metapredict 3.0.1__tar.gz → 3.0.2__tar.gz

{metapredict-3.0.1 → metapredict-3.0.2}/.gitignore

@@ -5,7 +5,7 @@ __pycache__/
 
 # C extensions
 *.so
-.DS_Store
+*.DS_Store
 *~
 
 metapredict/tests/test_cli/output/*

{metapredict-3.0.1 → metapredict-3.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: metapredict
-Version: 3.0.1
+Version: 3.0.2
 Summary: A machine learning-based tool for predicting protein disorder.
 Author-email: Ryan Emenecker <remenecker@wustl.edu>
 License: MIT
@@ -22,7 +22,7 @@ Requires-Dist: pytest>=6.1.2; extra == "test"
 
 # metapredict: A machine learning-based tool for predicting protein disorder.
 
-### Last updated November 2024
+### Last updated May 2026
 
 ## Current default version: V3
 In November 2024, we changed the default version of metapredict from V2 to V3. Small increments (3.0.x) may be made as bug fixes or feature enhancements.

{metapredict-3.0.1 → metapredict-3.0.2}/README.md

@@ -1,6 +1,6 @@
 # metapredict: A machine learning-based tool for predicting protein disorder.
 
-### Last updated November 2024
+### Last updated May 2026
 
 ## Current default version: V3
 In November 2024, we changed the default version of metapredict from V2 to V3. Small increments (3.0.x) may be made as bug fixes or feature enhancements.

{metapredict-3.0.1 → metapredict-3.0.2}/changelog.md

@@ -1,6 +1,12 @@
 ## Changelog
 This section is a log of recent changes with metapredict. My hope is that as I change things, this section can help you figure out why a change was made and if it will break any of your current workflows. The first major changes were made for the 0.56 release, so tracking will start there. Reasons are not provided for bug fixes for because the reason can assumed to be fixing the bug...
 
+#### V3.0.2 (May 2026)
+Changes:
+
+* Updated `metapredict-caid` and CAID output logic: The default IDR/folded domain binarization now uses an algorithmic approach to decompose IDRs and folded domains, rather than a strict per-residue cutoff. This provides more biologically meaningful domain assignments and better reflects the underlying disorder/folded state segmentation.
+
+
 #### V3.0.1 (November 2024)
 Changes:
 

{metapredict-3.0.1 → metapredict-3.0.2}/docs/usage/command-line.rst

@@ -756,10 +756,18 @@ The third argument specifies the version of Metapredict to use. The options are:
 - ``v2``
 - ``v3``
 
+
 **Example**:
 
 .. code-block:: bash
 
     $ metapredict-caid proteins.fasta output/ v3
 
+CAID Output Binarization: Algorithmic Domain Assignment
+------------------------------------------------------
+
+By default, ``metapredict-caid`` uses an algorithmic approach to assign binary labels for IDRs and folded domains. Instead of applying a strict per-residue disorder score cutoff, metapredict decomposes each sequence into contiguous intrinsically disordered regions (IDRs) and folded domains using a domain segmentation algorithm. This results in more biologically meaningful domain assignments that better reflect the underlying disorder/folded state segmentation.
+
+If you prefer the legacy strict cutoff-based assignment, you can use the ``--use-fixed-cutoff`` flag to specify a threshold for per-residue binarization.
+
 

metapredict-3.0.2/metapredict/_version.py

@@ -0,0 +1 @@
+__version__ = "3.0.2"

{metapredict-3.0.1 → metapredict-3.0.2}/metapredict/analysis/caid2_analysis.py

@@ -1,3 +1,4 @@
+"""
 # code to carry out the caid2 analsis for Disorder PDB dataset. 
 
 '''
@@ -8,7 +9,7 @@ facing.
 '''
 
 
-"""
+
 #  This is commented out because it requires sklearn. Given that none of the stuff
 #  in the analysis part of metapredict is necessary for users, I'm leaving
 #  stuff back here commenting out to avoid addint sklearn as another dependency. 
@@ -21,6 +22,20 @@ from sklearn.metrics import roc_auc_score, average_precision_score, f1_score, pr
 import math
 import matplotlib.pyplot as plt
 
+def use_domains_function(seq_domain):
+    # domain-based binary classification using DisorderObject
+    cur_sequence = seq_domain.sequence
+    cur_scores = seq_domain.disorder
+
+    # build a per-residue binary mask from the IDR domain boundaries
+    # (boundaries are half-open Python-indexed [start, end) intervals).
+    cur_binary_mask = [0] * len(cur_sequence)
+    for boundary in seq_domain.disordered_domain_boundaries:
+        start, end = boundary[0], boundary[1]
+        for i in range(start, end):
+            cur_binary_mask[i] = 1
+    return cur_binary_mask
+
 def read_caid2_seq_disorder(caid_file='caid2_disorder_pdb.fasta'):
     '''
     
@@ -80,7 +95,10 @@ def stretch(scores, base=0.1, top=0.95):
 
 
 
-def get_metapredict_scores(caid2_seqs_scores, version, cutoff=None, plddt=False, smoothing=None, stretch_scores=False):
+def get_metapredict_scores(caid2_seqs_scores, version, cutoff=None, plddt=False, 
+                           smoothing=None, 
+                           stretch_scores=False, 
+                           use_domains=False):
     '''
     function to get the metapredict scores that match
     to each sequence in the caid2 dataset.
@@ -98,6 +116,8 @@ def get_metapredict_scores(caid2_seqs_scores, version, cutoff=None, plddt=False,
         whether to smooth scores over some window. Default=None (no smoothing)
     stretch_scores : bool
         whether to stretch the scores
+    use_domains : bool
+        whether to use domain-based binary classification
 
     Returns
     --------
@@ -127,7 +147,7 @@ def get_metapredict_scores(caid2_seqs_scores, version, cutoff=None, plddt=False,
     
     # now get metapredict predictions.
     if plddt==False:
-        metapredict_scores = predict(caid2_seqs, version=version)
+        metapredict_scores = predict(caid2_seqs, version=version, return_domains=use_domains)
     else:
         metapredict_scores = predict_pLDDT(caid2_seqs, version=version, return_as_disorder_score=True)
 
@@ -151,12 +171,18 @@ def get_metapredict_scores(caid2_seqs_scores, version, cutoff=None, plddt=False,
     results={}
     for s in metapredict_scores:
         name=s
-        sequence=metapredict_scores[s][0]
-        scores=metapredict_scores[s][1]
-        binary_scores=np.array(scores)
-        binary_scores[binary_scores<cutoff] = 0
-        binary_scores[binary_scores>=cutoff] = 1
-        results[name] = {'sequence':sequence, 'scores':scores, 'binary':binary_scores.astype(int).tolist()}
+        if not use_domains:
+            sequence=metapredict_scores[s][0]
+            scores=metapredict_scores[s][1]
+            binary_scores=np.array(scores)
+            binary_scores[binary_scores<cutoff] = 0
+            binary_scores[binary_scores>=cutoff] = 1
+            results[name] = {'sequence':sequence, 'scores':scores, 'binary':binary_scores.astype(int).tolist()}
+        else:
+            sequence=metapredict_scores[s].sequence
+            scores=metapredict_scores[s].disorder
+            binary_scores=np.array(use_domains_function(metapredict_scores[s]))
+            results[name] = {'sequence':sequence, 'scores':scores, 'binary':binary_scores.astype(int).tolist()}
     return results
 
 
@@ -209,7 +235,8 @@ def calc_mcc(metapredict_scores, caid_scores):
     return mcc_value
 
 def calculate_stats(version='V2', cutoff=None, smoothing=None, stretch_scores=False,
-    evaluation_fasta='caid2_disorder_pdb.fasta'):
+    evaluation_fasta='caid2_disorder_pdb.fasta',
+    use_domains=False):
     '''
     Calculate the AUC, APS, and F1 max
 
@@ -233,6 +260,9 @@ def calculate_stats(version='V2', cutoff=None, smoothing=None, stretch_scores=Fa
         the fasta file to use for evaluation. 
         Default is the caid2_disorder_pdb.fasta
 
+    use_domains : bool
+        Whether to use domain-based binary classification. Default is False (per-residue binary classification)
+
     whether to stretch the scores
 
     Returns
@@ -249,7 +279,7 @@ def calculate_stats(version='V2', cutoff=None, smoothing=None, stretch_scores=Fa
     # get caid dict. 
     caid_vals = read_caid2_seq_disorder(caid_file=evaluation_fasta)
     # do metapredict prediction
-    metapredict_vals = get_metapredict_scores(caid_vals, version, cutoff=cutoff, smoothing=smoothing, stretch_scores=stretch_scores)
+    metapredict_vals = get_metapredict_scores(caid_vals, version, cutoff=cutoff, smoothing=smoothing, stretch_scores=stretch_scores, use_domains=use_domains)
     # get linear values for metapredict and caid
     metapredict_linear = []
     caid_linear = ''
@@ -284,7 +314,8 @@ def calculate_stats(version='V2', cutoff=None, smoothing=None, stretch_scores=Fa
 
 
 
-def print_current_network_accuracy(evaluation='all', additional_networks=None):
+
+def print_current_network_accuracy(evaluation='all', additional_networks=None, use_domains=False):
     '''
     Function to print out the current network accuracies. Just a nice
     one-liner to have sitting around. 
@@ -298,6 +329,9 @@ def print_current_network_accuracy(evaluation='all', additional_networks=None):
     additional_networks : list
         additional networks to test. Must be in the 
         metapredict_networks dictionary in network_parameters.py
+
+    use_domains : bool
+    whether to use domain-based binary classification. Default is False (per-residue binary classification)
     '''
     # list of current networks
     nets=['V1', 'V2', 'V3']
@@ -327,7 +361,8 @@ def print_current_network_accuracy(evaluation='all', additional_networks=None):
 
     # add the results for each network 
     for net in nets:
-        results = calculate_stats(version=net)
+        results = calculate_stats(version=net,
+                                  use_domains=use_domains)
         temp=''
         for result in results:
             temp = temp + f'{result} = {results[result]}, '
@@ -336,4 +371,9 @@ def print_current_network_accuracy(evaluation='all', additional_networks=None):
     # print the results
     print(eval_string)
 
+print('no domains')
+print_current_network_accuracy()
+
+print('with domains')
+print_current_network_accuracy(use_domains=True)
 """