jasterv/sarscov-hierarchy
1
0
Fork 0
mirror of https://codeberg.org/JasterV/sarscov-hierarchy.git synced 2026-04-26 18:10:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/master'

Browse source
This commit is contained in:
manudiv16 2020-05-24 00:40:02 +02:00
commit e7ce5d46c5
7 changed files with 4 additions and 101 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -15,7 +15,7 @@ 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!
You must install the sequences.fasta and sequences.csv files rom 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) to execute this project.
We provide you a .zip file with 2 other fasta and csv files to try out without downloading anything so, have fun!

91
output/hierarchy
View file

@ -1,91 +0,0 @@
graph "Hierarchy Sars-Cov-2" {
node [shape=plaintext]
"Kazakhstan,South Africa" -- Kazakhstan
"Kazakhstan,South Africa" -- "South Africa"
"Kazakhstan,South Africa,Colombia" -- "Kazakhstan,South Africa"
"Kazakhstan,South Africa,Colombia" -- Colombia
"Jamaica,South Korea" -- Jamaica
"Jamaica,South Korea" -- "South Korea"
"Hong Kong,Viet Nam" -- "Hong Kong"
"Hong Kong,Viet Nam" -- "Viet Nam"
"France,Brazil" -- France
"France,Brazil" -- Brazil
"France,Brazil,Taiwan" -- "France,Brazil"
"France,Brazil,Taiwan" -- Taiwan
"Kazakhstan,South Africa,Colombia,Bangladesh" -- "Kazakhstan,South Africa,Colombia"
"Kazakhstan,South Africa,Colombia,Bangladesh" -- Bangladesh
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay" -- "Kazakhstan,South Africa,Colombia,Bangladesh"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay" -- Uruguay
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan" -- "Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan" -- "France,Brazil,Taiwan"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam" -- "Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam" -- Guam
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka" -- "Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka" -- "Sri Lanka"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland" -- "Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka"
"Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland" -- Poland
"Hong Kong,Viet Nam,Sweden" -- "Hong Kong,Viet Nam"
"Hong Kong,Viet Nam,Sweden" -- Sweden
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea" -- "Hong Kong,Viet Nam,Sweden"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea" -- "Jamaica,South Korea"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland" -- "Hong Kong,Viet Nam,Sweden,Jamaica,South Korea"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland" -- "Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland"
"India,Australia" -- India
"India,Australia" -- Australia
"Israel,Peru" -- Israel
"Israel,Peru" -- Peru
"Japan,Greece" -- Japan
"Japan,Greece" -- Greece
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands" -- "Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands" -- Netherlands
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China" -- "Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China" -- China
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown" -- "Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China"
"Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown" -- Unknown
"Japan,Greece,India,Australia" -- "Japan,Greece"
"Japan,Greece,India,Australia" -- "India,Australia"
"Japan,Greece,India,Australia,Spain" -- "Japan,Greece,India,Australia"
"Japan,Greece,India,Australia,Spain" -- Spain
"Puerto Rico,Czech Republic" -- "Puerto Rico"
"Puerto Rico,Czech Republic" -- "Czech Republic"
"USA,Turkey" -- USA
"USA,Turkey" -- Turkey
"Israel,Peru,Germany" -- "Israel,Peru"
"Israel,Peru,Germany" -- Germany
"Israel,Peru,Germany,USA,Turkey" -- "Israel,Peru,Germany"
"Israel,Peru,Germany,USA,Turkey" -- "USA,Turkey"
"Israel,Peru,Germany,USA,Turkey,Nepal" -- "Israel,Peru,Germany,USA,Turkey"
"Israel,Peru,Germany,USA,Turkey,Nepal" -- Nepal
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown" -- "Israel,Peru,Germany,USA,Turkey,Nepal"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown" -- "Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain" -- "Japan,Greece,India,Australia,Spain"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland" -- Finland
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan" -- Pakistan
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic" -- "Puerto Rico,Czech Republic"
"Iran,Philippines" -- Iran
"Iran,Philippines" -- Philippines
"Thailand,Italy" -- Thailand
"Thailand,Italy" -- Italy
"Thailand,Italy,Iran,Philippines" -- "Thailand,Italy"
"Thailand,Italy,Iran,Philippines" -- "Iran,Philippines"
"Tunisia,Nigeria" -- Tunisia
"Tunisia,Nigeria" -- Nigeria
"Tunisia,Nigeria,Thailand,Italy,Iran,Philippines" -- "Tunisia,Nigeria"
"Tunisia,Nigeria,Thailand,Italy,Iran,Philippines" -- "Thailand,Italy,Iran,Philippines"
"Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq" -- "Tunisia,Nigeria,Thailand,Italy,Iran,Philippines"
"Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq" -- Iraq
"Uzbekistan,Belgium" -- Uzbekistan
"Uzbekistan,Belgium" -- Belgium
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic,Malaysia" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic"
"Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic,Malaysia" -- Malaysia
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq" -- "Uzbekistan,Belgium"
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq" -- "Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq"
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq,Serbia" -- "Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq"
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq,Serbia" -- Serbia
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq,Serbia,Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic,Malaysia" -- "Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq,Serbia"
"Uzbekistan,Belgium,Tunisia,Nigeria,Thailand,Italy,Iran,Philippines,Iraq,Serbia,Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic,Malaysia" -- "Israel,Peru,Germany,USA,Turkey,Nepal,Hong Kong,Viet Nam,Sweden,Jamaica,South Korea,Kazakhstan,South Africa,Colombia,Bangladesh,Uruguay,France,Brazil,Taiwan,Guam,Sri Lanka,Poland,Netherlands,China,Unknown,Japan,Greece,India,Australia,Spain,Finland,Pakistan,Puerto Rico,Czech Republic,Malaysia"
}

BIN
output/hierarchy.pdf
View file

Binary file not shown.

BIN
output/hierarchy_med.pdf
View file

Binary file not shown.

BIN
output/hierarchy_min.pdf
View file

Binary file not shown.

2
src/python/sarscovhierarchy.py
View file

@ -21,7 +21,7 @@ def main():
ids = csv_table.values('Accession')
fasta_map = FastaMap(fasta_path).filter(lambda item: item[0] in ids)
print("Files processing finished!")
labels = csv_table.dict_of('Accession', 'Geo_Location')
print("\nBuilding hierarchy...")
distances_table = fasta_map.compare_all_samples()

10
src/python/utils/tree.py
View file

@ -1,7 +1,6 @@
from ete3 import Tree, TreeStyle
from os import environ
environ['QT_QPA_PLATFORM']='offscreen'
class HierarchyTree:
def __init__(self, table, labels=None):
@ -16,17 +15,12 @@ class HierarchyTree:
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))
self._show_tree(f"({closest_pair})")
def _show_tree(self, tuple_repr):
for key in self.__labels:
tuple_repr = tuple_repr.replace(key, self.__labels[key])
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
print(t)
@staticmethod
@ -36,7 +30,7 @@ class HierarchyTree:
closest_id, distance = min(value.items(), key=lambda x: x[-1])
closest_pairs.append((key, closest_id, distance))
sample1, sample2, _ = min(closest_pairs, key=lambda x: x[-1])
return sample1, sample2
return sample2, sample1
@staticmethod
def build_relation(pair, table):