Skip to content
DraconiticResearch
Search Sources API
179,152 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BY 4.0ACS Omega

LASSBio-classFLOW: A Semiautomated KNIME Workflow for Classification Model Benchmarking and Virtual Screening

  • Pedro de Sena Murteira Pinheiro1
  • Jefferson Muniz Alves da Silva1
  • Bárbara da Silva Mascarenhas de Jesus1
  • Daniel Alencar Rodrigues2
  • Lídia Moreira Lima1
  1. 1Universidade Federal do Rio de Janeiro , , Av. Carlos Chagas Filho, 373─Cidade Universitária−CCS , , ,
  2. 2Royal College of Surgeons in Ireland , , 123 St Stephen’s Green , ,
Read full textPDFDOICite

Abstract

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.

Related

  1. Development of a Screening Workflow for the Halogenation of Nitrogen Heterocycles with Vanadium-Dependent Haloperoxidases.
    Carter U Brzezinski, Sergio A Solis, Hannah S Slocumb +2
    ACS bio & med chem AuPeer-reviewedCC BYFull textInorganic & organometallic chemistryEurope PMC
  2. A Validated SEM-EDS Workflow for Screening Rare High-Mg Minerals in Fine-Grained Chang’e-6 Lunar Soil
    Jiangyan Yuan, Kaihui Shi, Yi Chen +2
    ACS OmegaPeer-reviewedCC BY-NC-ND 4.0Full textMaterials & polymersCrossrefDOAJ
  3. AGENTi: APCI-ESI Analyte Ionization Fidelity Pre-Screening Workflow using Multimodel Inference.
    Mithony Keng, Kenneth M Merz
    Journal of chemical information and modelingPeer-reviewedCC BYFull textPhysical chemistryEurope PMC
  4. Benchmarking Vision–Language and Vision Foundation Models for Few-Shot Defect Screening in PEM Fuel-Cell SEM Micrographs
    Sami Ekici, Turab Selçuk, Masud Kabir
    BatteriesPeer-reviewedCC BY 4.0Electrochemistry & energyCrossref
  5. Two barriers to benchmarking structure-based virtual screening against the AcrB efflux pump: a sample-size ceiling and an identifiability failure
    Ibrahim Ibrahim Shuaibu
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{pinheiro2026lassbioclassflow,
  title = {{LASSBio-classFLOW: A Semiautomated KNIME Workflow for Classification Model Benchmarking and Virtual Screening}},
  author = {Pedro de Sena Murteira Pinheiro and Jefferson Muniz Alves da Silva and Bárbara da Silva Mascarenhas de Jesus and Daniel Alencar Rodrigues and Lídia Moreira Lima},
  journal = {ACS Omega},
  year = {2026},
  month = oct,
  doi = {10.1021/acsomega.6c09298},
  url = {https://pubs.acs.org/acsodf/article/11/41/64107/5444587/LASSBio-classFLOW-A-Semiautomated-KNIME-Workflow},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - LASSBio-classFLOW: A Semiautomated KNIME Workflow for Classification Model Benchmarking and Virtual Screening
AU  - Pedro de Sena Murteira Pinheiro
AU  - Jefferson Muniz Alves da Silva
AU  - Bárbara da Silva Mascarenhas de Jesus
AU  - Daniel Alencar Rodrigues
AU  - Lídia Moreira Lima
PY  - 2026
DA  - 2026/10/05
JO  - ACS Omega
DO  - 10.1021/acsomega.6c09298
UR  - https://pubs.acs.org/acsodf/article/11/41/64107/5444587/LASSBio-classFLOW-A-Semiautomated-KNIME-Workflow
AB  - 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.
SN  - 2470-1343
ER  -