v3.0.0-beta1

New features

• New Command Line Interface with improved separation between the predict and train module.
• Customized XGBoost model that includes impute values and CAPICE versioning.
• Added support for edge cases (breakends, symbolic alleles and alternative contigs).
• Revamped input that no longer depends on CADD 1.4 but instead depends on VEP104.
• Added a manual annotator module that processes the VEP features. Each module is separate and are loaded in dynamically, no codebase chanes have to be made in order to start supporting new features.
• Added bash script to convert a VEP output VCF to a CAPICE ready input TSV.
• Added helper script to balance out an input dataset on allele frequency, consequence and the amount of benign vs pathogenic samples.

Changed

• Separated CAPICE framework from CAPICE model. New models can now be released independently.
• Variants are no longer removed if they contain no feature at all. Instead, CAPICE will now throw an error when a gap is present within the CHROM, POS, REF or ALT column.
• Reduced overall code complexity.
• PEP8 formatting guidelines with maximum line length 100 characters.
• Updated testing.
• Changed logging. It is no longer possible to let CAPICE create a logfile. Instead, CAPICE logs DEBUG and INFO to system STDout and WARNING, ERROR and CRITICAL to STDerr.
• Changed logging output format to YYYY-MM-DD <loglevel>: <msg>

Removed

• Removed deprecated files in CAPICE_example.
• Removed ability to create train-test / validation datasets directly through CAPICE. Use the supplied helper script in order to perform these steps.

Bug fixes

• Fixed a bug when -v / --verbose flag was called, CAPICE would not output DEBUG level logmessages.
• Fixed a bug within trianing that would throw a ValueError when used with XGBoost 1.4.2

v2.0.1

Bug Fixes

• Fix #61 Broken .tsv to .vcf converter is outdated

v2.0.0

Additions:

• Added setup.py for easy installation
• Added the CAPICE training scripts, so users are now able to create new CAPICE like models.
• Added config.cfg for additional setup.

General improvements:

• Changed code structure for be more object orientated

Command line interface:

• Changed input argument --input_path to -i
• Removed input argument --model_path
• Made output argument --prediction_savepath optional with -o
• Added flags for verbose (-v), force (-f) and train (--train)

Output:

• Changed output of CAPICE to no longer remove duplicate entries upon 'chrom-pos-ref-alt'
• Exposed transcript identifier
• Removed unused columns (prediction and combined_prediction)

Bugfixes:

• #16 Apply command-line argument conventions
• #17 Expose transcript identifier for predicted score
• #18 Add tests for Python code
• #20 Add training scripts to Github to enable reproducing the model
• #21 Log warnings for variants that can't be processed
• #24 'there shouldn't be any nulls' and 'feature from the model not in data' log messages
• #28 PIP install pandas==1.0.2 on Python 3.9+ fails to install

v1.3.1

Bug Fixes

• Fix #4 Scipy version not specified
• Fix #25 Extend capice2vcf to convert precomputed scores

v1.3.0

New Features

• Introduce capice2vcf command-line application that transforms a capice prediction score file to a vcf (variant call format) file

v1.2

Merge pull request #5 from molgenis/chore/travis

enable travis

v1.1

Merge pull request #2 from molgenis/bartcharbon-patch-1

Replace absolute path with relative path