enzymetk 0.0.2__tar.gz → 0.0.7__tar.gz

{enzymetk-0.0.2 → enzymetk-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: enzymetk
-Version: 0.0.2
+Version: 0.0.7
 Home-page: https://github.com/arianemora/enzyme-tk/
 Author: Ariane Mora
 Author-email: ariane.n.mora@gmail.com
@@ -13,22 +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: fair-esm
 Requires-Dist: scikit-learn
 Requires-Dist: numpy
 Requires-Dist: seaborn
 Requires-Dist: sciutil
-Requires-Dist: pandas==2.1.4
+Requires-Dist: tqdm
+Requires-Dist: pandas
 Requires-Dist: biopython
-Requires-Dist: sentence_transformers
-Requires-Dist: pubchempy
-Requires-Dist: pyfaidx
-Requires-Dist: spacy
+Requires-Dist: transformers
+Requires-Dist: torch
+Requires-Dist: huggingface_hub
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -37,6 +37,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: project-url
 Dynamic: requires-dist
 Dynamic: requires-python
@@ -45,14 +46,100 @@ Dynamic: requires-python
 
 Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperable modules that act on dataframes. These modules are designed to be imported into pipelines for specific function. For this reason, `steps` as each module is called (e.g. finding similar proteins with `BLAST` would be considered a step) are designed to be as light as possible. An example of a pipeline is the [annotate-e](https://github.com/ArianeMora/annotate-e)  ` pipeline, this acts to annotate a fasta with an ensemble of methods (each is designated as an Enzyme-tk step). 
 
+
+**If you have any issues installing, let me know - this has been tested only on Linux/Ubuntu. Please post an issue!**
+
 ## Installation
 
 ## 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) 
 
 For this clone the repo and then install the requirements for the specific modules you use 
@@ -71,6 +158,7 @@ This is a work-in progress! e.g. some tools (e.g. proteInfer and CLEAN) require
 
 Here are some of the tools that have been implemented to be chained together as a pipeline:
 
+[boltz2](https://github.com/jwohlwend/boltz)
 [mmseqs2](https://github.com/soedinglab/mmseqs2)  
 [foldseek](https://github.com/steineggerlab/foldseek)  
 [diamond](https://github.com/bbuchfink/diamond)  
@@ -89,6 +177,7 @@ Here are some of the tools that have been implemented to be chained together as
 [fasttree](https://morgannprice.github.io/fasttree/)  
 [Porechop](https://github.com/rrwick/Porechop)  
 [prokka](https://github.com/tseemann/prokka)  
+
 ## Things to note
 
 All the tools use the conda env of `enzymetk` by default.
@@ -120,6 +209,12 @@ 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 can install 2 ways, with a conda env by command line:
+
+```
+enzymetk install_diamond
+```
+
 ```python
 id_col = 'Entry'
 seq_col = 'Sequence'
@@ -148,6 +243,34 @@ df = pd.DataFrame(rows, columns=[id_col, seq_col])
 print(df)
 df << (ActiveSitePred(id_col, seq_col, squidly_dir, num_threads) >> Save('tmp/squidly_as_pred.pkl'))
 
+```
+### Boltz2
+
+Boltz2 is a model for predicting structures. Note you need docko installed as I run via that.
+
+Below is an example using boltz with 4 threads, and uses a cofactor (intermediate in this case). Just set to be None for a single substrate version.
+```
+import sys
+from enzymetk.dock_boltz_step import Boltz
+from enzymetk.save_step import Save
+import pandas as pd
+import os
+os.environ['MKL_THREADING_LAYER'] = 'GNU'
+
+output_dir = 'tmp/'
+num_threads = 4
+id_col = 'Entry'
+seq_col = 'Sequence'
+substrate_col = 'Substrate'
+intermediate_col = 'Intermediate'
+
+rows = [['P0DP23_boltz_8999', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'], 
+        ['P0DP24_boltz_p1', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'],
+        ['P0DP23_boltz_p2', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'], 
+        ['P0DP24_boltz_p3', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'],
+        ['P0DP24_boltz_p4', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]']]
+df = pd.DataFrame(rows, columns=[id_col, seq_col, substrate_col, intermediate_col])
+df << (Boltz(id_col, seq_col, substrate_col, intermediate_col, f'{output_dir}', num_threads) >> Save(f'{output_dir}test.pkl'))
 ```
 
 ### Chai
@@ -257,6 +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-0.0.2 → enzymetk-0.0.7}/README.md

@@ -2,14 +2,100 @@
 
 Enzyme-tk is a collection of tools for enzyme engineering, setup as interoperable modules that act on dataframes. These modules are designed to be imported into pipelines for specific function. For this reason, `steps` as each module is called (e.g. finding similar proteins with `BLAST` would be considered a step) are designed to be as light as possible. An example of a pipeline is the [annotate-e](https://github.com/ArianeMora/annotate-e)  ` pipeline, this acts to annotate a fasta with an ensemble of methods (each is designated as an Enzyme-tk step). 
 
+
+**If you have any issues installing, let me know - this has been tested only on Linux/Ubuntu. Please post an issue!**
+
 ## Installation
 
 ## 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) 
 
 For this clone the repo and then install the requirements for the specific modules you use 
@@ -28,6 +114,7 @@ This is a work-in progress! e.g. some tools (e.g. proteInfer and CLEAN) require
 
 Here are some of the tools that have been implemented to be chained together as a pipeline:
 
+[boltz2](https://github.com/jwohlwend/boltz)
 [mmseqs2](https://github.com/soedinglab/mmseqs2)  
 [foldseek](https://github.com/steineggerlab/foldseek)  
 [diamond](https://github.com/bbuchfink/diamond)  
@@ -46,6 +133,7 @@ Here are some of the tools that have been implemented to be chained together as
 [fasttree](https://morgannprice.github.io/fasttree/)  
 [Porechop](https://github.com/rrwick/Porechop)  
 [prokka](https://github.com/tseemann/prokka)  
+
 ## Things to note
 
 All the tools use the conda env of `enzymetk` by default.
@@ -77,6 +165,12 @@ 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 can install 2 ways, with a conda env by command line:
+
+```
+enzymetk install_diamond
+```
+
 ```python
 id_col = 'Entry'
 seq_col = 'Sequence'
@@ -105,6 +199,34 @@ df = pd.DataFrame(rows, columns=[id_col, seq_col])
 print(df)
 df << (ActiveSitePred(id_col, seq_col, squidly_dir, num_threads) >> Save('tmp/squidly_as_pred.pkl'))
 
+```
+### Boltz2
+
+Boltz2 is a model for predicting structures. Note you need docko installed as I run via that.
+
+Below is an example using boltz with 4 threads, and uses a cofactor (intermediate in this case). Just set to be None for a single substrate version.
+```
+import sys
+from enzymetk.dock_boltz_step import Boltz
+from enzymetk.save_step import Save
+import pandas as pd
+import os
+os.environ['MKL_THREADING_LAYER'] = 'GNU'
+
+output_dir = 'tmp/'
+num_threads = 4
+id_col = 'Entry'
+seq_col = 'Sequence'
+substrate_col = 'Substrate'
+intermediate_col = 'Intermediate'
+
+rows = [['P0DP23_boltz_8999', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'], 
+        ['P0DP24_boltz_p1', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'],
+        ['P0DP23_boltz_p2', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'], 
+        ['P0DP24_boltz_p3', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]'],
+        ['P0DP24_boltz_p4', 'MALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAAMALWMRLLPLLALLALWGPDPAAA', 'CCCCC(CC)COC(=O)C1=CC=CC=C1C(=O)OCC(CC)CCCC', 'CC1=C(C2=CC3=C(C(=C([N-]3)C=C4C(=C(C(=N4)C=C5C(=C(C(=N5)C=C1[N-]2)C)C=C)C)C=C)C)CCC(=O)[O-])CCC(=O)[O-].[Fe]']]
+df = pd.DataFrame(rows, columns=[id_col, seq_col, substrate_col, intermediate_col])
+df << (Boltz(id_col, seq_col, substrate_col, intermediate_col, f'{output_dir}', num_threads) >> Save(f'{output_dir}test.pkl'))
 ```
 
 ### Chai
@@ -214,6 +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-0.0.2 → enzymetk-0.0.7}/enzymetk/annotateEC_CLEAN_step.py

@@ -116,7 +116,7 @@ class CLEAN(Step):
                 print(output_filenames)
                 for sub_df in output_filenames:
                     df = pd.concat([df, sub_df])
-                return df
+                return self.__filter_df(df)
             else:
-                return self.__execute([df, tmp_dir])
+                return self.__filter_df(self.__execute([df, tmp_dir]))
                 return df

{enzymetk-0.0.2 → 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 __execute(self, df: pd.DataFrame, tmp_dir: str) -> pd.DataFrame:
-        tmp_dir = '/disk1/ariane/vscode/degradeo/pipeline/tmp/'
-        input_filename = f'{tmp_dir}/creepasjkdkajshdkja.csv'
+    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):
+        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-0.0.2 → 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-0.0.7/enzymetk/dock_boltz_step.py

@@ -0,0 +1,73 @@
+from enzymetk.step import Step
+import pandas as pd
+import logging
+import numpy as np
+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: 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 = []
+        
+        for run_id, seq, substrate, intermediate in df[[self.id_col, self.seq_col, self.substrate_col, self.intermediate_col]].values:
+            # Might have an issue if the things are not correctly installed in the same dicrectory 
+            if not isinstance(substrate, str):
+                substrate = ''
+            print(run_id, seq, substrate)
+            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)
+                df_list = np.array_split(df, self.num_threads)
+                results = pool.map(self.__execute, df_list)
+            else:
+                results = self.__execute(df)
+            df['output_dir'] = results
+            return df
+        else:
+            print('No output directory provided')