Mercurial > repos > althonos > gecco

comparison CHANGELOG.md @ 3:359232b58f6a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"Update Galaxy tool wrapper to follow the IUC best practices"
author althonos
date Sun, 21 Nov 2021 19:47:22 +0000
parents
children 169849dfb098
comparison
equal deleted inserted replaced
2:e618ab1c78d9 3:359232b58f6a
1 # Changelog
2 All notable changes to this project will be documented in this file.
3
4 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
5 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
6
7 ## [Unreleased]
8 [Unreleased]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.5...master
9
10 ## [v0.8.5] - 2021-11-21
11 [v0.8.5]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.4...v0.8.5
12 ### Added
13 - Minimal compatibility support for running GECCO inside of Galaxy workflows.
14
15 ## [v0.8.4] - 2021-09-26
16 [v0.8.4]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.3-post1...v0.8.4
17 ### Fixed
18 - `gecco convert gbk --format bigslice` failing to run because of outdated code ([#5](https://github.com/zellerlab/GECCO/issues/5)).
19 - `gecco convert gbk --format bigslice` not creating files with names conforming to BiG-SLiCE expected input.
20 ### Changed
21 - Bump minimum `pyrodigal` version to `v0.6.2` to use platform-accelerated code if supported.
22
23 ## [v0.8.3-post1] - 2021-08-23
24 [v0.8.3-post1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.3...v0.8.3-post1
25 ### Fixed
26 - Wrong default value for `--threshold` being shown in `gecco run` help message.
27
28 ## [v0.8.3] - 2021-08-23
29 [v0.8.3]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.2...v0.8.3
30 ### Changed
31 - Default probability threshold for segmentation to 0.3 (from 0.4).
32
33 ## [v0.9.0] - 2021-08-10 - **YANKED**
34 [v0.9.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.2...v0.9.0
35 ### Changed
36 - Retrain internal model using `--select=0.35` instead of `--select=0.25` like before.
37 - Change default *p-value* filter from 1e-9 to 1e-5 to detect more features.
38
39 ## [v0.8.2] - 2021-07-31
40 [v0.8.2]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.1...v0.8.2
41 ### Fixed
42 - `gecco run` crashing on Python 3.6 because of missing `contextlib.nullcontext` class.
43 ### Changed
44 - `gecco run` and `gecco annotate` will not try to count the number of profiles when given an external HMM file with the `--hmm` flag.
45 - `PyHMMER.run` now reports the *p-value* of each domain in addition to the *e-value* as a `/note` qualifier.
46
47 ## [v0.8.1] - 2021-07-29
48 [v0.8.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.8.0...v0.8.1
49 ### Changed
50 - `gecco run` now filters out unneeded features before annotating, making it easier to analyze the results of a run with a custom `--model`.
51 ### Fixed
52 - `gecco` reporting about using Pfam `v33.1` while actually using `v34.0` because of an outdated field in `gecco/hmmer/Pfam.ini`.
53 ### Added
54 - Missing documentation for the `strand` attribute of `gecco.model.Gene`.
55
56 ## [v0.8.0] - 2021-07-03
57 [v0.8.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.7.0...v0.8.0
58 ### Changed
59 - Retrain internal model using new sequence embeddings and remove broken/duplicate BGCs from MIBiG 2.0.
60 - Bump minimum `pyhmmer` version to `v0.4.0` to improve exception handling.
61 - Bump minimum `pyrodigal` version to `v0.5.0` to fix sequence decoding on some platforms.
62 - Use p-values instead of e-values to filter domains obtained with HMMER.
63 - `gecco cv` and `gecco train` now seed the RNG with a user-defined seed before shuffling rows of training data.
64 ### Fixed
65 - Extraction of BGC compositions for the type predictor while training.
66 - `ClusterCRF.trained` failing to open an external model.
67 ### Added
68 - `Domain.pvalue` attribute to access the p-value of a domain annotation.
69 - Mandatory `pvalue` column to `FeatureTable` objects.
70 - Support for loading several feature tables in `gecco train` and `gecco cv`.
71 - Warnings to `ClusterCRF.fit` when selecting uninformative features.
72 - `--correction` flag to `gecco train` and `gecco cv`, allowing to give a multiple testing correction method when computing p-values with the Fisher Exact Tests.
73 ### Removed
74 - Outdated `gecco embed` command.
75 - Unused `--truncate` flag from the `gecco train` CLI.
76 - Tigrfam domains, which is not improving performance on the new training data.
77
78 ## [v0.7.0] - 2021-05-31
79 [v0.7.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.6.3...v0.7.0
80 ### Added
81 - Support for writing an AntiSMASH sideload JSON file after a `gecco run` workflow.
82 - Code for converting GenBank files in BiG-SLiCE compatible format with the `gecco convert` subcommand.
83 - Documentation about using GECCO in combination with AntiSMASH or BiG-SLiCE.
84 ### Changed
85 - Minimum Biopython version to `v1.73` for compatibility with older bioinformatics tooling.
86 - Internal domain composition shipped in the `gecco.types` with newer composition array obtained directly from MIBiG files.
87 ### Removed
88 - Outdated notice about `-vvv` verbosity level in the help message of the main `gecco` command.
89
90 ## [v0.6.3] - 2021-05-10
91 [v0.6.3]: https://git.embl.de/grp-zeller/GECCO/compare/v0.6.2...v0.6.3
92 ### Fixed
93 - HMMER annotation not properly handling inputs with multiple contigs.
94 - Some progress bar totals displaying as floats in the CLI.
95 ### Changed
96 - `PyHMMER` now sets the `Z` and `domZ` values from the number of proteins given to the search pipeline.
97 - `gecco.cli` delegates imports to make CLI more responsive.
98 - `pkg_resources` has been replaced with `importlib.resources` and `importlib.metadata` where applicable.
99 - `multiprocessing.cpu_count` has been replaced with `os.cpu_count` where applicable.
100
101 ## [v0.6.2] - 2021-05-04
102 [v0.6.2]: https://git.embl.de/grp-zeller/GECCO/compare/v0.6.1...v0.6.2
103 ### Fixed
104 - `gecco cv loto` crashing because of outdated code.
105 ### Changed
106 - Logging-style prompt will only display if GECCO is running with `-vv` flag.
107 ### Added
108 - GECCO bioRxiv paper reference to `Cluster.to_seq_record` output record.
109
110 ## [v0.6.1] - 2021-03-15
111 [v0.6.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.6.0...v0.6.1
112 ### Fixed
113 - Progress bar not being disabled by `-q` flag in CLI.
114 - Fallback to using HMM name if accession is not available in `PyHMMER`.
115 - Group genes by source contig and process them separately in `PyHMMER` to avoid bogus E-values.
116 ### Added
117 - `psutil` dependency to get the number of physical CPU cores on the host machine.
118 - Support for using an arbitrary mapping of positives to negatives in `gecco embed`.
119 ### Removed
120 - Unused and outdated `HMMER` and `DomainRow` classes from `gecco.hmmer`.
121
122 ## [v0.6.0] - 2021-02-28
123 [v0.6.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.5...v0.6.0
124 ### Changed
125 - Updated internal model with a cleaned-up version of the MIBiG-2.0
126 Pfam-33.1/Tigrfam-15.0 embedding.
127 - Updated internal InterPro catalog.
128 ### Fixed
129 - Features not being grouped together in `gecco cv` and `gecco train`
130 when provided with a feature table where rows were not sorted by
131 protein IDs.
132
133 ## [v0.5.5] - 2021-02-28
134 [v0.5.5]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.4...v0.5.5
135 ### Fixed
136 - `gecco cv` bug causing only the last fold to be written.
137
138 ## [v0.5.4] - 2021-02-28
139 [v0.5.4]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.3...v0.5.4
140 ### Changed
141 - Replaced `verboselogs`, `coloredlogs` and `better-exceptions` with `rich`.
142 ### Removed
143 - `tqdm` training dependency.
144 ### Added
145 - `gecco annotate` command to produce a feature table from a genomic file.
146 - `gecco embed` to embed BGCs into non-BGC regions using feature tables.
147
148 ## [v0.5.3] - 2021-02-21
149 [v0.5.3]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.2...v0.5.3
150 ### Fixed
151 - Coordinates of genes in output GenBank files.
152 - Potential issue with the number of CPUs in `PyHMMER.run`.
153 ### Changed
154 - Bump required `pyrodigal` version to `v0.4.2` to fix buffer overflow.
155
156 ## [v0.5.2] - 2021-01-29
157 [v0.5.2]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.1...v0.5.2
158 ### Added
159 - Support for downloading HMM files directly from GitHub releases assets.
160 - Validation of filtered HMMs with MD5 checksum.
161 ### Fixed
162 - Invalid coordinates of protein domains in GenBank output files.
163 - `gecco.interpro` module not being added to wheel distribution.
164 ### Changed
165 - Bump required `pyhmmer` version to `v0.2.1`.
166
167 ## [v0.5.1] - 2021-01-15
168 [v0.5.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.5.0...v0.5.1
169 ### Fixed
170 - `--hmm` flag being ignored in in `gecco run` command.
171 - `PyHMMER` using HMM names instead of accessions, causing issues with Pfam HMMs.
172
173 ## [v0.5.0] - 2021-01-11
174 [v0.5.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.5...v0.5.0
175 ### Added
176 - Explicit support for Python 3.9.
177 ### Changed
178 - [`pyhmmer`](https://pypi.org/project/pyhmmer) is used to annotate protein sequences instead of HMMER3 binary `hmmsearch`.
179 - HMM files are stored in binary format to speedup parsing and reduce storage size.
180 - `tqdm` is now a *training*-only dependency.
181 - `gecco cv` now requires *training* dependencies.
182
183 ## [v0.4.5] - 2020-11-23
184 [v0.4.5]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.4...v0.4.5
185 ### Added
186 - Additional `fold` column to cross-validation table output.
187 ### Changed
188 - Use sequence ID instead of protein ID to extract type from cluster in `gecco cv`.
189 - Install HMM data in pre-pressed format to make `hmmsearch` runs faster on short sequences.
190 - `gecco.orf` was rewritten to extract genes from input sequences in parallel.
191
192 ## [v0.4.4] - 2020-09-30
193 [v0.4.4]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.3...v0.4.4
194 ### Added
195 - `gecco cv loto` command to run LOTO cross-validation using BGC types
196 for stratification.
197 - `header` keyword argument to `FeatureTable.dump` and `ClusterTable.dump`
198 to write the table without the column header allowing to append to an
199 existing table.
200 - `__getitem__` implementation for `FeatureTable` and `ClusterTable`
201 that returns a single row or a sub-table from a table.
202 ### Fixed
203 - `gecco cv` command now writes results iteratively instead of holding
204 the tables for every fold in memory.
205 ### Changed
206 - Bumped `pandas` training dependency to `v1.0`.
207
208 ## [v0.4.3] - 2020-09-07
209 [v0.4.3]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.2...v0.4.3
210 ### Fixed
211 - GenBank files being written with invalid `/cds` feature type.
212 ### Changed
213 - Blocked installation of Biopython `v1.78` or newer as it removes `Bio.Alphabet`
214 and breaks the current code.
215
216 ## [v0.4.2] - 2020-08-07
217 [v0.4.2]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.1...v0.4.2
218 ### Fixed
219 - `TypeClassifier.predict_types` using inverse type probabilities when
220 given several clusters to process.
221
222 ## [v0.4.1] - 2020-08-07
223 [v0.4.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.4.0...v0.4.1
224 ### Fixed
225 - `gecco run` command crashing on input sequences not containing any genes.
226
227 ## [v0.4.0] - 2020-08-06
228 [v0.4.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.3.0...v0.4.0
229 ### Added
230 - `gecco.model.ProductType` enum to model the biosynthetic class of a BGC.
231 ### Removed
232 - `pandas` interaction from internal data model.
233 - `ClusterCRF` code specific to cross-validation.
234 ### Changed
235 - `pandas`, `fisher` and `statsmodels` dependencies are now optional.
236 - `gecco train` command expects a cluster table in addition to the feature
237 table to know the types of the input BGCs.
238
239 ## [v0.3.0] - 2020-08-03
240 [v0.3.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.2.2...v0.3.0
241 ### Changed
242 - Replaced Nearest-Neighbours classifier with Random Forest to perform type
243 prediction for candidate BGCs.
244 - `gecco.knn` module was renamed to implementation-agnostic name `gecco.types`.
245 ### Fixed
246 - Extraction of domain composition taking a long time in `gecco train` command.
247 ### Removed
248 - `--metric` argument to the `gecco run` CLI command.
249
250 ## [v0.2.2] - 2020-07-31
251 [v0.2.2]: https://git.embl.de/grp-zeller/GECCO/compare/v0.2.1...v0.2.2
252 ### Changed
253 - `Domain` and `Gene` can now carry qualifiers that are used when they
254 are translated to a sequence feature.
255 ### Added
256 - InterPro names, accessions, and HMMER e-value for each annotated domain
257 in GenBank output files.
258
259 ## [v0.2.1] - 2020-07-23
260 [v0.2.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.2.0...v0.2.1
261 ### Fixed
262 - Various potential crashes in `ClusterRefiner` code.
263 ### Removed
264 - Uneeded feature dictionary filtering in `ClusterCRF` for models with
265 Fisher Exact Test feature selection.
266
267 ## [v0.2.0] - 2020-07-23
268 [v0.2.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.1.1...v0.2.0
269 ### Fixed
270 - `pandas` warning about unsorted columns in `gecco run`.
271 ### Removed
272 - `Gene.probability` property, replaced by `Gene.maximum_probability` and
273 `Gene.average_probability` properties to be explicit.
274 ### Changed
275 - Internal model now uses `Pfam` and `Tigrfam` with the top 35% features
276 selected with Fisher's Exact Test.
277 - `ClusterRefiner` now removes genes on `Cluster` edges if they do not
278 contain any domain annotation.
279
280 ## [v0.1.1] - 2020-07-22
281 [v0.1.1]: https://git.embl.de/grp-zeller/GECCO/compare/v0.1.0...v0.1.1
282 ### Added
283 - `ClusterCRF.predict_probabilities` to annotate a list of `Gene`.
284 ### Changed
285 - BGC probability is now stored at the `Domain` level instead of at the `Gene`
286 level, independently of the feature extraction level used by the CRF.
287 - `ClusterKNN` will use the model path provided to `gecco run` if any.
288 ### Docs
289 - Added this changelog file to document changes in the code.
290 - Added documentation to `gecco` submodules missing some.
291 - Included the `CHANGELOG.md` file to the generated docs.
292
293 ## [v0.1.0] - 2020-07-17
294 [v0.1.0]: https://git.embl.de/grp-zeller/GECCO/compare/v0.0.1...v0.1.0
295 Initial release.
296
297 ## [v0.0.1] - 2018-08-13
298 [v0.0.1]: https://git.embl.de/grp-zeller/GECCO/compare/37afb97...v0.0.1
299 Proof-of-concept.