Structure-guided expansion of kinase fragment libraries driven by support vector machine models

Fragment-Based Design of Kinase Inhibitors: A Practical Guide

“…This gave us confi dence to utilize predicted binding modes from previously crystallized kinase inhibitors of the same or similar scaffold in library design. This method of predicted binding mode was utilized in the de novo design of several kinase libraries and fragment expansion using the predicted binding modes led to the synthesis of several kinase active libraries [ 68 ]. The analysis is based on alignment of kinases proteins X-ray structures from the PDB in a common frame of reference Since many excellent reviews on FBLD and FBDD have been published showcasing very successful and elegant practical kinase inhibitor examples [ 36 , 69 , 70 ], here only a few recent reports of the various FBDD strategies are summarized, see Table 2 .…”

Computational Methods in Drug Discovery

“…The final library included compounds predicted to have some activity against kinase targets and showed good hit rates against six different kinases. These compounds, however, did not exhibit the desirable specificity, and the authors suggested that more specific pharmacophores may be necessary (Erickson et al, 2010). Rolland et al (2005) used a similar strategy to design a library that could be screened with GPCR targets.…”

“…This strategy has been used to create several libraries directed at particular target types. For example, Erickson et al (2010) generated seven libraries meant to be screened for kinase inhibitors. The group initially generated a fragment library from over 1400 Fig.…”

Predicting network of drug–enzyme interaction based on machine learning method

“…SVM was originally developed by Vapnik et al [57][58][59][60][61] and has been successfully and widely used in a number of biological classification problems [62][63][64][65][66][67][68][69][70][71]. SVM is based on the structure risk minimization (SRM) principle from statistical learning theory [57].…”