ete3 added

README.md

@@ -15,6 +15,11 @@ pip install -r requeriments.txt 📝
 
 ### ✨ Execute
 
+From the [NCBI official database](https://www.ncbi.nlm.nih.gov/labs/virus/vssi/#/virus?VirusLineage_ss=Severe%20acute%20respiratory%20syndrome%20coronavirus%202%20(SARS-CoV-2),%20taxid:2697049&SeqType_s=Nucleotide) download the sequences.fasta and sequences.csv files and you are ready to try this project!
+
+We provide you a .zip file with 2 other fasta and csv files to try out without downloading anything so, have fun!
+
+
 ```
 cd src/python
   

src/python/sarscovhierarchy.py

@@ -2,7 +2,6 @@ import os
 import signal
 from os.path import join
 from sys import argv
-from zipfile import ZipFile
 
 from utils.csv_table import CsvTable
 from utils.fasta_map import FastaMap
@@ -27,7 +26,6 @@ def main():
     distances_table = fasta_map.compare_all_samples()
     tree = HierarchyTree(distances_table, labels)
     tree.build_tree()
-    tree.show()
     print("Done!")
 
 

src/python/utils/fasta_map.py

@@ -67,7 +67,7 @@ class FastaMap:
             sequences = filter(None, fasta.read().split('>'))
             for seq in sequences:
                 rna_id, rna = self._get_rna(seq)
-                data[rna_id] = rna
+                data[rna_id] = rna if len(rna) < 1000 else rna[:1000]
         return data
 
     def _compare_all_samples(self):

src/python/utils/tree.py

@@ -1,30 +1,29 @@
-from graphviz import Graph
+from ete3 import Tree, TreeStyle
 
 
 class HierarchyTree:
     def __init__(self, table, labels=None):
-        self.__dot = Graph("Hierarchy Sars-Cov-2",
-                           node_attr={'shape': 'plaintext'})
         self.__table = table
         self.__labels = labels
 
     def build_tree(self):
         hierarchy_table = self.__table
+        closest_pair = tuple()
         while len(hierarchy_table) > 1:
             closest_pair = self.find_closest_pair(hierarchy_table)
-            self._add_relation(closest_pair)
             new_relation = self.build_relation(closest_pair, hierarchy_table)
             hierarchy_table = self.refactor_table(
                 closest_pair, new_relation, hierarchy_table)
+        self._show_tree(str(closest_pair))
 
-    def show(self):
-        self.__dot.render("../../output/hierarchy")
-
-    def _add_relation(self, pair):
-        node1, node2 = tuple(map(self.__transform, pair))
-        new_node = f"{node1},{node2}"
-        self.__dot.edge(new_node, node1)
-        self.__dot.edge(new_node, node2)
+    def _show_tree(self, tuple_repr):
+        t = Tree(tuple_repr + ";")
+        ts = TreeStyle()
+        ts.show_leaf_name = True
+        ts.mode = "c"
+        ts.arc_start = -180  # 0 degrees = 3 o'clock
+        ts.arc_span = 180
+        t.render("hierarchy.png", tree_style=ts)
 
     def __transform(self, value):
         value = str(value).translate(