bioRxiv Science⌕ Search

Biology subjects

Nasimian, A.

Publications and source records attributed to Nasimian, A..

2 recordsLinked to original sources

Understanding the characteristic behavior of the wild-type and mutant protein structure of FLT3 protein by computational methods

FLT3 emerges as a commonly mutated protein with significant prognostic implications in acute myeloid leukemia (AML). Point mutations or deletions in the tyrosine kinase domain (TKD) at the activation loop and internal tandem duplications (ITD) in the juxtamembrane (JM) region (and less commonly in the TKD) are the primary mutations that occur in the FLT3 protein. Besides, AML treatment with tyrosine kinase inhibitor drugs may result in the acquisition of TKD mutations in the FLT3-ITD structure. All these mutations will induce activation of the kinase activity of FLT3 protein leading to activation of downstream signaling pathways. Therefore, finding better therapeutics against each of these mutant FLT3 proteins is crucial in the treatment of AML. This study aims to comprehend the characteristic behavior of TKD mutants (C and F in Y842), ITD mutants, and the combination of ITD with TKD mutations (C and F in Y842) in the FLT3 protein through computational approaches, including Molecular Dynamic (MD) simulation, cluster analysis, and machine learning techniques. The MD simulation studies revealed the alterations in the optimized state, flexibility, and compactness nature between FLT3-WT and mutated FLT3 proteins and identified significant changes in the point mutants, ITD, and the combined ITD and TKD mutated FLT3 protein structures. Cluster analysis also confirmed that these mutations significantly impact the overall flexibility of the protein structures, especially in the point-mutated structures of FLT3-Y842C and FLT3-ITD-Y842F. These findings emphasize the diverse protein conformations of mutated structures of the FLT3 protein, contributing to the deregulation of FLT3 protein function, and identified these mutated proteins as promising therapeutic targets in the treatment of AML.

bioinformatics↗

A Clear, Legible, Explainable, Transparent, and Elucidative (CLETE) Binary Classification Platform for Tabular Data

Therapeutic resistance continues to impede overall survival rates for those affected by cancer. Although driver genes are associated with diverse cancer types, a scarcity of instrumental methods for predicting therapy response or resistance persists. Therefore, the impetus for designing predictive tools for therapeutic response is crucial and tools based on machine learning open new opportunities. Here, we present an easily accessible platform dedicated to Clear, Legible, Explainable, Transparent, and Elucidative (CLETE) yet wholly modifiable binary classification models. Our platform encompasses both unsupervised and supervised feature selection options, hyperparameter search methodologies, under-sampling and over-sampling methods, and normalization methods, along with fifteen machine learning algorithms. The platform furnishes a k-fold receiver operating curve (ROC) - area under the curve (AUC) and accuracy plots, permutation feature importance, SHapley Additive exPlanations (SHAP) plots, and Local Interpretable Model-agnostic Explanations (LIME) plots to interpret the model and individual predictions. We have deployed a unique custom metric for hyperparameter search, which considers both training and validation scores, thus ensuring a check on under or over-fitting. Moreover, we introduce an innovative scoring method, NegLog2RMSL, which incorporates both training and test scores for model evaluation that facilitates the evaluation of models via multiple parameters. In a bid to simplify the user interface, we provide a graphical interface that sidesteps programming expertise and is compatible with both Windows and Mac OS. Platform robustness has been validated using pharmacogenomic data for 23 drugs across four diseases and holds the potential for utilization with any form of tabular data.

bioinformatics↗