enzymetk 0.0.3__py3-none-any.whl → 0.0.6__py3-none-any.whl

enzymetk/__init__.py

@@ -22,7 +22,7 @@ Date: March 2025
 __title__ = 'enzymetk'
 __description__ = 'Toolkit for enzymes and what not'
 __url__ = 'https://github.com/arianemora/enzyme-tk/'
-__version__ = '0.0.3'
+__version__ = '0.0.6'
 __author__ = 'Ariane Mora'
 __author_email__ = 'ariane.n.mora@gmail.com'
 __license__ = 'GPL3'

enzymetk/dock_chai_step.py

@@ -11,16 +11,17 @@ logger.setLevel(logging.INFO)
     
 class Chai(Step):
     
-    def __init__(self, id_col: str, seq_col: str, substrate_col: str, output_dir: str, num_threads: int):
+    def __init__(self, id_col: str, seq_col: str, substrate_col: str, cofactor_col: str, output_dir: str, num_threads: int):
         self.id_col = id_col
         self.seq_col = seq_col
         self.substrate_col = substrate_col
+        self.cofactor_col = cofactor_col
         self.output_dir = output_dir or None
         self.num_threads = num_threads or 1
 
     def __execute(self, df: pd.DataFrame, tmp_dir: str) -> pd.DataFrame:
         output_filenames = []
-        for run_id, seq, substrate in df[[self.id_col, self.seq_col, self.substrate_col]].values:
+        for run_id, seq, substrate, cofactor in df[[self.id_col, self.seq_col, self.substrate_col, self.cofactor_col]].values:
             # Might have an issue if the things are not correctly installed in the same dicrectory 
             if not isinstance(substrate, str):
                 substrate = ''
@@ -28,7 +29,8 @@ class Chai(Step):
             run_chai(run_id, # name
                     seq, # sequence
                     substrate, # ligand as smiles
-                    tmp_dir)
+                    tmp_dir,
+                    cofactor) # cofactor as smiles
             output_filenames.append(f'{tmp_dir}/{run_id}/')
         return output_filenames
     

enzymetk/dock_vina_step.py

@@ -4,6 +4,7 @@ from docko.docko import *
 import logging
 import numpy as np
 import os
+from pathlib import Path
 from multiprocessing.dummy import Pool as ThreadPool
 
 logger = logging.getLogger(__name__)
@@ -21,34 +22,66 @@ class Vina(Step):
         self.substrate_col = substrate_col
         self.substrate_name_col = substrate_name_col
         self.active_site_col = active_site_col  # Expects active site residues as a string separated by |
-        self.output_dir = output_dir or None
+        self.output_dir = Path( output_dir) or None
         self.num_threads = num_threads or 1
 
     def __execute(self, df: pd.DataFrame) -> pd.DataFrame:
         output_filenames = []
         # ToDo: update to create from sequence if the path doesn't exist.
         for label, structure_path, seq, substrate_smiles, substrate_name, residues in df[[self.id_col, self.structure_col, self.sequence_col, self.substrate_col, self.substrate_name_col, self.active_site_col]].values:
-            os.system(f'mkdir {self.output_dir}{label}')
+
             try:
+                structure_path = str(structure_path)
                 residues = str(residues)
                 residues = [int(r) + 1 for r in residues.split('|')]
-                if not os.path.exists(f'{structure_path}'):
-                    # Try get the AF2 structure we expect the label to be the uniprot id
-                    get_alphafold_structure(label, f'{self.output_dir}{label}/{label}_AF2.pdb')
-                    structure_path = f'{self.output_dir}{label}/{label}_AF2.pdb'
-                clean_one_pdb(f'{structure_path}', f'{self.output_dir}{label}/{label}.pdb')
-                pdb_to_pdbqt_protein(f'{self.output_dir}{label}/{label}.pdb', f'{self.output_dir}{label}/{label}.pdbqt')
-                score = dock(sequence='', protein_name=label, smiles=substrate_smiles, ligand_name=substrate_name, residues=residues, 
-                            protein_dir=f'{self.output_dir}', ligand_dir=f'{self.output_dir}', output_dir=f'{self.output_dir}{label}/', pH=7.4,
-                            method='vina', size_x=10.0, size_y=10.0, size_z=10.0)
-                output_filename = f'{self.output_dir}{label}/{label}.pdb'
-                output_filenames.append(output_filename)
+
+                label_dir = self.output_dir / label
+                label_dir.mkdir(parents=True, exist_ok=True)
+                structure_path = Path(structure_path)
+
+                if not structure_path.exists():
+                    # Try to download AF2 structure
+                    get_alphafold_structure(label, label_dir / f"{label}_AF2.pdb")
+                    structure_path = label_dir / f"{label}_AF2.pdb"
+
+                # Skip if still not found
+                if not structure_path.exists():
+                    print(f"Skipping {label}: AF2 structure not found.")
+                    output_filenames.append(None)
+                    continue
+            
+                # Proceed with docking
+                pdb_path = label_dir / f"{label}.pdb"
+                pdbqt_path = label_dir / f"{label}.pdbqt"
+
+                clean_one_pdb(str(structure_path), str(pdb_path))
+                pdb_to_pdbqt_protein(str(pdb_path), str(pdbqt_path))
+
+                score = dock(
+                    sequence='',
+                    protein_name=label,
+                    smiles=substrate_smiles,
+                    ligand_name=substrate_name,
+                    residues=residues,
+                    protein_dir=str(self.output_dir),
+                    ligand_dir=str(self.output_dir),
+                    output_dir=str(label_dir),
+                    pH=7.4,
+                    method='vina',
+                    size_x=10.0,
+                    size_y=10.0,
+                    size_z=10.0
+                )
+
+                output_filenames.append(str(pdb_path))
+                
             except Exception as e:
                 print(f'Error docking {label}: {e}')
                 output_filenames.append(None)
+            
         return output_filenames
-        
-    
+
+ 
     def execute(self, df: pd.DataFrame) -> pd.DataFrame:
         if self.output_dir:
             if self.num_threads > 1:
@@ -60,4 +93,4 @@ class Vina(Step):
             df['output_dir'] = results
             return df
         else:
-            print('No output directory provided')
+            print('No output directory provided')

enzymetk/embedprotein_esm3_step.py

@@ -0,0 +1,71 @@
+# ESM 3 script
+from esm.sdk.api import ESMProtein
+from tempfile import TemporaryDirectory
+import torch
+import os
+import pandas as pd
+from esm.models.esm3 import ESM3
+from esm.sdk.api import ESMProtein, SamplingConfig
+from huggingface_hub import login
+from enzymetk.step import Step
+import numpy as np
+from tqdm import tqdm 
+
+# CUDA setup
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"   # see issue #152
+cuda = True
+DEVICE = torch.device("cuda" if cuda else "cpu")
+device = DEVICE 
+
+
+class EmbedESM3(Step):
+    
+    def __init__(self, id_col: str, seq_col: str, extraction_method='mean', num_threads=1, 
+                 tmp_dir: str = None, env_name: str = 'enzymetk', save_tensors=False): # type: ignore
+        login()
+        self.client = ESM3.from_pretrained("esm3-open").to("cuda")
+        self.seq_col = seq_col
+        self.id_col = id_col
+        self.num_threads = num_threads or 1
+        self.extraction_method = extraction_method
+        self.tmp_dir = tmp_dir
+        self.env_name = env_name
+        self.save_tensors = save_tensors
+
+    def __execute(self, df: pd.DataFrame, tmp_dir: str) -> pd.DataFrame: 
+        client = self.client
+        means = []
+        for id, seq in tqdm(df[[self.id_col, self.seq_col]].values):
+            protein = ESMProtein(
+                sequence=(
+                    seq
+                )
+            )
+            protein_tensor = client.encode(protein)
+            output = client.forward_and_sample(
+                protein_tensor, SamplingConfig(return_per_residue_embeddings=True)
+            )
+            if self.save_tensors:
+                torch.save(output.per_residue_embedding, os.path.join(tmp_dir, f'{id}.pt'))
+            means.append(np.array(output.per_residue_embedding.mean(dim=0).cpu()))
+        df['esm3_mean']  = means
+        return df
+    
+    def execute(self, df: pd.DataFrame) -> pd.DataFrame:
+        if self.tmp_dir is None:
+            with TemporaryDirectory() as tmp_dir:
+                if self.num_threads > 1:
+                    dfs = []
+                    df_list = np.array_split(df, self.num_threads)
+                    for df_chunk in tqdm(df_list):
+                        dfs.append(self.__execute(df_chunk, tmp_dir))
+                    df = pd.DataFrame()
+                    for tmp_df in tqdm(dfs):
+                        df = pd.concat([df, tmp_df])
+                    return df
+                else:
+                    df = self.__execute(df, tmp_dir)
+                    return df
+        else:
+            df = self.__execute(df, self.tmp_dir)
+            return df

enzymetk/inpaint_ligandMPNN_step.py

@@ -16,7 +16,8 @@ import os
 
 class LigandMPNN(Step):
     
-    def __init__(self, pdb_column_name: str, ligand_mpnn_dir: str, output_dir: str, tmp_dir: str = None, args=None, num_threads: int = 1, env_name: str = 'ligandmpnn_env'):
+    def __init__(self, pdb_column_name: str, ligand_mpnn_dir: str, output_dir: str, 
+                 tmp_dir: str = None, args=None, num_threads: int = 1, env_name: str = 'ligandmpnn_env'):
         self.pdb_column_name = pdb_column_name
         self.ligand_mpnn_dir = ligand_mpnn_dir
         self.output_dir = output_dir
@@ -34,7 +35,7 @@ class LigandMPNN(Step):
         os.chdir(self.ligand_mpnn_dir)
         
         for pdb_file in df[ self.pdb_column_name].values:
-            cmd = ['conda', 'run', '-n', self.env_name, 'python3', f'{self.ligand_mpnn_dir}run.py', '--pdb_path', pdb_file,  '--out_folder', f'{self.output_dir}']
+            cmd = ['conda', 'run', '-n', self.env_name, 'python3', f'{self.ligand_mpnn_dir}run.py', '--pdb_path', pdb_file,  '--out_folder', f'{self.output_dir}'] 
             if self.args is not None:
                 cmd.extend(self.args)
             result = subprocess.run(cmd, check=True)

enzymetk/similarity_reaction_step.py

@@ -26,16 +26,16 @@ class ReactionDist(Step):
     def __execute(self, data: list) -> np.array:
         reaction_df = data        
         rows = []
+        fp_params = rdChemReactions.ReactionFingerprintParams()
+        rxn = rdChemReactions.ReactionFromSmarts(self.smiles_string)
+        rxn_fp = rdChemReactions.CreateStructuralFingerprintForReaction(rxn, ReactionFingerPrintParams=fp_params) #rdChemReactions.CreateStructuralFingerprintForReaction(rxn, ReactionFingerPrintParams=fp_params)
+
         # compare all fp pairwise without duplicates
         for smile_id, smiles in tqdm(reaction_df[[self.id_column_name, self.smiles_column_name]].values): # -1 so the last fp will not be used
             mol_ = rdChemReactions.ReactionFromSmarts(smiles)
-            fp_params = rdChemReactions.ReactionFingerprintParams()
             # Note: if you don't pass , ReactionFingerPrintParams=fp_params you get different results
             # i.e. reactions that don't appear to be the same are reported as similar of 1.0
             # https://github.com/rdkit/rdkit/discussions/5263
-            rxn = rdChemReactions.ReactionFromSmarts(self.smiles_string)
-
-            rxn_fp = rdChemReactions.CreateStructuralFingerprintForReaction(rxn, ReactionFingerPrintParams=fp_params)
             fps = rdChemReactions.CreateStructuralFingerprintForReaction(mol_, ReactionFingerPrintParams=fp_params)
             rows.append([smile_id,
                          self.smiles_string, 

enzymetk/similarity_substrate_step.py

@@ -1,3 +1,5 @@
+import sys
+sys.path.append('/disk1/ariane/vscode/enzyme-tk/')
 from enzymetk.step import Step
 import pandas as pd
 import numpy as np
@@ -8,6 +10,7 @@ from rdkit.Chem import rdChemReactions
 import pandas as pd
 import os
 from rdkit.DataStructs import FingerprintSimilarity
+from rdkit.Chem import rdFingerprintGenerator
 from rdkit.Chem.Fingerprints import FingerprintMols
 import random
 import string
@@ -28,12 +31,15 @@ class SubstrateDist(Step):
         tmp_label = ''.join(random.choices(string.ascii_letters + string.digits, k=10))
         
         rxn = Chem.MolFromSmiles(self.smiles_string)
-        rxn_fp = FingerprintMols.FingerprintMol(rxn)
+        # Switched to using morgan fingerprints https://greglandrum.github.io/rdkit-blog/posts/2023-01-18-fingerprint-generator-tutorial.html
+        # followed this tutorial
+        mfpgen = rdFingerprintGenerator.GetMorganGenerator(radius=2,fpSize=2048)
+        rxn_fp = mfpgen.GetFingerprint(rxn)
         rows = []
         # compare all fp pairwise without duplicates
         for smile_id, smiles in tqdm(reaction_df[[self.id_column_name, self.smiles_column_name]].values): # -1 so the last fp will not be used
             mol_ = Chem.MolFromSmiles(smiles)
-            fps = FingerprintMols.FingerprintMol(mol_)
+            fps = mfpgen.GetFingerprint(mol_)
             rows.append([smile_id, 
                          smiles, 
                          DataStructs.TanimotoSimilarity(fps, rxn_fp), 

{enzymetk-0.0.3.dist-info → enzymetk-0.0.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: enzymetk
-Version: 0.0.3
+Version: 0.0.6
 Home-page: https://github.com/arianemora/enzyme-tk/
 Author: Ariane Mora
 Author-email: ariane.n.mora@gmail.com
@@ -18,17 +18,12 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: fair-esm
 Requires-Dist: scikit-learn
 Requires-Dist: numpy
 Requires-Dist: seaborn
 Requires-Dist: sciutil
-Requires-Dist: pandas==2.1.4
+Requires-Dist: pandas
 Requires-Dist: biopython
-Requires-Dist: sentence_transformers
-Requires-Dist: pubchempy
-Requires-Dist: pyfaidx
-Requires-Dist: spacy
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier

{enzymetk-0.0.3.dist-info → enzymetk-0.0.6.dist-info}/RECORD

@@ -1,16 +1,17 @@
-enzymetk/__init__.py,sha256=M0RnPOHNcHlvlUeRzbaIZmDhumeBjnVxZHXs7s_4g7A,1575
+enzymetk/__init__.py,sha256=q1VxzDTE-F13VrPzIJjRJmwyPEaPfZyqKdkIJx406Ag,1575
 enzymetk/annotateEC_CLEAN_step.py,sha256=Id4uMtETKjvsnz58SGXlw9r-5T0TYOcvhS3Mi9xhHTw,5448
 enzymetk/annotateEC_CREEP_step.py,sha256=CZ0mh1UhVp0VShAzHnr9iifB2h1bCeMaHmBUj__t80Y,4215
 enzymetk/annotateEC_proteinfer_step.py,sha256=GTy27Z5SyG2EPvlf9HTZZ-HRG8FrAs9p0G0OCPmcIW4,6245
 enzymetk/dock_boltz_step.py,sha256=pHkJSMTgKq0deEM-_cphXlQH1VL73BvRh8JEpv8ighA,1779
-enzymetk/dock_chai_step.py,sha256=3LFnsmxmkKWesbM1pXxCUlPDDD0E93ezpojBdEEdVzw,1871
-enzymetk/dock_vina_step.py,sha256=_pPJ9ClpMYwPUl6Y7udqzrRzBJeKhENk3U3zy238PVY,3220
+enzymetk/dock_chai_step.py,sha256=YVHJHm1oAN6oOVfi7aV-6cqlQdA05yEIN0lhWAsj4oI,2011
+enzymetk/dock_vina_step.py,sha256=o1M7En9DQPMTJx5Lh29cAPkZTvD3EkNrBvFMGlT-HAo,3826
 enzymetk/embedchem_chemberta_step.py,sha256=uS7qf_adO0X_sACnCp3ULakTtepx0soHL9y6WMnaaqk,2328
 enzymetk/embedchem_rxnfp_run.py,sha256=n6ERAhql947-L0-_xvsBHLFyixjUW5yknDPHdM4CNOQ,1061
 enzymetk/embedchem_rxnfp_step.py,sha256=fmkJcuKpHllDNxkq0zV1jM2R7KREyEEG1KrVngOcvC8,2111
 enzymetk/embedchem_selformer_run.py,sha256=ibN7pbSRl1YqpHgVVaQKWpUk0E80U5ue_2dDlttn10M,1566
 enzymetk/embedchem_selformer_step.py,sha256=UQkRc6V7N1Zk3p4gR_MEKALX45bhhGw_8_xc5kM44Yw,1461
 enzymetk/embedchem_unimol_step.py,sha256=9KL4bto2O1YujZy5UpauBtGlIEUwTRMa8raVqFnX0zQ,2133
+enzymetk/embedprotein_esm3_step.py,sha256=l_8Bfyh0JgJ5R3xo2tPVgrfFBsHqoNGeIIwWwIXzPQI,2575
 enzymetk/embedprotein_esm_step.py,sha256=f99unRqyfw9Gsr2j7-7rwqtnxdYAZ3RXppLW549vpaE,5896
 enzymetk/esm-extract.py,sha256=W9n9--Pde2uUuIQP9LrPMHlLZGfpKvrJQ-SuTvGRYmc,5160
 enzymetk/filter_sequence_step.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -18,7 +19,7 @@ enzymetk/filter_structure_step.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 enzymetk/generate_msa_step.py,sha256=w-CrKPMxAwqjsbPQcRq3HP12FyiyuDq0qnt0ObsVhPk,2325
 enzymetk/generate_oligopool_step.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 enzymetk/generate_tree_step.py,sha256=eee2pILdm3lxVYTsO3CoTCwbY7MfdSK3ve84uMkLwnY,3130
-enzymetk/inpaint_ligandMPNN_step.py,sha256=t3A0znvgB44MnAQn_hebOMuhASN2qObbzYLGf8nTPbo,3013
+enzymetk/inpaint_ligandMPNN_step.py,sha256=DOHXTo6BUeEqzYsoJrS5komi1R0yMybeh5ljyRQLIGs,3032
 enzymetk/main.py,sha256=aY9dEM0a_1jnIJaRTrysLD4KqD5vWMx2OTavh3s4ZxA,1789
 enzymetk/metagenomics_porechop_trim_reads_step.py,sha256=0-wEDqMRFr5c8TtzUmbgUL6S1UgigR5oOano1l_MYDU,2156
 enzymetk/metagenomics_prokka_annotate_genes.py,sha256=VdBTkzUUwq4dMHMm-fb7CBVjTH57gRULLfrGJzqBbWg,2572
@@ -33,13 +34,13 @@ enzymetk/save_step.py,sha256=g-1XvurzUNoIRO8pNOHlvVUyTU_87JW-ZFGf5asna2A,293
 enzymetk/sequence_search_blast.py,sha256=rqtse4lG2Zeg3UgtMIV6RLu7wyv7q7w0SxPia_4N4zE,5022
 enzymetk/similarity_foldseek_step.py,sha256=_Vrvv6UCwHBP94lS9V5QX61dyxsoAr10gjp1PubXUig,6185
 enzymetk/similarity_mmseqs_step.py,sha256=FSne7ATtkPBDJzk_-c6W-ZHfGStiGNEtpWMerXlEZZU,3494
-enzymetk/similarity_reaction_step.py,sha256=4hVUMLxxkhokoVFkVcWnFfV0H_-uoG7kHIv07g3f4ZQ,2856
-enzymetk/similarity_substrate_step.py,sha256=JknH0uhLc1OKVJbnXWtBIArgthXteijl7MuGWzBqVlA,2386
+enzymetk/similarity_reaction_step.py,sha256=yQRyipdG2CyjEZ7hmr4Y-pGa32eAmxjWm4zqABCh6-g,2942
+enzymetk/similarity_substrate_step.py,sha256=Sw8C2TCDHLMoYeay69bj6p_dKhmpMV4hBUkm4pYBBxQ,2732
 enzymetk/step.py,sha256=LmcIyUh7XFxyt2P2LwtFJZ8Ca9Nyo7nLz6dRejHxkoc,1762
-enzymetk-0.0.3.data/data/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-enzymetk-0.0.3.dist-info/licenses/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-enzymetk-0.0.3.dist-info/METADATA,sha256=eFL4-SCDtyE50Admu1H5f29liYHXr04WDc31NBb-9Co,23068
-enzymetk-0.0.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-enzymetk-0.0.3.dist-info/entry_points.txt,sha256=RU3pSTXg2RyNLlc0asRpBYRkmv5GpRP7teeDY7Tr7e0,52
-enzymetk-0.0.3.dist-info/top_level.txt,sha256=Qct8wLw9EjZ4yfKaKeJHBjWWuoK_FwHZgbIBb6PwBgg,9
-enzymetk-0.0.3.dist-info/RECORD,,
+enzymetk-0.0.6.data/data/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+enzymetk-0.0.6.dist-info/licenses/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+enzymetk-0.0.6.dist-info/METADATA,sha256=vgGo4q5EI_j-lv9EMy16BJOIuiaTgZcC1xMGdLRAc80,22931
+enzymetk-0.0.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+enzymetk-0.0.6.dist-info/entry_points.txt,sha256=RU3pSTXg2RyNLlc0asRpBYRkmv5GpRP7teeDY7Tr7e0,52
+enzymetk-0.0.6.dist-info/top_level.txt,sha256=Qct8wLw9EjZ4yfKaKeJHBjWWuoK_FwHZgbIBb6PwBgg,9
+enzymetk-0.0.6.dist-info/RECORD,,