enzymetk 0.0.1__tar.gz → 0.0.2__tar.gz

{enzymetk-0.0.1 → enzymetk-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: enzymetk
-Version: 0.0.1
+Version: 0.0.2
 Home-page: https://github.com/arianemora/enzyme-tk/
 Author: Ariane Mora
 Author-email: ariane.n.mora@gmail.com
@@ -47,22 +47,28 @@ Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperabl
 
 ## Installation
 
+## Install base package to import modules
+
 ```bash
-source enzymetk/conda_envs/install_all.sh
+pip install enzymetk
 ```
 
-## Install subsets of enzyme-tk
+### Install only the specific requirements you need (recomended) 
 
+For this clone the repo and then install the requirements for the specific modules you use 
 ```bash
 git clone git@github.com:ArianeMora/enzyme-tk.git
-python setup.py sdist bdist_wheel
-pip install dist/enzymetk-0.0.1.tar.gz
+cd enzymetk/conda_envs/ # would recommend looking at thes
+# e.g. to install all from within that folder you would do
+source install_all.sh
 ```
 
 ## Usage
 
 If you have any issues at all just email me using my caltech email: `amora at caltech . edu`
 
+This is a work-in progress! e.g. some tools (e.g. proteInfer and CLEAN) require extra data to be downloaded in order to run (like model weights.) I'm working on integrating these atm, buzz me if you need this!
+
 Here are some of the tools that have been implemented to be chained together as a pipeline:
 
 [mmseqs2](https://github.com/soedinglab/mmseqs2)  
@@ -169,8 +175,8 @@ df << (Chai(id_col, seq_col, substrate_col, f'{output_dir}', num_threads) >> Sav
 ChemBERTa2 encodes reactions and SMILES strings into a vector space. Note this requires the base environment, i.e. `enzymetk` conda env.
 
 ```python
-from steps.embedchem_chemberta_step import ChemBERT
-from steps.save_step import Save
+from enzymetk.embedchem_chemberta_step import ChemBERT
+from enzymetk.save_step import Save
 
 output_dir = 'tmp/'
 num_threads = 1
@@ -180,7 +186,7 @@ substrate_col = 'Substrate'
 rows = [['P0DP23', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC'], 
         ['P0DP24', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC']]
 df = pd.DataFrame(rows, columns=[id_col, seq_col, substrate_col])
-df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl'))
+new_df = (df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl')))
 ```
 
 ### CLEAN
@@ -206,11 +212,11 @@ df << (CLEAN(id_col, seq_col, clean_dir, num_threads=num_threads) >> Save(f'clea
 ```
 ### ClustalOmega
 
-ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path.
+ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path. You need to have installed it first (check out the `conda_envs` directory in enzymetk.)
 
 ```python
-from steps.generate_msa_step import ClustalOmega
-from steps.save_step import Save
+from enzymetk.generate_msa_step import ClustalOmega
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -230,8 +236,8 @@ df << (ClustalOmega(id_col, seq_col) >> Save('tmp/clustalomega_test.pkl'))
 CREEP is a tool for predicting the EC number of a reaction. At the moment it only supports reactions to EC however we are extending this to other modalities. 
 
 ```python
-from steps.annotateEC_CREEP_step import CREEP
-from steps.save_step import Save
+from enzymetk.annotateEC_CREEP_step import CREEP
+from enzymetk.save_step import Save
 import pandas as pd
 
 # CREEP expects you to have downloaded the data from the zotero page and put it in the data/CREEP folder
@@ -252,8 +258,8 @@ df << (CREEP(id_col, reaction_col, CREEP_cache_dir='/disk1/share/software/CREEP/
 EmbedESM is a tool for embedding a set of sequences using ESM2.
 
 ```python
-from steps.embedprotein_esm_step import EmbedESM
-from steps.save_step import Save
+from enzymetk.embedprotein_esm_step import EmbedESM
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -280,8 +286,8 @@ If you pass a database, you need to pass the path to the database.
 The columns expect a path to a pdb file i.e. the output from the `Chai` step.
 
 ```python
-from steps.similarity_foldseek_step import FoldSeek
-from steps.save_step import Save
+from enzymetk.similarity_foldseek_step import FoldSeek
+from enzymetk.save_step import Save
 import pandas as pd
 
 # id_col: str, seq_col: str, proteinfer_dir: str,

{enzymetk-0.0.1 → enzymetk-0.0.2}/README.md

@@ -4,22 +4,28 @@ Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperabl
 
 ## Installation
 
+## Install base package to import modules
+
 ```bash
-source enzymetk/conda_envs/install_all.sh
+pip install enzymetk
 ```
 
-## Install subsets of enzyme-tk
+### Install only the specific requirements you need (recomended) 
 
+For this clone the repo and then install the requirements for the specific modules you use 
 ```bash
 git clone git@github.com:ArianeMora/enzyme-tk.git
-python setup.py sdist bdist_wheel
-pip install dist/enzymetk-0.0.1.tar.gz
+cd enzymetk/conda_envs/ # would recommend looking at thes
+# e.g. to install all from within that folder you would do
+source install_all.sh
 ```
 
 ## Usage
 
 If you have any issues at all just email me using my caltech email: `amora at caltech . edu`
 
+This is a work-in progress! e.g. some tools (e.g. proteInfer and CLEAN) require extra data to be downloaded in order to run (like model weights.) I'm working on integrating these atm, buzz me if you need this!
+
 Here are some of the tools that have been implemented to be chained together as a pipeline:
 
 [mmseqs2](https://github.com/soedinglab/mmseqs2)  
@@ -126,8 +132,8 @@ df << (Chai(id_col, seq_col, substrate_col, f'{output_dir}', num_threads) >> Sav
 ChemBERTa2 encodes reactions and SMILES strings into a vector space. Note this requires the base environment, i.e. `enzymetk` conda env.
 
 ```python
-from steps.embedchem_chemberta_step import ChemBERT
-from steps.save_step import Save
+from enzymetk.embedchem_chemberta_step import ChemBERT
+from enzymetk.save_step import Save
 
 output_dir = 'tmp/'
 num_threads = 1
@@ -137,7 +143,7 @@ substrate_col = 'Substrate'
 rows = [['P0DP23', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC'], 
         ['P0DP24', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC']]
 df = pd.DataFrame(rows, columns=[id_col, seq_col, substrate_col])
-df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl'))
+new_df = (df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl')))
 ```
 
 ### CLEAN
@@ -163,11 +169,11 @@ df << (CLEAN(id_col, seq_col, clean_dir, num_threads=num_threads) >> Save(f'clea
 ```
 ### ClustalOmega
 
-ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path.
+ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path. You need to have installed it first (check out the `conda_envs` directory in enzymetk.)
 
 ```python
-from steps.generate_msa_step import ClustalOmega
-from steps.save_step import Save
+from enzymetk.generate_msa_step import ClustalOmega
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -187,8 +193,8 @@ df << (ClustalOmega(id_col, seq_col) >> Save('tmp/clustalomega_test.pkl'))
 CREEP is a tool for predicting the EC number of a reaction. At the moment it only supports reactions to EC however we are extending this to other modalities. 
 
 ```python
-from steps.annotateEC_CREEP_step import CREEP
-from steps.save_step import Save
+from enzymetk.annotateEC_CREEP_step import CREEP
+from enzymetk.save_step import Save
 import pandas as pd
 
 # CREEP expects you to have downloaded the data from the zotero page and put it in the data/CREEP folder
@@ -209,8 +215,8 @@ df << (CREEP(id_col, reaction_col, CREEP_cache_dir='/disk1/share/software/CREEP/
 EmbedESM is a tool for embedding a set of sequences using ESM2.
 
 ```python
-from steps.embedprotein_esm_step import EmbedESM
-from steps.save_step import Save
+from enzymetk.embedprotein_esm_step import EmbedESM
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -237,8 +243,8 @@ If you pass a database, you need to pass the path to the database.
 The columns expect a path to a pdb file i.e. the output from the `Chai` step.
 
 ```python
-from steps.similarity_foldseek_step import FoldSeek
-from steps.save_step import Save
+from enzymetk.similarity_foldseek_step import FoldSeek
+from enzymetk.save_step import Save
 import pandas as pd
 
 # id_col: str, seq_col: str, proteinfer_dir: str,

{enzymetk-0.0.1 → enzymetk-0.0.2}/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__ = '0.0.1'
+__version__ = '0.0.2'
 __author__ = 'Ariane Mora'
 __author_email__ = 'ariane.n.mora@gmail.com'
 __license__ = 'GPL3'

{enzymetk-0.0.1 → enzymetk-0.0.2}/enzymetk/predict_catalyticsite_run.py

@@ -11,7 +11,7 @@ def run_as_inference(output_dir, fasta_file, squidly_dir, toks_per_batch, as_thr
     elif esm2_model == "esm2_t48_15B_UR50D":
         cr_model_as = cr_model_as or f"{squidly_dir}Squidly_CL_15B.pt"
         lstm_model_as = lstm_model_as or f"{squidly_dir}Squidly_LSTM_15B.pth"
-    as_threshold = 0.99
+    as_threshold = 0.97
     #esm2_model = "esm2_t48_15B_UR50D"
     # 	python /scratch/project/squid/code_modular/SQUIDLY_run_model_LSTM.py ${FILE} ${ESM2_MODEL} ${CR_MODEL_AS}
     # ${LSTM_MODEL_AS} ${OUT} --toks_per_batch ${TOKS_PER_BATCH} --AS_threshold ${AS_THRESHOLD} --monitor

{enzymetk-0.0.1 → enzymetk-0.0.2}/enzymetk/sequence_search_blast.py

@@ -3,6 +3,7 @@ Step to run multiple sequence alignment with the Clustal Omega tool.
  ./clustalo -i /home/helen/degradeo/pipeline/helen_data/sequences_test_fasta.txt
 """
 from enzymetk.step import Step
+import logging
 
 import pandas as pd
 import numpy as np
@@ -12,10 +13,17 @@ import os
 import subprocess
 import random
 import string
+from tqdm import tqdm 
+
+
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+
 
 class BLAST(Step):
     
-    def __init__(self, id_col: str, sequence_col: str, label_col=None, database=None, mode='blastp', args=None, tmp_dir=None):
+    def __init__(self, id_col: str, sequence_col: str, label_col=None, database=None,
+                 mode='blastp', args=None, tmp_dir=None, num_threads=1):
         self.id_col = id_col
         self.seq_col = sequence_col
         self.label_col = label_col  # This is whether it is query or reference
@@ -23,6 +31,7 @@ class BLAST(Step):
         self.database = database
         self.args = args
         self.tmp_dir = tmp_dir
+        self.num_threads = num_threads
         if self.database is None and self.label_col is None:
             raise ValueError('Database is not set, you can pass a database that you have already created see diamond for more information or the sequences \
                              as part of your dataframe and pass the label column (this needs to have two values: reference and query) reference \
@@ -74,7 +83,27 @@ class BLAST(Step):
         return df
 
     def execute(self, df: pd.DataFrame) -> pd.DataFrame:
-        if self.tmp_dir is not None:
-            return self.__execute([df, self.tmp_dir])
         with TemporaryDirectory() as tmp_dir:
-            return self.__execute([df, tmp_dir])
+            tmp_dir = self.tmp_dir if self.tmp_dir is not None else tmp_dir
+            if self.num_threads > 1:
+                output_filenames = []
+                df_list = np.array_split(df, self.num_threads)
+                for df_chunk in tqdm(df_list):
+                    try:
+                        output_filenames.append(self.__execute([df_chunk, tmp_dir]))
+                    except Exception as e:
+                         logger.error(f"Error in executing ESM2 model: {e}")
+                         continue
+                df = pd.DataFrame()
+                for sub_df in output_filenames:
+                    df = pd.concat([df, sub_df])
+                return df
+            
+            else:
+                return self.__execute([df, tmp_dir])
+            
+    # def execute(self, df: pd.DataFrame) -> pd.DataFrame:
+    #     if self.tmp_dir is not None:
+    #         return self.__execute([df, self.tmp_dir])
+    #     with TemporaryDirectory() as tmp_dir:
+    #         return self.__execute([df, tmp_dir])

{enzymetk-0.0.1 → enzymetk-0.0.2}/enzymetk/similarity_foldseek_step.py

@@ -7,13 +7,17 @@ repo and then copy it out of it.
 """
 from enzymetk.step import Step
 
-
+import logging
 import pandas as pd
 import numpy as np
 from tempfile import TemporaryDirectory
 import subprocess
 import random
 import string
+from tqdm import tqdm 
+
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
 
 
 def process_clustering(filename, df, id_column_name):
@@ -34,13 +38,14 @@ def process_clustering(filename, df, id_column_name):
 class FoldSeek(Step):
     
     def __init__(self, id_column_name: str, query_column_name: str, reference_database: str, method='search', query_type='structures', 
-                 args=None, tmp_dir: str = None):
+                 args=None, num_threads=1, tmp_dir: str = None):
         self.query_column_name = query_column_name
         self.id_column_name = id_column_name
         self.reference_database = reference_database # pdb should be the default
         self.tmp_dir = tmp_dir
         self.method = method
         self.args = args
+        self.num_threads = num_threads
         self.query_type = query_type
         if self.method not in ['search', 'cluster']:
             print('Method must be in "search" or "cluster". Will likely fail... ')
@@ -107,8 +112,24 @@ class FoldSeek(Step):
         return df
     
     def execute(self, df: pd.DataFrame) -> pd.DataFrame:
-        if self.tmp_dir is not None:
-            return self.__execute([df, self.tmp_dir])
         with TemporaryDirectory() as tmp_dir:
-            return self.__execute([df, tmp_dir])
-            return df
+            tmp_dir = self.tmp_dir if self.tmp_dir is not None else tmp_dir
+            if self.num_threads > 1:
+                output_filenames = []
+                df_list = np.array_split(df, self.num_threads)
+                for df_chunk in tqdm(df_list):
+                    try:
+                        output_filenames.append(self.__execute([df_chunk, tmp_dir]))
+                    except Exception as e:
+                         logger.error(f"Error in executing ESM2 model: {e}")
+                         continue
+                df = pd.DataFrame()
+                print(output_filenames)
+                for p in output_filenames:
+                    sub_df = pd.read_pickle(p)
+                    df = pd.concat([df, sub_df])
+                return df
+            
+            else:
+                output_filename = self.__execute([df, tmp_dir])
+                return pd.read_pickle(output_filename)

{enzymetk-0.0.1 → enzymetk-0.0.2}/enzymetk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: enzymetk
-Version: 0.0.1
+Version: 0.0.2
 Home-page: https://github.com/arianemora/enzyme-tk/
 Author: Ariane Mora
 Author-email: ariane.n.mora@gmail.com
@@ -47,22 +47,28 @@ Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperabl
 
 ## Installation
 
+## Install base package to import modules
+
 ```bash
-source enzymetk/conda_envs/install_all.sh
+pip install enzymetk
 ```
 
-## Install subsets of enzyme-tk
+### Install only the specific requirements you need (recomended) 
 
+For this clone the repo and then install the requirements for the specific modules you use 
 ```bash
 git clone git@github.com:ArianeMora/enzyme-tk.git
-python setup.py sdist bdist_wheel
-pip install dist/enzymetk-0.0.1.tar.gz
+cd enzymetk/conda_envs/ # would recommend looking at thes
+# e.g. to install all from within that folder you would do
+source install_all.sh
 ```
 
 ## Usage
 
 If you have any issues at all just email me using my caltech email: `amora at caltech . edu`
 
+This is a work-in progress! e.g. some tools (e.g. proteInfer and CLEAN) require extra data to be downloaded in order to run (like model weights.) I'm working on integrating these atm, buzz me if you need this!
+
 Here are some of the tools that have been implemented to be chained together as a pipeline:
 
 [mmseqs2](https://github.com/soedinglab/mmseqs2)  
@@ -169,8 +175,8 @@ df << (Chai(id_col, seq_col, substrate_col, f'{output_dir}', num_threads) >> Sav
 ChemBERTa2 encodes reactions and SMILES strings into a vector space. Note this requires the base environment, i.e. `enzymetk` conda env.
 
 ```python
-from steps.embedchem_chemberta_step import ChemBERT
-from steps.save_step import Save
+from enzymetk.embedchem_chemberta_step import ChemBERT
+from enzymetk.save_step import Save
 
 output_dir = 'tmp/'
 num_threads = 1
@@ -180,7 +186,7 @@ substrate_col = 'Substrate'
 rows = [['P0DP23', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC'], 
         ['P0DP24', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC']]
 df = pd.DataFrame(rows, columns=[id_col, seq_col, substrate_col])
-df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl'))
+new_df = (df << (ChemBERT(id_col, substrate_col, num_threads) >> Save(f'{output_dir}chemberta.pkl')))
 ```
 
 ### CLEAN
@@ -206,11 +212,11 @@ df << (CLEAN(id_col, seq_col, clean_dir, num_threads=num_threads) >> Save(f'clea
 ```
 ### ClustalOmega
 
-ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path.
+ClustalOmega is a tool for aligning a set of sequences. This gets installed to the system (expecting a linux machine) and added to the bash path. You need to have installed it first (check out the `conda_envs` directory in enzymetk.)
 
 ```python
-from steps.generate_msa_step import ClustalOmega
-from steps.save_step import Save
+from enzymetk.generate_msa_step import ClustalOmega
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -230,8 +236,8 @@ df << (ClustalOmega(id_col, seq_col) >> Save('tmp/clustalomega_test.pkl'))
 CREEP is a tool for predicting the EC number of a reaction. At the moment it only supports reactions to EC however we are extending this to other modalities. 
 
 ```python
-from steps.annotateEC_CREEP_step import CREEP
-from steps.save_step import Save
+from enzymetk.annotateEC_CREEP_step import CREEP
+from enzymetk.save_step import Save
 import pandas as pd
 
 # CREEP expects you to have downloaded the data from the zotero page and put it in the data/CREEP folder
@@ -252,8 +258,8 @@ df << (CREEP(id_col, reaction_col, CREEP_cache_dir='/disk1/share/software/CREEP/
 EmbedESM is a tool for embedding a set of sequences using ESM2.
 
 ```python
-from steps.embedprotein_esm_step import EmbedESM
-from steps.save_step import Save
+from enzymetk.embedprotein_esm_step import EmbedESM
+from enzymetk.save_step import Save
 import pandas as pd
 
 id_col = 'Entry'
@@ -280,8 +286,8 @@ If you pass a database, you need to pass the path to the database.
 The columns expect a path to a pdb file i.e. the output from the `Chai` step.
 
 ```python
-from steps.similarity_foldseek_step import FoldSeek
-from steps.save_step import Save
+from enzymetk.similarity_foldseek_step import FoldSeek
+from enzymetk.save_step import Save
 import pandas as pd
 
 # id_col: str, seq_col: str, proteinfer_dir: str,