awk '{o[length($1)]++}END{for (i in o) print i,o[i]}' in5.txt | sort -n |awk '{s+=$2;print $0,s}' > in5-seqlen.txt
189 1 251 cover 50% of all
251 1 335 cover 66% of all
283 3 377 cover 75% of all

awk '{o[length($1)]++}END{for (i in o) print i,o[i]}' in4.txt | sort -n |awk '{s+=$2;print $0,s}' > in4-seqlen.txt
183 10 2020
249 7 2681
285 9 3010

ln -s /media/reczko/DATA/bak/doc/foukas/
ln -s foukas/cullpdb3class-tra.txt  tra.txt
split -l 4000 tra.txt
mv xaa tra4000.txt	      
mv xab tra500.txt	      
ln -s tra4000.txt in.txt    
python cull2csv.py          
mv encodings.txt  tra4000.csv
(* 13 20)
260

cd ~/doc/foukas/dat/foukas
ln -s ~/doc/foukas/dat/tra4000.txt in.txt
reczko@reczkoG5:~/doc/foukas/dat/foukas$ python ~/doc/foukas/dat/cull2csv.py
mv encodings.txt tra4000.tsv
https://usegalaxy.elixir-greece.org/history/export_archive?id=319886f37b7797fe

#up to here win13
#win15
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv encodings.txt tra4000-win15.tsv 
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv in.txt in.txt4
reczko@reczkoG5:~/doc/foukas/dat/foukas$ ln -s /home/reczko/doc/foukas/dat/tra500.txt in.txt
reczko@reczkoG5:~/doc/foukas/dat/foukas$ python ~/doc/foukas/dat/cull2csv-with-header.py
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv encodings.txt tra500-win15.tsv
ln -s ~/doc/foukas/dat/foukas/cullpdb3class-tra.txt in.txt

reczko@reczkoG5:~/doc/foukas/dat/foukas$ python ~/doc/foukas/dat/cull2nn-csv.py
reczko@reczkoG5:~/doc/foukas/dat/foukas$ cp encodings.txt tra500-win17-nn.txt
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv in.txt in.txt5
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv in.txt4 in.txt
reczko@reczkoG5:~/doc/foukas/dat/foukas$ python ~/doc/foukas/dat/cull2nn-csv.py
reczko@reczkoG5:~/doc/foukas/dat/foukas$ cp encodings.txt tra4000-win17-nn.txt

python ~/doc/foukas/dat/cull2snns.py 
reczko@reczkoG5:~/doc/foukas/dat/foukas$ mv encodings.txt tra4000-win-snns.pat

#win21
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ ln -s ~/snns/ss/princeton-data-jzthree/cullpdb3class-tra.txt 
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ ln -s cullpdb3class-tra.txt tra.txt
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ split -l 4000 tra.txt
mv xaa tra4000.txt	      
mv xab tra500.txt	      
ln -s tra4000.txt in.txt    
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ python cull2snns.py 
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ mv encodings.txt tra4000-win21.pat
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ mv in.txt in4.txt
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ ln -s tra500.txt in.txt
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ python cull2snns.py 
]0;~/snns/foukas/datreczko@max:~/snns/foukas/dat$ mv encodings.txt val500-win21.pat

#win25
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win25.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win25.pat

#win29
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win29.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win29.pat

#win33
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win33.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win33.pat

#win37
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win37.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win37.pat

#win41
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win41.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win41.pat

#win45
mv in4.txt in.txt
python cull2snns.py 
mv encodings.txt tra4000-win45.pat
mv in.txt in4.txt
mv in5.txt in.txt
python cull2snns.py
mv in.txt in5.txt
mv encodings.txt val500-win45.pat