Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
A
Annotation de séquences bactériennes
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Pacome Riobe
Annotation de séquences bactériennes
Commits
68fda1a1
Commit
68fda1a1
authored
2 months ago
by
Pacome Riobe
Browse files
Options
Downloads
Patches
Plain Diff
Mise à jour et ajout de parsers
parent
a1dd29f8
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
Code
+145
-17
145 additions, 17 deletions
Code
with
145 additions
and
17 deletions
Code
+
145
−
17
View file @
68fda1a1
import argparse
import matplotlib.pyplot as plt
import gffutils
import pandas as pd
from collections import Counter
#STAT
def avg_lenght(db):
avg = Counter()
# Longueur moyenne des Features :
CDS_lengths = [feature.end - feature.start + 1 for feature in db.features_of_type("CDS")]
region_lengths = [feature.end - feature.start + 1 for feature in db.features_of_type("region")]
coding_exon_lengths = [feature.end - feature.start + 1 for feature in db.features_of_type("coding_exon")]
intron_lengths = [feature.end - feature.start + 1 for feature in db.features_of_type("intron")]
avg_CDS_length = sum(CDS_lengths) / len(CDS_lengths) if CDS_lengths else 0
avg_region_length = sum(region_lengths) / len(region_lengths) if region_lengths else 0
avg_coding_exon_length = sum(coding_exon_lengths) / len(coding_exon_lengths) if coding_exon_lengths else 0
avg_intron_length = sum(intron_lengths) / len(intron_lengths) if intron_lengths else 0
avg["CDS"] = avg_CDS_length
avg["region"] = avg_region_length
avg["coding_exon"] = avg_coding_exon_length
avg["intron"] = avg_intron_length
return avg
def count(db):
"""
Stat
Parameters:
- db: base de donné
Returns:
- stats (dict) : exemple --> Counter({'coding_exon': 4, 'intron': 3, 'region': 1, 'CDS': 1, 'average_gene_length': 0})
"""
stats = Counter()
for feature in db.all_features(): #methode gffutils
stats[feature.featuretype] += 1
return stats
def fusions_stat(count, avg):
"""
Combinaisons de plusieurs dictionnaires stat dans 1 tableau
Parameters:
- stats (dict): Un dictionnaire avec le nombre de chaque type de feature.
- avg (dict): Un dictionnaire avec la longueur moyenne de chaque type de feature.
Returns:
- Un unique tableau et sa c'est beau
"""
# Transformer les dict en tableau
count_df = pd.DataFrame(count.items(), columns=["Feature Type", "Count"])
avg_df = pd.DataFrame(avg.items(), columns=["Feature Type", "Average Length"])
# Fusion les tableaux sur la colonne "Feature Type"
combined_df = pd.merge(count_df, avg_df, on="Feature Type", how="left") #faut que klé des deux dict soit les memes
return combined_df
#LIEN
def liens(feature):
"""
LIEN NCBI
Parameters:
- feature (gffutils.Feature): Un objet représentant une feature du fichier GFF.
Returns:
- str: lienS
"""
base_url = "https://www.ncbi.nlm.nih.gov/gene/?term="
# ID de gène
if "ID" in feature.attributes:
gene_id = feature.attributes["ID"][0] # Prend la première valeur si plusieurs
return f'<a href="{base_url}{gene_id}" target="_blank">{gene_id}</a>'
# Si CDS --> utilise son id
if "CDS" in feature.attributes:
cds_id = feature.attributes["CDS"][0]
return f'<a href="{base_url}{cds_id}" target="_blank">{cds_id}</a>'
return "N/A" # Si aucun lien disponible
def graphe(stats):
"""
Génère un histogramme de la distribution des features du GFF.
Parameters:
- stats (dict): Dictionnaire contenant le nombre de chaque type de feature.
- output_image (str): Nom du fichier image pour sauvegarder le graphique.
Returns:
- Sauvegarde un fichier PNG et affiche le graphique.
"""
# Filtrer pour ne garder que les features (et pas les moyennes de longueur)
filtered_stats = {k: v for k, v in stats.items() if not k.startswith("average")}
# Création du graphique
plt.figure(figsize=(10, 5))
plt.bar(filtered_stats.keys(), filtered_stats.values(), color='skyblue')
# Ajout des labels
plt.xlabel("Feature Type")
plt.ylabel("Count")
plt.title("Feature Distribution in GFF File")
plt.xticks(rotation=45) # Rotation des labels pour lisibilité
# Sauvegarde et affichage
return plt.show()
def gff_a_html(gff_file, output_html):
"""
...
...
@@ -12,7 +126,7 @@ def gff_a_html(gff_file, output_html):
Returns:
- rien mais enregistre un fichier HTML avec un tableau de donnée la ou on lui a demandé
"""
# base de données temporaire du fichier
# base de données temporaire du fichier
db = gffutils.create_db(gff_file, dbfn=":memory:", force=True, keep_order=True, merge_strategy="create_unique", sort_attribute_values=True)
# memory : pour pas stocker sur disque (RAM)
#force = true : recrée base si elle existe déja
...
...
@@ -28,31 +142,45 @@ def gff_a_html(gff_file, output_html):
"Start": feature.start,
"End": feature.end,
"Strand": feature.strand,
"
Locus ID
": feature.attributes.get(
"locus_tag", ["N/A"])[0]
,
"
Parent
": feature.attributes.get(
"Parent", ["None"])[0]
,
"
Gene Product": feature.attributes.get("product", ["Unknown"])[0],
"
Sequence
": feature.attributes.get(
'Sequence')
,
"
CDS
": feature.attributes.get(
'CDS')
,
"
External Link": liens(feature)
}
data.append(entry)
# TABLEAU :
df = pd.DataFrame(data, columns=["ID", "Start", "End", Strand]) #le reste fonctionne pas
# DATA
df = pd.DataFrame(data, columns=["ID", "Start", "End", "Strand", "Sequence", "CDS", "External Link"])
df_html = df.to_html(index=False, escape=False) #html
# fichier HTML
df.to_html(output_html, index=False)
# STAT
cnt = count(db)
avg = avg_lenght(db)
stats_df = fusions_stat(cnt, avg)
stats_html = stats_df.to_html(index=False) #html
print(f"HTML table generated: {output_html}")
# GRAPH
graph = graphe(cnt)
graph_html = graph.to_html(index=False)
# TOUS les tableaux dans 1 fichier HTML
with open(output_html, "w", encoding="utf-8") as f:
f.write("<h1> DATA </h1>\n")
f.write(df_html) # 1er tableau
f.write("<h1> Statistics </h1>\n")
f.write(stats_html) # 2e tableau
f.write("<h1> Graph </h1>\n")
f.write(graph_html)
if __name__ == "__main__":
#chemin des fichiers de Clara :
#gff_file = "/Users/claramoreno/PycharmProjects/PythonProjectPaster/wormbase_gff2_alt.txt"
#output_html = "/Users/claramoreno/PycharmProjects/PythonProjectPaster/output.html"
print(f"HTML file saved as {output_html}")
#chemin des fichiers :
#gff_file =
#output_html =
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("-g", "--gff_file", type=str, help="Enter a gff file")
parser.add_argument("-o", "--outfile", type=str, help="Enter a path for the outfile")
args = parser.parse_args()
print(gff_a_html(args.gff_file,args.outfile))
print(gff_a_html(gff_file,output_html))
\ No newline at end of file
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment