=head1 NAME
norsnet - identifies unstructured loops from sequence
=head1 SYNOPSIS
norsnet <FASTA_FILE> <RDBPROF_FILE> <HSSP_FILE> <OUTPUT_FILE> <PROTEIN_NAME> <PROFBVAL_FILE> <OUTPUT_MODE> <DEBUG>
=head1 DESCRIPTION
NORSnet is a neural network based method that focuses on the identification of unstructured loops.
NORSnet was trained to distinguish between very long contiguous segments with non-regular secondary structure (NORS regions) and well-folded proteins. NORSnet was trained on predicted information rather than on experimental data. Therefore, it was optimized on a large data, which is not biased by today's experimental means of capturing disorder. Thus, NORSnet reached into regions in sequence space that are not covered by the specialized disorder predictors. One disadvantage of this approach is that it is not optimal for the identification of the "average" disordered region.
=head2 Conversion of PSI-BLAST alignment to HSSP format
The most up-to-date procedure can be found at L<https://www.rostlab.org/owiki/index.php/How_to_generate_an_HSSP_file_from_alignment#Generating_an_HSSP_profile>.
=over
=item 1. Convert BLAST output to a Single Alignment Format (SAF):
__datadir__/librg-utils-perl/blast2saf.pl fasta=<query_fasta_file> maxAli=3000 eSaf=1 \
saf=<saf_formatted_file> <blast_output>
=item 2. Convert SAF format to HSSP:
__datadir__/librg-utils-perl/copf.pl <saf_formatted_file> formatIn=saf formatOut=hssp \
fileOut=<hssp_formatted_file> exeConvertSeq=convert_seq
=item 3. Filter results to 80% redundancy:
__datadir__/librg-utils-perl/hssp_filter.pl red=80 <hssp_formatted_file> fileOut=<filtered_hssp_formatted_file>
=back
=head2 Output format
=head3 Output mode 1
Tabular output, columns:
pos amino acid number (1..)
res residue 1-letter code
node1 output of neural network node 1
node2 output of neural network node 2
pred node1 / ( node1 + node2 )
n40 pred < 0.40 ? '-' : 'N'
n40fil at least 31 AA long stretches of 'N' in n40
n59 pred < 0.59 ? '-' : 'N'
n59fil at least 31 AA long stretches of 'N' in n59
'N' is for non-regular secondary structure.
=head1 REFERENCES
=over
=item Schlessinger, A., Liu, J., and Rost, B. (2007). Natively unstructured loops differ from other loops. PLoS Comput Biol, 3(7), e140.
=back
=head1 OPTIONS
=over
=item FASTA_FILE
File containing protein amino-acid sequence in fasta format.
=item RDBPROF_FILE
Secondary structure and solvent accessibility prediction by PROF in rdb format.
=item HSSP_FILE
PSI-BLAST alignment profile file converted to HSSP format.
=item OUTPUT_FILE
The name of the final NORSnet output file.
=item PROFBVAL_FILE
Flexible/rigid residues prediction by profbval(1) in rdb format (mode 5).
=item OUTPUT_MODE
NORSnet can create output files in different formats for different purposes. Valid modes are `1', `2' or `3'. Default mode: I<1>.
=over
=item -
Default mode. Use this when you do not want to give a value here but you want to specify B<debug>.
=item I<1>
for metadisorder(1)
=back
=item DEBUG
Set to 1 for debugging messages
=back
=head1 OUTPUT
=over
=item number -
residue number
=item residue -
residue type
=item raw -
raw value of the different between the two output nodes
=back
=head1 EXAMPLES
norsnet __docdir__/examples/cad23.f __docdir__/examples/cad23-fil.rdbProf __docdir__/examples/cad23-fil.hssp cad23.norsnet cad23 __docdir__/examples/cad23.profbval
=head1 ENVIRONMENT
=over
=item NORSNET_ROOT
Overrides __pkgdatadir__, the path to helper scripts and data files.
=back
=head1 FILES
=over
=item F<*.norsnet>
default output file extension
=item F<__docdir__/examples>
default precomputed input files directory
=back
=head1 NOTES
=over
=item 1. It is recommended to create the profiles using 3 iteration of PSI-BLAST against big database
=item 2. It is also recommended to filter the hssp files using hssp_filter.pl from the Prof package using the following command: perl hssp_filter.pl hssp_file red=80
=back
=head1 AUTHOR
A. Schlessinger <avnersch@gmail.com>
=head1 SEE ALSO
=over
=item profbval(1), prof(1).
=item Main website
L<http://www.predictprotein.org/>
=back
=cut
# vim:et: