Ekl-mgenomics 0.1__tar.gz

ekl_mgenomics-0.1/Ekl_mgenomics/chunker.py

@@ -0,0 +1,28 @@
+from Bio import SeqIO
+from pathlib import Path
+def run_chunk(fasta_path,blast_precursor):
+    c=0
+    size=0
+    for record in SeqIO.parse(fasta_path,"fasta"):
+        c+=1
+        size=size+int(len(record.seq))
+        print(f"No. of bp in {record.id}= {len(record.seq)}")
+        r=Path(blast_precursor)/f"C{c}"
+        r.mkdir(parents=True,exist_ok=True)                         # folder per Seq
+        v=0
+        for i in range(0,len(record.seq),200000):
+            v+=1
+            with open(r/f"C{c}CH{v}.fasta","w") as f:
+                f.write(f">chunk_{i}_{record.id}_Coordinate_{i+200000 if i+200000<len(record.seq) else i+len(record.seq[i:])}\n")
+                f.write(str(record.seq[i:i+200000]))
+            
+            
+    print(f"Contigs= {c}")
+    if c==1:
+        print("It is a Circular DNA")
+
+    print(f"Genome Size= {size}")
+    return fasta_path,blast_precursor
+    
+    
+ 

ekl_mgenomics-0.1/Ekl_mgenomics/cli.py

@@ -0,0 +1,47 @@
+import sys
+import os
+import subprocess
+from Ekl_mgenomics.chunker import run_chunk
+from Ekl_mgenomics.report import read, printt
+
+def main():
+    fasta_path = sys.argv[1]                         # user types: magtools mygenome.fasta
+
+    base = os.path.splitext(fasta_path)[0]           # "mygenome.fasta" → "mygenome"
+    blast_precursor = base + "_chunks/"              # chunk subfolders → "mygenome_chunks/"
+    blast_results = base + "_blast_results/"         # all tsvs → "mygenome_blast_results/"
+    output = base + "_OrganismTaxonomy.tsv"          # final output
+
+    # Step 1 — chunk
+    print("Step 1: Chunking fasta...")
+    run_chunk(fasta_path, blast_precursor)
+
+    # Step 2 — BLAST
+    print("\nStep 2: Running BLAST (this will take a while)...")
+    os.makedirs(blast_results, exist_ok=True)        # create blast_results folder
+
+    for contig_folder in sorted(os.listdir(blast_precursor)):          # loop C1, C2, C3...
+        contig_path = os.path.join(blast_precursor, contig_folder)
+        if os.path.isdir(contig_path):                                 # make sure it's a folder
+            for fasta_file in sorted(os.listdir(contig_path)):        # loop C1CH1.fasta...
+                if fasta_file.endswith(".fasta"):
+                    fasta_in = os.path.join(contig_path, fasta_file)
+                    tsv_out = os.path.join(blast_results, fasta_file.replace(".fasta", ".tsv"))
+                    
+                    print(f"  BLASTing {fasta_file}...")
+                    subprocess.run([
+                        "blastn",
+                        "-query", fasta_in,
+                        "-db", "nt",
+                        "-remote",
+                        "-max_target_seqs", "3",
+                        "-max_hsps", "5",
+                        "-outfmt", "7 qacc sacc evalue staxids sscinames",
+                        "-out", tsv_out
+                    ])
+
+    # Step 3 — report
+    print("\nStep 3: Generating report...")
+    read(blast_results)
+    printt(output,fasta_path)
+    print(f"\nDone! Results saved to {output}")

ekl_mgenomics-0.1/Ekl_mgenomics/report.py

@@ -0,0 +1,79 @@
+import os
+from Bio import Entrez
+Entrez.email="eklavyakumar1602@gmail.com"
+dict={}
+def read(blast_results):
+    d={}
+    for i in sorted(os.listdir(blast_results)):
+       if i.endswith(".tsv"):
+        with open(blast_results+i)as f:
+            ch=i[:-4]
+            for j in f:
+                if j.startswith("#")==False:
+                    if j.strip()=="":
+                        continue
+                    id=j.split("\t")[-2]
+                    
+                    if ch not in d:
+                        d[ch]={}
+                    if id not in d[ch]:
+                        d[ch][id]=1
+                    else:
+                        d[ch][id]+=1
+            n=ch.split("CH")[0]
+            if ch in d:
+                m=max(d[ch],key=d[ch].get)
+                if n not in dict:
+                    dict[n]={}
+                if m not in dict[n]:
+                    dict[n][m]=[]
+                dict[n][m].append(ch)
+            
+           
+    print(d)
+    print(dict)
+    return dict
+
+def ScientificName(n):
+    m=Entrez.efetch(db="taxonomy",id=n,retmode="xml")
+    h=Entrez.read(m)
+    k=h[0]["ScientificName"]
+    return k
+
+def printt(output,fasta_path):
+    l=len(dict)
+    d={}
+    for i in dict:
+        for j in dict[i]:
+            e=len(dict[i][j])
+            if j not in d:
+                d[j]=0
+            d[j]+=e
+    m=max(d,key=d.get)
+    m=ScientificName(m)
+    with open(output,"w")as f:
+        f.write("MAG\tNo_Of_Contigs\tOrganismName\n")
+        f.write(f"{fasta_path}\t{l}\t{m}\n")
+        f.write("Contigs\tTotalChunks\tSpeciesAssigned\tNo_Of_Chunks\tName_of_Chunk\n")
+        for i in dict:
+            s=a=c=p=""
+            k=0
+            for j in dict[i]:
+                k=k+len(dict[i][j])
+                if a=="":
+                    a=ScientificName(j)
+                else:
+                    a=a+"/"+ScientificName(j)
+                if p=="":
+                    p=str(len(dict[i][j]))
+                else:
+                    p=p+"/"+str(len(dict[i][j]))
+                if c=="":
+                    c="-".join(dict[i][j])
+                else:
+                    c=c+"/"+"-".join(dict[i][j])
+            f.write(f"{i}\t{k}\t{a}\t{p}\t{c}\n")
+
+                    
+
+              

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.4
+Name: Ekl_mgenomics
+Version: 0.1
+Requires-Dist: biopython
+Dynamic: requires-dist

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+pyproject.toml
+setup.py
+Ekl_mgenomics/__init__.py
+Ekl_mgenomics/chunker.py
+Ekl_mgenomics/cli.py
+Ekl_mgenomics/report.py
+Ekl_mgenomics.egg-info/PKG-INFO
+Ekl_mgenomics.egg-info/SOURCES.txt
+Ekl_mgenomics.egg-info/dependency_links.txt
+Ekl_mgenomics.egg-info/entry_points.txt
+Ekl_mgenomics.egg-info/requires.txt
+Ekl_mgenomics.egg-info/top_level.txt

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+ekl_tax = Ekl_mgenomics.cli:main

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/requires.txt

@@ -0,0 +1 @@
+biopython

ekl_mgenomics-0.1/Ekl_mgenomics.egg-info/top_level.txt

@@ -0,0 +1 @@
+Ekl_mgenomics

ekl_mgenomics-0.1/PKG-INFO

@@ -0,0 +1,5 @@
+Metadata-Version: 2.4
+Name: Ekl_mgenomics
+Version: 0.1
+Requires-Dist: biopython
+Dynamic: requires-dist

ekl_mgenomics-0.1/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

ekl_mgenomics-0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

ekl_mgenomics-0.1/setup.py

@@ -0,0 +1,15 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="Ekl_mgenomics",
+    version="0.1",
+    packages=find_packages(),
+    install_requires=[
+        "biopython",
+    ],
+    entry_points={
+        "console_scripts": [
+            "ekl_tax=Ekl_mgenomics.cli:main",
+        ]
+    }
+)