melite 0.2.0

Tabular classification benchmarking toolkit for model selection, repeated stratified cross-validation, final model export, and artifact-based inference.

MELITE: Multi-model Evaluation and Learning for Inference-ready Tabular Experiments

MELITE is a pre-stable Python toolkit for tabular classification benchmarking, model selection, repeated stratified cross-validation, final model export, and artifact-based inference.

MELITE is tabular at the modeling level. The learning algorithms consume numeric X and y arrays, so the feature matrix may come from PCA, UMAP, fingerprints, descriptors, clinical variables, experimental measurements, industrial features, or manually selected numeric features.

Project Identity

Project: MELITE
PyPI distribution: melite
Import package: melite
CLI: melite
Version: 0.2.0
License: LGPL-3.0-or-later
Status: alpha / pre-stable

Documentation

The live documentation is published at:

https://nanobiostructuresrg.github.io/melite/

Key pages:

• Installation
• Quick Start
• CLI Reference
• Configuration
• API Reference

Installation

After PyPI publication:

python -m pip install melite

For local development:

git clone https://github.com/NanoBiostructuresRG/melite.git
cd melite
python -m pip install -e .

For development and documentation tools:

python -m pip install -e ".[dev]"
python -m pip install -e ".[docs]"

Quick Start

Run a fast smoke benchmark with the bundled synthetic example dataset:

melite run --smoke --config examples/example_config.toml

Export a selected model artifact:

melite export --row 0 --csv examples/output/results.csv --outdir examples/output/

Run artifact-based inference:

import numpy as np
from melite import predict

X_new = np.load("examples/sample_PCA70.npz")["X"]
result = predict("examples/output/Model_SVC_sample_pca70.pkl", X_new)
print(result["predictions"])
print(result["probabilities"])

Scope

MELITE does	MELITE does not
Accept prepared X and y arrays.	Generate fingerprints.
Benchmark SVC, Random Forest, and XGBoost classifiers.	Process SMILES.
Select the best row by F1-macro.	Generate PCA or UMAP reductions from raw data.
Export a final retrained .pkl model.	Act as a general AutoML framework.
Run artifact-based inference through predict().	Promise a stable 1.0 API yet.
Handle any numeric tabular matrix.	Generate or validate domain-specific descriptors.

Datasets are registered as concrete tabular matrix candidates under [datasets.<dataset_id>]. The dataset_id is user-defined and is used in results.csv, figures, and exported model filenames.

[datasets.morgan_r2_2048]
path = "data/morgan_r2_2048.npz"
label_path = "raw/labels.npy"
family = "fingerprints"
method = "Morgan"
variant = "r2_2048"

[datasets.rdkit_descriptors]
path = "data/rdkit_descriptors.npz"
label_path = "raw/labels.npy"
family = "descriptors"
method = "RDKit"

[datasets.pca85]
path = "data/PCA85.npz"
label_path = "raw/labels.npy"
family = "dimensionality"
method = "PCA"
level = 85

Each registered dataset must define path and label_path. Optional metadata fields are family, method, variant, level, and description; they are reported for traceability and do not drive special-case model execution. Registered datasets are loaded strictly: missing files, missing X, non-2D or non-numeric X, length mismatches, and embedded y mismatches fail the run. Legacy [benchmark].reduction_types and levels configs are still accepted and are normalized into equivalent dataset entries such as PCA70 and UMAP90.

CLI

melite --help
melite run --help
melite export --help
melite --version

Common commands:

melite run
melite run --smoke
melite run --config my_config.toml
melite export --row 0
melite export --config my_config.toml --row 0
melite export --row 0 --force

Public API

from melite import Config
from melite import load_datasets
from melite import plot_cv_distributions
from melite import predict
from melite import __version__

Modules not listed above are importable directly but are not part of the public contract and may change before 0.2.0.

Input Format

raw/labels.npy          <- target vector y, shape (n_samples,)
data/morgan_r2_2048.npz <- required key: X, optional key: y
data/rdkit_descriptors.npz
data/PCA85.npz
data/UMAP90.npz

Each .npz file must contain an X array. If an embedded y array is present, MELITE validates it against the configured label_path.

Outputs

output/
|-- results.txt
|-- results.csv
|-- Model_<model>_<dataset>.pkl
`-- figures/
    `-- <model>_<dataset>.png

Local inputs and generated artifacts such as raw/, data/, output/, .pkl, and .joblib files are intentionally ignored by Git.

Validation

The current dev/v0.2.0 branch targets:

python -m pytest tests/ -v --basetemp=.review_pytest_tmp -o cache_dir=.review_pytest_cache
mkdocs build --strict
python -m build
python -m twine check dist/*
melite --help
melite run --help
melite export --help
melite --version

Citation

If you use MELITE in your research, please cite it using the metadata in CITATION.cff.

Contreras-Torres, F. F., & Murrieta, A. C. (2026). MELITE: Multi-model
Evaluation and Learning for Inference-ready Tabular Experiments (0.1.11).
Tecnologico de Monterrey. https://github.com/NanoBiostructuresRG/melite

Authors

Developed by Flavio F. Contreras-Torres

Tecnologico de Monterrey

Co-author: Ana C. Murrieta

Tecnologico de Monterrey

License

This project is licensed under the terms of the GNU Lesser General Public License v3.0 or later.

SPDX identifier: LGPL-3.0-or-later