Bump version to 4.1.0

Author: jakobnissen

CHANGELOG.md

@@ -1,6 +1,13 @@
 # Changelog
 
-## v4.0.2-DEV
+## v4.1.0
+* Fix typo in output AAE_Z cluster names. They are now called e.g. "aae_z_1"
+  instead of "aae_z1"
+* Clean up the directory structure of Avamb workflow.
+* Fix the CheckM2 dependencies to allow CheckM2 to be installed
+* Allow the Avamb workflow to be run on Slurm clusters
+* Fix issue #161: Mismatched refhash when spaces in FASTA headers
+* Allow setting the RNG seed from command line
 
 ## v4.0.1
 * Fix Random.choice for Tensor on Python 3.11. See issue #148

pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
 # Currently pycoverm does not have binaries for Python > 3.11.
 # The dependency resolver, will not error on Python 3.11, but attempt
 # to build pycoverm from source, but will not get the deps required for that.
-requires-python = "<3.12.*,>=3.9.0"
+requires-python = "<3.12,>=3.9.0"
 scripts = {vamb = "vamb.__main__:main"}
 
 [metadata]
@@ -28,3 +28,6 @@ readme = {file = "README.md"}
 [build-system]
 requires = ["setuptools ~= 63.0", "Cython ~= 0.29"]
 build-backend = "setuptools.build_meta"
+
+[tool.ruff]
+ignore = ["E501"]

test/ci.py

@@ -26,7 +26,7 @@ def changelog_version(path):
     with open(path) as file:
         next(file)  # header
         textline = next(filter(None, map(str.strip, file)))
-    regex = re.compile(r"## v([0-9]+)\.([0-9]+)\.([0-9]+)(?:-([0-9A-Za-z]+)?)")
+    regex = re.compile(r"## v([0-9]+)\.([0-9]+)\.([0-9]+)(?:-([0-9A-Za-z]+)?)?")
     m = regex.search(textline)
     if m is None:
         raise ValueError("Could not find version in first non-header line of CHANGELOG")

vamb/__init__.py

@@ -19,7 +19,7 @@
 7) Split bins using vamb.vambtools
 """
 
-__version__ = (4, 0, 2, "DEV")
+__version__ = (4, 1, 0)
 
 from . import vambtools
 from . import parsebam

vamb/vambtools.py

@@ -560,7 +560,7 @@ def concatenate_fasta(
 
     Output: None
     """
-    
+
     identifiers: set[str] = set()
     for inpathno, inpath in enumerate(inpaths):
         try:
@@ -572,7 +572,7 @@ def concatenate_fasta(
                 for entry in byte_iterfasta(infile):
                     if len(entry) < minlength:
                         continue
-                    
+
                     if rename:
                         entry.rename(f"S{inpathno + 1}C{entry.identifier}".encode())
 

workflow_avamb/src/manual_drep_JN.py

@@ -294,7 +294,11 @@ def compute_to_remove(
     parser.add_argument(
         "--bins_extension", type=str, default=".fna", help="Extension of the bins  "
     )
-    parser.add_argument("--min_bin_size", type=int, help="Min bin length to be considered for dereplication ")
+    parser.add_argument(
+        "--min_bin_size",
+        type=int,
+        help="Min bin length to be considered for dereplication ",
+    )
 
     opt = parser.parse_args()
     args = vars(parser.parse_args())
@@ -311,5 +315,5 @@ def compute_to_remove(
         min_comp=opt.comp,
         max_cont=opt.cont,
         bins_extension=opt.bins_extension,
-        min_bin_size=opt.min_bin_size
+        min_bin_size=opt.min_bin_size,
     )

workflow_avamb/src/transfer_contigs_and_aggregate_all_nc_bins.py

@@ -338,35 +338,27 @@ def write_nc_bin_scores(
 
     opt = parser.parse_args()
 
-    path_run = (
-        opt.r
-    ) 
+    path_run = opt.r
 
-    path_clusters = (
-        opt.c
-    ) 
+    path_clusters = opt.c
     with open(path_clusters) as file:
         cluster_contigs = vamb.vambtools.read_clusters(file)
 
     with open(opt.cs_d) as f:
         cluster_scores = json.load(f)
 
-    path_clusters_not_r = (
-        opt.cnr
-    ) 
+    path_clusters_not_r = opt.cnr
 
     with open(path_clusters_not_r) as file:
         cluster_not_r_contigs = vamb.vambtools.read_clusters(file)
 
-    path_bins_ripped_checkm_quality_report = (
-        opt.sbr
-    ) 
+    path_bins_ripped_checkm_quality_report = opt.sbr
 
     ripped_bins_scores_ar = np.loadtxt(
         path_bins_ripped_checkm_quality_report, dtype=str, skiprows=1, ndmin=2
     )
 
-    drep_folder = opt.d  
+    drep_folder = opt.d
 
     with open(opt.bp_d) as f:
         bin_path = json.load(f)