enzymetk 0.0.6__tar.gz → 0.0.7__tar.gz

{enzymetk-0.0.6 → enzymetk-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: enzymetk
-Version: 0.0.6
+Version: 0.0.7
 Home-page: https://github.com/arianemora/enzyme-tk/
 Author: Ariane Mora
 Author-email: ariane.n.mora@gmail.com
@@ -13,17 +13,22 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Python: >=3.8
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: scikit-learn
 Requires-Dist: numpy
 Requires-Dist: seaborn
 Requires-Dist: sciutil
+Requires-Dist: tqdm
 Requires-Dist: pandas
 Requires-Dist: biopython
+Requires-Dist: transformers
+Requires-Dist: torch
+Requires-Dist: huggingface_hub
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -49,8 +54,91 @@ Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperabl
 ## Install base package to import modules
 
 ```bash
+conda create --name enzymetk python==3.12 -y
 pip install enzymetk
+# Install torch for your specific cuda version
+pip install torch torchvision #--index-url https://download.pytorch.org/whl/cu130
 ```
+## If you're at the bleeding edge, and going to use older models e.g. chemBERTa2 you may need to run
+```
+pip uninstall transformers -y
+pip install "transformers<5"
+```
+
+## For each module run install the first time you're running it
+This will install as a venv where possible and conda where the tools don't allow for venvs.
+See specific tools for info.
+```
+bm = BLAST(id_col, seq_col, label_col)
+bm.install() # by default will create a venv or if needed a conda env
+```
+Note if you want to use your specific environment you can install externally and override the installed venv or conda env e.g.
+```
+bm = BLAST(id_col, seq_col, label_col)
+bm.conda = 'blast_env' # an already installed env on your computer
+bm.venv = None # so it knows to use conda i.e. forces it not to use venv
+```
+
+## Modules requiring conda
+
+- CREEP [not tested again]
+- CLEAN [not tested again]
+- ProteInfer [not tested again]
+
+## Modules able to run in venv
+- BLAST [cpu, tested with both, see notebook]
+- ChemBERTA [cpu, colab]
+- Boltz
+- Chai: conda install -c conda-forge pdbfixer
+
+- esm2/3 [cpu, see notebook]
+- foldseek [tested and works]
+- ligandmpnn
+- mmseqs [can get working...]
+- msa []
+- reaction_similarity [good, cpu]
+- rxnfp [needs specific python version so not easy in colab] hence install is with `enzymetk install rxnfp` requires conda
+- substrate_similarity [good, cpu]
+- tree
+- unimol [good, cpu]
+
+Docko git@github.com:ArianeMora/docko.git 
+ValueError: CCD component ALA not found!
+boltz predict  boltz.fasta --use_msa_server --cache ./mol
+
+srun -p gpu --qos=normal --gres=gpu:1 --pty --mem=64G  --time=000:30:00 bash
+
+pipelines: reads --> poreChop --> Flye --> Prokka --> Squidly --> Foldseek --> Boltz --> Chai
+pipelines: seqs --> BLAST --> Proteinfer --> Foldseek -->  MMseqs --> ClustalOmega --> FastTree
+pipelines: reactions --> rxnFP --> selformer --> uniMol --> chemBERTa2 --> RDkit reaction similarity
+
+
+| Module                       | Name          | Description                                                                       | Colab ipynb|
+|------------------------------|---------------|-----------------------------------------------------------------------------------|------------|
+| Metagenomics                 | PoreChop      | Used to filter adapters for nanopore sequences in metagenomics   pipeline.        | y          |
+| Metagenomics                 | Flye          | Used to assemble the metagenomes.                                                 | ?          |
+| Metagenomics                 | Prokka        | Annotation of genes within the genome.                                            | ?          |
+| Function prediction          | Proteinfer    | Annotation of genes to function (GO or EC class) using ML.                        | 33          |
+| Function prediction          | CLEAN         | Annotation of genes to EC class using ML.                                         | 11          |
+| Function prediction          | CREEP         | Annotation of genes to EC class using ML.                                         | 13          |
+| Function prediction          | Func-e        | Annotation of genes to reaction using ML.                                         | This study. |
+| Function prediction          | Squidly       | Annotation of catalytic residues using ML.                                        | 36          |
+| Embedding generation         | ESM2 & 3      | Conversion of amino acid sequence to a numerical embedding   using a PLM.         | 46,47       |
+| Embedding generation         | RxnFP         | Conversion of reaction smiles to a numerical embedding using a   language model.  | 48          |
+| Embedding generation         | Selformer     | Conversion of reaction selfies to a numerical embedding using   a language model. | 49          |
+| Embedding generation         | Uni-mol       | Conversion of molecule smiles to a numerical embedding using a   language model.  | 50          |
+| Embedding generation         | ChemBERTa2    | Conversion of reaction smiles to a numerical embedding using a   language model.  | 51          |
+| Docking                      | Chai          | Diffusion based folding of a protein and ligand.                                  | 42          |
+| Docking                      | Boltz         | Diffusion based folding of a protein and ligand.                                  | 52          |
+| Similarity                   | Diamond       | Sequence similarity calculation   using basic local alignment search.             | 53          |
+| Similarity                   | Foldseek      | Fast structure similarity search.                                                 | 54          |
+| Similarity                   | MMseqs        | Fast sequence clustering.                                                         | 55          |
+| Docking                      | StructureZyme | Alignment and calculation of structure metrics.                                   | 56          |
+| Oligo design                 | Oligopoolio   | Calculation of oligo fragments for gene assembly.                                 | This study. |
+| Sequencing                   | LevSeq        | Sequence verification of protein variants.                                        | 34          |
+| MSA generation               | ClustalOmega  | Creation of multiple sequence alignments (MSA).                                   | 57          |
+| Phylogenetic tree generation | FastTree      | Creation of multiple phylogenetic trees.                                          | 58          |
+
 
 ### Install only the specific requirements you need (recomended) 
 
@@ -121,7 +209,11 @@ The steps are the main building blocks of the pipeline. They are responsible for
 
 BLAST is a tool for searching a database of sequences for similar sequences. Here you can either pass a database that you have already created or pass the sequences as part of your dataframe and pass the label column (this needs to have two values: reference and query) reference refers to sequences that you want to search against and query refers to sequences that you want to search for.
 
-Note you need to have installed the BLAST environment.
+Note you can install 2 ways, with a conda env by command line:
+
+```
+enzymetk install_diamond
+```
 
 ```python
 id_col = 'Entry'
@@ -288,6 +380,16 @@ 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.
 
+Either in your own conda env: `pip install esm-fair` or you can run:
+
+```
+id_col = 'Entry'
+seq_col = 'Sequence'
+label_col = 'ActiveSite'
+esm = EmbedESM(id_col, seq_col, extraction_method='mean', tmp_dir='tmp', rep_num=36) # i.e. the representation number you want usually the last layer 
+esm.install() # And follow the instructions to activate the env
+```
+
 ```python
 from enzymetk.embedprotein_esm_step import EmbedESM
 from enzymetk.save_step import Save

{enzymetk-0.0.6 → enzymetk-0.0.7}/README.md

@@ -10,8 +10,91 @@ Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperabl
 ## Install base package to import modules
 
 ```bash
+conda create --name enzymetk python==3.12 -y
 pip install enzymetk
+# Install torch for your specific cuda version
+pip install torch torchvision #--index-url https://download.pytorch.org/whl/cu130
 ```
+## If you're at the bleeding edge, and going to use older models e.g. chemBERTa2 you may need to run
+```
+pip uninstall transformers -y
+pip install "transformers<5"
+```
+
+## For each module run install the first time you're running it
+This will install as a venv where possible and conda where the tools don't allow for venvs.
+See specific tools for info.
+```
+bm = BLAST(id_col, seq_col, label_col)
+bm.install() # by default will create a venv or if needed a conda env
+```
+Note if you want to use your specific environment you can install externally and override the installed venv or conda env e.g.
+```
+bm = BLAST(id_col, seq_col, label_col)
+bm.conda = 'blast_env' # an already installed env on your computer
+bm.venv = None # so it knows to use conda i.e. forces it not to use venv
+```
+
+## Modules requiring conda
+
+- CREEP [not tested again]
+- CLEAN [not tested again]
+- ProteInfer [not tested again]
+
+## Modules able to run in venv
+- BLAST [cpu, tested with both, see notebook]
+- ChemBERTA [cpu, colab]
+- Boltz
+- Chai: conda install -c conda-forge pdbfixer
+
+- esm2/3 [cpu, see notebook]
+- foldseek [tested and works]
+- ligandmpnn
+- mmseqs [can get working...]
+- msa []
+- reaction_similarity [good, cpu]
+- rxnfp [needs specific python version so not easy in colab] hence install is with `enzymetk install rxnfp` requires conda
+- substrate_similarity [good, cpu]
+- tree
+- unimol [good, cpu]
+
+Docko git@github.com:ArianeMora/docko.git 
+ValueError: CCD component ALA not found!
+boltz predict  boltz.fasta --use_msa_server --cache ./mol
+
+srun -p gpu --qos=normal --gres=gpu:1 --pty --mem=64G  --time=000:30:00 bash
+
+pipelines: reads --> poreChop --> Flye --> Prokka --> Squidly --> Foldseek --> Boltz --> Chai
+pipelines: seqs --> BLAST --> Proteinfer --> Foldseek -->  MMseqs --> ClustalOmega --> FastTree
+pipelines: reactions --> rxnFP --> selformer --> uniMol --> chemBERTa2 --> RDkit reaction similarity
+
+
+| Module                       | Name          | Description                                                                       | Colab ipynb|
+|------------------------------|---------------|-----------------------------------------------------------------------------------|------------|
+| Metagenomics                 | PoreChop      | Used to filter adapters for nanopore sequences in metagenomics   pipeline.        | y          |
+| Metagenomics                 | Flye          | Used to assemble the metagenomes.                                                 | ?          |
+| Metagenomics                 | Prokka        | Annotation of genes within the genome.                                            | ?          |
+| Function prediction          | Proteinfer    | Annotation of genes to function (GO or EC class) using ML.                        | 33          |
+| Function prediction          | CLEAN         | Annotation of genes to EC class using ML.                                         | 11          |
+| Function prediction          | CREEP         | Annotation of genes to EC class using ML.                                         | 13          |
+| Function prediction          | Func-e        | Annotation of genes to reaction using ML.                                         | This study. |
+| Function prediction          | Squidly       | Annotation of catalytic residues using ML.                                        | 36          |
+| Embedding generation         | ESM2 & 3      | Conversion of amino acid sequence to a numerical embedding   using a PLM.         | 46,47       |
+| Embedding generation         | RxnFP         | Conversion of reaction smiles to a numerical embedding using a   language model.  | 48          |
+| Embedding generation         | Selformer     | Conversion of reaction selfies to a numerical embedding using   a language model. | 49          |
+| Embedding generation         | Uni-mol       | Conversion of molecule smiles to a numerical embedding using a   language model.  | 50          |
+| Embedding generation         | ChemBERTa2    | Conversion of reaction smiles to a numerical embedding using a   language model.  | 51          |
+| Docking                      | Chai          | Diffusion based folding of a protein and ligand.                                  | 42          |
+| Docking                      | Boltz         | Diffusion based folding of a protein and ligand.                                  | 52          |
+| Similarity                   | Diamond       | Sequence similarity calculation   using basic local alignment search.             | 53          |
+| Similarity                   | Foldseek      | Fast structure similarity search.                                                 | 54          |
+| Similarity                   | MMseqs        | Fast sequence clustering.                                                         | 55          |
+| Docking                      | StructureZyme | Alignment and calculation of structure metrics.                                   | 56          |
+| Oligo design                 | Oligopoolio   | Calculation of oligo fragments for gene assembly.                                 | This study. |
+| Sequencing                   | LevSeq        | Sequence verification of protein variants.                                        | 34          |
+| MSA generation               | ClustalOmega  | Creation of multiple sequence alignments (MSA).                                   | 57          |
+| Phylogenetic tree generation | FastTree      | Creation of multiple phylogenetic trees.                                          | 58          |
+
 
 ### Install only the specific requirements you need (recomended) 
 
@@ -82,7 +165,11 @@ The steps are the main building blocks of the pipeline. They are responsible for
 
 BLAST is a tool for searching a database of sequences for similar sequences. Here you can either pass a database that you have already created or pass the sequences as part of your dataframe and pass the label column (this needs to have two values: reference and query) reference refers to sequences that you want to search against and query refers to sequences that you want to search for.
 
-Note you need to have installed the BLAST environment.
+Note you can install 2 ways, with a conda env by command line:
+
+```
+enzymetk install_diamond
+```
 
 ```python
 id_col = 'Entry'
@@ -249,6 +336,16 @@ 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.
 
+Either in your own conda env: `pip install esm-fair` or you can run:
+
+```
+id_col = 'Entry'
+seq_col = 'Sequence'
+label_col = 'ActiveSite'
+esm = EmbedESM(id_col, seq_col, extraction_method='mean', tmp_dir='tmp', rep_num=36) # i.e. the representation number you want usually the last layer 
+esm.install() # And follow the instructions to activate the env
+```
+
 ```python
 from enzymetk.embedprotein_esm_step import EmbedESM
 from enzymetk.save_step import Save

enzymetk-0.0.7/enzymetk/__init__.py

@@ -0,0 +1,122 @@
+###############################################################################
+#                                                                             #
+#    This program is free software: you can redistribute it and/or modify     #
+#    it under the terms of the GNU General Public License as published by     #
+#    the Free Software Foundation, either version 3 of the License, or        #
+#    (at your option) any later version.                                      #
+#                                                                             #
+#    This program is distributed in the hope that it will be useful,          #
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of           #
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the            #
+#    GNU General Public License for more details.                             #
+#                                                                             #
+#    You should have received a copy of the GNU General Public License        #
+#    along with this program. If not, see <http://www.gnu.org/licenses/>.     #
+#                                                                             #
+###############################################################################
+
+"""
+Author: Ariane Mora
+Date: March 2025
+"""
+__title__ = 'enzymetk'
+__description__ = 'Toolkit for enzymes and what not'
+__url__ = 'https://github.com/arianemora/enzyme-tk/'
+__version__ = '0.0.7'
+__author__ = 'Ariane Mora'
+__author_email__ = 'ariane.n.mora@gmail.com'
+__license__ = 'GPL3'
+
+
+# Core classes
+from enzymetk.step import Step, Pipeline
+from enzymetk.save_step import Save
+
+# EC Annotation
+from enzymetk.annotateEC_CLEAN_step import CLEAN
+from enzymetk.annotateEC_CREEP_step import CREEP
+from enzymetk.annotateEC_proteinfer_step import ProteInfer
+
+# Docking
+from enzymetk.dock_boltz_step import Boltz
+from enzymetk.dock_chai_step import Chai
+from enzymetk.dock_vina_step import Vina
+
+# Chemical Embeddings
+from enzymetk.embedchem_chemberta_step import ChemBERT
+from enzymetk.embedchem_rxnfp_step import RxnFP
+from enzymetk.embedchem_selformer_step import SelFormer
+from enzymetk.embedchem_unimol_step import UniMol
+
+# Protein Embeddings
+from enzymetk.embedprotein_esm_step import EmbedESM
+from enzymetk.embedprotein_esm3_step import EmbedESM3
+
+# Sequence Generation/Alignment
+from enzymetk.generate_msa_step import ClustalOmega
+from enzymetk.generate_tree_step import FastTree
+
+# Protein Design
+from enzymetk.inpaint_ligandMPNN_step import LigandMPNN
+
+# Metagenomics
+from enzymetk.metagenomics_porechop_trim_reads_step import PoreChop
+from enzymetk.metagenomics_prokka_annotate_genes import Prokka
+
+# Prediction
+from enzymetk.predict_catalyticsite_step import ActiveSitePred
+
+# Sequence Search
+from enzymetk.sequence_search_blast import BLAST
+
+# Similarity Search
+from enzymetk.similarity_foldseek_step import FoldSeek
+from enzymetk.similarity_mmseqs_step import MMseqs
+from enzymetk.similarity_reaction_step import ReactionDist
+from enzymetk.similarity_substrate_step import SubstrateDist
+
+# Structure Search (aliased to avoid conflict with similarity_foldseek_step.FoldSeek)
+from enzymetk.structure_search_foldseek import FoldSeek as StructureFoldSeek
+
+
+__all__ = [
+    # Core
+    'Step',
+    'Pipeline', 
+    'Save',
+    # EC Annotation
+    'CLEAN',
+    'CREEP',
+    'ProteInfer',
+    # Docking
+    'Boltz',
+    'Chai',
+    'Vina',
+    # Chemical Embeddings
+    'ChemBERT',
+    'RxnFP',
+    'SelFormer',
+    'UniMol',
+    # Protein Embeddings
+    'EmbedESM',
+    'EmbedESM3',
+    # Sequence Generation/Alignment
+    'ClustalOmega',
+    'FastTree',
+    # Protein Design
+    'LigandMPNN',
+    # Metagenomics
+    'PoreChop',
+    'Prokka',
+    # Prediction
+    'ActiveSitePred',
+    # Sequence Search
+    'BLAST',
+    # Similarity Search
+    'FoldSeek',
+    'MMseqs',
+    'ReactionDist',
+    'SubstrateDist',
+    # Structure Search
+    'StructureFoldSeek',
+]

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/annotateEC_CREEP_step.py

@@ -5,9 +5,12 @@ import subprocess
 import logging
 import numpy as np
 import os
+from enzymetk.step import run_script
+from pathlib import Path
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
+SCRIPT_DIR = Path(__file__).parent.resolve()
 
 """
 import os
@@ -38,9 +41,14 @@ class CREEP(Step):
         self.args_extract = args_extract
         self.args_retrieval = args_retrieval
             
+    def install(self, env_args=None):
+        # Try to automatically install CREEP conda env
+        run_script('install_CREEP.sh', verbose=True)
+        self.CREEP_dir = SCRIPT_DIR.parent.resolve() / 'conda_envs' / 'CREEP'
+        self.CREEP_cache_dir = f'{self.CREEP_dir}/data/'
+
     def __execute(self, df: pd.DataFrame, tmp_dir: str):
-        tmp_dir = '/disk1/ariane/vscode/degradeo/pipeline/tmp/'
-        input_filename = f'{tmp_dir}/creepasjkdkajshdkja.csv'
+        input_filename = f'{tmp_dir}/input.csv'
         df.to_csv(input_filename, index=False)
         cmd = ['conda', 'run', '-n', self.env_name, 'python', f'{self.CREEP_dir}scripts/step_02_extract_CREEP.py', '--pretrained_folder', 
                                  f'{self.CREEP_cache_dir}output/easy_split', 

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/annotateEC_proteinfer_step.py

@@ -5,7 +5,10 @@ from multiprocessing.dummy import Pool as ThreadPool
 from tempfile import TemporaryDirectory
 import os
 import subprocess
+from enzymetk.step import run_script
+from pathlib import Path    
 
+SCRIPT_DIR = Path(__file__).parent.resolve()
 
 class ProteInfer(Step):
     
@@ -53,6 +56,12 @@ class ProteInfer(Step):
         self.ec3_filter = ec3_filter
         self.ec4_filter = ec4_filter
         
+    def install(self, env_args=None):
+        # Try to automatically install CREEP conda env
+        run_script('install_CREEP.sh', verbose=True)
+        self.CREEP_dir = SCRIPT_DIR.parent.resolve() / 'conda_envs' / 'CREEP'
+        self.CREEP_cache_dir = f'{self.CREEP_dir}/data/'
+
     def __execute(self, data: list) -> np.array:
         df, tmp_dir = data
         # Make sure in the directory of proteinfer

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/dock_boltz_step.py

@@ -1,6 +1,5 @@
 from enzymetk.step import Step
 import pandas as pd
-from docko.boltz import run_boltz_affinity
 import logging
 import numpy as np
 from multiprocessing.dummy import Pool as ThreadPool
@@ -9,16 +8,40 @@ from multiprocessing.dummy import Pool as ThreadPool
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
+try:
+    from docko.boltz import run_boltz_affinity
+except ImportError as e:
+    print("Boltz: Needs docko package. Install with: pip install docko.")    
+
     
 class Boltz(Step):
     
-    def __init__(self, id_col: str, seq_col: str, substrate_col: str, intermediate_col: str, output_dir: str, num_threads: int):
+    def __init__(self, id_col: str, seq_col: str, substrate_col: str, intermediate_col: str, output_dir: str, 
+                num_threads: 1, env_name = None, args=None):
+        super().__init__()
         self.id_col = id_col
         self.seq_col = seq_col
         self.substrate_col = substrate_col
         self.intermediate_col = intermediate_col
         self.output_dir = output_dir or None
         self.num_threads = num_threads or 1
+        self.conda = env_name
+        self.env_name = env_name
+        self.args = args
+
+    def install(self, env_args=None):
+        # e.g. env args could by python=='3.1.1.
+        self.install_venv(env_args)
+        # Now the specific
+        try:
+            cmd = [f'{self.env_name}/bin/pip', 'install', 'docko']
+            self.run(cmd)
+        except Exception as e:
+            cmd = [f'{self.env_name}/bin/pip3', 'install', 'docko']
+            self.run(cmd)
+        self.run(cmd)
+        # Now set the venv to be the location:
+        self.venv = f'{self.env_name}/bin/python'
 
     def __execute(self, df: pd.DataFrame) -> pd.DataFrame:
         output_filenames = []
@@ -28,11 +51,15 @@ class Boltz(Step):
             if not isinstance(substrate, str):
                 substrate = ''
             print(run_id, seq, substrate)
-            run_boltz_affinity(run_id, seq, substrate, self.output_dir, intermediate)
+            if self.args:
+                run_boltz_affinity(run_id, seq, substrate, self.output_dir, intermediate, self.args)
+            else:
+                run_boltz_affinity(run_id, seq, substrate, self.output_dir, intermediate)
             output_filenames.append(f'{self.output_dir}/{run_id}/')
         return output_filenames
     
     def execute(self, df: pd.DataFrame) -> pd.DataFrame:
+        
         if self.output_dir:
             if self.num_threads > 1:
                 pool = ThreadPool(self.num_threads)

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/dock_chai_step.py

@@ -1,9 +1,13 @@
 from enzymetk.step import Step
 import pandas as pd
-from docko.chai import run_chai
+
 import logging
 import numpy as np
 
+try:
+    from docko.chai import run_chai
+except ImportError as e:
+    print("Chai: Needs docko package. Install with: pip install docko.")    
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
@@ -11,7 +15,9 @@ logger.setLevel(logging.INFO)
     
 class Chai(Step):
     
-    def __init__(self, id_col: str, seq_col: str, substrate_col: str, cofactor_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: 1, venv_name = 'enzymetk', env_name = None):
+        super().__init__()
         self.id_col = id_col
         self.seq_col = seq_col
         self.substrate_col = substrate_col
@@ -19,6 +25,21 @@ class Chai(Step):
         self.output_dir = output_dir or None
         self.num_threads = num_threads or 1
 
+    def install(self, env_args=None):
+        # e.g. env args could by python=='3.1.1.
+        self.install_venv(env_args)
+        # Now the specific
+        try:
+            cmd = [f'{self.env_name}/bin/pip', 'install', 'docko']
+            self.run(cmd)
+        except Exception as e:
+            cmd = [f'{self.env_name}/bin/pip3', 'install', 'docko']
+            self.run(cmd)
+        self.run(cmd)
+        # Now set the venv to be the location:
+        self.venv = f'{self.env_name}/bin/python'
+
+
     def __execute(self, df: pd.DataFrame, tmp_dir: str) -> pd.DataFrame:
         output_filenames = []
         for run_id, seq, substrate, cofactor in df[[self.id_col, self.seq_col, self.substrate_col, self.cofactor_col]].values:

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/dock_vina_step.py

@@ -1,12 +1,18 @@
 from enzymetk.step import Step
 import pandas as pd
-from docko.docko import *
+
 import logging
 import numpy as np
 import os
 from pathlib import Path
 from multiprocessing.dummy import Pool as ThreadPool
 
+
+try:
+    from docko.docko import *
+except ImportError as e:
+    print("Vina: Needs docko package. Install with: pip install docko.")    
+
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
@@ -14,7 +20,8 @@ logger.setLevel(logging.INFO)
 class Vina(Step):
     
     def __init__(self, id_col: str, structure_col: str, sequence_col: str, 
-                 substrate_col: str, substrate_name_col: str, active_site_col: str, output_dir: str, num_threads: int):
+                 substrate_col: str, substrate_name_col: str, active_site_col: str, output_dir: str, num_threads: 1, 
+                 venv_name = 'enzymetk', env_name = None):
         print('Expects active site residues as a string separated by |. Zero indexed.')
         self.id_col = id_col
         self.structure_col = structure_col
@@ -25,6 +32,20 @@ class Vina(Step):
         self.output_dir = Path( output_dir) or None
         self.num_threads = num_threads or 1
 
+    def install(self, env_args=None):
+        # e.g. env args could by python=='3.1.1.
+        self.install_venv(env_args)
+        # Now the specific
+        try:
+            cmd = [f'{self.env_name}/bin/pip', 'install', 'docko']
+            self.run(cmd)
+        except Exception as e:
+            cmd = [f'{self.env_name}/bin/pip3', 'install', 'docko']
+            self.run(cmd)
+        self.run(cmd)
+        # Now set the venv to be the location:
+        self.venv = f'{self.env_name}/bin/python'
+
     def __execute(self, df: pd.DataFrame) -> pd.DataFrame:
         output_filenames = []
         # ToDo: update to create from sequence if the path doesn't exist.

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/embedchem_chemberta_step.py

@@ -16,7 +16,6 @@ class ChemBERT(Step):
         self.seq_len_limit = 500
         self.embedding_len = 768
         
-        
     def __execute(self, data: list) -> np.array:
         results = []
         for v in data:

{enzymetk-0.0.6 → enzymetk-0.0.7}/enzymetk/embedchem_rxnfp_step.py

@@ -16,10 +16,28 @@ logger.setLevel(logging.INFO)
     
 class RxnFP(Step):
     
-    def __init__(self, smiles_col: str, num_threads: int, env_name: str = 'rxnfp'):
+    def __init__(self, smiles_col: str, num_threads: 1, 
+                 env_name = 'rxnfp', venv_name = None):
+        super().__init__()
         self.value_col = smiles_col
         self.num_threads = num_threads or 1
+        self.conda = env_name
         self.env_name = env_name
+        self.venv = venv_name if venv_name else f'{env_name}/bin/python'
+
+    def install(self, env_args=['--python', '3.8']):
+        # e.g. env args could by python=='3.1.1.
+        self.install_conda(env_args=env_args)
+        # Now the specific
+        try:
+            cmd = [f'pip', 'install', 'rxnfp', 'rdkit=2020.03.3', 'tmap', 'numpy==1.23', 'sciutil']
+            self.run(cmd)
+        except Exception as e:
+            cmd = [f'pip', 'install', 'rxnfp', 'rdkit=2020.03.3', 'tmap', 'numpy==1.23', 'sciutil']
+            self.run(cmd)
+        self.run(cmd)
+        # Now set the venv to be the location:
+        self.conda = f'{self.env_name}'
 
     def __execute(self, df: pd.DataFrame, tmp_dir: str) -> pd.DataFrame:
         tmp_label = ''.join(random.choices(string.ascii_letters + string.digits, k=10))
@@ -27,7 +45,7 @@ class RxnFP(Step):
         output_filename = f'{tmp_dir}/rxnfp_{tmp_label}.pkl'
         input_filename = f'{tmp_dir}/input_{tmp_label}.csv'
         df.to_csv(input_filename, index=False)
-        cmd = ['conda', 'run', '-n', self.env_name, 'python', Path(__file__).parent/'embedchem_rxnfp_run.py', '--out', output_filename, 
+        cmd = ['python', Path(__file__).parent/'embedchem_rxnfp_run.py', '--out', output_filename, 
                                 '--input', input_filename, '--label', self.value_col]
         self.run(cmd)
         # Might have an issue if the things are not correctly installed in the same dicrectory