MAYA is user-friendly and supports various input file formats (CSV, TSV, XLSX, JASON, and XML), requering only a dataset with SMILES notation, molecualr identifiers, and associated activity/property values. Users can customize the analysis by selecting specific descriptors and demensionality reduction techniques (e.g., PCA) through simple parameters setting. The tool automates the following key processes:

The script consist in a funtion that automatically implement:

1. Data curation: Ensures high-quality data by validating and preprocessing molecualr datasets.
2. Descriptors calculation: Computes structural, physicochemical, and biological descriptors for molecular characterization.
3. Tanimoto simmilarity calculation: Quantifies molecular similarity to support chemical space analysis
4. Dimensionality reduction: Applies techniques like PCA and t-SNE to reduce complexity while preserving meaningful patters.
5. 2D interactive visualization: Generates customizable, interactive plots displaying molecualr structures, PCA-derived variability, SMILES notaton, and user-defined visual attributes (e.g., point size, shape, color palette, and transparency)

MAYA's visualizations are designed to enhance intepretability, offering researchers a clear and interactive way to explore chemical spaces. The tools is particularly suited for chemoinformatics applications, such as drug discovery, where understanding complex structured-activity relationships is critical.

Here you can find more detailed information about how MAYA works

# This is an example
from maya_chem import MayaAnalyzer, MayaConfig
import numpy as np

# Crear configuración
config = MayaConfig(data_path="TEST.xlsx")

# Actualizar claves relevantes
config.data.update({
    "id_col": "molregno",
    "smiles_col": "canonical_smiles",
    "activities": ["standard_value"]
})
config.analysis["fingerprint"] = ["morgan", 'maccs']
config.analysis["reduction_method"] = ['pca']
config.viz["output_dir"] = "/content/MAYA/colab_results"

# Correr pipeline
analyzer = MayaAnalyzer(config)
results = analyzer.run(color_by='standard_value')
figs = analyzer.visualize(interactive_mode=True, color_by='standard_value')

print("✅ Pipeline completed. Check '/content/MAYA/colab_results' for outputs.")

See this notebook for more detailed usage

To perform an automated analysis of your database annotated with any activity, property, or score by constructing a chemical multiverse focused on a deeper understanding of multiple structure-activity relationships.

You can customize the descriptors and techniques used depending on the required focus. You can select which descriptors you want to use, and you can also input a similarity matrix of any desired descriptor, allowing its integration into the generated visualizations.

Access to well-documented code is provided, covering database curation processes, similarity calculations, and dimensionality reduction techniques.

1. Google Colaboratory
   The easiest way to use the script is ti open it in Google Colaboratory. The only thing needed is a Google account.
2. Local installation
   You can also setup your own local environment if you do not want to run the script through a Google service.

MAYA current supports Pythob 3.10

rdkit (2022.09.05)

matplotlib (3.7.1)

pandas (2.1.4)

seaborn (0.13.1)

sklearn (1.3.2)

Research contained in this package was supported by the Consejo Nacional de Humanidades, Ciencia y Tecnología (CONAHCYT) for the scholarship No. CVU 1340927