perf: optimize min-match-percentage default (#107)

Author: balajtimate

README.md

@@ -148,7 +148,7 @@ optional arguments:
   --read-layout-min-match-percentage FLOAT
                         minimum percentage of reads that contain a given
                         adapter sequence in order for it to be considered
-                        as the library's 3'-end adapter (default: 2)
+                        as the library's 3'-end adapter (default: 0.1)
   --read-layout-min-frequency-ratio FLOAT
                         minimum frequency ratio between the first and second
                         most frequent adapter in order for the former to be

data/adapter_fragments.txt

@@ -1,20 +1,17 @@
-AATGATACGGCGACC
-ACACTCTTTCCCTAC
-ATCTCGTATGCCGTC
-CAAGCAGAAGACGGC
-CCGAGCCCACGAGAC
-CCGGTTCTTCCCTGC
-CGACAGGTTCAGAGT
-CGGTCTCGGCATTCC
-CTGTAGGCACCATCA
-GATCGGAAGAGCGGT
-GATCGGAAGAGCTCG
-GATCGTCGGACTGTA
-GCCTTGGCACCCGAG
-GTCTCGTGGGCTCGG
-GTGACTGGAGTTCAG
-TCGGACTGTAGAACT
-TCGTCGGCAGCGTCA
-TGGAATTCTCGGGTG
-AGATCGGAAGAGCGT
-AGATCGGAAGAGCAC
+AATGATACGGCG
+ACACTCTTTCCC
+ATCTCGTATGCC
+CAAGCAGAAGAC
+CCGAGCCCACGA
+CCGGTTCTTCCC
+CGACAGGTTCAG
+CGGTCTCGGCAT
+CTGTAGGCACCA
+GATCGTCGGACT
+GCCTTGGCACCC
+GTCTCGTGGGCT
+GTGACTGGAGTT
+TCGGACTGTAGA
+TCGTCGGCAGCG
+TGGAATTCTCGG
+AGATCGGAAGAG

htsinfer/cli.py

@@ -170,7 +170,7 @@ def __call__(
         dest="read_layout_min_match_pct",
         metavar="FLOAT",
         type=float,
-        default=2,
+        default=0.1,
         help=(
             "minimum percentage of reads that contain a given adapter "
             "sequence in order for it to be considered as the library's "

htsinfer/get_read_layout.py

@@ -182,7 +182,7 @@ def __init__(
         path: Path,
         adapter_file: Path,
         out_dir: Path = Path.cwd(),
-        min_match_pct: float = 2,
+        min_match_pct: float = 0.1,
         min_freq_ratio: float = 2,
     ):
         """Class constructor."""

htsinfer/models.py

@@ -413,7 +413,7 @@ class Args(BaseModel):
     threads: int = 1
     transcripts_file: Path = Path()
     read_layout_adapter_file: Path = Path()
-    read_layout_min_match_pct: float = 2
+    read_layout_min_match_pct: float = 0.1
     read_layout_min_freq_ratio: float = 2
     lib_source_min_match_pct: float = 2
     lib_source_min_freq_ratio: float = 2