0.6.0

Changed

• Updated internal model with a cleaned-up version of the MIBiG-2.0
  Pfam-33.1/Tigrfam-15.0 embedding.
• Updated internal InterPro catalog.

Fixed

• Features not being grouped together in gecco cv and gecco train
  when provided with a feature table where rows were not sorted by
  protein IDs.

0.5.5

Fixed

• gecco cv bug causing only the last fold to be written.

0.5.4

Changed

• Replaced verboselogs, coloredlogs and better-exceptions with rich.

Removed

• tqdm training dependency.

Added

• gecco annotate command to produce a feature table from a genomic file.
• gecco embed to embed BGCs into non-BGC regions using feature tables.

0.5.3

Fixed

• Coordinates of genes in output GenBank files.
• Potential issue with the number of CPUs in PyHMMER.run.

Changed

• Bump required pyrodigal version to v0.4.2 to fix buffer overflow.

0.5.2

Added

• Support for downloading HMM files directly from GitHub releases assets.
• Validation of filtered HMMs with MD5 checksum.

Fixed

• Invalid coordinates of protein domains in GenBank output files.
• gecco.interpro module not being added to wheel distribution.

Changed

• Bump required pyhmmer version to v0.2.1.

0.5.1

Fixed

• --hmm flag being ignored in in gecco run command.
• PyHMMER using HMM names instead of accessions, causing issues with Pfam HMMs.

0.5.0

Added

• Explicit support for Python 3.9.

Changed

• pyhmmer is used to annotate protein sequences instead of HMMER3 binary hmmsearch.
• HMM files are stored in binary format to speedup parsing and reduce storage size.
• tqdm is now a training-only dependency.
• gecco cv now requires training dependencies.

0.4.5

Added

• Additional fold column to cross-validation table output.

Changed

• Use sequence ID instead of protein ID to extract type from cluster in gecco cv.
• Install HMM data in pre-pressed format to make hmmsearch runs faster on short sequences.
• gecco.orf was rewritten to extract genes from input sequences in parallel.

0.4.4

Added

• gecco cv loto command to run LOTO cross-validation using BGC types
  for stratification.
• header keyword argument to FeatureTable.dump and ClusterTable.dump
  to write the table without the column header allowing to append to an
  existing table.
• __getitem__ implementation for FeatureTable and ClusterTable
  that returns a single row or a sub-table from a table.

Fixed

• gecco cv command now writes results iteratively instead of holding
  the tables for every fold in memory.

Changed

• Bumped pandas training dependency to v1.0.

0.4.3

Fixed

• GenBank files being written with invalid /cds feature type.

Changed

• Blocked installation of Biopython v1.78 or newer as it removes Bio.Alphabet
  and breaks the current code.