cdhit-reader 0.2.0__tar.gz → 0.5.0__tar.gz

{cdhit-reader-0.2.0/cdhit_reader.egg-info → cdhit_reader-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: cdhit-reader
-Version: 0.2.0
+Version: 0.5.0
 Summary: CD-HIT cluster parser
 Home-page: https://github.com/telatin/cdhit-parser
 Download-URL: https://github.com/telatin/cdhit-parser
@@ -18,8 +18,16 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Description-Content-Type: text/markdown
-Provides-Extra: cli
 License-File: LICENSE.md
+Requires-Dist: click>=7.1.2
+Requires-Dist: importlib-resources>=1.4.0
+Requires-Dist: more-itertools>=8.4.0
+Requires-Dist: pytest>=5.4.3
+Requires-Dist: xopen>=1.0.1
+Provides-Extra: cli
+Requires-Dist: plotille; extra == "cli"
+Dynamic: download-url
+Dynamic: license-file
 
 # cdhit-parser
 
@@ -52,6 +60,24 @@ Load all clusters in to a list:
 clusters = read_cdhit(input).read_items()
 ```
 
+### Sequence to cluster lookup
+
+`Clustering` loads a whole .clstr file and provides a reverse index
+(`seqcluster`) mapping each sequence name to the name of its cluster:
+
+```python
+from cdhit_reader import Clustering
+
+clustering = Clustering.from_file(input)
+
+print(len(clustering))                      # number of clusters
+for cluster in clustering:                  # iterate over the clusters
+    print(cluster.name)
+
+# Which cluster does a sequence belong to?
+print(clustering.seqcluster["seq1.A"])      # e.g. "Cluster 0"
+```
+
 ## Read FASTA file
 
 ```python

{cdhit-reader-0.2.0 → cdhit_reader-0.5.0}/README.md

@@ -29,6 +29,24 @@ Load all clusters in to a list:
 clusters = read_cdhit(input).read_items()
 ```
 
+### Sequence to cluster lookup
+
+`Clustering` loads a whole .clstr file and provides a reverse index
+(`seqcluster`) mapping each sequence name to the name of its cluster:
+
+```python
+from cdhit_reader import Clustering
+
+clustering = Clustering.from_file(input)
+
+print(len(clustering))                      # number of clusters
+for cluster in clustering:                  # iterate over the clusters
+    print(cluster.name)
+
+# Which cluster does a sequence belong to?
+print(clustering.seqcluster["seq1.A"])      # e.g. "Cluster 0"
+```
+
 ## Read FASTA file
 
 ```python

cdhit_reader-0.5.0/cdhit_reader/__init__.py

@@ -0,0 +1,42 @@
+from importlib import import_module
+
+from ._reader import ParsingError, ClusterSequence, Cluster, Clustering, ClstrReader, read_cdhit, SeqType, Strand
+from ._fasta import FastaParsingError, Sequence, FastaReader, read_fasta
+from ._version import __version__
+
+_LAZY_EXPORTS = {
+    "cli": ("._cli", "cli"),
+    "compare": ("._compare", "compare"),
+    "test": ("._testit", "test"),
+}
+
+__all__ = [
+    "ParsingError",
+    "FastaParsingError",
+    "ClusterSequence",
+    "Cluster",
+    "Clustering",
+    "ClstrReader",
+    "read_cdhit",
+    "FastaReader",
+    "read_fasta",
+    "SeqType",
+    "Strand",
+    "Sequence",
+    "__version__",
+    "cli",
+    "compare",
+    "test",
+]
+
+
+def __getattr__(name):
+    if name in _LAZY_EXPORTS:
+        module_name, attribute_name = _LAZY_EXPORTS[name]
+        module = import_module(module_name, __name__)
+        return getattr(module, attribute_name)
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+def __dir__():
+    return sorted(set(globals()) | set(__all__))

{cdhit-reader-0.2.0 → cdhit_reader-0.5.0}/cdhit_reader/_cli.py

@@ -1,12 +1,9 @@
-
-import sys
 from statistics import mean
 
 import click
 
 from ._reader import read_cdhit
 from ._version import __version__
-#from ._writer import write_fasta
 
 
 @click.command(context_settings=dict(help_option_names=["-h", "--help"]))
@@ -22,31 +19,33 @@ def cli(clstr, stats: bool, hist: bool, all: bool):
     \b
     Warning
     -------
-    The commad line interface is in EXPERIMENTAL stage.  
+    The commad line interface is in EXPERIMENTAL stage.
     """
 
     nitems = 0
     nseqs = 0
     seq_lens = []
-    for item in read_cdhit(clstr):
-        seq_lens.append(len(item))
-        nitems += 1
-        nseqs  += len(item)
-        if all:
-            print(item)
-            for s in item.sequences:
-                print(f"   {s}")
+    with read_cdhit(clstr) as reader:
+        for item in reader:
+            seq_lens.append(len(item))
+            nitems += 1
+            nseqs += len(item)
+            if all:
+                print(item)
+                for s in item.sequences:
+                    print(f"   {s}")
     if stats:
         click.echo(f"Input file: {clstr}")
         click.echo(f"Number of clusters: {nitems}")
         click.echo(f"Total sequences: {nseqs}")
-        
-        msg = f"Cluster size: min {min(seq_lens)}, mean {mean(seq_lens):.2f}, max {max(seq_lens)}"
-        click.echo(msg)
+
+        if seq_lens:
+            msg = f"Cluster size: min {min(seq_lens)}, mean {mean(seq_lens):.2f}, max {max(seq_lens)}"
+            click.echo(msg)
 
     if hist:
         show_hist(seq_lens)
 
 
 def show_hist(seq_lens):
-    pass
+    pass

{cdhit-reader-0.2.0 → cdhit_reader-0.5.0}/cdhit_reader/_compare.py

@@ -1,26 +1,35 @@
-from email.policy import default
 import sys
-from statistics import mean
+import os
+import subprocess
+import tempfile
 
 import click
+from xopen import xopen
 
 from ._reader import read_cdhit
 from ._version import __version__
-from xopen import xopen
-import os
-import tempfile
-import subprocess
+
+TAG1 = "1:::"
+TAG2 = "2:::"
+
 
 def has_cdhit():
     cmd = ["cd-hit", "-h"]
-    # Run cmd and save stdout as "cdout" variable, ignore exit status
+    # Run cmd and inspect stdout, ignore exit status
     try:
         cdout = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE).stdout.decode("utf-8")
-        if "CD-HIT" in cdout:
-            return True
+        return "CD-HIT" in cdout
     except Exception:
         return False
-  
+
+
+def strip_tag(name: str) -> str:
+    """
+    Remove the relabeling prefix (TAG1/TAG2, same length) from a sequence name.
+    """
+    return name[len(TAG1):]
+
+
 def read_fasta(path):
     name = None
     comment = ""
@@ -38,11 +47,13 @@ def read_fasta(path):
                 seq += line
     yield name, comment, seq
 
+
 def relabel_fasta(path, prefix, outpath):
     with xopen(outpath, "a") as out:
         for name, comment, seq in read_fasta(path):
             out.write(">{}{}{}{}\n{}\n".format(prefix, name, " " if len(comment) > 1 else "", comment, seq))
 
+
 def split_cluster(cluster, tag1, tag2):
     pool1, pool2 = [], []
     for sequence in cluster.sequences:
@@ -52,17 +63,19 @@ def split_cluster(cluster, tag1, tag2):
             pool2.append(sequence)
         else:
             raise ValueError("Sequence {} does not start with {} or {}".format(sequence.name, tag1, tag2))
+
+
 @click.command(context_settings=dict(help_option_names=["-h", "--help"]))
 @click.version_option(__version__)
 @click.argument("fasta1", type=click.Path(exists=True))
 @click.argument("fasta2", type=click.Path(exists=True))
-@click.option("--tag1",   help="Name of the first dataset")
-@click.option("--tag2",  help="Name of the second dataset")
+@click.option("--tag1", help="Name of the first dataset")
+@click.option("--tag2", help="Name of the second dataset")
 @click.option("--id", help="Identity threshold [default: 0.9]", default=0.95, type=float)
 @click.option("--type", type=click.STRING, help="Type of the sequences (nucl or prot)")
-@click.option("--tempdir",type=click.Path(exists=True), help="Temporary directory for intermediate files", default=tempfile.gettempdir())
+@click.option("--tempdir", type=click.Path(exists=True), help="Temporary directory for intermediate files", default=tempfile.gettempdir())
 @click.option("--verbose", default=False, is_flag=True, help="Show verbose information")
-def compare(fasta1, fasta2, tag1: str, tag2: str, tempdir, type: str, id: float,verbose: bool):
+def compare(fasta1, fasta2, tag1: str, tag2: str, tempdir, type: str, id: float, verbose: bool):
     """
     Compare FASTA files
 
@@ -75,12 +88,9 @@ def compare(fasta1, fasta2, tag1: str, tag2: str, tempdir, type: str, id: float,
         click.echo("cd-hit is not installed. Please install it and try again.")
         sys.exit(1)
     # Generate temporary directory inside "tempdir"
-    TAG1      = "1:::"
-    TAG2      = "2:::"
     # tmp is a temporary directory not to be deleted
     tmp = tempfile.mkdtemp(dir=tempdir, prefix="cdhit_")
 
-    #tmp = tempfile.TemporaryDirectory(dir=tempdir, prefix="cdhit_reader_", suffix=".tmp")
     if verbose:
         print("Temporary directory: {}".format(tmp), file=sys.stderr)
 
@@ -97,42 +107,41 @@ def compare(fasta1, fasta2, tag1: str, tag2: str, tempdir, type: str, id: float,
     if prefix1 == prefix2:
         print("Warning: prefixes are identical ({}): specify manual prefixes with --tag1 and --tag2".format(prefix1))
         exit(1)
-    
+
     # Delete fasta_file if present:
     if os.path.exists(fasta_file):
         os.remove(fasta_file)
-    
+
     if verbose:
         print("Relabeling {} to {}".format(fasta1, fasta_file), file=sys.stderr)
-    
+
     relabel_fasta(fasta1, TAG1, fasta_file)
 
     if verbose:
         print("Relabeling {} to {}".format(fasta2, fasta_file), file=sys.stderr)
-    
+
     relabel_fasta(fasta2, TAG2, fasta_file)
 
     tags = {
         TAG1: prefix1,
         TAG2: prefix2
-    } 
+    }
     if verbose:
         print("Relabeling {} to {} (prefix: {})".format(fasta1, fasta_file, prefix1), file=sys.stderr)
         print("Relabeling {} to {} (prefix: {})".format(fasta2, fasta_file, prefix2), file=sys.stderr)
-        
-    cmd = ["cd-hit" if type=="prot" else "cd-hit-est", "-i", fasta_file, "-o", clstr_file, "-c", str(id), "-d", "1000"]
+
+    cmd = ["cd-hit" if type == "prot" else "cd-hit-est", "-i", fasta_file, "-o", clstr_file, "-c", str(id), "-d", "1000"]
     if verbose:
         print("Running {}".format(" ".join(cmd)), file=sys.stderr)
     subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
 
-
-    stats = {TAG1: [], TAG2: [], "both": [], "multi": [], "dupl_" + TAG1: [],  "dupl_" + TAG2: []}
+    stats = {TAG1: [], TAG2: [], "both": [], "multi": [], "dupl_" + TAG1: [], "dupl_" + TAG2: []}
     for cluster in read_cdhit(clstr_file + ".clstr"):
-        
-        pool = (cluster.refname)[0:len(TAG1)]
+
+        pool = cluster.refname[:len(TAG1)]
         if pool != TAG1 and pool != TAG2:
             raise ValueError("Cluster {} does not start with {} or {}".format(cluster.refname, TAG1, TAG2))
-        seqname = cluster.refname[len(pool) + 1:]
+        seqname = strip_tag(cluster.refname)
         if len(cluster) == 1:
             # Singleton
             stats[pool].append(seqname)
@@ -141,31 +150,28 @@ def compare(fasta1, fasta2, tag1: str, tag2: str, tempdir, type: str, id: float,
             pair = []
             check = False
             for seq in cluster.sequences:
-                sub_pool = (seq.name)[0:len(TAG1)]
-                sub_seqname = (seq.name)[len(pool) + 1:]
+                sub_pool = seq.name[:len(TAG1)]
+                sub_seqname = strip_tag(seq.name)
                 pair.append(sub_seqname)
                 if sub_pool != pool:
                     check = True
-            if check == True:    
+            if check:
                 stats["both"].append(":".join(pair))
             else:
-                stats["dupl_" + pool ].append(":".join(pair))
+                stats["dupl_" + pool].append(":".join(pair))
         else:
-            
+
             stats["multi"].append(",".join(i.name for i in cluster.sequences))
-    
 
-    for key, list in stats.items():
-        print("{} {}".format(key, len(list)), file=sys.stderr)
-        for seqnames in list:
+    for key, seqnames_list in stats.items():
+        print("{} {}".format(key, len(seqnames_list)), file=sys.stderr)
+        for seqnames in seqnames_list:
             key = tags[key] if key in tags else key
-            key = "dupl_" + tags[key[-1*len(TAG1):]] if key[-1*len(TAG1):] in tags else key
+            key = "dupl_" + tags[key[-1 * len(TAG1):]] if key[-1 * len(TAG1):] in tags else key
             seqnames = seqnames.replace(TAG1, tags[TAG1] + "#").replace(TAG2, tags[TAG2] + "#")
-            
+
             print(key, seqnames, sep="\t")
 
-    #if not verbose:
-    #    os.remove(tmp)
 
 def show_hist(seq_lens):
     pass