MolPipeline : A python package for processing molecules with RDKit in scikit-learn

• Published in: ChemRxiv
• Main Authors: Sieg, Jochen, Feldmann, Christian Wolfgang, Hemmerich, Jennifer, Stork, Conrad, Sandfort, Frederik, Eiden, Philipp, Mathea, Miriam
• Format: Paper
• Language: English
• Published: Washington American Chemical Society 19.04.2024
• Edition: 1
• Subjects: Algorithms; Chemistry; Chemoinformatics - Computational Chemistry; Data processing; Machine Learning; Pipelines; Theoretical and Computational Chemistry; scikit-learn; RDKit; Python
• ISSN: 2573-2293
• DOI: 10.26434/chemrxiv-2024-kd11b

The open-source package scikit-learn provides various machine learning algorithms and data processing tools, including the Pipeline class, which allows users to prepend custom data transformation steps to the machine learning model. We introduce the MolPipeline package, which extends this concept to chemoinformatics by wrapping default functionalities of RDKit, such as reading and writing SMILES strings or calculating molecular descriptors from a molecule object. We aimed to build an easy-to-use Python package to create completely automated end-to-end pipelines that scale to large data sets. Particular emphasis was put on handling erroneous instances, where resolution would require manual intervention in default pipelines. In addition, we included common cheminformatics tasks, like scaffold splits and molecular standardization, natively in the pipeline framework and adaptable for the needs of various projects.