docs(update doco for R220):

update md5sum, changelog, and announcement.

docs/src/announcements.rst

@@ -1,6 +1,17 @@
 Announcements
 =============
 
+GTDB-Tk 2.4.0 available
+-----------------------
+
+*TBA*
+
+* GTDB-Tk version ``2.4.0`` is now available.
+* This version of GTDB-Tk requires a new version of the GTDB-Tk reference package (Release 220).
+  `gtdbtk_r220_data.tar.gz <https://data.gtdb.ecogenomic.org/releases/release220/220.0/auxillary_files/gtdbtk_package/>`_.
+
+
+
 GTDB-Tk 2.3.0 available
 -----------------------
 

docs/src/changelog.rst

@@ -8,11 +8,18 @@ Change log
 
 Bug Fixes:
 
+* (`#576 <https://github.com/Ecogenomics/GTDBTk/issues/576>`_) When all genomes fail the prodigal step in the classify_wf, The
+bac120 summary file is still produced with the all failed genomes listed as 'Unclassified'
+* (`#573 <https://github.com/Ecogenomics/GTDBTk/issues/573>`_) When running the 3 classify steps independently, a genome can be filtered out in the align
+step but still be classified in the identify step. To avoid duplication of row, the genome is classified with a warning.
+* (`#540 <https://github.com/Ecogenomics/GTDBTk/issues/540>`_) Empty files are skipped during the sketch step of Mash,
+they are then catch in the prodigal step and are returned as 'Unclassified'
+* (`#549 <https://github.com/Ecogenomics/GTDBTk/issues/549>`_) : `--force` has been modified to deal with #540. Prodigal
+wasn't returning the empty files as failed genomes, it was only skipping them. These genomes are now returned in the summary file and flagged as Unclassified.
 
 Major Changes:
 
 * FastANI has been replaced by skani as the primary tool for computing Average Nucleotide Identity (ANI).Users may notice slight variations in the results compared to those obtained using FastANI.
-
 * In the generated `summary.tsv` files, several columns have been renamed for clarity and consistency. The following columns have been affected:
 
     - "`fastani_reference`" column has been renamed to "`closest_genome_reference`".
@@ -23,9 +30,6 @@ Major Changes:
 
  These changes have been implemented to improve the readability and understanding of the data within the `summary.tsv` files. Users should update their scripts or processes accordingly to reflect these renamed column headers.
 
-Minor Changes:
-
-
 
 
 2.3.2

docs/src/installing/index.rst

@@ -33,13 +33,13 @@ Hardware requirements
      - Storage
      - Time
    * - Archaea
-     - ~45 GB
-     - ~85 GB
-     - ~1 hour / 1,000 genomes @ 64 CPUs
+     - ~60 GB
+     - ~106 GB
+     - ~90 minutes / 1,000 genomes @ 64 CPUs
    * - Bacteria
-     - ~65GB (410 GB when using --full_tree)
-     - ~85 GB
-     - ~1 hour / 1,000 genomes @ 64 CPUs
+     - ~90GB (545 GB when using --full_tree)
+     - ~106 GB
+     - ~90 minutes / 1,000 genomes @ 64 CPUs
 
 .. note::
    The amount reported of memory reported can vary depending on the number of pplacer threads.

gtdbtk/config/common.py

@@ -11,8 +11,8 @@ class __GTDBTkCommonConfig:
     that requires the setting of the GTDB-Tk reference data path.
     """
 
-    MIN_REF_DATA_VERSION = 'r207'
-    COMPATIBLE_REF_DATA_VERSIONS = ['r207','r214']
+    MIN_REF_DATA_VERSION = 'r220'
+    COMPATIBLE_REF_DATA_VERSIONS = ['r220']
 
     BACKBONE_PPLACER_REF_PKG = 'gtdbtk_package_backbone.refpkg'
     CLASS_LEVEL_PPLACER_REF_PKG = 'gtdbtk.package.{iter}.refpkg'
@@ -333,31 +333,20 @@ def get_REF_HASHES(self,version=None):
         if version is not None and version not in compatible_versions:
             raise ValueError(f"Version {version} is not compatible with this version of GTDB-Tk. Compatible versions are {compatible_versions}")
 
-        if version is None or version==214:
+        if version is None or version==220:
             return {
-                self.PPLACER_DIR: '6786e9fc16b31db7d6eaaa9f8cfa87a8a4974434',
-                self.MASK_DIR: '8d5a2139feabbb70789c62155f3761d2aeed1601',
+                self.PPLACER_DIR: '75fdd0e093c9af6a73cb510c3d0cd2041265e093',
+                self.MASK_DIR: 'f4b8ebfa59526a7a86f09752b47e8de1efc384c7',
                 self.MARKER_DIR: '163f542c3f0a40f59df45d453aa235b39aa96e27',
-                self.RADII_DIR: '4753acc920001a1400788ee89cb4632900449055',
-                self.MSA_FOLDER: '75df495678a121497e14346b453caf42f4b03922',
-                self.METADATA_DIR: 'a089cc36bf79a40c7506019accc5f93e940d9fed',
-                self.TAX_FOLDER: '89b12cf8106f326887599dcb30ef94ebba142035',
-                self.SKANI_DIR: 'e12824beccc15fe67a373e2aa8eee72feecf89c6',
-                self.RED_DIR: 'c24a2f48bb0c1df38f92a8f526aa846f596c94c6'
-            }
-        elif version==207:
-            return {
-                self.PPLACER_DIR: '20903925a856a58b102a7b0ce160c5cbd2cf675b',
-                self.MASK_DIR: '50e414a9de18170e8cb97f990f89ff60a0fe29d5',
-                self.MARKER_DIR: '163f542c3f0a40f59df45d453aa235b39aa96e27',
-                self.RADII_DIR: '8fd13b1c5d7a7b073ba96fb628581613b293a374',
-                self.MSA_FOLDER: '24f250d7cf0eb0bc65dccd2f3c9247e553ea322f',
-                self.METADATA_DIR: '9772fbeac1311b31e10293fa610eb33aa1ec8e15',
-                self.TAX_FOLDER: '6fb0233b05633242369b40c026fd1ee53e266afa',
-                self.SKANI_DIR: '973c456c02f55bb82908a6811c7076e207e9b206',
-                self.RED_DIR: '7b8b67b3157204b470c9eb809d3c39c4effffabc'
+                self.RADII_DIR: '63d06ecc8b4547addd22c5b06ada4a28c5332bcc',
+                self.MSA_FOLDER: '3d5c1cf5346b244fcb0a9d48d2f1a9358a71cc7a',
+                self.METADATA_DIR: '01b8c23253cef097b1bc233d609dae9eb84c98e2',
+                self.TAX_FOLDER: '6758173fa61ae4a77f5588ec2874ea52ed345feb',
+                self.SKANI_DIR: 'ff58a1d7e0584da324d140701ee12cead4f0df9d',
+                self.RED_DIR: '206bd781997fffbac951b4437dd75e6543139fd6'
             }
 
+
     REF_HASHES = property(get_REF_HASHES)
 
 

gtdbtk/external/pplacer.py

@@ -21,6 +21,7 @@
 import queue
 import re
 import subprocess
+import sys
 
 from tqdm import tqdm
 
@@ -76,6 +77,8 @@ def run(self, cpus, model, ref_pkg, json_out, msa_file, pplacer_out,
 
         out_q = mp.Queue()
         pid = mp.Value('i', 0)
+        # print(f'Running pplacer with the following command: {" ".join(args)}')
+        # sys.exit(0)
         p_worker = mp.Process(target=self._worker, args=(
             args, out_q, pplacer_out, pid))
         p_writer = mp.Process(target=self._writer, args=(out_q, pid))