1.1 --- a/allpy/base.py	Thu Dec 16 18:35:56 2010 +0300
     1.2 +++ b/allpy/base.py	Thu Dec 16 18:51:05 2010 +0300
     1.3 @@ -199,6 +199,9 @@
     1.4          self.sequences = []
     1.5          self.columns = []
     1.6  
     1.7 +    # Alignment modification methods
     1.8 +    # ==============================
     1.9 +
    1.10      def append_sequence(self, sequence):
    1.11          """Add sequence to alignment.
    1.12  
    1.13 @@ -218,6 +221,9 @@
    1.14              self.columns[j][seq] = sequence[i]
    1.15          self.sequences.append(sequence)
    1.16  
    1.17 +    # Alignment IO methods
    1.18 +    # ====================
    1.19 +
    1.20      @classmethod
    1.21      def from_fasta(cls, file):
    1.22          """Create new alignment from FASTA file."""
    1.23 @@ -237,6 +243,69 @@
    1.24              line = "".join(map(char, row))
    1.25              fasta.save_file(file, line, seq.name, seq.description)
    1.26  
    1.27 +    # Data access methods for alignment
    1.28 +    # =================================
    1.29 +
    1.30 +    def rows(self):
    1.31 +        """Return list of rows (temporary objects) in alignment.
    1.32 +
    1.33 +        Each row is a dictionary of { column : monomer }.
    1.34 +        
    1.35 +        For gap positions there is no key for the column in row.
    1.36 +
    1.37 +        Each row has attribute `sequence` pointing to the sequence the row is
    1.38 +        describing.
    1.39 +
    1.40 +        Modifications of row have no effect on the alignment.
    1.41 +        """
    1.42 +        # For now, the function returns a list rather than iterator.
    1.43 +        # It is yet to see, whether memory performance here becomes critical,
    1.44 +        # or is random access useful.
    1.45 +        rows = []
    1.46 +        for sequence in self.sequences:
    1.47 +            row = util.UserDict()
    1.48 +            row.sequence = sequence
    1.49 +            for column in self.columns:
    1.50 +                if sequence in column:
    1.51 +                    row[column] = column[sequence]
    1.52 +            rows.append(row)
    1.53 +        return rows
    1.54 +
    1.55 +    def rows_as_lists(self):
    1.56 +        """Return list of rows (temporary objects) in alignment.
    1.57 +
    1.58 +        Each row here is a list of either monomer or None (for gaps).
    1.59 +
    1.60 +        Each row has attribute `sequence` pointing to the sequence of row.
    1.61 +
    1.62 +        Modifications of row have no effect on the alignment.
    1.63 +        """
    1.64 +        rows = []
    1.65 +        for sequence in self.sequences:
    1.66 +            row = util.UserList()
    1.67 +            row.sequence = sequence
    1.68 +            for column in self.columns:
    1.69 +                row.append(column.get(sequence))
    1.70 +            rows.append(row)
    1.71 +        return rows
    1.72 +
    1.73 +    def columns_as_lists(self):
    1.74 +        """Return list of columns (temorary objects) in alignment.
    1.75 +
    1.76 +        Each column here is a list of either monomer or None (for gaps).
    1.77 +
    1.78 +        Items of column are sorted in the same way as alignment.sequences.
    1.79 +
    1.80 +        Modifications of column have no effect on the alignment.
    1.81 +        """
    1.82 +        columns = []
    1.83 +        for column in self.columns:
    1.84 +            col = []
    1.85 +            for sequence in self.sequences:
    1.86 +                col.append(column.get(sequence))
    1.87 +            columns.append(col)
    1.88 +        return columns
    1.89 +
    1.90      ## Unclean code follows
    1.91  
    1.92      def length(self):