A Python Library for Efficient Computation of Molecular Fingerprints
This project created a Python library that computes molecular fingerprints efficiently and provides an intuitive interface for easy integration into machine learning workflows.
Sort & Slice: A Superior Alternative to Hash-Based Folding for ECFP Substructures
Sort & Slice outperforms hash-based folding for ECFP substructure pooling, offering a simple yet effective feature selection strategy.
Drug Classification Using Text Classification Methods on Drug SMILES Strings
Treating drug SMILES as text sentences and applying basic NLP methods can lead to competitive scores in drug classification tasks.
Hierarchical Graph Explainability for Molecular Moieties in Drug Discovery
分子構造の解明を通じた薬物探索における階層的グラフ説明性の重要性。
Unveiling Molecular Moieties through Hierarchical Graph Explainability in Drug Discovery and Virtual Screening
The author presents a Graph Neural Network using Graph Convolutional architectures to accurately predict molecular properties and bioactivity. The approach includes a hierarchical Explainable AI technique to identify relevant moieties at different levels.
© 2024 by Linnk AI