Review

bemis murcko scaffold split (Bemis Inc)

About

News

Press Release

Team

Advisors

Partners

Contact

Bioz Stars

Bioz vStars

Buy from Supplier

Structured Review

Bemis Inc bemis murcko scaffold split
Bemis Murcko Scaffold Split, supplied by Bemis Inc, used in various techniques. Bioz Stars score: 86/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/product/a+split/bemis+murcko+scaffolds/pm42210816-61-15-15
Average 86 stars, based on 1 article reviews

bemis murcko scaffold split - by Bioz Stars, 2026-11

86/100 stars

Images

other:

Article Title: ANNalog: generation of MedChem-similar molecules.
Article Snippet: An additional analysis was performed based on Bemis–Murcko scaffolds, identifying that within the training set, 321,494 molecule pairs (66%) contained distinct scaffolds.

Article Title: Physics-informed deep learning for molecular solubility prediction: integrating thermodynamic constraints with neural network architectures.
Article Snippet: Following standard practice [17,52], we use random split (80/10/10 train/val/test) and scaffold split (Bemis-Murcko scaffolds assigned entirely to train or test) to evaluate extrapolation.

Article Title: HYG-mol: An Interpretable Multimodal Hypergraph Framework for Molecular Property Prediction
Article Snippet: To rigorously assess the model’s generalization capability, all datasets were partitioned using the structure-based Bemis–Murcko scaffold splitting strategy [ ], in which molecules are grouped according to their core scaffolds to minimize information leakage between structurally similar compounds across data splits.

Biomarker Discovery:

Article Title: TxConformal: Controlling False Discoveries in AI-Driven Therapeutic Discovery
Article Snippet: .. We perform scaffold splits using Bemis–Murcko scaffolds with an 80/10/10 train/validation/test partition on SMILES ( create_scaffold_split ), and then further split the training portion 90/10 into train/validation for model fitting, leaving the original 10% validation split as the calibration set and the held-out 10% as the test set. ..

Article Title: XGBPred-ACSM: A Hybrid Descriptor-Driven XGBoost Framework for Anticancer Small Molecule Prediction
Article Snippet: .. To further assess the generalizability of the developed ML models for structures outside of closely related chemical structures, an additional scaffold-based validation was carried out using the Bemis–Murcko framework. ..

Activity Assay:

Article Title: Systematic Benchmarking of Kinase Bioactivity Models Across Splitting Strategies and Protein Representations
Article Snippet: .. Using a curated ChEMBL-derived kinase activity dataset of 352,874 records across 507 human protein kinase targets, we evaluated all models under three splitting strategies of increasing stringency: random, scaffold-based (Bemis–Murcko), and target-held-out. ..

Concentration Assay:

Article Title: A Leakage-Aware Drug Discovery Workflow for PKM2 and MAPK1 Integrating Scaffold Validation, Molecular Docking and Structural Triage.
Article Snippet: .. Bemis–Murcko scaffolds were used to summarize active-scaffold concentration and to support scaffold-aware split construction. ..