stanscofi and benchscofi: a new standard for drug repurposing by collaborative filtering - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Open Source Software Année : 2024

stanscofi and benchscofi: a new standard for drug repurposing by collaborative filtering

Résumé

Drug development is still a time-consuming and costly process as of today, while the failure rate in the successful commercialization of drug candidates is high. Drug repurposing is an approach which screens currently available chemical compounds and tool molecules to uncover novel therapeutic indications. In particular, collaborative filtering has sparked interest, as this framework allows us to deal with implicit information on drug-disease associations. As popular as drug repurposing might be, the lack of standard training, validation pipelines and benchmark datasets hinders the development and assessment of drug repurposing methods. To overcome this issue, we propose the Python package stanscofi (STANdard for drug Screening in COllaborative FIltering), which permits the quick implementation of ready-to-go drug repurposing models and ensures proper training and validation of the methods. We also built the Python package benchscofi (BENCHmark for drug Screening in COllaborative FIltering) upon stanscofi to implement several algorithms from the state-of-the-art and enable the first large-scale benchmark of the field.
Fichier principal
Vignette du fichier
10.21105.joss.05973.pdf (211.46 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY NC ND - Paternité - Pas d'utilisation commerciale - Pas de modification

Dates et versions

hal-04329740 , version 1 (07-12-2023)
hal-04329740 , version 2 (26-01-2024)

Identifiants

Citer

Clémence Réda, Jill-Jênn Vie, Olaf Wolkenhauer. stanscofi and benchscofi: a new standard for drug repurposing by collaborative filtering. Journal of Open Source Software, 2024, 9 (93), pp.5973. ⟨10.21105/joss.05973⟩. ⟨hal-04329740v2⟩
50 Consultations
48 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More