Fixed bug preventing Nucleus to work with TensorFlow 2.0. Added util.vis routines for visualizing DeepVariant pileup examples. FASTA reader now supports keep_true_case option for keeping the original casing. VCF writer now supports writing headerless VCF files. SAM reader now supports optional fields of type 'B'. variant_utils now supports gVCF files. Numerous minor bug fixes.
0.4.1
* The pip package is slightly more robust.
0.4.0
The Nucleus pip package now works with Python 3.
0.3.0
Reading of VCF, SAM, and most other genomics files is now twice as fast. Read range and end calculations are now done in C++ for speed. VcfReader can now read "headerless" VCF files. variant_utils.major_allele_frequency now 5x faster. Memory leaks fixed in TFRecordReader/Writer and gfile_cc.
0.2.3
Nucleus no longer depends on any specific version of TensorFlow's python code. This should make it easier to use Nucleus with for example TensorFlow 2.0. Added BCF support to VcfWriter. Fixed memory leaks in VcfWriter::Write. Added print_tfrecord example program.
0.2.2
* Faster SAM file querying and read overlap calculations. * Writing protocol buffers to files uses less memory. * Smaller pip package. * nucleus/util:io\_utils refactored into nucleus/io:tfrecord and nucleus/io:sharded\_file\_utils. * Alleles coming from VCF files are now always normalized as uppercase.