QSAR‐based targeting anaplastic lymphoma kinase (ALK) variants with noncognate inhibitors in pediatric acute lymphoblastic leukemia

Abstract

Human anaplastic lymphoma kinase (ALK) is a potential target for the treatment of pediatric acute lymphoblastic leukemia. However, a number of residue mutations in ALK kinase domain have been observed to cause drug resistance in pediatric acute lymphoblastic leukemia chemotherapy. Here, a chemometrics quantitative structure‐activity relationship predictor was developed using a structure‐based panel of kinase‐inhibitor activity data. The predictor was validated rigorously through internal cross‐validation and external blind test to ensure its statistical reliability, which was then used to computationally construct a systematic activity profile of 13 noncognate kinase inhibitors against both wild‐type ALKwt and cancer‐related variants ALKvt. It is revealed that most noncognate inhibitors exhibit weak potency on ALKwt, but some of them are able to selectively target ALKvt over ALKwt. The chemometrics findings were then evaluated by using a kinase inhibition protocol; results showed that few noncognate inhibitors are 2‐ to 5‐fold higher potent against ALK variant than wild‐type kinase.

High‐throughput statistical screening of antiinfective peptides from natural antibacterial protein repertoire: Chemometric prediction, molecular modeling, and susceptibility analysis

“…Therefore, PCA analysis was applied to extract few informative latent variables from the crude variable pools and then correlated with the peptide antibacterial activity (MIC) by using support vector machine (SVM), a classical machine learning algorithm based on statistical learning theory, which aims at the structural risk minimization rather than the traditional empirical risk minimization and is especially suitable for small‐sample, high‐dimensional, and strong collinear problems . Here, the radial basis function was used as the kernel of SVM, and the optimum values of model parameter ε‐insensitive loss function, penalty c , and kernel parameter σ 2 were determined by grid‐searching method.…”

ProBiS-Fold Approach for Annotation of Human Structures from the AlphaFold Database with No Corresponding Structure in the PDB to Discover New Druggable Binding Sites

“…We have developed the Protein Binding Sites (ProBiS) tools consisting of web servers, databases, and algorithms for protein binding site and ligand prediction. These have been independently validated and compared with a number of other competing methods − and have been extensively used in pharmaceutical research. − The ProBiS algorithm compares local physicochemical and geometrical properties of protein surface structures to detect common amino acid motifs independent of the folding of the proteins. This algorithm is unique because it does not require that a binding site on a protein be known in advance but rather compares the entire surface of the protein in question to the surfaces of other proteins and identifies similar binding sites based on the local surface similarities that can be identified.…”

Statistical analysis and heuristic identification of unexpected interactions from the neurokinase‐inhibitor interactome in trigeminal neuralgia pharmacological intervention

“…Protein kinases share homologous primary sequence, conserved folding scaffold, and analogous biological function, and many kinase inhibitors therefore exhibit considerable promiscuity and broad specificity that may interact with a wide array of protein kinases and kinase mutants . It is hypothesized that certain protein kinases involved in the pathogenesis of TN can be targeted unexpectedly by multiple kinase inhibitors to elicit therapeutic potency on the disease.…”