emdbva 0.0.1.dev150__tar.gz → 0.0.1.dev152__tar.gz

{emdbva-0.0.1.dev150/emdbva.egg-info → emdbva-0.0.1.dev152}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: emdbva
-Version: 0.0.1.dev150
+Version: 0.0.1.dev152
 Summary: CryoEM validation toolkit
 Home-page: https://test.pypi.org/project/va/
 Author: Zhe Wang

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152/emdbva.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: emdbva
-Version: 0.0.1.dev150
+Version: 0.0.1.dev152
 Summary: CryoEM validation toolkit
 Home-page: https://test.pypi.org/project/va/
 Author: Zhe Wang

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/emdbva.egg-info/SOURCES.txt

@@ -26,6 +26,7 @@ va/metrics/emda_mmcc.py
 va/metrics/emringer.py
 va/metrics/inclusion.py
 va/metrics/map_data_validation.py
+va/metrics/map_map_cc.py
 va/metrics/overlap_percentage.py
 va/metrics/phaserandomization.py
 va/metrics/phenix_cc.py

emdbva-0.0.1.dev152/va/metrics/map_map_cc.py

@@ -0,0 +1,139 @@
+"""PHENIX map-map correlation metric helpers."""
+
+import os
+import re
+import subprocess
+from distutils.spawn import find_executable
+
+
+_MAP_MAP_CC_PATTERN = re.compile(
+    r"Map-map CC is\s+([-+]?(?:\d+(?:\.\d*)?|\.\d+)(?:[eE][-+]?\d+)?)"
+)
+
+
+def parse_map_map_cc_output(stdout_text):
+    """Extract the map-map correlation value from PHENIX output.
+
+    Args:
+        stdout_text (str): Combined standard output and error text from
+            ``phenix.map_correlations``.
+
+    Returns:
+        float or None: The parsed correlation, or ``None`` when the expected
+        result line is absent or cannot be converted to a number.
+    """
+    if not isinstance(stdout_text, str):
+        return None
+    match = _MAP_MAP_CC_PATTERN.search(stdout_text)
+    if match is None:
+        return None
+    try:
+        return float(match.group(1))
+    except (TypeError, ValueError):
+        return None
+
+
+def run_map_map_cc(map1_path, map2_path, output_path, echo=True):
+    """Run PHENIX map-map correlation for two map files.
+
+    Args:
+        map1_path (str): Path to the first map.
+        map2_path (str): Path to the second map.
+        output_path (str): Directory for the PHENIX stdout diagnostic file.
+        echo (bool): Whether to print captured PHENIX output.
+
+    Returns:
+        tuple: ``(errlist, result, stdout_text)``. ``result`` is empty when
+        the executable, inputs, subprocess, or parser fails.
+    """
+    errlist = []
+    result = {}
+    stdout_text = ""
+
+    phenix_path = find_executable("phenix.map_correlations")
+    if phenix_path is None:
+        return ["Phenix executable phenix.map_correlations is not available."], result, stdout_text
+
+    if not os.path.isfile(map1_path):
+        errlist.append("Map file does not exist: {}".format(map1_path))
+    if not os.path.isfile(map2_path):
+        errlist.append("Map file does not exist: {}".format(map2_path))
+    if errlist:
+        return errlist, result, stdout_text
+
+    try:
+        os.makedirs(output_path, exist_ok=True)
+    except OSError as exc:
+        return ["Could not create output directory {}: {}".format(output_path, exc)], result, stdout_text
+
+    command = [phenix_path, map1_path, map2_path]
+    try:
+        completed = subprocess.run(
+            command,
+            cwd=output_path,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            text=True,
+            check=False,
+        )
+        stdout_text = completed.stdout or ""
+    except OSError as exc:
+        return ["Failed to run phenix.map_correlations: {}".format(exc)], result, stdout_text
+    finally:
+        log_path = os.path.join(output_path, "map_correlations.stdout")
+        try:
+            with open(log_path, "w", encoding="utf-8") as log_file:
+                log_file.write(stdout_text)
+        except OSError as exc:
+            errlist.append("Could not write {}: {}".format(log_path, exc))
+
+    if echo:
+        print(stdout_text, end="")
+    if completed.returncode != 0:
+        errlist.append("phenix.map_correlations exited with code {}".format(completed.returncode))
+    if "error" in stdout_text.lower():
+        errlist.extend(
+            line.strip() for line in stdout_text.splitlines() if "error" in line.lower()
+        )
+
+    correlation = parse_map_map_cc_output(stdout_text)
+    if correlation is None:
+        errlist.append("Could not parse 'Map-map CC is ...' from PHENIX output.")
+
+    if not errlist:
+        map1_name = os.path.basename(map1_path)
+        map2_name = os.path.basename(map2_path)
+        result = {"name": [map1_name, map2_name], "value": correlation}
+    return errlist, result, stdout_text
+
+
+def write_map_map_cc_json(map1_path, map2_path, correlation, output_path):
+    """Write a successful map-map correlation result as a JSON fragment.
+
+    Args:
+        map1_path (str): Path to the first map.
+        map2_path (str): Path to the second map.
+        correlation (float): Parsed map-map correlation value.
+        output_path (str): Directory in which to write the fragment.
+
+    Returns:
+        str: Path to the written JSON file.
+    """
+    import json
+
+    os.makedirs(output_path, exist_ok=True)
+    map1_name = os.path.basename(map1_path)
+    map2_name = os.path.basename(map2_path)
+    pair_name = "{}_{}".format(map1_name, map2_name)
+    output_file = os.path.join(output_path, pair_name + "_cc.json")
+    data = {
+        "map_map_cc": {
+            pair_name: {
+                "names": [map1_name, map2_name],
+                "value": correlation,
+            }
+        }
+    }
+    with open(output_file, "w", encoding="utf-8") as handle:
+        json.dump(data, handle, indent=2)
+    return output_file

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/va/preparation.py

@@ -961,7 +961,8 @@ class PreParation:
 
         breakdigits = 2
         emdbidmin = 4
-        if len(emdid) >= emdbidmin and isinstance(emdid, str):
+        emdbidmax = 7
+        if isinstance(emdid, str) and emdid.isdigit() and emdbidmin <= len(emdid) <= emdbidmax:
             topsubpath = emdid[:breakdigits]
             middlesubpath = emdid[breakdigits:-breakdigits]
             subpath = os.path.join(topsubpath, middlesubpath, emdid)

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/va/prepareandrun_codon_airflow.py

@@ -149,8 +149,9 @@ class prepareandrun():
         idsubdirs = collections.OrderedDict()
         breakdigits = 2
         emdbidmin = 4
+        emdbidmax = 7
         for id in emdids:
-            if len(id) >= emdbidmin and isinstance(id, str):
+            if isinstance(id, str) and id.isdigit() and emdbidmin <= len(id) <= emdbidmax:
                 topsubpath = id[:breakdigits]
                 middlesubpath = id[breakdigits:-breakdigits]
                 subpath = os.path.join(topsubpath, middlesubpath, id)

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/va/schemas/emdb_entry_full.schema.json

@@ -4,7 +4,7 @@
   "type": "object",
   "description": "Root object keyed by EMDB id(s), e.g. \"8117\", or map output keys, e.g. \"emd_8117.map\".",
   "patternProperties": {
-    "^\\d{4,5}$": {
+    "^\\d{4,7}$": {
       "$ref": "#/definitions/EmdbEntry"
     },
     "^[A-Za-z0-9._-]+\\.map$": {

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/va/validationanalysis.py

@@ -211,15 +211,11 @@ class ValidationAnalysis:
         else:
             self.cl = contourlevel
         if self.emdid:
-            digits = [i for i in str(self.emdid)]
-            if len(digits) == 4:
-                subdir = '{}/{}/'.format(digits[0] + digits[1], self.emdid)
-                self.workdir = MAP_SERVER_PATH + subdir + 'va/'
-            elif len(digits) == 5:
-                subdir = '{}/{}/{}/'.format(digits[0] + digits[1], digits[2], self.emdid)
-                self.workdir = MAP_SERVER_PATH + subdir + 'va/'
-            else:
-                pass
+            emdid_text = str(self.emdid)
+            if not emdid_text.isdigit() or not 4 <= len(emdid_text) <= 7:
+                raise ValueError('EMDB IDs must contain 4 to 7 digits.')
+            subdir = os.path.join(emdid_text[:2], emdid_text[2:-2], emdid_text)
+            self.workdir = os.path.join(MAP_SERVER_PATH, subdir, 'va') + '/'
             self.queue = queue
         else:
             self.workdir = workdir

{emdbva-0.0.1.dev150 → emdbva-0.0.1.dev152}/va/version.py

@@ -18,5 +18,5 @@ under the License.
 
 """
 
-__version__ = '0.0.1.dev150'
+__version__ = '0.0.1.dev152'
 __em_statistics_version__ = '202505.v01'