# convert to clstm format reczko@max:~/bak/doc/sci/biology/protein/structure-prediction/ss/princeton-data-jzthree$ awk -f cullpdb2letters1.awk cullpdb+profile_6133_filtered.txt > cullpdb-all.txt wc cullpdb-all.txt 5534 11068 2377704 cullpdb-all.txt reczko@max:~/bak/doc/sci/biology/protein/structure-prediction/ss/princeton-data-jzthree$ head -4500 cullpdb-all.txt > cullpdb-tra.txt