v2.0.4

Maintenance release that removes tensorflow-probability as dependency and eases installation of learnMSA via pip.

v2.0.3

Fixed some compatibility and installation issues.

v2.0.1

Added language model support (--use_language_model) for significantly improved accuracy.

With this option, learnMSA aligns about 6% points more columns correct on average on HomFam benchmark than state-of-the-art tools including learnMSA without LM support.

v1.3.4

Added sequence cropping to accomodate very long outlies.
Previously, learnMSA would be very slow, if the input includes sequences many times longer than the average. This release provides a fix by implementing the command line option --crop x to crop inputs longer than x (defaulting to 3 times the average). Cropping can be disabled (the original behavior) with --crop disable.
Cropping does only affect model training, not the decoded MSA which will always respect the full input.

v1.3.2

Fixed missing package data for the --use_language_model option.

v1.3.1

• improved numerical stability across TF versions
• minor bugfixing

v1.3.0

• Use pyfamsa to align insertions, also made aligning insertions the default behavior (also added --unaligned_insertions flag).
• Use biopython for data parsing. Many more input file formats are now available as well as the experimental indexed_data flag for large datasets that allows constant memory model training.
• Multi GPU training works now.
• Added the highly experimental --use_language_model flag that uses a large, pretrained protein language model to guide the MSA and improve alignment accuracy.
• added sequence weighting

v1.2.4

Another hotfix for a rare bug when aligning insertions

v1.2.3

Hotfix for a regression bug

v1.2.1

Added a limit on insertions lengths to be aligned (500) for performance reasons. Longer insertions are skipped and will be left unaligned.