PySAR 2.5.1__tar.gz → 2.5.2__tar.gz

{pysar-2.5.1 → pysar-2.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PySAR
-Version: 2.5.1
+Version: 2.5.2
 Summary: Analysing Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.
 Author-email: AJ McKenna <amckenna41@qub.ac.uk>
 Maintainer-email: AJ McKenna <amckenna41@qub.ac.uk>
@@ -70,8 +70,13 @@ Dynamic: license-file
 
 `pySAR` is a Python library for analysing Sequence Activity Relationships (SARs)/Sequence Function Relationships (SFRs) of protein sequences. 
 
+
+<h2 align="center">
+  The NEW front-end app for pySAR is available 
+  <a href="https://pysar-app.vercel.app/" target="_blank">here</a>!
+</h2>
+
 * 📖 The published research article is available [here][article].
-* 🌍 A front-end app for `pySAR` is available [here][frontend] (coming soon).
 * 💻 A quick Colab notebook demo of `pySAR` is available [here][demo]. 
 * 📰 A **Medium** article that dives deeper into SARs and the `pySAR` software itself is available [here][medium].
 
@@ -739,3 +744,4 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [config]: https://github.com/amckenna41/pySAR/blob/master/CONFIG.md
 [medium]: https://ajmckenna69.medium.com/pysar-a3de9f71733f
 [directed_evolution]: https://en.wikipedia.org/wiki/Directed_evolution_(protein_engineering)
+[frontend]: https://pysar-app.vercel.app/

{pysar-2.5.1 → pysar-2.5.2}/PySAR.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PySAR
-Version: 2.5.1
+Version: 2.5.2
 Summary: Analysing Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.
 Author-email: AJ McKenna <amckenna41@qub.ac.uk>
 Maintainer-email: AJ McKenna <amckenna41@qub.ac.uk>
@@ -70,8 +70,13 @@ Dynamic: license-file
 
 `pySAR` is a Python library for analysing Sequence Activity Relationships (SARs)/Sequence Function Relationships (SFRs) of protein sequences. 
 
+
+<h2 align="center">
+  The NEW front-end app for pySAR is available 
+  <a href="https://pysar-app.vercel.app/" target="_blank">here</a>!
+</h2>
+
 * 📖 The published research article is available [here][article].
-* 🌍 A front-end app for `pySAR` is available [here][frontend] (coming soon).
 * 💻 A quick Colab notebook demo of `pySAR` is available [here][demo]. 
 * 📰 A **Medium** article that dives deeper into SARs and the `pySAR` software itself is available [here][medium].
 
@@ -739,3 +744,4 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [config]: https://github.com/amckenna41/pySAR/blob/master/CONFIG.md
 [medium]: https://ajmckenna69.medium.com/pysar-a3de9f71733f
 [directed_evolution]: https://en.wikipedia.org/wiki/Directed_evolution_(protein_engineering)
+[frontend]: https://pysar-app.vercel.app/

{pysar-2.5.1 → pysar-2.5.2}/PySAR.egg-info/SOURCES.txt

@@ -9,6 +9,7 @@ PySAR.egg-info/requires.txt
 PySAR.egg-info/top_level.txt
 docs/conf.py
 pySAR/__init__.py
+pySAR/config.py
 pySAR/descriptors.py
 pySAR/encoding.py
 pySAR/evaluate.py

{pysar-2.5.1 → pysar-2.5.2}/README.md

@@ -20,8 +20,13 @@
 
 `pySAR` is a Python library for analysing Sequence Activity Relationships (SARs)/Sequence Function Relationships (SFRs) of protein sequences. 
 
+
+<h2 align="center">
+  The NEW front-end app for pySAR is available 
+  <a href="https://pysar-app.vercel.app/" target="_blank">here</a>!
+</h2>
+
 * 📖 The published research article is available [here][article].
-* 🌍 A front-end app for `pySAR` is available [here][frontend] (coming soon).
 * 💻 A quick Colab notebook demo of `pySAR` is available [here][demo]. 
 * 📰 A **Medium** article that dives deeper into SARs and the `pySAR` software itself is available [here][medium].
 
@@ -688,4 +693,5 @@ DOI: 10.1021/acs.jcim.0c00073 <br><br>
 [license]: https://github.com/amckenna41/pySAR/blob/master/LICENSE
 [config]: https://github.com/amckenna41/pySAR/blob/master/CONFIG.md
 [medium]: https://ajmckenna69.medium.com/pysar-a3de9f71733f
-[directed_evolution]: https://en.wikipedia.org/wiki/Directed_evolution_(protein_engineering)
+[directed_evolution]: https://en.wikipedia.org/wiki/Directed_evolution_(protein_engineering)
+[frontend]: https://pysar-app.vercel.app/

{pysar-2.5.1 → pysar-2.5.2}/docs/conf.py

@@ -15,7 +15,7 @@ sys.path.insert(0, os.path.abspath('..'))
 project = 'pySAR'
 copyright = '2026, AJ McKenna'
 author = 'AJ McKenna'
-release = '2.5.1'
+release = '2.5.2'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

{pysar-2.5.1 → pysar-2.5.2}/pySAR/__init__.py

@@ -1,6 +1,6 @@
 """ pySAR software metadata. """
 __name__ = 'pySAR'
-__version__ = "2.5.1"
+__version__ = "2.5.2"
 __description__ = 'A Python package used to analysis Sequence Activity Relationships (SARs) of protein sequences and their mutants using Machine Learning.'
 __author__ = 'AJ McKenna: https://github.com/amckenna41'
 __authorEmail__ = 'amckenna41@qub.ac.uk'
@@ -13,6 +13,9 @@ __keywords__ = ["bioinformatics", "protein engineering", "python", "pypi", "mach
         "directed evolution", "drug discovery", "sequence activity relationships", "SAR", "aaindex", "protpy", "protein descriptors"]
 __test_suite__ = "tests"
 
+from .encoding import SortKey, EncodingResult
+from .config import PySARConfig
+
 __all__ = [
     '__version__',
     '__description__',
@@ -25,4 +28,7 @@ __all__ = [
     '__status__',
     '__keywords__',
     '__test_suite__',
+    'SortKey',
+    'EncodingResult',
+    'PySARConfig',
 ]

pysar-2.5.2/pySAR/config.py

@@ -0,0 +1,103 @@
+################################################################################
+#################                  PySARConfig                 #################
+################################################################################
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Union
+
+
+@dataclass
+class PySARConfig:
+    """
+    Typed configuration container for PySAR and Encoding.
+
+    All parameters mirror the keys in the JSON configuration files so a
+    ``PySARConfig`` instance can be used wherever a config filepath is accepted.
+    Fields left as *None* fall back to the defaults encoded in the JSON file.
+
+    Parameters
+    ==========
+    :config_file: str
+        Path to the JSON configuration file.  When provided all other fields
+        are used as overrides rather than replacements.
+    :dataset: str
+        Path to the CSV dataset of protein sequences and activity values.
+    :sequence_col: str
+        Name of the column in *dataset* that contains the protein sequences.
+    :activity_col: str
+        Name of the column in *dataset* that contains the activity/fitness values.
+    :algorithm: str
+        Sklearn regression algorithm name (e.g. ``'plsregression'``, ``'randomforest'``).
+    :parameters: dict
+        Keyword arguments forwarded to the sklearn model constructor.
+    :test_split: float
+        Fraction of data held back for testing (0 < test_split < 1).
+    :use_dsp: bool
+        Apply a DSP (FFT) pipeline to the AAI-encoded sequences before modelling.
+    :spectrum: str
+        Informational spectrum to use when *use_dsp* is True.
+        One of ``'power'``, ``'real'``, ``'imaginary'``, ``'absolute'``.
+    :window_type: str
+        Window function to apply before the FFT (e.g. ``'hamming'``, ``'blackman'``).
+    :filter_type: str
+        Filter to apply after the FFT (e.g. ``'savgol'``, ``'medfilt'``).
+    :descriptors_csv: str
+        Path to a pre-calculated descriptors CSV file.  When provided the
+        ``Descriptors`` class will import values directly rather than
+        recomputing them.
+
+    Usage
+    =====
+    >>> cfg = PySARConfig(
+    ...     config_file="thermostability.json",
+    ...     algorithm="randomforest",
+    ...     test_split=0.1,
+    ... )
+    >>> from pySAR import PySAR
+    >>> sar = PySAR(cfg.config_file, algorithm=cfg.algorithm, test_split=cfg.test_split)
+    """
+
+    config_file: str = ""
+    dataset: Optional[str] = None
+    sequence_col: Optional[str] = None
+    activity_col: Optional[str] = None
+    algorithm: Optional[str] = None
+    parameters: Optional[Dict[str, Any]] = None
+    test_split: Optional[float] = None
+    use_dsp: Optional[bool] = None
+    spectrum: Optional[str] = None
+    window_type: Optional[str] = None
+    filter_type: Optional[str] = None
+    descriptors_csv: Optional[str] = None
+
+    def to_kwargs(self) -> Dict[str, Any]:
+        """
+        Return a dict of non-None, non-config_file fields suitable for passing
+        as ``**kwargs`` to :class:`~pySAR.pySAR.PySAR` or
+        :class:`~pySAR.encoding.Encoding`.
+
+        Returns
+        =======
+        :kwargs: dict
+            Only fields that have been explicitly set (i.e. are not None) are
+            included.  The ``config_file`` field is excluded since it is passed
+            as a positional argument.
+        """
+        result: Dict[str, Any] = {}
+        for field_name in (
+            "dataset",
+            "sequence_col",
+            "activity_col",
+            "algorithm",
+            "parameters",
+            "test_split",
+            "use_dsp",
+            "spectrum",
+            "window_type",
+            "filter_type",
+            "descriptors_csv",
+        ):
+            value = getattr(self, field_name)
+            if value is not None:
+                result[field_name] = value
+        return result

{pysar-2.5.1 → pysar-2.5.2}/pySAR/descriptors.py

@@ -12,6 +12,7 @@ import itertools
 import time
 from tqdm import tqdm
 from functools import lru_cache
+from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from .utils import *
 import protpy as protpy
@@ -374,13 +375,15 @@ class Descriptors():
     [14] B. Hollas, “An analysis of the autocorrelation descriptor for molecules,” J. Math. Chem., 
         vol. 33, no. 2, pp. 91–101, 2003.
     """
-    def __init__(self, 
-                 config_file: str = "", 
-                 protein_seqs: Optional[Union[pd.Series, str]] = None, 
+    def __init__(self,
+                 config_file: str = "",
+                 protein_seqs: Optional[Union[pd.Series, str]] = None,
+                 n_jobs: int = 1,
                  **kwargs) -> None:
 
         self.config_file = config_file
         self.protein_seqs = protein_seqs
+        self.n_jobs = max(1, int(n_jobs))
         self.kwargs = locals()['kwargs'] #get any keyword argument variables of class
         self.config_parameters = {}
 
@@ -1995,55 +1998,40 @@ class Descriptors():
         #start time counter
         start = time.time() 
 
-        #iterate over all descriptors, calculating each using their respective function and the protpy package
-        for descr in tqdm(self.all_descriptors_list(), unit=" descriptor", position=0, 
-            desc="Descriptors", mininterval=30, ncols=90):
-
-            #if descriptor attribute DF is empty then call its respective get_descriptor function
-            if (descr == "amino_acid_composition" and getattr(self, "amino_acid_composition").empty):
-                self.amino_acid_composition = self.get_amino_acid_composition()
-
-            if (descr == "dipeptide_composition" and getattr(self, "dipeptide_composition").empty):
-                    self.dipeptide_composition = self.get_dipeptide_composition()
-
-            if (descr == "tripeptide_composition" and getattr(self, "tripeptide_composition").empty):
-                    self.tripeptide_composition = self.get_tripeptide_composition()
-
-            if (descr == "moreaubroto_autocorrelation" and getattr(self, "moreaubroto_autocorrelation").empty):
-                self.moreaubroto_autocorrelation = self.get_moreaubroto_autocorrelation()
-
-            if (descr == "moran_autocorrelation" and getattr(self, "moran_autocorrelation").empty):
-                self.moran_autocorrelation = self.get_moran_autocorrelation()
-
-            if (descr == "geary_autocorrelation" and getattr(self, "geary_autocorrelation").empty):
-                self.geary_autocorrelation = self.get_geary_autocorrelation()
-
-            if (descr == "ctd" and getattr(self, "ctd").empty):
-                    self.ctd = self.get_ctd()
-
-            if (descr == "ctd_composition" and getattr(self, "ctd_composition").empty):
-                    self.ctd_composition = self.get_ctd_composition()
-
-            if (descr == "ctd_transition" and getattr(self, "ctd_transition").empty):
-                self.ctd_transition = self.get_ctd_transition()
-            
-            if (descr == "ctd_distribution" and getattr(self, "ctd_distribution").empty):
-                self.ctd_distribution = self.get_ctd_distribution()
-
-            if (descr == "conjoint_triad" and getattr(self, "conjoint_triad").empty):
-                    self.conjoint_triad = self.get_conjoint_triad()
-
-            if (descr == "sequence_order_coupling_number" and getattr(self, "sequence_order_coupling_number").empty):
-                    self.sequence_order_coupling_number = self.get_sequence_order_coupling_number()
-
-            if (descr == "quasi_sequence_order" and getattr(self, "quasi_sequence_order").empty):
-                    self.quasi_sequence_order = self.get_quasi_sequence_order()
-
-            if (descr == "pseudo_amino_acid_composition" and getattr(self, "pseudo_amino_acid_composition").empty):
-                    self.pseudo_amino_acid_composition = self.get_pseudo_amino_acid_composition()
+        #map each descriptor name to its getter for sequential and parallel dispatch
+        _getter_map = [
+            ('amino_acid_composition',                  self.get_amino_acid_composition),
+            ('dipeptide_composition',                   self.get_dipeptide_composition),
+            ('tripeptide_composition',                  self.get_tripeptide_composition),
+            ('moreaubroto_autocorrelation',             self.get_moreaubroto_autocorrelation),
+            ('moran_autocorrelation',                   self.get_moran_autocorrelation),
+            ('geary_autocorrelation',                   self.get_geary_autocorrelation),
+            ('ctd',                                     self.get_ctd),
+            ('ctd_composition',                         self.get_ctd_composition),
+            ('ctd_transition',                          self.get_ctd_transition),
+            ('ctd_distribution',                        self.get_ctd_distribution),
+            ('conjoint_triad',                          self.get_conjoint_triad),
+            ('sequence_order_coupling_number',          self.get_sequence_order_coupling_number),
+            ('quasi_sequence_order',                    self.get_quasi_sequence_order),
+            ('pseudo_amino_acid_composition',           self.get_pseudo_amino_acid_composition),
+            ('amphiphilic_pseudo_amino_acid_composition', self.get_amphiphilic_pseudo_amino_acid_composition),
+        ]
 
-            if (descr == "amphiphilic_pseudo_amino_acid_composition" and getattr(self, "amphiphilic_pseudo_amino_acid_composition").empty):
-                    self.amphiphilic_pseudo_amino_acid_composition = self.get_amphiphilic_pseudo_amino_acid_composition()
+        if self.n_jobs > 1:
+            #compute descriptors concurrently; skip any already populated from a prior import
+            pending = [(name, getter) for name, getter in _getter_map if getattr(self, name).empty]
+            with ThreadPoolExecutor(max_workers=self.n_jobs) as executor:
+                futures = {executor.submit(getter): name for name, getter in pending}
+                for future in tqdm(as_completed(futures), total=len(futures), unit=" descriptor",
+                                   desc="Descriptors", ncols=90):
+                    name = futures[future]
+                    setattr(self, name, future.result())
+        else:
+            #iterate over all descriptors sequentially, calculating each using their respective function
+            for name, getter in tqdm(_getter_map, unit=" descriptor", position=0,
+                                     desc="Descriptors", mininterval=30, ncols=90):
+                if getattr(self, name).empty:
+                    setattr(self, name, getter())
 
         #stop time counter, calculate elapsed time
         end = time.time()      
@@ -2320,13 +2308,14 @@ class Descriptors():
 
        return all_descriptors
 
-    def _calculate_descriptor_batch(self, 
-                                   descriptor_func: Callable, 
+    def _calculate_descriptor_batch(self,
+                                   descriptor_func: Callable,
                                    desc_name: str = "",
                                    **kwargs) -> pd.DataFrame:
         """
         Generic helper method to calculate descriptors for all sequences, preventing code repetition.
-        
+        Uses self.n_jobs threads to parallelise across sequences when n_jobs > 1.
+
         Parameters
         ==========
         :descriptor_func: Callable
@@ -2335,16 +2324,28 @@ class Descriptors():
             Name of descriptor for progress tracking
         :kwargs: dict
             Additional keyword arguments to pass to descriptor function
-        
+
         Returns
         =======
         :pd.DataFrame
             Dataframe with calculated descriptor values for all sequences
         """
-        iterator = tqdm(self.protein_seqs, desc=f"Computing {desc_name}") if desc_name else self.protein_seqs
+        seqs = list(self.protein_seqs)
 
-        # accumulate results in a list to avoid O(n²) repeated concat
-        desc_list = [descriptor_func(seq, **kwargs) for seq in iterator]
+        if self.n_jobs <= 1:
+            iterator = tqdm(seqs, desc=f"Computing {desc_name}", ncols=90) if desc_name else seqs
+            # accumulate results in a list to avoid O(n²) repeated concat
+            desc_list = [descriptor_func(seq, **kwargs) for seq in iterator]
+        else:
+            desc_list = [None] * len(seqs)
+            with ThreadPoolExecutor(max_workers=self.n_jobs) as executor:
+                futures = {executor.submit(descriptor_func, seq, **kwargs): i
+                           for i, seq in enumerate(seqs)}
+                progress = tqdm(as_completed(futures), total=len(seqs),
+                                desc=f"Computing {desc_name}", ncols=90) if desc_name else as_completed(futures)
+                for future in progress:
+                    i = futures[future]
+                    desc_list[i] = future.result()
 
         return pd.concat(desc_list, ignore_index=False).reset_index(drop=True)