RefgenDetector 3.0.4__tar.gz → 3.0.6__tar.gz

{refgendetector-3.0.4/src/RefgenDetector.egg-info → refgendetector-3.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: RefgenDetector
-Version: 3.0.4
+Version: 3.0.6
 Author: Mireia Marin i Ginestar
 Author-email: <mireia.marin@crg.eu>
 Keywords: python

{refgendetector-3.0.4 → refgendetector-3.0.6}/setup.py

@@ -5,7 +5,7 @@ from pathlib import Path
 
 this_directory = Path(__file__).parent
 long_description = (this_directory / "README.md").read_text()
-VERSION = '3.0.4'
+VERSION = '3.0.6'
 DESCRIPTION = 'RefgenDetector'
 
 

{refgendetector-3.0.4 → refgendetector-3.0.6/src/RefgenDetector.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: RefgenDetector
-Version: 3.0.4
+Version: 3.0.6
 Author: Mireia Marin i Ginestar
 Author-email: <mireia.marin@crg.eu>
 Keywords: python

{refgendetector-3.0.4 → refgendetector-3.0.6}/src/RefgenDetector.egg-info/SOURCES.txt

@@ -17,4 +17,5 @@ src/refgenDetector/refgenDetector_main.py
 src/refgenDetector/variant_files.py
 src/refgenDetector/exceptions/NoFileException.py
 src/refgenDetector/exceptions/__init__.py
+src/refgenDetector/github_msgpacks/__init__.py
 src/refgenDetector/msgpacks/__init__.py

{refgendetector-3.0.4 → refgendetector-3.0.6}/src/refgenDetector/aligment_files.py

@@ -124,13 +124,18 @@ def comparison(dict_SN_LN, target_file):
                 for ref in flavors_GRCh37
             ]
             
-            match_flavors = max(matches_flavors, key=lambda x: x[0])
-            if match_flavors: #if some flavor was defined it prints it
-                console.print(f"[bold]Species detected:[/bold] {match_flavors[2]} "
-                f"[bold]\nReference genome version  :[/bold] {match_flavors[1]}")
-            else: #if there wasnt any flavor inferred, the major release it printed
-                console.print(f"[bold]Species detected:[/bold] Homo sapiens \n["
-                              f"bold]Reference genome version  :[/bold] GRCh37")
+            match_flavors = max(matches_flavors, key=lambda x: len(x[0]))
+
+            if len(match_flavors[0]) > 0:
+                console.print(
+                    f"[bold]Species detected:[/bold] {match_flavors[2]} "
+                    f"[bold]\nReference genome version  :[/bold] {match_flavors[1]}"
+                )
+            else:
+                console.print(
+                    "[bold]Species detected:[/bold] Homo sapiens "
+                    "\n[bold]Reference genome version  :[/bold] GRCh37"
+                )
 
         elif max_match[1] == "GRCh38": #checks for GRCh38 flavors
 
@@ -145,9 +150,11 @@ def comparison(dict_SN_LN, target_file):
             else: # if no GRCh38 flavor is inferred, the major release is printed
                 console.print(f"[bold]Species detected:[/bold] Homo sapiens \n["
                               f"bold]Reference genome version  :[/bold] GRCh38")        
-        else: # print the major releases with no considered flavors.
-            console.print(f"[bold]Species detected:[/bold] {match[2]} "
-                  f"\n[bold]Reference genome version:[/bold] {match[1]}")
+        else:  # print the major releases with no considered flavors
+            console.print(
+                f"[bold]Species detected:[/bold] {max_match[2]} "
+                f"\n[bold]Reference genome version:[/bold] {max_match[1]}"
+            )
 
 
 

{refgendetector-3.0.4 → refgendetector-3.0.6}/src/refgenDetector/download_reference.py

@@ -57,6 +57,7 @@ def get_paths():
 
 def is_already_setup(dst: Path) -> bool:
     """Return True if at least one .msgpack file exists in dst."""
+    print(dst)
     if not dst.exists():
         return False
     return any(dst.glob("*.msgpack"))

{refgendetector-3.0.4 → refgendetector-3.0.6}/src/refgenDetector/refgenDetector_main.py

@@ -8,7 +8,7 @@ __maintainer__ = "Mireia Marin Ginestar"
 __email__ = "mireia.marin@crg.eu"
 __status__ = "Developement"
 
-version = "3.0.4"
+version = "3.0.6"
 
 import os
 import sys

{refgendetector-3.0.4 → refgendetector-3.0.6}/src/refgenDetector/variant_files.py

@@ -24,6 +24,7 @@ MSGPACK_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "msgpacks
 final_results = []
 console = Console(highlight=False)
 _msgpack_cache = {}
+_current_chr = None
 
 def gather_and_sum(lists):
     """
@@ -54,13 +55,18 @@ def get_matches(snps_dict, chr_):
         A list with the number of matches for each version, which is used to infer the reference genome version.
     """
     
-    global _msgpack_cache
+    global _msgpack_cache, _current_chr
     start = time.time()
 
     genome_versions = ["hg18", "GRCh37", "GRCh38", "T2T"]
     matches = []
 
-    # Extract arrays once
+    # If we've moved on to a different chromosome, drop the previous
+    # chromosome's msgpacks before loading the new ones.
+    if chr_ != _current_chr:
+        _msgpack_cache.clear()
+        _current_chr = chr_
+
     positions = np.array(list(snps_dict.keys()), dtype=np.int64)
     nucleotides = np.array(list(snps_dict.values()))
 
@@ -76,16 +82,15 @@ def get_matches(snps_dict, chr_):
 
         ref_dict = _msgpack_cache[cache_key]
 
-        # Vectorized: look up all positions at once, compare arrays
         ref_nucs = np.array([ref_dict.get(p, None) for p in positions])
         match_count = int(np.sum(ref_nucs == nucleotides))
 
         matches.append([version_name, match_count])
 
-    #console.print("Getting matches. Took:", time.time() - start, "s")
     return matches
 
 
+
 def trimming_indels(content, ref):
     """
     If a row is longer than one position it is deleted, deleting this way any indels