Achondroplasia (ACH) is the most frequent form of dwarfism and is caused by gain-of-function mutations in the fibroblast growth factor receptor 3–encoding (FGFR3-encoding) gene. Although potential therapeutic strategies for ACH, which aim to reduce excessive FGFR3 activation, have emerged over many years, the use of tyrosine kinase inhibitor (TKI) to counteract FGFR3 hyperactivity has yet to be evaluated. Here, we have reported that the pan-FGFR TKI, NVP-BGJ398, reduces FGFR3 phosphorylation and corrects the abnormal femoral growth plate and calvaria in organ cultures from embryos of the Fgfr3^Y367C/+ mouse model of ACH. Moreover, we demonstrated that a low dose of NVP-BGJ398, injected subcutaneously, was able to penetrate into the growth plate of Fgfr3^Y367C/+ mice and modify its organization. Improvements to the axial and appendicular skeletons were noticeable after 10 days of treatment and were more extensive after 15 days of treatment that started from postnatal day 1. Low-dose NVP-BGJ398 treatment reduced intervertebral disc defects of lumbar vertebrae, loss of synchondroses, and foramen-magnum shape anomalies. NVP-BGJ398 inhibited FGFR3 downstream signaling pathways, including MAPK, SOX9, STAT1, and PLCγ, in the growth plates of Fgfr3^Y367C/+ mice and in cultured chondrocyte models of ACH. Together, our data demonstrate that NVP-BGJ398 corrects pathological hallmarks of ACH and support TKIs as a potential therapeutic approach for ACH.

Recently, a new promising nonlinear method, the support vector machine (SVM), was proposed by Vapnik. It rapidly found numerous applications in chemistry, biochemistry and pharmacochemistry. Several attempts using SVM in drug design have been reported. It became an attractive nonlinear approach in this field. In this review, the theoretical basis of SVM in classification and regression is briefly described. Its applications in QSPR/QSAR studies, and particularly in drug design are discussed. Comparative studies with some linear and other nonlinear methods show SVMs high performance both in classification and correlation.