vantami 0.4.3__tar.gz

vantami-0.4.3/LICENSE

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2025, Mateusz Iwan
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

vantami-0.4.3/PKG-INFO

@@ -0,0 +1,143 @@
+Metadata-Version: 2.4
+Name: vantami
+Version: 0.4.3
+Summary: A collection of ML/AI tools for chemistry applications.
+Home-page: https://github.com/MateuszIwan/VantaMI
+Author: Mateusz Iwan
+Author-email: mateusz.iwan@hotmail.com
+Project-URL: Source, https://github.com/M-Iwan/VantaMI
+Project-URL: Bug Tracker, https://github.com/M-Iwan/VantaMI/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=2.4
+Requires-Dist: pandas>=3.0
+Requires-Dist: polars>=1.40
+Requires-Dist: matplotlib>=3.10
+Requires-Dist: seaborn>=0.13
+Requires-Dist: scipy>=1.17
+Provides-Extra: full
+Requires-Dist: scikit-learn>=1.8; extra == "full"
+Requires-Dist: rdkit>=2026.03; extra == "full"
+Requires-Dist: transformers>=5.5; extra == "full"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+![](files/NovaMI.png)
+
+### What is this repository?
+A collection of ML/AI code for chemistry applications developed during my PhD.
+
+If you find the repo or its parts useful, it can be installed using:
+`pip install vantami`
+
+Full install:
+
+`pip install "vantami[full]"`
+
+The usual versioning conventions are followed loosely, with minor version bumps usually meaning a substantial update to a specific module.
+
+### Repository Structure
+Last updated on version: 0.4.3
+
+```
+vantami/
+├── deprecated/   Old code kept because it might be useful one day (incl. MMMTGNN in deep/mmmtgnn.py)
+├── dev/  New stuff I'm working on
+├── dist/  PyPI distribution files
+├── environments/   Environments for special-need code (CDDD, Mordred) 
+├── vantami/
+│   ├── cache.py  Functions for caching required data
+│   ├── api/
+│   │   ├── convert.py   Conversion from IUPAC names to SMILES using OPSIN
+│   │   └── resolve.py   Get SMILES from name using PubChem, CIR, or (WIP) CAS
+│   ├── chemistry/
+│   │   └── molecule.py   Standardize molecule, embed it in 3D, and dock using SMINA
+│   ├── cli/
+│   │   ├── CDDD.py   CLI wrapper for CDDD descriptors
+│   │   ├── CIR.py   CLI wrapper of CIR name resolver
+│   │   ├── Dock.py  Wrapper for molecule.py
+│   │   ├── MolStandardizer.py   Molecule standardization using RDKit
+│   │   ├── Mordred.py   CLI wrapper for Mordred descriptors
+│   │   └── OptunaOptimization.py   Old code for Optuna optimization.
+│   ├── data/
+│   │   ├── cluster.py   Clustering using Butina/Murcko/Connected Components algorithms
+│   │   ├── descriptors.py   Descriptor calculations: ECFP, MACCS, Klek, CDDD, RDKit, Mordred, ChemBERTa, MAPC
+│   │   ├── filter.py   Filter outliers based on molecular parameters
+│   │   ├── manager.py   Main class for managing data during training and inference
+│   │   ├── manipulate.py   Helper functions for checks/data manipulation  
+│   │   ├── partition.py   Partitioning algoriths; convenience wrappers around scikit-learn and cluster.py
+│   │   ├── similarity.py   Parallel distance matrix / k-neighbors calculations
+│   │   └── transform.py   Main class for normalizing/processing data before training
+│   ├── deep/  PyTorch stack: MMTUnit + MMDataset + MMLoader (legacy MMMTGNN under deprecated/deep/)
+│   │   ├── dataset.py   MMDataset / MMBatch for multi-modal Polars-backed samples
+│   │   ├── loader.py   MMLoader (collate → MMBatch)
+│   │   ├── models.py   MMTUnit base class and concrete units (e.g. TestModel)
+│   │   ├── modules.py   GNN/CNN/RNN/linear builders used by units
+│   │   ├── utils.py   Activations and small helpers
+│   │   └── vectorizer.py   GraphVectorizer, StringVectorizer (legacy MMGV → deprecated.deep.mmgv)
+│   ├── io/
+│   │   ├── database.py   Preprocessing of ChEMBL and BindingDB files
+│   │   └── file.py   IO functions for several formats I'm using; works with Pandas/Polars DFs
+│   ├── metrics/
+│   │   └── modellability.py   MODI index
+│   ├── ml/
+│   │   ├── augood.py   AU-GOOD framework for model's performance evaluation
+│   │   ├── evaluate.py   Code for simple unit/ensemble evaluations
+│   │   ├── models.py   Self-contained, sklearn-compatibile models and ensembles; I'm very happy with this one :)
+│   │   ├── optimize.py   Hyperparameter optimization; functions at the top of the file are outdated
+│   │   ├── params.py   Pre-defined parameters for Optuna
+│   │   ├── score.py   Functions for scoring models; Outdated, now included with Unit and Ensemble classes
+│   │   ├── select.py   Sequential feature selection; Outdated
+│   │   └── utils.p   Helper functions for building Units from just names of models and descriptors
+│   ├── nlp/  
+│   │   ├── article.py   Article class for retrieving metadata based on DOI/Names
+│   │   ├── cluster.py   Latent Dirichlet Allocation for abstract-based clustering
+│   │   └── tokenize.py   Word and document tokenizers
+│   ├── standardize/   
+│   │   ├── clean.py   Wrappers around RDKit functions for standaradizing SMILES
+│   │   ├── duplicates.py   Duplicate processing based on Median Absolute Deviation
+│   │   ├── filter.py   Filter based on selected features
+│   │   └── validate.py   Structure validation and error finding
+│   ├── stats/
+│   │   ├── tests.py   Statistical tests
+│   │   └── utils.py   Helper functions
+│   └── visualize/
+│       ├── ecdf.py   Emprical Cumulative Distribution Function of molecular inter-distance 
+│       ├── embedding.py   t-SNE and UMAP
+│       ├── performance.py   WIP: AU-GOOD framework-related plots
+│       ├── predictions.py   Bunch of plots for assessing model performance; currently only Regression
+│       ├── properties.py   Plot and compare molecular properties between datasets
+│       └── utils.py   Helper functions and my custom palette
+├── vantami-r/
+│   └── R/
+│       └── lmm.R  Linear Mixed Models code
+├── projects/
+│   ├── cddd_setup   Files for setting up CDDD environment anywhere
+│   ├── osmordred_setup   WIP: Corrected Mordred descriptors
+│   └── qcg_template   Template for QCG PilotJob training on bigger scale (one node)
+├── temp/   Storage for temporary files
+├── tests/   Whatever I'm developing at the moment
+├── .gitignore   
+├── CHANGELOG.md   List of more important changes between versions
+├── code_dev.ipynb   Currently tested/developed additions
+├── LICENSE   
+├── pyproject.toml  
+├── README.md   This file!
+└── setup.py   Most of required libraries, some day I *might* add specific versions.
+```

vantami-0.4.3/README.md

@@ -0,0 +1,103 @@
+![](files/NovaMI.png)
+
+### What is this repository?
+A collection of ML/AI code for chemistry applications developed during my PhD.
+
+If you find the repo or its parts useful, it can be installed using:
+`pip install vantami`
+
+Full install:
+
+`pip install "vantami[full]"`
+
+The usual versioning conventions are followed loosely, with minor version bumps usually meaning a substantial update to a specific module.
+
+### Repository Structure
+Last updated on version: 0.4.3
+
+```
+vantami/
+├── deprecated/   Old code kept because it might be useful one day (incl. MMMTGNN in deep/mmmtgnn.py)
+├── dev/  New stuff I'm working on
+├── dist/  PyPI distribution files
+├── environments/   Environments for special-need code (CDDD, Mordred) 
+├── vantami/
+│   ├── cache.py  Functions for caching required data
+│   ├── api/
+│   │   ├── convert.py   Conversion from IUPAC names to SMILES using OPSIN
+│   │   └── resolve.py   Get SMILES from name using PubChem, CIR, or (WIP) CAS
+│   ├── chemistry/
+│   │   └── molecule.py   Standardize molecule, embed it in 3D, and dock using SMINA
+│   ├── cli/
+│   │   ├── CDDD.py   CLI wrapper for CDDD descriptors
+│   │   ├── CIR.py   CLI wrapper of CIR name resolver
+│   │   ├── Dock.py  Wrapper for molecule.py
+│   │   ├── MolStandardizer.py   Molecule standardization using RDKit
+│   │   ├── Mordred.py   CLI wrapper for Mordred descriptors
+│   │   └── OptunaOptimization.py   Old code for Optuna optimization.
+│   ├── data/
+│   │   ├── cluster.py   Clustering using Butina/Murcko/Connected Components algorithms
+│   │   ├── descriptors.py   Descriptor calculations: ECFP, MACCS, Klek, CDDD, RDKit, Mordred, ChemBERTa, MAPC
+│   │   ├── filter.py   Filter outliers based on molecular parameters
+│   │   ├── manager.py   Main class for managing data during training and inference
+│   │   ├── manipulate.py   Helper functions for checks/data manipulation  
+│   │   ├── partition.py   Partitioning algoriths; convenience wrappers around scikit-learn and cluster.py
+│   │   ├── similarity.py   Parallel distance matrix / k-neighbors calculations
+│   │   └── transform.py   Main class for normalizing/processing data before training
+│   ├── deep/  PyTorch stack: MMTUnit + MMDataset + MMLoader (legacy MMMTGNN under deprecated/deep/)
+│   │   ├── dataset.py   MMDataset / MMBatch for multi-modal Polars-backed samples
+│   │   ├── loader.py   MMLoader (collate → MMBatch)
+│   │   ├── models.py   MMTUnit base class and concrete units (e.g. TestModel)
+│   │   ├── modules.py   GNN/CNN/RNN/linear builders used by units
+│   │   ├── utils.py   Activations and small helpers
+│   │   └── vectorizer.py   GraphVectorizer, StringVectorizer (legacy MMGV → deprecated.deep.mmgv)
+│   ├── io/
+│   │   ├── database.py   Preprocessing of ChEMBL and BindingDB files
+│   │   └── file.py   IO functions for several formats I'm using; works with Pandas/Polars DFs
+│   ├── metrics/
+│   │   └── modellability.py   MODI index
+│   ├── ml/
+│   │   ├── augood.py   AU-GOOD framework for model's performance evaluation
+│   │   ├── evaluate.py   Code for simple unit/ensemble evaluations
+│   │   ├── models.py   Self-contained, sklearn-compatibile models and ensembles; I'm very happy with this one :)
+│   │   ├── optimize.py   Hyperparameter optimization; functions at the top of the file are outdated
+│   │   ├── params.py   Pre-defined parameters for Optuna
+│   │   ├── score.py   Functions for scoring models; Outdated, now included with Unit and Ensemble classes
+│   │   ├── select.py   Sequential feature selection; Outdated
+│   │   └── utils.p   Helper functions for building Units from just names of models and descriptors
+│   ├── nlp/  
+│   │   ├── article.py   Article class for retrieving metadata based on DOI/Names
+│   │   ├── cluster.py   Latent Dirichlet Allocation for abstract-based clustering
+│   │   └── tokenize.py   Word and document tokenizers
+│   ├── standardize/   
+│   │   ├── clean.py   Wrappers around RDKit functions for standaradizing SMILES
+│   │   ├── duplicates.py   Duplicate processing based on Median Absolute Deviation
+│   │   ├── filter.py   Filter based on selected features
+│   │   └── validate.py   Structure validation and error finding
+│   ├── stats/
+│   │   ├── tests.py   Statistical tests
+│   │   └── utils.py   Helper functions
+│   └── visualize/
+│       ├── ecdf.py   Emprical Cumulative Distribution Function of molecular inter-distance 
+│       ├── embedding.py   t-SNE and UMAP
+│       ├── performance.py   WIP: AU-GOOD framework-related plots
+│       ├── predictions.py   Bunch of plots for assessing model performance; currently only Regression
+│       ├── properties.py   Plot and compare molecular properties between datasets
+│       └── utils.py   Helper functions and my custom palette
+├── vantami-r/
+│   └── R/
+│       └── lmm.R  Linear Mixed Models code
+├── projects/
+│   ├── cddd_setup   Files for setting up CDDD environment anywhere
+│   ├── osmordred_setup   WIP: Corrected Mordred descriptors
+│   └── qcg_template   Template for QCG PilotJob training on bigger scale (one node)
+├── temp/   Storage for temporary files
+├── tests/   Whatever I'm developing at the moment
+├── .gitignore   
+├── CHANGELOG.md   List of more important changes between versions
+├── code_dev.ipynb   Currently tested/developed additions
+├── LICENSE   
+├── pyproject.toml  
+├── README.md   This file!
+└── setup.py   Most of required libraries, some day I *might* add specific versions.
+```

vantami-0.4.3/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"

vantami-0.4.3/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

vantami-0.4.3/setup.py

@@ -0,0 +1,50 @@
+from pathlib import Path
+from setuptools import setup, find_packages
+
+ROOT = Path(__file__).parent
+README = ROOT / "README.md"
+
+package_data: dict[str, list[str]] = {
+    "novami": ["files/klekota_roth.joblib"],
+}
+
+setup(
+    name="vantami",
+    version="0.4.3",
+    author="Mateusz Iwan",
+    author_email="mateusz.iwan@hotmail.com",
+    description="A collection of ML/AI tools for chemistry applications.",
+    long_description=README.read_text(encoding="utf-8"),
+    long_description_content_type="text/markdown",
+    url="https://github.com/MateuszIwan/VantaMI",
+    project_urls={
+        "Source": "https://github.com/M-Iwan/VantaMI",
+        "Bug Tracker": "https://github.com/M-Iwan/VantaMI/issues",
+    },
+    packages=find_packages(),
+    include_package_data=False,
+    package_data=package_data,
+    install_requires=[
+        "numpy >= 2.4",
+        "pandas >= 3.0",
+        "polars >= 1.40",
+        "matplotlib >= 3.10",
+        "seaborn >= 0.13",
+        "scipy >= 1.17",
+    ],
+    extras_require={
+        "full": [
+            "scikit-learn >= 1.8",
+            "rdkit >= 2026.03",
+            "transformers >= 5.5",
+        ],
+    },
+    python_requires=">=3.13",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Operating System :: OS Independent",
+        "Intended Audience :: Science/Research",
+        "Topic :: Scientific/Engineering :: Chemistry",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    ]
+)

vantami-0.4.3/vantami/__init__.py

@@ -0,0 +1,12 @@
+from vantami import api
+from vantami import chemistry
+from vantami import cli
+from vantami import data
+from vantami import deep
+from vantami import io
+from vantami import metrics
+from vantami import nlp
+from vantami import standardize
+from vantami import ml
+from vantami import stats
+from vantami import visualize

vantami-0.4.3/vantami/api/convert.py

@@ -0,0 +1,45 @@
+import os
+import json
+
+import polars as pl
+
+
+def opsin_convert(df: pl.DataFrame, opsin_paths: str, name_col: str = 'Name', out_col: str = 'SMILES'):
+    """
+    Convert IUPAC names to SMILES
+
+    Parameters
+    ----------
+
+    df: pl.DataFrame
+        A polars DataFrame
+    opsin_paths: str
+        Path to a JSON file containing paths for OPSIN-related files. Must contain path to opsin .jar file ['opsin']
+        and to a directory with read/write permission ['io']
+    name_col: str
+        Name of the column with IUPAC names of chemicals
+    out_col: str
+        Name of the column for output
+    """
+
+    with open(opsin_paths, 'r') as file:
+        paths = json.load(file)
+
+    in_path = os.path.join(paths['io'], 'names_in.txt')
+    out_path = os.path.join(paths['io'], 'names_out.txt')
+
+    names = df[name_col].to_list()
+
+    with open(in_path, 'w') as f:
+        for name in names:
+            f.write(name + '\n')
+
+    open(out_path, 'w')
+
+    command = f"java -jar {paths['opsin']} -osmi {in_path} {out_path}"
+    os.system(command)
+
+    smiles = open(out_path, 'r').readlines()
+
+    df = df.with_columns(pl.Series(out_col, smiles))
+    return df