq)):
                for k in range(0, 4):
                    if orf_seq[letter] in list(dic.keys())[k][-1]:
                        dic[list(dic.keys())[k]] += 1
            dic['DNA-GC'] = ((dic['DNA-C'] + dic['DNA-G']) / (
                    dic['DNA-A'] + dic['DNA-C'] + dic['DNA-T'] + dic['DNA-G'])) * 100
            return dic

        def count_aa(aa_seq):
            dic = {'G': 0, 'A': 0, 'L': 0, 'V': 0, 'I': 0, 'P': 0, 'F': 0, 'S': 0, 'T': 0, 'C': 0,
                   'Y': 0, 'N': 0, 'Q': 0, 'D': 0, 'E': 0, 'R': 0, 'K': 0, 'H': 0, 'W': 0, 'M': 0}
            for letter in range(len(aa_seq)):
                if aa_seq[letter] in dic.keys():
                    dic[aa_seq[letter]] += 1
            return dic

        def sec_st_fr(aa_seq):
            from Bio.SeqUtils.ProtParam import ProteinAnalysis
            st_dic = {'Helix': 0, 'Turn': 0, 'Sheet': 0}
            stu = ProteinAnalysis(aa_seq).secondary_structure_fraction()
            st_dic['Helix'] = stu[0]
            st_dic['Turn'] = stu[1]
            st_dic['Sheet'] = stu[2]
            return st_dic

        self.feat={"SVM4311": ["DNA-A", "DNA-T", "DNA-G", "DNA-GC", "AA_Len", "G", "A", "S", "T", "N", "Turn", "Sheet",
                   "_PolarizabilityC1", "_PolarizabilityC3", "_SolventAccessibilityC1", "_SecondaryStrC1",
                   "_SecondaryStrC2", "_SecondaryStrC3", "_ChargeC2", "_ChargeC3", "_PolarityC1", "_NormalizedVDWVC1",
                   "_NormalizedVDWVC3", "_HydrophobicityC2", "_HydrophobicityC3", "_SecondaryStrT23",
                   "_NormalizedVDWVT13", "_PolarizabilityD1001", "_SolventAccessibilityD1001",
                   "_SolventAccessibilityD2001", "_SolventAccessibilityD3001", "_SecondaryStrD1025", "_ChargeD1075",
                   "_ChargeD2001", "_ChargeD2025", "_ChargeD3025", "_ChargeD3050", "_PolarityD1075", "_PolarityD3025",
                   "_NormalizedVDWVD1001", "_NormalizedVDWVD3050", "_HydrophobicityD2001", "DG", "DT", "GD"],
                   "RF5748": ["DNA-A", "DNA-T", "DNA-G", "DNA-GC", "AA_Len", "G", "A", "S", "T", "N", "Turn", "Sheet",
                   "_PolarizabilityC1", "_PolarizabilityC3", "_SecondaryStrC1", "_SecondaryStrC2", "_SecondaryStrC3",
                   "_ChargeC1", "_ChargeC2", "_ChargeC3", "_NormalizedVDWVC1", "_NormalizedVDWVC3", "_HydrophobicityC2",
                   "_HydrophobicityC3", "_SolventAccessibilityT12", "_SolventAccessibilityT13", "_SecondaryStrT23",
                   "_NormalizedVDWVT23", "_HydrophobicityT12", "_PolarizabilityD1001", "_SolventAccessibilityD1001",
                   "_SolventAccessibilityD2001", "_SolventAccessibilityD3001", "_SecondaryStrD1001",
                   "_SecondaryStrD1025", "_ChargeD1025", "_ChargeD1075", "_ChargeD2001", "_ChargeD2025", "_ChargeD3025",
                   "_ChargeD3050", "_PolarityD1001", "_PolarityD1050", "_PolarityD1075", "_PolarityD3025",
                   "_NormalizedVDWVD1001", "_NormalizedVDWVD3001", "_HydrophobicityD1001", "_HydrophobicityD2001", "NG",
                   "DG", "DT", "GD", "GT"],
                   "ANN4311": ["DNA-A", "DNA-T", "DNA-G", "DNA-GC", "AA_Len", "G", "A", "S", "T", "N", "Turn", "Sheet",
                   "_PolarizabilityC1", "_PolarizabilityC3", "_SolventAccessibilityC1", "_SecondaryStrC1",
                   "_SecondaryStrC2", "_SecondaryStrC3", "_ChargeC2", "_ChargeC3", "_PolarityC1", "_NormalizedVDWVC1",
                   "_NormalizedVDWVC3", "_HydrophobicityC2", "_HydrophobicityC3", "_SecondaryStrT23",
                   "_NormalizedVDWVT13", "_PolarizabilityD1001", "_SolventAccessibilityD1001",
                   "_SolventAccessibilityD2001", "_SolventAccessibilityD3001", "_SecondaryStrD1025", "_ChargeD1075",
                   "_ChargeD2001", "_ChargeD2025", "_ChargeD3025", "_ChargeD3050", "_PolarityD1075", "_PolarityD3025",
                   "_NormalizedVDWVD1001", "_NormalizedVDWVD3050", "_HydrophobicityD2001", "DG", "DT", "GD"]}

        self.df_output = self.df.copy()
        self.df_output.drop(['DNAseq','AAseq'],axis=1,inplace=True)
        dna_feat = {}
        aa_len = {}
        aroma_dic = {}
        iso_dic = {}
        aa_content = {}
        st_dic_master = {}
        CTD_dic = {}
        dp = {}
        for i in range(len(self.df)):
            i_name = self.df.index[i]
            dna_feat[i_name] = count_orf(self.df.iloc[i]['DNAseq'])
            aa_len[i_name] = len(self.df.iloc[i]['AAseq'])
            aroma_dic[i_name] = ProteinAnalysis(self.df.iloc[i]['AAseq']).aromaticity()
            iso_dic[i_name] = ProteinAnalysis(self.df.iloc[i]['AAseq']).isoelectric_point()
            aa_content[i_name] = count_aa(self.df.iloc[i]['AAseq'])
            st_dic_master[i_name] = sec_st_fr(self.df.iloc[i]['AAseq'])
            CTD_dic[i_name] = CTD.CalculateCTD(self.df.iloc[i]['AAseq'])
            dp[i_name] = AAComposition.CalculateDipeptideComposition(self.df.iloc[i]['AAseq'])
        for j in self.df.index:
            self.df.loc[j, dna_feat[j].keys()] = dna_feat[j].values() #dic with multiple values
            self.df.loc[j, 'AA_Len'] = int(aa_len[j]) #dic with one value
            self.df.loc[j, 'Aromaticity'] = aroma_dic[j]
            self.df.loc[j, 'IsoelectricPoint'] = iso_dic[j]
            self.df.loc[j, aa_content[j].keys()] = aa_content[j].values()
            self.df.loc[j, st_dic_master[j].keys()] = st_dic_master[j].values()
            self.df.loc[j, CTD_dic[j].keys()] = CTD_dic[j].values()
            self.df.loc[j, dp[j].keys()] = dp[j].values()
        self.df.drop(['DNAseq','AAseq'],axis=1,inplace=True)

    def Prediction(self):
        import os
        import pickle
        import json
        import pandas as pd
        import numpy as np
        from pathlib import Path
        ft_scaler = pd.DataFrame(self.scaler.transform(self.df.iloc[:, :]), index=self.df.index,columns=self.df.columns)
        ft_scaler = ft_scaler.drop(columns=[col for col in self.df if col not in self.feat[self.name]], axis=1)
        scores = self.model.predict_proba(ft_scaler)
        pos_scores = np.empty((self.df.shape[0], 0), float)
        for x in scores:
            pos_scores = np.append(pos_scores, round(x[1]*100))
        self.df_output.reset_index(inplace=True)
        self.df_output['{} DPO Prediction (%)'.format(self.name)]= pos_scores
        self.df_output = self.df_output.sort_values(by='{} DPO Prediction (%)'.format(self.name), ascending=False)
        self.df_output.to_html('output.html', index=False, justify='center')

if __name__ == '__main__':
    import os
    import sys
    __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))

    model = sys.argv[1]
    fasta_file = sys.argv[2]

    PDPO = PDPOPrediction(__location__,model,fasta_file)
    PDPO.Datastructure()
    PDPO.Prediction()