view release on metacpan or  search on metacpan

lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod  view on Meta::CPAN

# PODNAME: AI::TensorFlow::Libtensorflow::Manual::Notebook::InferenceUsingTFHubEnformerGeneExprPredModel


## DO NOT EDIT. Generated from notebook/InferenceUsingTFHubEnformerGeneExprPredModel.ipynb using ./maint/process-notebook.pl.

use strict;
use warnings;
use utf8;
use constant IN_IPERL => !! $ENV{PERL_IPERL_RUNNING};
no if IN_IPERL, warnings => 'redefine'; # fewer messages when re-running cells

use feature qw(say);
use Syntax::Construct qw( // );

use lib::projectroot qw(lib);

BEGIN {
    if( IN_IPERL ) {
        $ENV{TF_CPP_MIN_LOG_LEVEL} = 3;
    }
    require AI::TensorFlow::Libtensorflow;
}

use URI ();
use HTTP::Tiny ();
use Path::Tiny qw(path);

use File::Which ();

use List::Util ();

use Data::Printer ( output => 'stderr', return_value => 'void', filters => ['PDL'] );
use Data::Printer::Filter::PDL ();
use Text::Table::Tiny qw(generate_table);

my $s = AI::TensorFlow::Libtensorflow::Status->New;
sub AssertOK {
    die "Status $_[0]: " . $_[0]->Message
        unless $_[0]->GetCode == AI::TensorFlow::Libtensorflow::Status::OK;
    return;
}
AssertOK($s);

use PDL;
use AI::TensorFlow::Libtensorflow::DataType qw(FLOAT);

use FFI::Platypus::Memory qw(memcpy);
use FFI::Platypus::Buffer qw(scalar_to_pointer);

sub FloatPDLTOTFTensor {
    my ($p) = @_;
    return AI::TensorFlow::Libtensorflow::Tensor->New(
        FLOAT, [ reverse $p->dims ], $p->get_dataref, sub { undef $p }
    );
}

sub FloatTFTensorToPDL {
    my ($t) = @_;

    my $pdl = zeros(float,reverse( map $t->Dim($_), 0..$t->NumDims-1 ) );

    memcpy scalar_to_pointer( ${$pdl->get_dataref} ),
        scalar_to_pointer( ${$t->Data} ),
        $t->ByteSize;

lib/AI/TensorFlow/Libtensorflow/Manual/Notebook/InferenceUsingTFHubEnformerGeneExprPredModel.pod  view on Meta::CPAN

  
  $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

=head1 CPANFILE

  requires 'AI::TensorFlow::Libtensorflow';
  requires 'AI::TensorFlow::Libtensorflow::DataType';
  requires 'Archive::Extract';
  requires 'Bio::DB::HTS::Faidx';
  requires 'Bio::Location::Simple';
  requires 'Bio::Tools::Run::Samtools';
  requires 'Data::Frame';
  requires 'Data::Printer';
  requires 'Data::Printer::Filter::PDL';
  requires 'Devel::Timer';
  requires 'Digest::file';
  requires 'FFI::Platypus::Buffer';
  requires 'FFI::Platypus::Memory';
  requires 'File::Which';
  requires 'Filesys::DiskUsage';
  requires 'HTTP::Tiny';