molcraft 0.1.0a4__tar.gz → 0.1.0a5__tar.gz

{molcraft-0.1.0a4 → molcraft-0.1.0a5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: molcraft
-Version: 0.1.0a4
+Version: 0.1.0a5
 Summary: Graph Neural Networks for Molecular Machine Learning
 Author-email: Alexander Kensert <alexander.kensert@gmail.com>
 License: MIT License

{molcraft-0.1.0a4 → molcraft-0.1.0a5}/molcraft/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '0.1.0a4'
+__version__ = '0.1.0a5'
 
 import os
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"

{molcraft-0.1.0a4 → molcraft-0.1.0a5}/molcraft.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: molcraft
-Version: 0.1.0a4
+Version: 0.1.0a5
 Summary: Graph Neural Networks for Molecular Machine Learning
 Author-email: Alexander Kensert <alexander.kensert@gmail.com>
 License: MIT License

{molcraft-0.1.0a4 → molcraft-0.1.0a5}/molcraft.egg-info/SOURCES.txt

@@ -19,8 +19,6 @@ molcraft.egg-info/SOURCES.txt
 molcraft.egg-info/dependency_links.txt
 molcraft.egg-info/requires.txt
 molcraft.egg-info/top_level.txt
-molcraft/experimental/__init__.py
-molcraft/experimental/peptides.py
 tests/test_chem.py
 tests/test_featurizers.py
 tests/test_layers.py

molcraft-0.1.0a4/molcraft/experimental/__init__.py

@@ -1 +0,0 @@
-from molcraft.experimental import peptides

molcraft-0.1.0a4/molcraft/experimental/peptides.py

@@ -1,281 +0,0 @@
-import re
-import keras
-import numpy as np
-import tensorflow as tf
-import tensorflow_text as tf_text
-from rdkit import Chem
-
-from molcraft import ops
-from molcraft import chem 
-from molcraft import features 
-from molcraft import featurizers
-from molcraft import tensors
-from molcraft import descriptors
-from molcraft import layers 
-
-    
-def Graph(
-    inputs,
-    atom_features: list[features.Feature] | str | None = 'auto',
-    bond_features: list[features.Feature] | str | None = 'auto',
-    molecule_features: list[descriptors.Descriptor] | str | None = 'auto',
-    super_atom: bool = True,
-    radius: int | float | None = None,
-    self_loops: bool = False,
-    include_hs: bool = False,
-    **kwargs,
-):
-    featurizer = featurizers.MolGraphFeaturizer(
-        atom_features=atom_features,
-        bond_features=bond_features,
-        molecule_features=molecule_features,
-        super_atom=super_atom,
-        radius=radius,
-        self_loops=self_loops,
-        include_hs=include_hs,
-        **kwargs,
-    )
-
-    tensor_list: list[tensors.GraphTensor] = [
-        featurizer(residues[tag]).update({'context': {'tag': tag}}) for tag in inputs
-    ]
-    return tf.stack(tensor_list, axis=0)
-        
-
-def Lookup(graph: tensors.GraphTensor) -> 'LookupLayer':
-    lookup = LookupLayer()
-    lookup._build(graph)
-    return lookup
-
-
-@keras.saving.register_keras_serializable(package='molcraft')
-class SequenceSplit(keras.layers.Layer):
-
-    _pattern = "|".join([
-        r'(\[[A-Za-z0-9]+\]-[A-Z]\[[A-Za-z0-9]+\])', # N-term mod + mod
-        r'([A-Z]\[[A-Za-z0-9]+\]-\[[A-Za-z0-9]+\])', # C-term mod + mod
-        r'([A-Z]-\[[A-Za-z0-9]+\])', # C-term mod
-        r'(\[[A-Za-z0-9]+\]-[A-Z])', # N-term mod
-        r'([A-Z]\[[A-Za-z0-9]+\])', # Mod
-        r'([A-Z])', # No mod
-    ])
-
-    def call(self, inputs):
-        inputs = tf_text.regex_split(inputs, self._pattern, self._pattern)
-        inputs = keras.ops.concatenate([
-            tf.strings.join([inputs[:, :-1], '-[X]']),
-            inputs[:, -1:]
-        ], axis=1)
-        return inputs.to_tensor()
-
-
-
-
-@keras.saving.register_keras_serializable(package='molcraft')
-class LookupLayer(keras.layers.Layer):
-
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
-        self._sequence_splitter = SequenceSplit()
-
-    def call(self, sequence: tf.Tensor) -> tensors.GraphTensor:
-        sequence = self._sequence_splitter(sequence)
-        indices = self._tag_to_index.lookup(sequence)
-        indices = tf.sort(tf.unique(tf.reshape(indices, [-1]))[0])[1:]
-        graph = self.graph[indices]
-        return tensors.to_dict(graph)
-
-    def _build(self, x):
-
-        if isinstance(x, tensors.GraphTensor):
-            tensor = tensors.to_dict(x)
-            self._spec = tf.nest.map_structure(
-                tf.type_spec_from_value, tensor
-            )
-        else:
-            self._spec = x
-
-        self._graph = tf.nest.map_structure(
-            lambda s: self.add_weight(
-                shape=s.shape, 
-                dtype=s.dtype, 
-                trainable=False,
-                initializer='zeros'
-            ),
-            self._spec
-        )
-
-        if isinstance(x, tensors.GraphTensor):
-            tf.nest.map_structure(
-                lambda v, x: v.assign(x),
-                self._graph, tensor
-            )
-
-        graph = tf.nest.map_structure(
-            keras.ops.convert_to_tensor, self._graph
-        )
-        self._graph_tensor = tensors.from_dict(graph)
-
-        tags = self._graph_tensor.context['tag']
-
-        self._tag_to_index = tf.lookup.StaticHashTable(
-            tf.lookup.KeyValueTensorInitializer(
-                keys=tags,
-                values=range(len(tags)),
-            ),
-            default_value=-1,
-        )
-
-    def get_config(self):
-        config = super().get_config()
-        spec = keras.saving.serialize_keras_object(self._spec)
-        config['spec'] = spec
-        return config 
-    
-    @classmethod
-    def from_config(cls, config: dict) -> 'LookupLayer':
-        spec = config.pop('spec')
-        spec = keras.saving.deserialize_keras_object(spec)
-        layer = cls(**config)
-        layer._build(spec)
-        return layer
-
-    @property 
-    def graph(self) -> tensors.GraphTensor:
-        return self._graph_tensor
-    
-
-@keras.saving.register_keras_serializable(package='molcraft')
-class Gather(keras.layers.Layer):
-
-    def __init__(
-        self, 
-        padding: list[tuple[int]] | tuple[int] | int = 1, 
-        mask_value: int = 0,
-        **kwargs
-    ) -> None:
-        super().__init__(**kwargs)
-        self.padding = padding
-        self.mask_value = mask_value
-        self._readout_layer = layers.Readout(mode='mean')
-        self.supports_masking = True
-        self._sequence_splitter = SequenceSplit()
-
-    def get_config(self):
-        config = super().get_config()
-        config['mask_value'] = self.mask_value 
-        config['padding'] = self.padding
-        return config 
-
-    def call(self, inputs) -> tf.Tensor:
-
-        graph, sequence = inputs
-
-        tag = graph['context']['tag']
-        data = self._readout_layer(graph)
-
-        table = tf.lookup.experimental.MutableHashTable(
-            key_dtype=tf.string,
-            value_dtype=tf.int32,
-            default_value=-1
-        )
-
-        table.insert(tag, tf.range(tf.shape(tag)[0]))
-        sequence = self._sequence_splitter(sequence)
-        sequence = table.lookup(sequence)
-
-        readout = ops.gather(data, keras.ops.where(sequence == -1, 0, sequence)) 
-        readout = keras.ops.where(sequence[..., None] == -1, 0.0, readout)
-        return readout
-
-    def compute_mask(
-        self, 
-        inputs: tensors.GraphTensor, 
-        mask: bool | None = None
-    ) -> tf.Tensor | None:
-        # if self.mask_value is None:
-        #     return None
-        _, sequence = inputs
-        sequence = self._sequence_splitter(sequence)
-        return keras.ops.not_equal(sequence, '')
-
-
-residues = {
-    "A": "N[C@@H](C)C(=O)O",
-    "C": "N[C@@H](CS)C(=O)O",
-    "C[Carbamidomethyl]": "N[C@@H](CSCC(=O)N)C(=O)O",
-    "D": "N[C@@H](CC(=O)O)C(=O)O",
-    "E": "N[C@@H](CCC(=O)O)C(=O)O",
-    "F": "N[C@@H](Cc1ccccc1)C(=O)O",
-    "G": "NCC(=O)O",
-    "H": "N[C@@H](CC1=CN=C-N1)C(=O)O",
-    "I": "N[C@@H](C(CC)C)C(=O)O",
-    "K": "N[C@@H](CCCCN)C(=O)O",
-    "K[Acetyl]": "N[C@@H](CCCCNC(=O)C)C(=O)O",
-    "K[Crotonyl]": "N[C@@H](CCCCNC(C=CC)=O)C(=O)O",
-    "K[Dimethyl]": "N[C@@H](CCCCN(C)C)C(=O)O",
-    "K[Formyl]": "N[C@@H](CCCCNC=O)C(=O)O",
-    "K[Malonyl]": "N[C@@H](CCCCNC(=O)CC(O)=O)C(=O)O",
-    "K[Methyl]": "N[C@@H](CCCCNC)C(=O)O",
-    "K[Propionyl]": "N[C@@H](CCCCNC(=O)CC)C(=O)O",
-    "K[Succinyl]": "N[C@@H](CCCCNC(CCC(O)=O)=O)C(=O)O",
-    "K[Trimethyl]": "N[C@@H](CCCC[N+](C)(C)C)C(=O)O",
-    "L": "N[C@@H](CC(C)C)C(=O)O",
-    "M": "N[C@@H](CCSC)C(=O)O",
-    "M[Oxidation]": "N[C@@H](CCS(=O)C)C(=O)O",
-    "N": "N[C@@H](CC(=O)N)C(=O)O",
-    "P": "N1[C@@H](CCC1)C(=O)O",
-    "P[Oxidation]": "N1CC(O)C[C@H]1C(=O)O",
-    "Q": "N[C@@H](CCC(=O)N)C(=O)O",
-    "R": "N[C@@H](CCCNC(=N)N)C(=O)O",
-    "R[Deamidated]": "N[C@@H](CCCNC(N)=O)C(=O)O",
-    "R[Dimethyl]": "N[C@@H](CCCNC(N(C)C)=N)C(=O)O",
-    "R[Methyl]": "N[C@@H](CCCNC(=N)NC)C(=O)O",
-    "S": "N[C@@H](CO)C(=O)O",
-    "T": "N[C@@H](C(O)C)C(=O)O",
-    "V": "N[C@@H](C(C)C)C(=O)O",
-    "W": "N[C@@H](CC(=CN2)C1=C2C=CC=C1)C(=O)O",
-    "Y": "N[C@@H](Cc1ccc(O)cc1)C(=O)O",
-    "Y[Nitro]": "N[C@@H](Cc1ccc(O)c(N(=O)=O)c1)C(=O)O",
-    "Y[Phospho]": "N[C@@H](Cc1ccc(OP(O)(=O)O)cc1)C(=O)O",
-    "[Acetyl]-A": "N(C(C)=O)[C@@H](C)C(=O)O",
-    "[Acetyl]-C": "N(C(C)=O)[C@@H](CS)C(=O)O",
-    "[Acetyl]-D": "N(C(=O)C)[C@H](C(=O)O)CC(=O)O",
-    "[Acetyl]-E": "N(C(=O)C)[C@@H](CCC(O)=O)C(=O)O",
-    "[Acetyl]-F": "N(C(C)=O)[C@@H](Cc1ccccc1)C(=O)O",
-    "[Acetyl]-G": "N(C(=O)C)CC(=O)O",
-    "[Acetyl]-H": "N(C(=O)C)[C@@H](Cc1[nH]cnc1)C(=O)O",
-    "[Acetyl]-I": "N(C(=O)C)[C@@H]([C@H](CC)C)C(=O)O",
-    "[Acetyl]-K": "N(C(C)=O)[C@@H](CCCCN)C(=O)O",
-    "[Acetyl]-L": "N(C(=O)C)[C@@H](CC(C)C)C(=O)O",
-    "[Acetyl]-M": "N(C(=O)C)[C@@H](CCSC)C(=O)O",
-    "[Acetyl]-N": "N(C(C)=O)[C@@H](CC(=O)N)C(=O)O",
-    "[Acetyl]-P": "N1(C(=O)C)CCC[C@H]1C(=O)O",
-    "[Acetyl]-Q": "N(C(=O)C)[C@@H](CCC(=O)N)C(=O)O",
-    "[Acetyl]-R": "N(C(C)=O)[C@@H](CCCN=C(N)N)C(=O)O",
-    "[Acetyl]-S": "N(C(C)=O)[C@@H](CO)C(=O)O",
-    "[Acetyl]-T": "N(C(=O)C)[C@@H]([C@H](O)C)C(=O)O",
-    "[Acetyl]-V": "N(C(=O)C)[C@@H](C(C)C)C(=O)O",
-    "[Acetyl]-W": "N(C(C)=O)[C@@H](Cc1c2ccccc2[nH]c1)C(=O)O",
-    "[Acetyl]-Y": "N(C(C)=O)[C@@H](Cc1ccc(O)cc1)C(=O)O"
-}
-
-residues_reverse = {}
-def register_peptide_residues(residues_: dict[str, str], canonicalize=True):
-    for residue, smiles in residues_.items():
-        if canonicalize:
-            smiles = Chem.MolToSmiles(Chem.MolFromSmiles(smiles))
-        residues[residue] = smiles
-        residues_reverse[residues[residue]] = residue
-    
-register_peptide_residues(residues, canonicalize=False)
-
-def _extract_residue_type(residue_tag: str) -> str:
-    pattern = r"(?<!\[)[A-Z](?![^\[]*\])"
-    return [match.group(0) for match in re.finditer(pattern, residue_tag)][0]
-
-special_residues = {}
-for key, value in residues.items():
-    special_residues[key + '-[X]'] = value.rstrip('O')
-
-register_peptide_residues(special_residues, canonicalize=False)