Update

ASCN/ASCN_Download.py

@@ -0,0 +1,74 @@
+from Bio import Entrez
+import sys
+
+
+def fetch_sequences(database, accession_numbers):
+    """
+    Fetch sequences from NCBI database using accession numbers.
+    
+    Args:
+        database (str): Database name to fetch sequences from.
+        accession_numbers (list): List of accession numbers.
+        
+    Returns:
+        None
+    """
+    Entrez.email = "fakeemail@exemplo.com"
+    Entrez.tool = "fetch_sequences.py"
+
+    # Join the accession numbers into a comma-separated string
+    accession_list = ",".join(accession_numbers)
+
+    try:
+        # Fetch the sequences
+        fetch_results = Entrez.efetch(db=database, id=accession_list, rettype="fasta", retmode="text")
+        sys.stdout.write(fetch_results.read())
+        fetch_results.close()
+    except Exception as e:
+        print(f"Error fetching sequences: {e}")
+        sys.exit(1)
+
+
+def read_accession_numbers(file_path):
+    """
+    Read accession numbers from a file.
+    
+    Args:
+        file_path (str): Path to the file containing accession numbers.
+        
+    Returns:
+        list: List of accession numbers.
+    """
+    try:
+        with open(file_path) as file:
+            # Filter out empty lines and strip whitespace from each line
+            accession_numbers = [line.strip() for line in file if line.strip()]
+        return accession_numbers
+    except FileNotFoundError:
+        print(f"Error: File '{file_path}' not found.")
+        sys.exit(1)
+
+
+def main():
+    """
+    Main function to execute the script.
+    """
+    if len(sys.argv) != 3:
+        print("Usage: python fetch_sequences.py [database] "
+        "[file_path_to_accession_numbers]")
+        sys.exit(1)
+
+    database = sys.argv[1]
+    file_path = sys.argv[2]
+
+    accession_numbers = read_accession_numbers(file_path)
+
+    if not accession_numbers:
+        print("Error: No accession numbers found in the file.")
+        sys.exit(1)
+
+    fetch_sequences(database, accession_numbers)
+
+
+if __name__ == '__main__':
+    main()

ASCN/COI.txt

@@ -0,0 +1,52 @@
+COI
+OP394113
+
+OP394114
+MW593931
+MK578905
+FJ435802
+FJ435803
+ON005160
+MT023412
+MT023413
+MT023414
+
+MH675999
+MH676000
+MH676001
+MH676002
+MH676003
+MH676004
+MH676005
+MH676006
+MH676008
+
+MH676009
+MH676010
+MH676014
+MH676015
+MH676016
+MH676017
+MK041020
+MH675998
+MK041019
+MH676007
+MH676013
+MK041015
+MN097837
+MH676011
+MT260372
+MT260373
+MF568534
+LC637242
+MK040994
+OK662995
+MK040996
+OK662996
+MH676018
+MN888322
+MN888328
+MN888329
+MN888330
+KX810042
+MN444827

ASCN/ITS–2.txt

@@ -0,0 +1,52 @@
+ITS–2
+
+
+
+MW588022
+MK584657
+
+
+
+MT024000
+MT024001
+MT024001
+OK663216
+MH666081
+MH666082
+
+
+MH666083
+
+MH666084
+
+MH666086
+MH666087
+MH666088
+MH666089
+MH666093
+
+MH666094
+MH666095
+
+MH666080
+
+MH666085
+MH666092
+
+MN073464
+MH666090
+
+
+MF568535
+LC649794
+
+OK663213
+
+OK663214
+MH666096
+MN888331
+MN888348
+MN888349
+MN888350
+KX810046
+MN443038

Paper Stuff/ASCN_Numbers/18S_rRNA.txt

@@ -0,0 +1,45 @@
+18S rRNA
+OP394210
+OP394211
+OP394212
+MW588029
+MK584659
+FJ435746
+FJ435748
+ON005189
+MT023998
+MT023999
+MT023999
+OK663227
+MH664932
+MH664934
+MH664935
+MH664936
+MH664938
+MH664939
+MH664940
+MH664944
+MH664945
+MH664933
+MK041032
+MH664931
+MK041031
+MH664937
+MH664943
+MK041030
+MN073468
+MH664941
+MT261913
+MF568532
+LC637243
+MK041023
+OK663224
+MK041024
+OK663225
+MH664946
+MN888371
+MN888376
+MN888377
+MN888378
+KX810045
+MN443040

Paper Stuff/ASCN_Numbers/28S_rRNA.txt

@@ -0,0 +1,52 @@
+28S rRNA
+
+OP394209
+
+MW588034
+MK584658
+FJ435760
+FJ435761
+ON005195
+MT024041
+MT024042
+MT024043
+OK663238
+MH664949
+MH664952
+
+
+MH664953
+
+MH664954
+
+MH664956
+
+MH664957
+MH664958
+MH664961
+
+MH664962
+MH664951
+
+MH664948
+
+MH664955
+MH664960
+
+MN073465
+MH664950
+MT261904
+
+MF568533
+LC649795
+
+OK663236
+
+OK663236
+MH664963
+MN888357
+MN888361
+MN888362
+MN888363
+KX810049
+MN443035

Snakefile

@@ -0,0 +1,27 @@
+import Bio
+
+# Dataset
+sample_names = [os.path.splitext(os.path.basename(file))[0] for file in glob.glob("dataset/*.fasta")]
+
+# Define rule to generate all desired outputs
+rule all:
+    input:
+        expand("results/mafft/{sample}/tree/{sample}Tree.svg", sample=sample_names),    
+        expand("results/clustal_omega/{sample}/tree/{sample}Tree.svg", sample=sample_names),
+        expand("results/Muscle/{sample}/tree/{sample}Tree.svg", sample=sample_names),
+        expand("iqtree/{sample}/mafft/mafft.log", sample=sample_names),
+        expand("iqtree/{sample}/clustal_omega/clustal_omega.log", sample=sample_names),
+        expand("iqtree/{sample}/Muscle/Muscle.log", sample=sample_names)
+
+#Alignment rules
+rule ASCN_Download:
+    input:
+        ASCN="ASCN/{sample}.txt"
+    output:
+        fasta="results/mafft/{sample}/{sample}fileAligned.fasta"
+    params:
+        library=nuccore
+    shell:
+        """
+        python3 ASCN_Download.py nuccore ASCN > {sample}.fasta
+        """