From b2a7a75a903ac46ee52687077e301b5dfcbc8305 Mon Sep 17 00:00:00 2001
From: Hasindu Gamaarachchi <hasindu2008@gmail.com>
Date: Fri, 11 Aug 2023 13:58:29 +1000
Subject: [PATCH] more oneliners

---
 docs/oneliners.md | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/docs/oneliners.md b/docs/oneliners.md
index a06da6f..2c83990 100644
--- a/docs/oneliners.md
+++ b/docs/oneliners.md
@@ -3,20 +3,22 @@
 
 ## Extracting information for eye-balling and inspecting
 
-**Note that these commands are not efficient to be run routinely on giagntic datasets, instead are only for quickly eyeballing and inspecting relatively smaller datasets.**
+**Note that these commands are not efficient to be run routinely on gigantic datasets, instead are only for quickly eyeballing and inspecting relatively smaller datasets.**
 
 ```
 # print slow5 header:
-slow5tools view file.blow5 | grep '^[#@]' # from slow5tools v0.7.0: slow5tools skim --hdr file.blow5
+slow5tools view file.blow5 | grep '^[#@]'
+slow5tools skim --hdr file.blow5 # available from slow5tools v0.7.0
 
 # print read records without the header:
 slow5tools view file.blow5 | grep -v '^[#@]'
 
 # print the first 10 read records (without the header):
-slow5tools view file.blow5 | grep -v '^[#@]' | head -10 # from slow5tools v0.7.0: slow5tools skim --rid file.blow5 | head -10
+slow5tools view file.blow5 | grep -v '^[#@]' | head -10
 
 # print the list of read IDs:
-slow5tools view file.blow5 | grep -v '^[#@]' | awk '{print $1}' # from slow5tools v0.7.0: slow5tools skim --rid file.blow5
+slow5tools view file.blow5 | grep -v '^[#@]' | awk '{print $1}'
+slow5tools skim --rid file.blow5 # available from slow5tools v0.7.0
 
 # print all data columns (including the data type and column name), except the raw signal (column 8):
 slow5tools view file.blow5 | sed -n '/#char*/,$p' | cut -f 1-7,9-
@@ -30,6 +32,14 @@ slow5tools view file.blow5 | grep -v '^[#@]' | datamash mean 7 median 7 sstdev 7
 # extract the signal samples 100-200 (1-indexed) for the read-id r1:
 slow5tools get --to slow5 file.blow5 "r1" | grep -v '^[#@]' | awk '{print $8}' | cut -d, -f 100-200
 
+# print the axiliary data field 'median_before' (note: slow5tools skim is available from v0.7.0)
+slow5tools skim file.blow5 | awk -v c="median_before" 'NR==1{for (i=1; i<=NF; i++) if ($i==c){p=i; break};} {print $p}'
+
+# get the mean and standard deviation of the axiliary data field 'median_before'
+slow5tools skim file.blow5 | awk -v c="median_before" 'NR==1{for (i=1; i<=NF; i++) if ($i==c){p=i; break};} {print $p}' | tail -n+2 |  datamash mean 1 sstdev 1
+
+# count how many reads come from each 'channel_number'
+slow5tools skim file.blow5 | awk -v c="channel_number" 'NR==1{for (i=1; i<=NF; i++) if ($i==c){p=i; break};} {print $p}' | tail -n+2 |  sort | uniq -c
 ```
 
 ## Operatings on multiple files in parallel