Add PCP descriptors from Venkatarajan *et al.* (2001)

peptides/__init__.py

@@ -68,6 +68,14 @@ class MSWHIMScores(typing.NamedTuple):
     mswhim3: float
 
 
+class PCPDescriptors(typing.NamedTuple):
+    e1: float
+    e2: float
+    e3: float
+    e4: float
+    e5: float
+
+
 class ProtFPDescriptors(typing.NamedTuple):
     protfp1: float
     protfp2: float
@@ -1444,6 +1452,48 @@ class Peptide(typing.Sequence[str]):
             )
         return MSWHIMScores(*out)
 
+    def pcp_descriptors(self) -> PCPDescriptors:
+        """Compute the Physical-Chemical Properties of a protein sequence.
+
+        The PCP descriptors were constructed by performing multidimensional
+        scaling of 237 physical-chemical properties.
+
+        Returns:
+            `peptides.PCPDescriptors`: The computed average of PCP
+            descriptors descriptors of all the amino acids in the peptide.
+
+        Example:
+            >>> peptide = Peptide("QWGRRCCGWGPGRRYCVRWC")
+            >>> for i, pcp in enumerate(peptide.pcp_descriptors()):
+            ...     print(f"E{i+1:<3} {pcp: .4f}")
+            E1    0.0109
+            E2    0.0381
+            E3    0.1250
+            E4    0.0409
+            E5   -0.1059
+
+        References:
+            - Venkatarajan, M. S., and W. Braun.
+              *New Quantitative Descriptors of Amino Acids Based on
+              Multidimensional Scaling of a Large Number of
+              Physical–Chemical Properties*.
+              Molecular Modeling Annual. Dec 2001;7(12):445–53.
+              doi:10.1007/s00894-001-0058-5.
+            - Venkatarajan, M. S., D. Paris, and M. J. Mullan.
+              *A Novel Physico-Chemical Property Based Model for Studying
+              the Effects of Mutation on the Aggregation of Peptides*.
+              Protein and Peptide Letters. 2009;16(8):991–98.
+              doi:10.2174/092986609788923220. PMID:19689427.
+
+        """
+        out = array.array("d")
+        for i in range(len(tables.PCP_DESCRIPTORS)):
+            scale = tables.PCP_DESCRIPTORS[f"E{i+1}"]
+            out.append(
+                sum(scale.get(aa, 0) for aa in self.sequence) / len(self.sequence)
+            )
+        return PCPDescriptors(*out)
+
     def protfp_descriptors(self) -> ProtFPDescriptors:
         """Compute the ProtFP descriptors of a protein sequence.
 

peptides/data/pcp_descriptors/E1.csv

+A,0.008
+R,0.171
+N,0.255
+D,0.303
+C,-0.132
+Q,0.149
+E,0.221
+G,0.218
+H,0.023
+I,-0.353
+L,-0.267
+K,0.243
+M,-0.239
+F,-0.329
+P,0.173
+S,0.199
+T,0.068
+W,-0.296
+Y,-0.141
+V,-0.274

peptides/data/pcp_descriptors/E2.csv

+A,0.134
+R,-0.361
+N,0.038
+D,-0.057
+C,0.174
+Q,-0.184
+E,-0.280
+G,0.562
+H,-0.177
+I,0.071
+L,0.018
+K,-0.339
+M,-0.141
+F,-0.023
+P,0.286
+S,0.238
+T,0.147
+W,-0.186
+Y,-0.057
+V,0.136

peptides/data/pcp_descriptors/E3.csv

+A,-0.475
+R,0.107
+N,0.117
+D,-0.014
+C,0.070
+Q,-0.030
+E,-0.315
+G,-0.024
+H,0.041
+I,-0.088
+L,-0.265
+K,-0.044
+M,-0.155
+F,0.072
+P,0.407
+S,-0.015
+T,-0.015
+W,0.389
+Y,0.425
+V,-0.187

peptides/data/pcp_descriptors/E4.csv

+A,-0.039
+R,-0.258
+N,0.118
+D,0.225
+C,0.565
+Q,0.035
+E,0.157
+G,0.018
+H,0.280
+I,-0.195
+L,-0.274
+K,-0.325
+M,0.321
+F,-0.002
+P,-0.215
+S,-0.068
+T,-0.132
+W,0.083
+Y,-0.096
+V,-0.196

peptides/data/pcp_descriptors/E5.csv

+A,0.181
+R,-0.364
+N,-0.055
+D,0.156
+C,-0.374
+Q,-0.112
+E,0.303
+G,0.106
+H,-0.021
+I,-0.107
+L,0.206
+K,-0.027
+M,0.077
+F,0.208
+P,0.384
+S,-0.196
+T,-0.274
+W,0.297
+Y,-0.091
+V,-0.299