AI-TensorFlow-Libtensorflow
view release on metacpan - search on metacpan
view release on metacpan or search on metacpan
lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod view on Meta::CPAN
PDL: Float D [5313,896]
=head2 Plot predicted tracks
These predictions can be plotted
my @tracks = (
[ 'DNASE:CD14-positive monocyte female' => 41 => $predictions_p->slice('(41)') ],
[ 'DNASE:keratinocyte female' => 42 => $predictions_p->slice('(42)') ],
[ 'CHIP:H3K27ac:keratinocyte female' => 706 => $predictions_p->slice('(706)')],
[ 'CAGE:Keratinocyte - epidermal' => 4799 => log10(1 + $predictions_p->slice('(4799)')) ],
);
use PDL::Graphics::Gnuplot;
my $plot_output_path = 'enformer-target-interval-tracks.png';
my $gp = gpwin('pngcairo', font => ",10", output => $plot_output_path, size => [10,2. * @tracks], aa => 2 );
$gp->multiplot( layout => [1, scalar @tracks], title => $target_interval );
$gp->options(
offsets => [ graph => "0.01, 0, 0, 0" ],
lmargin => "at screen 0.05",
);
my $x = zeroes($predictions_p->dim(1))->xlinvals($target_interval->start, $target_interval->end);
my @tics_opts = (mirror => 0, out => 1);
for my $i (0..$#tracks) {
my ($title, $id, $y) = @{$tracks[$i]};
$gp->plot( {
title => $title,
border => [2],
ytics => { @tics_opts, locations => [ ceil(($y->max-$y->min)/2)->sclr ] },
( $i == $#tracks
? ( xtics => { format => '%.3f', @tics_opts } )
: ( xtics => 0 ) ),
( $i == $#tracks ? ( xlabel => 'location ({/Symbol \264}10^7 bases)' ) : () ),
},
with => 'filledcurves',
#'lc' => '#086eb5',
# $x scaled by 1e7; filled curve between $y and the x-axis
$x / 1e7, $y, pdl(0)
);
}
$gp->end_multi;
$gp->close;
if( IN_IPERL ) {
IPerl->png( bytestream => path($plot_output_path)->slurp_raw );
}
B<DISPLAY>:
=for html <span style="display:inline-block;margin-left:1em;"><p><img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAA+gAAAMgCAIAAAA/et9qAAAgAElEQVR4nOzdd2AUVeIH8Ddb0jshBAIEpSo1GjoIpyAgCOqd3uGdoGBBUQQFRUVBRbkTf9gOBQucqFiwUhSSgJQYCCSBkJBAet1k...
=head2 Parts of the original notebook that fall outside the scope
In the orignal notebook, there are several more steps that have not been ported here:
=over
=item 1.
"Compute contribution scores":
This task requires implementing C<@tf.function> to compile gradients.
=item 2.
"Predict the effect of a genetic variant" and "Score multiple variants":
The first task is possible, but the second task requires loading a pre-processing pipeline for scikit-learn and unfortunately this pipeline is stored as a pickle file that is valid for an older version of scikit-learn (version 0.23.2) and as such its...
=back
# Some code that could be used for working with variants.
1 if <<'COMMENT';
use Bio::DB::HTS::VCF;
my $clinvar_tbi_path = "${clinvar_path}.tbi";
unless( -f $clinvar_tbi_path ) {
system( qw(tabix), $clinvar_path );
}
my $v = Bio::DB::HTS::VCF->new( filename => $clinvar_path );
$v->num_variants
COMMENT
undef;
=head1 RESOURCE USAGE
use Filesys::DiskUsage qw/du/;
my $total = du( { 'human-readable' => 1, dereference => 1 },
$model_archive_path, $model_base, $new_model_base,
$targets_path,
$hg_gz_path,
$hg_bgz_path, $hg_bgz_fai_path,
$clinvar_path,
$plot_output_path,
);
say "Disk space usage: $total"; undef;
B<STREAM (STDOUT)>:
Disk space usage: 4.66G
view all matches for this distributionview release on metacpan - search on metacpan
( run in 0.937 second using v1.00-cache-2.02-grep-82fe00e-cpan-72ae3ad1e6da )