peptideIdentification | Python Fiddle

AMINO_DICT = {'A': 71, 'C': 103, 'E': 129, 'D': 115, 'G': 57, 'F': 147, 'I': 113,
              'H': 137, 'K': 128, 'M': 131, 'L': 113, 'N': 114, 'Q': 128, 'P': 97,
              'S': 87, 'R': 156, 'T': 101, 'W': 186, 'V': 99, 'Y': 163, 'X': 4, 'Z': 5}

def peptide_identification(spec_vec, proteome):
    '''
     Given: A space-delimited spectral vector Spectrum' and an amino acid string Proteome.
     Return: A substring of Proteome with maximum score against Spectrum'.
    '''
    result = {'score': - sys.maxint, 'sub_str': ""}
    
    for str_index in range(len(proteome)):
        
        new_score = 0
        new_sub_str = proteome[str_index]
        vec_index = AMINO_DICT[proteome[str_index]] 
        
        while vec_index < len(spec_vec) and str_index < len(proteome):
            
            new_score += spec_vec[vec_index]
            
            if vec_index == len(spec_vec) - 1:
                if new_score > result["score"]:
                    result["score"] = new_score
                    result["sub_str"] = new_sub_str
                    
            str_index += 1
            if str_index < len(proteome):
                new_sub_str += proteome[str_index]
                vec_index += AMINO_DICT[proteome[str_index]] 
    
    return result
################################################################################################
#spec_vec = [0, 0, 0, 0, 4, -2, -3, -1, -7, 6, 5, 3, 2, 1, 9, 3, -8, 0, 3, 1, 2, 1, 8]
#proteome = "XZZXZXXXZXZZXZXXZ"
#
#print peptide_identification(spec_vec, proteome)
################################################################################################

spec_vectors = [[0, -1, 5, -4, 5, 3, -1, -4, 5, -1, 0, 0, 4, -1, 0, 1, 4, 4, 4],
			   	[-4, 2, -2, -4, 4, -5, -1, 4, -1, 2, 5, -3, -1, 3, 2, -3]]
proteome = "XXXZXZXXZXZXXXZXXZX"
threshold = 5

def psm_search(spec_vectors, proteome, threshold):
    '''
     Given: A set of space-delimited spectral vectors SpectralVectors, an amino acid string
     Proteome, and an integer threshold.
     Return: The set PSMthreshold(Proteome, SpectralVectors) of Peptide- Spectrum Matches.
     
     PSMSet ← an empty set
     for each vector Spectrum' in SpectralVectors
          Peptide ← PeptideIdentification(Spectrum', Proteome)
          if Score(Peptide, Spectrum) ≥ threshold
              add the PSM (Peptide, Spectrum') to PSMSet
     return PSMSet
    '''
    pms_set = set()
    
    for spec_vec in spec_vectors:
        peptide = peptide_identification(spec_vec, proteome)
        if peptide["score"] >= threshold:
            pms_set.add(peptide["sub_str"])
    
    return pms_set

print psm_search(spec_vectors, proteome, threshold)

Python Fiddle

Python Cloud IDE