—#!perl
use
strict;
use
Data::Dumper;
use
Carp;
#
# This is a SAS Component
#
=head1 roles_to_protein_families
roles_to_protein_families can be used to locate the protein families containing
features that have assigned functions implying that they implement designated roles.
Note that for any input role (given as a role description), you may have a set
of distinct protein_families returned.
Example:
roles_to_protein_families [arguments] < input > output
The standard input should be a tab-separated table (i.e., each line
is a tab-separated set of fields). Normally, the last field in each
line would contain the identifer. If another column contains the identifier
use
-c N
where N is the column (from 1) that contains the subsystem.
This is a pipe command. The input is taken from the standard input, and the
output is to the standard output.
=head2 Documentation for underlying call
This script is a wrapper for the CDMI-API call roles_to_protein_families. It is documented as follows:
$return = $obj->roles_to_protein_families($roles)
=over 4
=item Parameter and return types
=begin html
<pre>
$roles is a roles
$return is a reference to a hash where the key is a role and the value is a protein_families
roles is a reference to a list where each element is a role
role is a string
protein_families is a reference to a list where each element is a protein_family
protein_family is a string
</pre>
=end html
=begin text
$roles is a roles
$return is a reference to a hash where the key is a role and the value is a protein_families
roles is a reference to a list where each element is a role
role is a string
protein_families is a reference to a list where each element is a protein_family
protein_family is a string
=end text
=back
=head2 Command-Line Options
=over 4
=item -c Column
This is used only if the column containing the subsystem is not the last column.
=item -i InputFile [ use InputFile, rather than stdin ]
=back
=head2 Output Format
The standard output is a tab-delimited file. It consists of the input
file with extra columns added.
Input lines that cannot be extended are written to stderr.
=cut
my
$usage
=
"usage: roles_to_protein_families [-c column] < input > output"
;
my
$column
;
my
$input_file
;
my
$kbO
= Bio::KBase::CDMI::CDMIClient->new_for_script(
'c=i'
=> \
$column
,
'i=s'
=> \
$input_file
);
if
(!
$kbO
) {
STDERR
$usage
;
exit
}
my
$ih
;
if
(
$input_file
)
{
open
$ih
,
"<"
,
$input_file
or
die
"Cannot open input file $input_file: $!"
;
}
else
{
$ih
= \
*STDIN
;
}
while
(
my
@tuples
= Bio::KBase::Utilities::ScriptThing::GetBatch(
$ih
,
undef
,
$column
)) {
my
@h
=
map
{
$_
->[0] }
@tuples
;
my
$h
=
$kbO
->roles_to_protein_families(\
@h
);
for
my
$tuple
(
@tuples
) {
#
# Process output here and print.
#
my
(
$id
,
$line
) =
@$tuple
;
my
$v
=
$h
->{
$id
};
if
(!
defined
(
$v
))
{
STDERR
$line
,
"\n"
;
}
elsif
(
ref
(
$v
) eq
'ARRAY'
)
{
foreach
$_
(
@$v
)
{
"$line\t$_\n"
;
}
}
else
{
"$line\t$v\n"
;
}
}
}