Merge branch 'main' of https://github.com/tahiri-lab/aPhyloGeo

README.md

@@ -4,6 +4,8 @@
         [![Py version](https://img.shields.io/pypi/pyversions/pysd.svg)](https://pypi.python.org/pypi/pysd/)
         [![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2Ftahiri-lab%2FaPhylogeo&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=hits&edge_flat=false)](https://hits.seeyoufarm.com)
         [![GitHub release](https://img.shields.io/github/v/release/tahiri-lab/aPhylogeo.svg?maxAge=3600)](https://github.com/tahiri-lab/aPhylogeo/releases/)
+        [![build and test](https://github.com/tahiri-lab/aPhyloGeo/actions/workflows/github-actions-demo.yml/badge.svg)]([https://github.com/matsengrp/gctree/actions/workflows/build-and-test.yml](https://github.com/tahiri-lab/aPhyloGeo/actions/workflows/github-actions-demo.yml))
+        [![PyPI version](https://badge.fury.io/py/aphylogeo.svg)](https://badge.fury.io/py/aphylogeo)
         </p>
 
 

aphylogeo/alignement.py

@@ -172,13 +172,13 @@ def align(self) -> Alignment:
             Alignment: The alignment object
         """
         if Params.alignment_method == "1":
-            self.centroidKey = self.getSequenceCentroid()[0]
-            self.centroidSeq = self.sequences.pop(self.centroidKey)
-            self.aligned = self.alignSequencesWithPairwise()
+            centroidKey = self.getSequenceCentroid()[0]
+            centroidSeq = self.sequences.pop(centroidKey)
+            aligned = self.alignSequencesWithPairwise(centroidKey, centroidSeq)
             if Params.fit_method == "1":
-                heuristicMSA = self.starAlignement()
+                heuristicMSA = self.starAlignement(centroidKey, aligned)
             elif Params.fit_method == "2":
-                heuristicMSA = self.narrowFitPairwise()
+                heuristicMSA = self.narrowFitPairwise(aligned)
 
         elif Params.alignment_method == "2":
             heuristicMSA = self.muscleAlign()
@@ -249,7 +249,7 @@ def ScoreSingle(self, args):
         score = aligner.score(seqA, seqB)
         return (seqAID, seqBID, score)
 
-    def alignSequencesWithPairwise(self):
+    def alignSequencesWithPairwise(self, centroidKey, centroidSeq):
         """
         Method that aligns multiple DNA sequences.
         The first speciment of the dataset is used as the main pivot.
@@ -269,7 +269,7 @@ def alignSequencesWithPairwise(self):
 
         seq_pairs = []
         for seqXID in seqs.keys():
-            seq_pairs.append([self.centroidKey, self.centroidSeq, seqXID, seqs[seqXID]])
+            seq_pairs.append([centroidKey, centroidSeq, seqXID, seqs[seqXID]])
 
         align_scores = Multi(seq_pairs, self.alignSingle).processingLargeData()
         aligned = {}
@@ -380,7 +380,7 @@ def alignSingle(self, args):
         aligned = aligner.align(sc, seqB)[0]
         return [seqBID, aligned, scID]
 
-    def narrowFitPairwise(self):
+    def narrowFitPairwise(self, aligned):
         """Fit length of a centroid sequence and its pairwise aligned sequences
 
         The length of each sequence from the pairwise alignment are set equal by
@@ -397,16 +397,16 @@ def narrowFitPairwise(self):
         -------
         A dictionary of all accessions and their fitted aligned sequences.
         """
-        seqs = self.getAlignSeqs()
-        max_len = max(self.getAlignSeqLens())
+        seqs = self.getAlignSeqs(aligned)
+        max_len = max(self.getAlignSeqLens(aligned))
         for nucleo_i in range(0, max_len):
             for seq_i in range(0, len(seqs)):
                 if self.isCurrentCharDash(seqs, seq_i, nucleo_i):
-                    seqs = self.insertDashToShorterSeq(seqs, nucleo_i)
+                    seqs = self.insertDashToShorterSeq(seqs, nucleo_i, aligned)
         seqs = self.appendDashToShorterSeqs(seqs, max_len)
-        return self.mergeFitPairwise(seqs)
+        return self.mergeFitPairwise(aligned, seqs)
 
-    def getAlignSeqs(self):
+    def getAlignSeqs(self, aligned):
         """Extract all sequences aligned using a pairwise alignment
 
         Parameters:
@@ -418,11 +418,11 @@ def getAlignSeqs(self):
         List of sequences aligned through pairwise alignment
         """
         seqs = []
-        for alignment in self.aligned:
-            seqs.append([str(seq) for seq in self.aligned[alignment].values()])
+        for alignment in aligned:
+            seqs.append([str(seq) for seq in aligned[alignment].values()])
         return list(sum(seqs, []))
 
-    def getAlignSeqLens(self):
+    def getAlignSeqLens(self, aligned):
         """Get length of all sequences aligned using a pairwise alignment
 
         Parameters:
@@ -433,9 +433,9 @@ def getAlignSeqLens(self):
         -------
         List of the length of each aligned sequences
         """
-        return [len(seq) for seq in self.getAlignSeqs()]
+        return [len(seq) for seq in self.getAlignSeqs(aligned)]
 
-    def getAlignCouple(self):
+    def getAlignCouple(self, aligned):
         """Get nested couple accessions and their respective sequences
 
         Parameters:
@@ -446,9 +446,9 @@ def getAlignCouple(self):
         -------
         List of paired accessions and their aligned sequences
         """
-        return [val for val in list(self.aligned.values())]
+        return [val for val in list(aligned.values())]
 
-    def extractOneAlignAcc(self, nest_ord=0):
+    def extractOneAlignAcc(self, aligned, nest_ord=0):
         """Extract the accession from a nested alignment couple
 
         Parameters:
@@ -463,11 +463,11 @@ def extractOneAlignAcc(self, nest_ord=0):
         accessions of a group of sequences aligned throug pairwise alignment.
         """
         try:
-            return [list(i)[nest_ord] for i in self.getAlignCouple()]
+            return [list(i)[nest_ord] for i in self.getAlignCouple(aligned)]
 
         # Return the centroid sequence if an invalid position is queried
         except IndexError:
-            return [list(i)[0] for i in self.getAlignCouple()]
+            return [list(i)[0] for i in self.getAlignCouple(aligned)]
 
     def isCurrentCharDash(self, seqs, seq_i, ch_i):
         """Assess whether the character at current cursor position is a dash
@@ -487,7 +487,7 @@ def isCurrentCharDash(self, seqs, seq_i, ch_i):
         except IndexError:
             return False
 
-    def insertDashToShorterSeq(self, seqs, ch_i):
+    def insertDashToShorterSeq(self, seqs, ch_i, aligned):
         """Insert a dash at the current position of a sequence
 
         Insert a dash (-) character in a sequence if its length is shorter
@@ -504,13 +504,13 @@ def insertDashToShorterSeq(self, seqs, ch_i):
         """
         for seq_j in range(0, len(seqs)):
             try:
-                if (len(seqs[seq_j]) < max(self.getAlignSeqLens())) & (seqs[seq_j][ch_i] != "-"):
+                if (len(seqs[seq_j]) < max(self.getAlignSeqLens(aligned))) & (seqs[seq_j][ch_i] != "-"):
                     seqs[seq_j] = seqs[seq_j][:ch_i] + "-" + seqs[seq_j][ch_i:]
             except IndexError:
                 seqs[seq_j] = seqs[seq_j][:ch_i] + "-"
         return seqs
 
-    def mergeFitPairwise(self, seqs):
+    def mergeFitPairwise(self, aligned, seqs):
         """Generate a dictionary of all accessions and their fitted sequences
 
         Parameters:
@@ -522,8 +522,8 @@ def mergeFitPairwise(self, seqs):
         -------
         Dict, Group of accessions and their fitted sequences from a pairwise alignment
         """
-        centroid = {list(set(self.extractOneAlignAcc()))[0]: seqs[0]}
-        non_centroid = dict(zip(self.extractOneAlignAcc(1), seqs[1::2]))
+        centroid = {list(set(self.extractOneAlignAcc(aligned)))[0]: seqs[0]}
+        non_centroid = dict(zip(self.extractOneAlignAcc(aligned, 1), seqs[1::2]))
         return centroid | non_centroid
 
     def appendDashToShorterSeqs(self, seqs, max_len):
@@ -540,7 +540,7 @@ def appendDashToShorterSeqs(self, seqs, max_len):
         """
         return [f"{str(seq):-<{max_len}}" for seq in seqs]
 
-    def starAlignement(self):
+    def starAlignement(self, centroidKey, aligned):
         """
         Method that combs through all the pairwise alignments couples and makes
         it so that every sequenced is aligned with every other sequences. If a
@@ -584,12 +584,12 @@ def starAlignement(self):
         Return:
             starAlign (dict) see self.heuristicMSA
         """
-        scKey = self.centroidKey
+        scKey = centroidKey
         starAlign = {}
 
-        for k in self.aligned.keys():
+        for k in aligned.keys():
             # couple is SeqA and SeqB of a pairwise alignement
-            couple = self.aligned[k]
+            couple = aligned[k]
 
             a = list(couple.keys())
             a.remove(scKey)
@@ -599,7 +599,7 @@ def starAlignement(self):
             starAlign[sNewKey] = str(couple[sNewKey])  # SeqB, *not* the reference
 
             if len(starAlign) > 2:
-                starAlign = self.merge(starAlign, scKey, sNewKey)
+                starAlign = self.merge(starAlign, scKey, sNewKey, centroidKey)
 
             starAlign["temp"] = starAlign[scKey]  # SeqA, the *old* reference
         starAlign.pop("temp")
@@ -613,7 +613,7 @@ def starAlignement(self):
 
         return starAlign
 
-    def merge(self, result, k1, k2):
+    def merge(self, result, k1, k2, centroidKey):
         """
         Method that loops through each position of two strings ans compares the Chars.
 
@@ -671,7 +671,7 @@ def merge(self, result, k1, k2):
                         + "Please check the previous methods"
                         + " and ensure the pairwise alignemnt is correct"
                         + "\nCentroid ID: "
-                        + str(self.centroidKey)
+                        + str(centroidKey)
                         + "\nPairwise seq ID"
                         + " last inserted: "
                         + str(k2)

tests/pairwise_align.yaml

@@ -0,0 +1,26 @@
+file_name: './datasets/example/geo.csv'
+specimen: 'id' #"Please enter the name of the colum containing the specimens names: "
+names: ['id', 'ALLSKY_SFC_SW_DWN', 'T2M', 'PRECTOTCORR', 'QV2M', 'WS10M']
+bootstrap_threshold: 0
+dist_threshold: 60
+window_size: 200
+step_size: 100
+bootstrap_amount: 100
+data_names: ['ALLSKY_SFC_SW_DWN_newick', 'T2M_newick', 'QV2M_newick', 'PRECTOTCORR_newick', 'WS10M_newick']
+reference_gene_dir: './datasets/example'
+reference_gene_file: 'sequences.fasta'
+makeDebugFiles: True
+alignment_method: '2' #Please select one ~ 1:pairwiseAligner, 2:MUSCLE, 3:CLUSTALW, 4:MAFFT
+distance_method: '0' #Please select one  ~ 0: All distance methods, 1: Least-Square distance, 2: Robinson-Foulds distance, 3: Euclidean distance (DendroPY)
+fit_method: '1' #Please select one ~ 1:Wider Fit by elongating with Gap (starAlignment), 2:Narrow-fit prevent elongation with gap when possible
+tree_type: '2' #Please select one ~ 1: BioPython consensus tree, 2: FastTree application
+rate_similarity: 90
+method_similarity: '1' #Please select one :
+    # 1: Hamming distance
+    # 2: Levenshtein distance
+    # 3: Damerau-Levenshtein distance
+    # 4: Jaro similarity
+    # 5: Jaro-Winkler similarity
+    # 6: Smith–Waterman similarity
+    # 7: Jaccard similarity
+    # 8: Sørensen-Dice similarity

tests/test_genetic.py

@@ -1,9 +1,7 @@
-import ast
 import os
 from io import StringIO
 from pathlib import Path
 
-import pandas as pd
 from Bio import AlignIO, Phylo
 from Bio.Phylo.PhyloXML import Phylogeny
 
@@ -22,42 +20,36 @@ def setup_class(self):
 
         print("Begin setup for test class test_genetic...")
 
-        # params_small = Params(os.path.join(os.path.dirname(__file__), "params_small.yaml"))
-        # sequences_small = aPhyloGeo.readFastaFile(params_small.reference_gene_file)
-        # small = AlignSequences(params_small.reference_gene_file, params_small.window_size, params_small.step_size,
-        #                        params_small.makeDebugFiles, params_small.bootstrapAmount)
-        params_very_small = Params(os.path.join(os.path.dirname(__file__), "params_very_small.yaml"))
-        sequences_very_small = utils.loadSequenceFile(params_very_small.reference_gene_file)
-        very_small = AlignSequences(
-            sequences_very_small,
-            params_very_small.window_size,
-            params_very_small.step_size,
-            params_very_small.makeDebugFiles,
-            params_very_small.bootstrapAmount,
-            params_very_small.alignment_method,
-            params_very_small.reference_gene_file,
-            params_very_small.fit_method,
-            params_very_small.rate_similarity,
-            params_very_small.method_similarity
-        )
-        very_small.align()
-        self.alignementSetup = [very_small]  # , small]
-        self.paramSetup = [params_very_small]  # , params_small]
-
+        Params.load_from_file(params_file = "tests/pairwise_align.yaml")
+
+        # Load parameters
+        ref_gene_dir = Params.reference_gene_dir
+        ref_gene_file = Params.reference_gene_file
+        sequences_very_small = utils.loadSequenceFile(os.path.join(ref_gene_dir, ref_gene_file))
+
+        # Build AlignSequence object
+        self.sequences = sequences_very_small.copy()
+        self.seq_alignment = AlignSequences(self.sequences)
+
+        # Get centroid key
+        self.centroid = self.seq_alignment.getSequenceCentroid()[0]
+        self.centroidSeqs = self.sequences.pop(self.centroid)
+
+        # Get pairwise alignment
+        self.aligned = self.seq_alignment.alignSequencesWithPairwise(self.centroid, self.centroidSeqs)
+
     def test_centroidKey(self):
         """
         This test is used to test the centroidKey function.
         """
 
         print("Begin test_centroidKey...")
-
-        for alignement in self.alignementSetup:
-            actual_centroid = alignement.centroidKey
-            filename = current_file + "/testFiles/getSequenceCentroid/seq very small"
-
-            with open(filename, "r") as expected_file:
-                expected_centroid = expected_file.read()
-                assert actual_centroid == expected_centroid
+        # actual_centroid = self.seq_alignment.getSequenceCentroid()[0]
+
+        filename = current_file + "/testFiles/getSequenceCentroid/seq very small"
+        with open(filename, "r") as expected_file:
+            expected_centroid = expected_file.read()
+            assert self.centroid == expected_centroid
 
     def test_aligned(self):
         """
@@ -66,24 +58,24 @@ def test_aligned(self):
 
         print("Begin test_aligned...")
 
-        for alignement in self.alignementSetup:
-            aligned = alignement.aligned
-
-            for key in aligned.keys():
+        for key in self.aligned.keys():
+            filename = current_file + "/testFiles/alignSequence/seq very small/" + key + ".fasta"
+            with open(filename, "r") as expected_file:
+                expected_file = expected_file.read()
                 expected = AlignSequences.fileToDict(current_file + "/testFiles/alignSequence/seq very small/" + key, ".fasta")
-                assert aligned[key] == expected
-
+                assert self.aligned[key] == expected               
+                
     def test_heuristicMSA(self):
         """
         This test is used to test the heuristicMSA function.
         """
 
         print("Begin test_heuristicMSA...")
 
-        for alignement in self.alignementSetup:
-            starAlignement = alignement.starAlignement()
-            expected = AlignSequences.fileToDict(current_file + "/testFiles/starAlignement/seq very small", ".fasta")
-            assert starAlignement == expected
+        # for alignement in self.alignementSetup:
+        starAlignement = self.aligned.starAlignement()
+        expected = AlignSequences.fileToDict(current_file + "/testFiles/starAlignement/seq very small", ".fasta")
+        assert starAlignement == expected
 
     def test_windowed(self):
         """