2026-10-08T20:32:01Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34070364 2026-10-05T14:20:10Z category_873 category_734 category_931 portal_63 item_type_3 month_year_10_2026

LASSBio-classFLOW: A Semiautomated KNIME Workflow for Classification Model Benchmarking and Virtual Screening Pedro de Sena Murteira Pinheiro (13978409) Jefferson Muniz Alves da Silva (25315965) Bárbara da Silva Mascarenhas de Jesus (23068377) Daniel Alencar Rodrigues (11730734) Lídia Moreira Lima (13978418) Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified support vector machine interactive performance evaluation https :// github consistent results across configurable class assignment based ligand screening 1190 inactive ). semiautomated knime workflow preserving user control guided model selection svm favored active classification model benchmarking model selection screening decisions model comparison class precision 750 ). 218 active therefore provides reusable environment nine algorithms nearest neighbors library prediction hyperparameter optimization flexible deployment fivefold cross fingerprints calculation dataset partitioning Machine learning-based quantitative structure–activity relationship (ML-QSAR) modeling requires consistent data preparation, validation, and model comparison. We present LASSBio-classFLOW, an open, modular, and semiautomated KNIME workflow for classification-based ligand screening. It integrates basic molecular structure preparation, configurable class assignment, descriptors and fingerprints calculation, dataset partitioning, hyperparameter optimization of nine algorithms, interactive performance evaluation, user-guided model selection, and external-library prediction. As an example, the workflow was evaluated using 1408 ROCK2 compounds from ChEMBL (218 active and 1190 inactive). Models were trained and optimized by fivefold cross-validation and evaluated on a held-out 20% test set. Support vector machine (SVM) and k-nearest neighbors (kNN) provided the most consistent results across both stages. On the held-out set, SVM favored active-class precision (0.861), whereas kNN achieved higher active recall (0.750). LASSBio-classFLOW (available at https://github.com/pedrosenamp/LASSBio-classFLOW_v1.0.git) therefore provides a transparent, reusable environment for benchmarking, comparative ML-QSAR development, and flexible deployment, while preserving user control over model selection and screening decisions. 2026-10-05T00:00:00Z Dataset Dataset 10.1021/acsomega.6c09298.s002 https://figshare.com/articles/dataset/LASSBio-classFLOW_A_Semiautomated_KNIME_Workflow_for_Classification_Model_Benchmarking_and_Virtual_Screening/34070364 CC BY-NC 4.0