xengsort 2.0.4__tar.gz → 2.0.5__tar.gz

{xengsort-2.0.4/xengsort.egg-info → xengsort-2.0.5}/PKG-INFO

@@ -1,9 +1,30 @@
 Metadata-Version: 2.1
 Name: xengsort
-Version: 2.0.4
-Summary: A fast xenograft read sorter based on space-efficient k-mer hashing
+Version: 2.0.5
+Summary: xenograft sorting of FASTQ reads into five categories: host, graft, both, neither, ambiguous
 Author-email: Jens Zentgraf <zentgraf@cs.uni-saarland.de>, Sven Rahmann <rahmann@cs.uni-saarland.de>
-License: MIT
+License: MIT License
+        
+        Copyright (c) 2019-2022 Jens Zentgraf & Sven Rahmann
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
 Project-URL: Homepage, https://gitlab.com/genomeinformatics/xengsort
 Project-URL: Bug Tracker, https://gitlab.com/genomeinformatics/xengsort/issues
 Classifier: Programming Language :: Python :: 3
@@ -14,7 +35,7 @@ Classifier: Environment :: Console
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Python: ==3.11
+Requires-Python: <3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy>=1.24

{xengsort-2.0.4 → xengsort-2.0.5}/pyproject.toml

@@ -1,17 +1,25 @@
 [build-system]
-requires = ["setuptools==68.2.2"]
+requires = ["setuptools>=69.0.3"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "xengsort"
-version = "2.0.4"
+version = "2.0.5"
+license = {file = "LICENSE"}
 authors = [
   { name="Jens Zentgraf", email="zentgraf@cs.uni-saarland.de" },
   { name="Sven Rahmann", email="rahmann@cs.uni-saarland.de" }
 ]
-description = "A fast xenograft read sorter based on space-efficient k-mer hashing"
+description = "xenograft sorting of FASTQ reads into five categories: host, graft, both, neither, ambiguous"
 readme = "README.md"
-requires-python = "==3.11"
+requires-python = "<3.12"
+dependencies = [
+  "numpy>=1.24",
+  "numba>=0.57",
+  "pytest",
+  "jsonargparse",
+]
+scripts = {xengsort = "xengsort.xengsort.xengsort_main:main"}
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
@@ -22,12 +30,9 @@ classifiers = [
     "Natural Language :: English",
     "Topic :: Scientific/Engineering :: Bio-Informatics"
 ]
-dependencies = [
-  "numpy>=1.24",
-  "numba>=0.57",
-  "pytest",
-  "jsonargparse",
-]
+
+[tool.setuptools]
+packages=["xengsort"]
 
 [project.urls]
 "Homepage" = "https://gitlab.com/genomeinformatics/xengsort"

{xengsort-2.0.4 → xengsort-2.0.5}/xengsort/xengsort/xengsort_classify.py

@@ -109,7 +109,6 @@ def compile_coverage_based_classification(cov, mask, params):
     ret_amb = 2
     ret_both = 3
     ret_neither = 4
-    ret_unclassified = 5
 
     # define default params:
     p = dict()
@@ -138,7 +137,6 @@ def compile_coverage_based_classification(cov, mask, params):
     def classify_xengsort_cov(counts, neither, stronghost, stronggraft, both, weakhost, weakgraft, weakboth, size):
         # number of bases covered by k-mers of each class
 
-
         # no k-mers
         if size <= W + min_size:
             return ret_amb
@@ -169,7 +167,7 @@ def compile_coverage_based_classification(cov, mask, params):
         scores[3] = score_neither = np.float64((size - popcount(s_w_host_graft_both)) / size)
 
         # ############### first classify ##########
-        # return: 0:host, 1:graft, 2:ambiguous, 3:both, 4:neither, 5:unclassified
+        # return: 0:host, 1:graft, 2:ambiguous, 3:both, 4:neither
 
         # No host
         if strongHostBits == 0 and weakHostBits <= W + 2:
@@ -585,10 +583,8 @@ def compile_classify_read_from_fastq(
              cond_contextmgr(path, f"-both.1.fq{compression}", count, filt) as both1, \
              cond_contextmgr(path, f"-both.2.fq{compression}", count, filt) as both2, \
              cond_contextmgr(path, f"-neither.1.fq{compression}", count, filt) as neither1, \
-             cond_contextmgr(path, f"-neither.2.fq{compression}", count, filt) as neither2, \
-             cond_contextmgr(path, f"-unclassified.1.fq{compression}", count, filt) as unclassified1,\
-             cond_contextmgr(path, f"-unclassified.2.fq{compression}", count, filt) as unclassified2:
-            streams = ((host1, host2), (graft1, graft2), (ambiguous1, ambiguous2), (both1, both2), (neither1, neither2), (unclassified1, unclassified2))
+             cond_contextmgr(path, f"-neither.2.fq{compression}", count, filt) as neither2:
+            streams = ((host1, host2), (graft1, graft2), (ambiguous1, ambiguous2), (both1, both2), (neither1, neither2))
 
             with ThreadPoolExecutor(max_workers=threads) as executor:
                 for fastq1, fastq2 in zip(fastqs, pairs):
@@ -649,9 +645,8 @@ def compile_classify_read_from_fastq(
              cond_contextmgr(path, f"-graft.fq{compression}", count, filt) as graft, \
              cond_contextmgr(path, f"-ambiguous.fq{compression}", count, filt) as ambiguous, \
              cond_contextmgr(path, f"-both.fq{compression}", count, filt) as both, \
-             cond_contextmgr(path, f"-neither.fq{compression}", count, filt) as neither, \
-             cond_contextmgr(path, f"-unclassified.fq{compression}", count, filt) as unclassified:
-            streams = (host, graft, ambiguous, both, neither, unclassified)
+             cond_contextmgr(path, f"-neither.fq{compression}", count, filt) as neither:
+            streams = (host, graft, ambiguous, both, neither)
 
             running_jobs = []
             with ThreadPoolExecutor(max_workers=threads) as executor:

xengsort-2.0.5/xengsort/xengsort/xengsort_info.py

@@ -0,0 +1,83 @@
+"""
+xengsort/xengsort.py:
+Collect and print information on a hash table stored on disk.
+"""
+
+from numba import njit
+
+from ..lowlevel import debug
+from ..srhash import print_statistics
+from ..io.hashio import load_hash, dump_to_datafiles
+
+
+def print_dict(d, title=None):
+    if title is not None:
+        print(f"\n### {title}")
+    for key, value in d.items():
+        print(f"- {key}: {value}")
+
+
+def print_values(values, valuetup, title=None):
+    if title is not None:
+        print(f"\n### {title}")
+    print(f"- value set specification: {valuetup}")
+    print(f"- value set name: {values.NAME}")
+    print(f"- value set nvalues: {values.NVALUES}")
+
+
+def compile_filter_function(expr):
+    if expr is not None:
+        f = eval(f'lambda key, choice, value: ({expr})')
+    else:
+        f = (lambda key, choice, value: True)
+    ff = njit(nogil=True)(f)
+    return ff
+
+
+def dump_dna_to_text(h, nvalues, infotup, prefix, packed, filterfunc):
+    fname = prefix + ".dna.txt"
+    raise NotImplementedError(f"DNA text dump not implemented yet. {fname=}")
+
+
+def main(args):
+    global debugprint0, debugprint1, debugprint2
+    global timestamp0, timestamp1, timestamp2
+    debugprint0, debugprint1, debugprint2 = debug.debugprint
+    timestamp0, timestamp1, timestamp2 = debug.timestamp
+    starttime = timestamp0(msg="\n# fastcash info")
+
+    h, values, infotup = load_hash(args.hashname)
+    (hashinfo, valueinfo, optinfo, appinfo) = infotup
+    print_dict(hashinfo, "Hash table properties")
+    print_dict(optinfo)
+    print_dict(appinfo)
+    print_values(values, valueinfo, "Value set properties")
+    SV = {'all': values.NVALUES, 'none': False}
+    sv = args.showvalues
+    sv = SV[sv] if sv in SV else int(sv)
+    print("!!!", sv)
+    print_statistics(h, level=args.statistics, show_values=sv)
+
+    # dump data if requested
+    fmt = args.format  # native, packed, text/txt, dna
+    anyformat = (fmt is not None)
+    prefix = args.outprefix
+    nvalues = values.NVALUES
+    filterfunc = compile_filter_function(args.filter)
+    if (prefix is None) and anyformat:
+        prefix = args.hashname
+    if prefix is not None:
+        startout = timestamp0(msg="\n## Data Output")
+        if fmt == "dna":
+            written = dump_dna_to_text(h, nvalues, infotup, prefix, filterfunc)
+        else:
+            if fmt is None:
+                fmt = "native"
+            elif fmt == "txt":
+                fmt = "text"
+            written = dump_to_datafiles(h, nvalues, infotup, prefix, fmt, filterfunc)
+        debugprint0(f"- wrote {written} items")
+        timestamp0(startout, msg="- done writing data; writing time")
+
+    # that's it; successfully exit the program
+    timestamp0(starttime, msg="- DONE; total time")

{xengsort-2.0.4 → xengsort-2.0.5}/xengsort/xengsort/xengsort_main.py

@@ -6,19 +6,25 @@ by Jens Zentgraf & Sven Rahmann, 2019--2023
 
 from importlib import import_module  # dynamically import subcommand
 from os import path
+from importlib.metadata import metadata
 
 from jsonargparse import ArgumentParser, ActionConfigFile, SUPPRESS
 from jsonargparse.typing import restricted_number_type
 
-from .._version import VERSION, DESCRIPTION
 from ..lowlevel.debug import set_debugfunctions
 
+NAME = "xengsort"
+VERSION = metadata(NAME).json['version']
+DESCRIPTION = f"{NAME} {VERSION}: " + metadata(NAME).json['summary']
+
+
 def get_config_path():
     mainpath = __file__
     xengsortfolder = path.dirname(mainpath)
     cfgpath = path.join(xengsortfolder, "config")
     return cfgpath
 
+
 def classify(p):
     p.add_argument("--fastq", "-q", metavar="FASTQ", required=True, nargs="+",
         help="single or first paired-end FASTQ file to classify")
@@ -41,7 +47,7 @@ def classify(p):
     p.add_argument("--params_coverage", type=dict, help=SUPPRESS)
         # help="All paramteres for classification based on coverage as a dictionary. Update in config file.")
     p.add_argument("--threads", "-T", "-j", metavar="INT", type=int,
-        help=f"maximum number of worker threads for classification")
+        help="maximum number of worker threads for classification")
     gmode = p.add_mutually_exclusive_group(required=False)
     gmode.add_argument("--filter", action="store_true",
         help="only output the graft FASTQ file, not the other class FASTQ files")
@@ -49,9 +55,9 @@ def classify(p):
         help="only count reads or read pairs for each class, do not output any FASTQ")
     p.add_argument("--prefetchlevel", metavar="INT",
         type=restricted_number_type("from_0_to_2", int, [(">=", 0), ("<=", 2)]),
-        help=f"amount of prefetching: none (0), second bucket (1), all buckets (2)")
+        help="amount of prefetching: none (0), second bucket (1), all buckets (2)")
     p.add_argument("--chunksize", "-C", metavar="FLOAT_SIZE_MB", type=float, default=8.0,
-        help=f"chunk size in MB; one chunk is allocated per thread.")
+        help="chunk size in MB; one chunk is allocated per thread.")
     p.add_argument("--chunkreads", "-R", metavar="INT", type=int,
         help="maximum number of reads per chunk per thread [SIZE_MB*(2**20) // 200]")
     p.add_argument("--progress", "-P", action="store_true",

{xengsort-2.0.4 → xengsort-2.0.5/xengsort.egg-info}/PKG-INFO

@@ -1,9 +1,30 @@
 Metadata-Version: 2.1
 Name: xengsort
-Version: 2.0.4
-Summary: A fast xenograft read sorter based on space-efficient k-mer hashing
+Version: 2.0.5
+Summary: xenograft sorting of FASTQ reads into five categories: host, graft, both, neither, ambiguous
 Author-email: Jens Zentgraf <zentgraf@cs.uni-saarland.de>, Sven Rahmann <rahmann@cs.uni-saarland.de>
-License: MIT
+License: MIT License
+        
+        Copyright (c) 2019-2022 Jens Zentgraf & Sven Rahmann
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
 Project-URL: Homepage, https://gitlab.com/genomeinformatics/xengsort
 Project-URL: Bug Tracker, https://gitlab.com/genomeinformatics/xengsort/issues
 Classifier: Programming Language :: Python :: 3
@@ -14,7 +35,7 @@ Classifier: Environment :: Console
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Python: ==3.11
+Requires-Python: <3.12
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy>=1.24

{xengsort-2.0.4 → xengsort-2.0.5}/xengsort.egg-info/SOURCES.txt

@@ -2,10 +2,8 @@ LICENSE
 MANIFEST.in
 README.md
 pyproject.toml
-setup.py
 tests/test_encoding.py
 tests/test_trimmed_reads.py
-xengsort/_version.py
 xengsort/cptasks_kmers.py
 xengsort/dnaencode.py
 xengsort/hash_s3c_fbcbvb.py
@@ -19,7 +17,6 @@ xengsort.egg-info/PKG-INFO
 xengsort.egg-info/SOURCES.txt
 xengsort.egg-info/dependency_links.txt
 xengsort.egg-info/entry_points.txt
-xengsort.egg-info/not-zip-safe
 xengsort.egg-info/requires.txt
 xengsort.egg-info/top_level.txt
 xengsort/io/fastaio.py
@@ -38,6 +35,7 @@ xengsort/lowlevel/llvm.py
 xengsort/values/xenograft.py
 xengsort/xengsort/xengsort_classify.py
 xengsort/xengsort/xengsort_index.py
+xengsort/xengsort/xengsort_info.py
 xengsort/xengsort/xengsort_load.py
 xengsort/xengsort/xengsort_main.py
 xengsort/xengsort/xengsort_remove.py

xengsort-2.0.4/setup.py

@@ -1,42 +0,0 @@
-# coding: utf-8
-NAME = "xengsort"
-
-import sys
-try:
-    from setuptools import setup
-except ImportError:
-    print(f"Please install setuptools before installing {NAME}.", file=sys.stderr)
-    exit(1)
-
-if sys.version_info < (3,10):
-    print(f"At least Python 3.10 is required for {NAME}.", file=sys.stderr)
-    exit(1)
-
-
-# load and set VERSION and DESCRIPTION
-vcontent = open(f"{NAME}/_version.py").read()
-exec(vcontent)
-
-setup(
-    name=NAME,
-    version=VERSION,
-    description=DESCRIPTION,
-    zip_safe=False,
-    license='MIT',
-    packages=[NAME],
-    entry_points={
-        "console_scripts": [
-            f"{NAME} = {NAME}.{NAME}.{NAME}_main:main",
-        ],
-    },
-    package_data={'': ['*.css', '*.sh', '*.html']},
-    classifiers=[
-        "Development Status :: 5 - Production/Stable",
-        "Environment :: Console",
-        "Intended Audience :: Science/Research",
-        "License :: OSI Approved :: MIT License",
-        "Natural Language :: English",
-        "Programming Language :: Python :: 3",
-        "Topic :: Scientific/Engineering :: Bio-Informatics"
-    ]
-)

xengsort-2.0.4/xengsort/_version.py

@@ -1,27 +0,0 @@
-VERSION = "2.0.4"
-__version__ = VERSION
-
-DESCRIPTION = f"xengsort {VERSION}: xenograft sorting of FASTQ reads into five categories: host, graft, both, neither, ambiguous"
-
-
-LONG_DESCRIPTION = """
-The xengsort tool is made for xenograft sorting of single-end or paired-end FASTQ reads.
-The input reads are assumed to be a mixture of reads from (mainly) two organisms,
-typically human (tumor) and mouse (normal tissue),
-obtained from sequencing a human tumor that was implanted
-into a mouse model to study its growth and evolution,
-or its behavior under certain treatments.
-
-Using a k-mer-based approach and an ultra-fast hash table,
-xengsort separates (sorts) reads into five categories:
-(1) host (mouse) reads,
-(2) graft (human) reads,
-(3) reads that could result from both species,
-(4) reads that fit neither species,
-(5) ambiguous reads, which contain conflicting information.
-
-So the reads (or pairs) from a FASTQ file (or a pair of FASTQ files)
-are split into five output files (or pairs of files).
-Compared to other alignment-free tools, xengsort can be up to 4 times faster.
-Compared to alignment-based tools, xengsort is faster by orders of magnitude.
-"""

xengsort-2.0.4/xengsort.egg-info/not-zip-safe

@@ -1 +0,0 @@
-