Change default corErrorRate from 50 to 30 (nanopore) and 30 to 25 (pa…

…cbio).
marbl · Aug 3, 2021 · 741911c · 741911c
1 parent 0e603ad
commit 741911c
Show file tree

Hide file tree

Showing 2 changed files with 60 additions and 3 deletions.
diff --git a/documentation/source/parameter-reference.rst b/documentation/source/parameter-reference.rst
@@ -914,7 +914,64 @@ assemble all input data, at the expense of runtime.
 .. _corErrorRate:
 
 corErrorRate <integer=unset>
-  Do not use overlaps with error rate higher than this (estimated error rate for `mhap` and `minimap` overlaps).
+  Do not use overlaps with error rate higher than this when computing corrected reads.
+
+  In Canu v2.2, this parameter was changed from 0.50 (for -nanopore) and 0.30
+  (for -pacbio) to 0.30 and 0.25, respectively.
+
+  The tables below show a significant speedup for Nanopore reads without much
+  loss in output quantity.  There is indication of a slight improvement in
+  corrected read quality at lower corErrorRate, however, read quality was not
+  directly evaluated.
+
+  For PacBio reads, with a smaller change in corErrorRate, the speedup is
+  about 10%.
+
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | CHM13 Chromosome X, nanopore, 105x input coverage                                        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | |               | | Corrected        | | Trimmed        | | Bogart          | | CPU Time |
+  | | corErrorRate  | | Coverage         | | Coverage       | | Error Rate      | | (hours)  |
+  +=================+====================+==================+===================+============+
+  | 5               | 22.0x              | 21.8x            | 0.3958%           |            |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 10              | 35.7x              | 35.2x            |                   |            |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 15              | 38.1x              | 37.5x            |                   |            |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 20              | 38.6x              | 38.0x            |                   | 1160       |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 25              | 38.7x              | 38.1x            |                   | 1290       |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 30              | 38.8x              | 38.1x            |                   | 1449       |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 40              | 38.8x              | 38.1x            |                   | 1625       |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 50              | 38.8x              | 38.2x            |                   | 3683       |
+  +-----------------+--------------------+------------------+-------------------+------------+
+
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | HG002 Chromosome X, nanopore, 20x input coverage                                         |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | |               | | Corrected        | | Trimmed        | | Bogart          | | CPU Time |
+  | | corErrorRate  | | Coverage         | | Coverage       | | Error Rate      | | (hours)  |
+  +=================+====================+==================+===================+============+
+  | 5               | --.-x              | --.-x            | -%                | 31         |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 10              |  3.9x              | --.-x            | -%                | 66         |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 15              |  9.6x              | --.-x            | -%                | 105        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 20              | 11.4x              | 11.2x            | 1.71%             | 134        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 25              | 11.9x              | 11.6x            | 1.79%             | 154        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 30              | 12.0x              | 11.8x            | 1.83%             | 169        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 40              | 12.2x              | 12.0x            | 1.94%             | 221        |
+  +-----------------+--------------------+------------------+-------------------+------------+
+  | 50              | 12.6x              | 12.3x            | 2.29%             | 709        |
+  +-----------------+--------------------+------------------+-------------------+------------+
 
 corConsensus <string="falconpipe">
   Which algorithm to use for computing read consensus sequences.  Only 'falcon' and 'falconpipe' are supported.

diff --git a/src/pipelines/canu.pl b/src/pipelines/canu.pl
@@ -608,7 +608,7 @@
     setGlobalIfUndef("corOvlErrorRate",  0.320);
     setGlobalIfUndef("obtOvlErrorRate",  0.120);
     setGlobalIfUndef("utgOvlErrorRate",  0.120);
-    setGlobalIfUndef("corErrorRate",     0.500);
+    setGlobalIfUndef("corErrorRate",     0.300);
     setGlobalIfUndef("obtErrorRate",     0.120);
     setGlobalIfUndef("oeaErrorRate",     getGlobal("utgOvlErrorRate"));
     setGlobalIfUndef("oeaHaploConfirm",  5);
@@ -622,7 +622,7 @@
     setGlobalIfUndef("corOvlErrorRate",  0.240);
     setGlobalIfUndef("obtOvlErrorRate",  0.045);
     setGlobalIfUndef("utgOvlErrorRate",  0.045);
-    setGlobalIfUndef("corErrorRate",     0.300);
+    setGlobalIfUndef("corErrorRate",     0.250);
     setGlobalIfUndef("obtErrorRate",     0.045);
     setGlobalIfUndef("oeaErrorRate",     getGlobal("utgOvlErrorRate"));
     setGlobalIfUndef("oeaHaploConfirm",  5);