Rescue reads rejected by start time. Recovers ~10%

nanoporetech · Dec 9, 2022 · da36bc9 · da36bc9
1 parent bf3dc89
commit da36bc9
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v0.2.19]
+### Fixed
+- Bug where approximate start times led to incorrectly rejecting candidate duplex pairs.
+
 ## [v0.2.18]
 ### Fixed
 - Bug where aligned BAMs would be used as inputs to filter_pairs. This meant running `filter_pairs` on a guppy directory would report an incorrect duplex rate

diff --git a/duplex_tools/__init__.py b/duplex_tools/__init__.py
@@ -10,7 +10,7 @@
     "split_on_adapter", "assess_split_on_adapter",
     "pairs_from_summary", "filter_pairs", "pair"]
 
-__version__ = '0.2.18'
+__version__ = '0.2.19'
 
 
 def main():

diff --git a/duplex_tools/pairs_from_summary.py b/duplex_tools/pairs_from_summary.py
@@ -165,7 +165,7 @@ def seqsummary_to_tempcompsummary(
     logger = duplex_tools.get_named_logger("FindPairs")
     # Default filtering
     seqsummary["candidate_followon"] = (
-        (-0.01 <= seqsummary["duration_until_next_start"])
+        (-1.00 <= seqsummary["duration_until_next_start"])
         & (seqsummary["duration_until_next_start"] < max_time_between_reads))
     logger.info(f'{seqsummary["candidate_followon"].sum()} pairs after '
                 f'filtering on duration between reads. (max '