Merge pull request #61 from hsgweon/pipits_UNITE_10.01.2024

Updated UNITE to 10.0. SINTAX is the default classifier.
hsgweon · Aug 18, 2024 · 560015d · 560015d
2 parents 7b1d370 + 2435024
commit 560015d
Show file tree

Hide file tree

Showing 8 changed files with 82 additions and 57 deletions.
diff --git a/README.md b/README.md
@@ -8,6 +8,12 @@
 
 ## Updates/Notice/News
 
+###### UPDATE (18 August 2024) - PIPITS 3.1
+> Significant changes.
+>
+> - **UNITE 10.0 added is the default DB version until further update.
+> - The default classifier now is SINTAX. It's much much quicker and provides very comparable results against RDP Classifier. This change is due to the fact that UNITE database has increased massively.
+
 ###### UPDATE (11 August 2023) - PIPITS 3.0
 > - Just a slight change in the installation instruction, namely from python=3.6 to python=3.8 to avoid "SyntaxError: invalid syntax"
 

diff --git a/bin/pipits_funits b/bin/pipits_funits
@@ -5,7 +5,7 @@ from pispino.seqtools import *
 from pispino.runcmd import *
 from pispino.logger import *
 
-__version__    = 3.0
+__version__    = 3.1
 
 __author__     = "Hyun Soon Gweon"
 __copyright__  = "Copyright 2015, The PIPITS Project"

diff --git a/bin/pipits_process b/bin/pipits_process
@@ -4,7 +4,7 @@ import sys, os, argparse, subprocess, shutil
 from pispino.runcmd import *
 from pispino.logger import *
 
-__version__    = 3.0
+__version__    = 3.1
 
 __author__     = "Hyun Soon Gweon"
 __copyright__  = "Copyright 2015, The PIPITS Project"
@@ -119,15 +119,15 @@ if __name__ == '__main__':
         dest = "taxassignmentmethod",
         help = "Choice of taxonomic assignment. By default, PIPITS will run both RDP Classifier and SINTAX (VSEARCH).",
         choices = ["all", "rdp", "sin"],
-        default = "all",
+        default = "sin",
         required = False)
     parser.add_argument(
         "--unite",
         action = "store",
         dest = "unite",
         help = "UNITE db version to be used - PIPITS will download db automaticlly. Leaving this option out will default to the most recent version of UNITE available to PIPITS.",
-        choices = ["27.10.2022", "10.05.2021", "04.02.2020", "02.02.2019", "01.12.2017", "28.06.2017"],
-        default = "27.10.2022",
+        choices = ["04.04.2024", "25.07.2023", "27.10.2022", "10.05.2021", "04.02.2020", "02.02.2019", "01.12.2017", "28.06.2017"],
+        default = "04.04.2024",
         required = False)
     options = parser.parse_args()
 
@@ -331,69 +331,87 @@ if __name__ == '__main__':
     # UNITE #
     #########
 
-    logger("Downloading UNITE trained database, version: " + options.unite, logging_file, display = True)
 
-    url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/UNITE_retrained_" + options.unite + ".tar.gz"
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "rdp":
 
-    if options.unite == "02.02.2019":
-        md5 = "8fd3b74a510bb20b67933a2ecc620f89"
-    elif options.unite == "01.12.2017":
-        md5 = "3c5be9c60fecf70076739379e7c9ead5"
-    elif options.unite == "28.06.2017":
-        md5 = "33fa78987751a494c586676ff3a0da65"
-    elif options.unite == "04.02.2020":
-        md5 = "b2f833c89794be20a5fdb6169d9205f1"
-    elif options.unite == "10.05.2021":
-        md5 = "13f1edfb1357eeda3f41ff8b0a15447f"
-    elif options.unite == "27.10.2022":
-        md5 = "7d31f5612a78607e50d4170b75d0cbfa"
-
-    downloadDB(
-        url = url,
-        md5 = md5,
-        output_dir = "pipits_db",
-        logging_file = logging_file,
-        summary_file = summary_file,
-        verbose = options.verbose)
-    logger(BLUE + "... done" + ENDC, logging_file, display = True)
+        logger("Downloading UNITE trained database, version: " + options.unite, logging_file, display = True)
+
+        url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/UNITE_retrained_" + options.unite + ".tar.gz"
+
+        if options.unite == "02.02.2019":
+            md5 = "8fd3b74a510bb20b67933a2ecc620f89"
+        elif options.unite == "01.12.2017":
+            md5 = "3c5be9c60fecf70076739379e7c9ead5"
+        elif options.unite == "28.06.2017":
+            md5 = "33fa78987751a494c586676ff3a0da65"
+        elif options.unite == "04.02.2020":
+            md5 = "b2f833c89794be20a5fdb6169d9205f1"
+        elif options.unite == "10.05.2021":
+            md5 = "13f1edfb1357eeda3f41ff8b0a15447f"
+        elif options.unite == "27.10.2022":
+            md5 = "7d31f5612a78607e50d4170b75d0cbfa"
+        elif options.unite == "25.07.2023":
+            md5 = "1c578d0aba436f0b66d9a73b2991086d"
+        elif options.unite == "04.04.2024":
+            md5 = "94812f45cbfed846b55a6e845e68f35f"
+
+        downloadDB(
+            url = url,
+            md5 = md5,
+            output_dir = "pipits_db",
+            logging_file = logging_file,
+            summary_file = summary_file,
+            verbose = options.verbose)
+        logger(BLUE + "... done" + ENDC, logging_file, display = True)
 
 
     ##################
     # VSEARCH SINTAX #
     ##################
 
-    logger("Downloading database for SINTAX", logging_file, display = True)
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "sin":
 
-    url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/UNITE_retrained_27.10.2022.sintax.fa.tar.gz"
-    md5 = "b26ebd07a5abb415e1ad35b8dc8108d2"
-
-    downloadDB(
-        url = url,
-        md5 = md5,
-        output_dir = "pipits_db",
-        logging_file = logging_file,
-        summary_file = summary_file,
-        verbose = options.verbose)
-    logger(BLUE + "... done" + ENDC, logging_file, display = True)
+        logger("Downloading database for SINTAX, version: " + options.unite, logging_file, display = True)
+
+        url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/UNITE_retrained_" + options.unite + ".sintax.fa.tar.gz"
+        md5 = "135cce3029569c1c0528a7fdd9ed6673"
+
+        if options.unite == "27.10.2022":
+            md5 = "b26ebd07a5abb415e1ad35b8dc8108d2"
+        elif options.unite == "25.07.2023":
+            md5 = "cf7dcd5e289a4d31c87fadb056caaca7"
+        elif options.unite == "04.04.2024":
+            md5 = "135cce3029569c1c0528a7fdd9ed6673"
+
+        downloadDB(
+            url = url,
+            md5 = md5,
+            output_dir = "pipits_db",
+            logging_file = logging_file,
+            summary_file = summary_file,
+            verbose = options.verbose)
+        logger(BLUE + "... done" + ENDC, logging_file, display = True)
 
 
     ##########
     # WARCUP #
     ##########
 
-    logger("Downloading WARCUP trained database: ", logging_file, display = True)
+    if options.warcup == True:
+
+        logger("Downloading WARCUP trained database: ", logging_file, display = True)
 
-    url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/warcup_retrained_V2.tar.gz"
-    md5 = "e84733f23121f00de03b2a9b5398d6fb"
+        url = "https://sourceforge.net/projects/pipits/files/PIPITS_DB/warcup_retrained_V2.tar.gz"
+        md5 = "e84733f23121f00de03b2a9b5398d6fb"
 
-    downloadDB(
-        url = url,
-        md5 = md5,
-        output_dir = "pipits_db",
-        logging_file = logging_file,
-        summary_file = summary_file,
-        verbose = options.verbose)
-    logger(BLUE + "... done" + ENDC, logging_file, display = True)
+        downloadDB(
+            url = url,
+            md5 = md5,
+            output_dir = "pipits_db",
+            logging_file = logging_file,
+            summary_file = summary_file,
+            verbose = options.verbose)
+        logger(BLUE + "... done" + ENDC, logging_file, display = True)
 
 
     ##########
@@ -540,7 +558,7 @@ if __name__ == '__main__':
     # VSINTAX against UNITE #
     #########################
 
-    if (options.taxassignmentmethod == "all" or "sin"):
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "sin":
 
         logger(ENDC + "Assigning taxonomy with VSEARCH-SINTAX [VSEARCH]" + ENDC, logging_file, display = True)
         PIPITS_UNITE_RETRAINED_VSEARCHSINTAXFORMATTED = "pipits_db/UNITE_retrained_" + options.unite + ".sintax.fa/UNITE_retrained_" + options.unite + ".sintax.fa"
@@ -619,8 +637,8 @@ if __name__ == '__main__':
     # RDP against UNITE #
     #####################
 
-    if (options.taxassignmentmethod == "all" or "rdp"):
-        
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "rdp":
+
         logger(ENDC + "Assigning taxonomy with UNITE [RDP Classifier]" + ENDC, logging_file, display = True)
         PIPITS_UNITE_RETRAINED_PROPERTIES = "pipits_db/UNITE_retrained_" + options.unite + "/UNITE_retrained/rRNAClassifier.properties"
         cmd = " ".join(["classifier",
@@ -795,10 +813,11 @@ if __name__ == '__main__':
 
         return totalCount, otus, sampleSize
 
-    if (options.taxassignmentmethod == "all" or "rdp"):    
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "rdp":
         otu_reads_count, otu_count, otu_sample_count = biomstats(options.outDir + "/otu_table_rdp.biom")
         phylo_reads_count, phylo_count, phylo_sample_count = biomstats(options.outDir + "/phylotype_table_rdp.biom")
-    else:
+
+    if options.taxassignmentmethod == "all" or options.taxassignmentmethod == "sin":
         otu_reads_count, otu_count, otu_sample_count = biomstats(options.outDir + "/otu_table_sintax.biom")
         phylo_reads_count, phylo_count, phylo_sample_count = biomstats(options.outDir + "/phylotype_table_sintax.biom")
 

diff --git a/pipits/__pycache__/__init__.cpython-36.pyc b/pipits/__pycache__/__init__.cpython-36.pyc
diff --git a/pipits/__pycache__/__init__.cpython-39.pyc b/pipits/__pycache__/__init__.cpython-39.pyc
diff --git a/pipits/__pycache__/pipits_SeqIO.cpython-36.pyc b/pipits/__pycache__/pipits_SeqIO.cpython-36.pyc
diff --git a/pipits/__pycache__/pipits_SeqIO.cpython-39.pyc b/pipits/__pycache__/pipits_SeqIO.cpython-39.pyc
diff --git a/setup.py b/setup.py
@@ -1,7 +1,7 @@
 from setuptools import setup
 import os
 
-__version__ = os.environ.get("VERSION", "3.0")
+__version__ = os.environ.get("VERSION", "3.1")
 
 setup(
 	name = "pipits",