dcatoolkit 0.1.2__tar.gz → 0.1.3__tar.gz

{dcatoolkit-0.1.2/src/dcatoolkit.egg-info → dcatoolkit-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcatoolkit
-Version: 0.1.2
+Version: 0.1.3
 Summary: Collection of useful modules and representations for managing DCA output data.
 Author-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>
 Maintainer-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>

{dcatoolkit-0.1.2 → dcatoolkit-0.1.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dcatoolkit"
-version = "0.1.2"
+version = "0.1.3"
 description = "Collection of useful modules and representations for managing DCA output data."
 keywords = ["dca", "toolkit", "DI", "coevolution"]
 

dcatoolkit-0.1.3/src/dcatoolkit/__init__.py

@@ -0,0 +1,4 @@
+
+__version__ = "0.1.3"
+from .representation import Pairs, DirectInformationData, StructureInformation, ResidueAlignment
+from .analytics import MSATools

dcatoolkit-0.1.3/src/dcatoolkit/analytics.py

@@ -0,0 +1,145 @@
+import re
+from collections import Counter
+from typing import Optional
+import string
+
+class MSATools:
+    """
+    Tools and interface for encapsulating MSA data and providing functionality for filtering and analysis.
+
+    Parameters
+    ----------
+    MSA : list of tuple of str, str
+        Loaded MSA that is a list of tuples where the first element is the header and the second element is its corresponding sequence.
+    """
+    def __init__(self, MSA: list[tuple[str, str]]):
+        self.MSA = MSA
+    
+    @staticmethod
+    def load_from_file(msa_filepath: str) -> 'MSATools':
+        """
+        Generates MSATools object from an MSA file in ".afa" format.
+
+        Parameters
+        ----------
+        msa_filepath : str
+            Filepath of the MSA in ".afa" format that is provided.
+        
+        Returns
+        -------
+        MSATools
+            An MSATools instance with the appropriate list of (header, sequence) tuples where sequences are simplified and converted to single line format.
+        """
+        msa_entries: list[tuple[str, str]] = []
+        with open(msa_filepath, 'r') as fs:
+            data = fs.read()
+        split_data = data.split(">")[1:]
+        for entry in split_data:
+            line_split_entry = entry.split("\n")
+            header = line_split_entry[0]
+            sequence = "".join(line_split_entry[1:])
+            msa_entries.append((">"+header, sequence))
+        return MSATools(msa_entries)
+
+    @staticmethod
+    def get_sequence_max_cont_gaps(sequence: str) -> int:
+        """
+        Find maximum number of continuous gaps in a specific sequence.
+
+        Parameters
+        ----------
+        sequence : str
+            Sequence of characters, potentially containing multiple of '-', a gap character.
+        
+        Returns
+        -------
+        int
+            The maximum number of continuous gaps in a sequence.
+        """
+        dash_match = re.findall(r"-+", sequence)
+        gap_counts = [len(match) for match in dash_match]
+        if len(gap_counts) > 0:
+            return max(gap_counts)
+        else:
+            return 0
+    
+    def gap_frequency(self) -> tuple[dict[int, int], dict[int, float]]:
+        """
+        Calculates the frequency of maximum continuous gaps throughout the MSA where the key corresponds to the number of continous gaps and the value corresponds to the number of sequences or the cumulative percentage of their sequences.
+
+        Returns
+        -------
+        tuple of dict of int, int and dict of int, int
+            Two element tuple where first element is a frequency count dictionary and the second element is a cumulative percentage of sequences with a specific maximum number of continous gaps.
+        """
+        max_gap_counts = []
+        for header, sequence in self.MSA:
+            max_gap_counts.append(MSATools.get_sequence_max_cont_gaps(sequence))
+        frequency_count_dict = dict(Counter(max_gap_counts))
+        cumul_perc_dict = {}
+        cumul_count = 0
+        for key in sorted(frequency_count_dict.keys()):
+            value = frequency_count_dict[key]
+            cumul_count += value
+            cumul_perc_dict[key] = cumul_count / len(self.MSA)
+        return (frequency_count_dict, cumul_perc_dict)
+    
+    def filter_by_continuous_gaps(self, max_gaps: Optional[int]=None) -> list[tuple[str, str]]:
+        """
+        Filter out entries in your MSA by the number of maximum continuous gaps specified unless None is provided. Also, removes .s and lowercase letters from the sequence.
+
+        Parameters
+        ----------
+        max_gaps : int
+            The maximum allowed number of continuous gaps in a sequence
+
+        Returns
+        -------
+        list of tuple of str, str
+            List of entries that are valid in that their sequences' number of maximum continuous gaps is within the threshold supplied as `max_gaps`. 
+        """
+        table = str.maketrans('', '', string.ascii_lowercase+".")
+        if max_gaps == None:
+            kept_entries = []
+            for header, sequence in self.MSA:
+                sequence = sequence.translate(table)
+                kept_entries.append((header, sequence))
+            return kept_entries
+        else:
+            kept_entries = []
+            for header, sequence in self.MSA:
+                sequence = sequence.translate(table)
+                if MSATools.get_sequence_max_cont_gaps(sequence) <= max_gaps:
+                    kept_entries.append((header, sequence))
+        return kept_entries
+
+    def write(self, filepath: str) -> None:
+        """
+        Writes this MSA's headers and sequences to the filepath specified.
+        
+        Parameters
+        ----------
+        filepath : str
+            Filepath to write the MSA supplied to.
+
+        Returns
+        -------
+        None
+        """
+        with open(filepath, 'w') as fs:
+            for header, sequence in self.MSA:
+                fs.write(header)
+                fs.write("\n")
+                fs.write(sequence)
+                fs.write("\n")
+
+    def __len__(self):
+        """
+        Returns the number of sequences, and equivalently, the number of headers in the MSA.
+
+        Returns
+        -------
+        int
+            length of the MSA list of header, sequence tuples.
+        """
+        return len(self.MSA)

{dcatoolkit-0.1.2 → dcatoolkit-0.1.3/src/dcatoolkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcatoolkit
-Version: 0.1.2
+Version: 0.1.3
 Summary: Collection of useful modules and representations for managing DCA output data.
 Author-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>
 Maintainer-email: Raheel Syed Ahmed <raheelsyedahmed@gmail.com>

{dcatoolkit-0.1.2 → dcatoolkit-0.1.3}/src/dcatoolkit.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 src/dcatoolkit/__init__.py
+src/dcatoolkit/analytics.py
 src/dcatoolkit/representation.py
 src/dcatoolkit.egg-info/PKG-INFO
 src/dcatoolkit.egg-info/SOURCES.txt

dcatoolkit-0.1.2/src/dcatoolkit/__init__.py

@@ -1,3 +0,0 @@
-
-__version__ = "0.1.2"
-from .representation import Pairs, DirectInformationData, StructureInformation, ResidueAlignment