Publications by authors named "Thanh Le Van"
The search for chemical hit material is a lengthy and increasingly expensive drug discovery process. To improve it, ligand-based quantitative structure-activity relationship models have been broadly applied to optimize primary and secondary compound properties. Although these models can be deployed as early as the stage of molecule design, they have a limited applicability domain─if the structures of interest differ substantially from the chemical space on which the model was trained, a reliable prediction will not be possible.
View Article and Find Full Text PDFArticle Synopsis
- AI is experiencing significant advancements due to machine learning breakthroughs in various fields like computer vision and natural language processing.
- A study in the European project ExCAPE focused on how well machine learning models trained on public pharmaceutical data perform when applied to internal industry data.
- The findings revealed that these models largely retain their predictive ability, with deep learning models outperforming other algorithms in industry settings, marking a key evaluation of machine learning use in pharmaceutical applications.
Aim: Diuretics are a cornerstone in treatment of heart failure (HF). Torasemide is a loop diuretic with a potential advantage over other diuretics. We aim to meta-analyse and compare the effect of torasemide with furosemide in HF patients.
View Article and Find Full Text PDFBackground: Our study aimed to compare three different percutaneous coronary intervention (PCI) approaches: culprit-only (COR) and complete (CR) revascularization - categorizing into immediate (ICR) or staged (SCR).
Methods: We searched 13 databases for randomized controlled trials. Articles were included if they compared at least two strategies.
Motivation: Subtyping cancer is key to an improved and more personalized prognosis/treatment. The increasing availability of tumor related molecular data provides the opportunity to identify molecular subtypes in a data-driven way. Molecular subtypes are defined as groups of samples that have a similar molecular mechanism at the origin of the carcinogenesis.
View Article and Find Full Text PDF