👤 Muzafar A Macha

The viability of cells and the integrity of the genome depend on the detection and repair of damaged DNA through intricate mechanisms. Cancer treatment employs chemotherapy or radiation therapy to eliminate neoplastic cells by causing substantial damage to their DNA. In many cases, improved DNA repair mechanisms lead to resistance to these medicines; therefore, it is essential to expand efforts to develop drugs that can sensitise cells to these treatments by inhibiting the DNA repair process. Multiple studies have demonstrated a correlation between the overexpression of Apurinic/Apyrimidinic Endonuclease (APE1), the primary mammalian enzyme responsible for excising apurinic or apyrimidinic sites in DNA, and the resistance of cells to cancer therapies; in contrast, APE1 downregulation increases cellular susceptibility to DNA-damaging agents. Thus, the effectiveness of existing therapies can be improved by promoting the targeted sensitization of cancer cells while protecting healthy cells. The current study aims to employ explainable artificial intelligence (XAI) to enhance the accuracy and reliability of machine learning models for the prediction of APE1 inhibitors. Various ML-based regression models are employed to predict the pIC50 value of different medicines. Bayesian optimization and the Permutation Feature Importance (PFI) approach are employed to determine the best hyperparameters of machine learning models and to discover the most significant features for recognizing drug candidates that target APE1 enzymes, respectively. To acquire comprehensive elucidations for the predictive models in our research, two XAI methodologies, namely SHAP and LIME, are used. The SHAP analysis reveals that the features 'C1SP2' and 'ASP-2' are essential in influencing the model's predictions. The SHAP values demonstrate variability for features such as 'maxHBint2' and 'GATS1s,' signifying that their impact is dependent on specific instances within the dataset. The LIME study corroborates these findings, demonstrating that 'C1SP2' and 'ASP-2' are the most significant positive contributors, whereas features like 'SHCHnX,' 'nHdCH2,' and 'GATS1s' result in a decrease in the predicted values. Due to the limited sample size of the APE1 dataset, direct training on this dataset posed challenges in model generalization and reliability. To overcome this limitation, the BACE-1 dataset is leveraged for model training, enabling the ML models to learn from a more extensive and diverse chemical space. Among the tested algorithms, XGBoost demonstrated superior predictive performance, achieving R Show less

Protein ubiquitination is one of the most crucial posttranslational modifications responsible for regulating the stability and activity of proteins involved in homeostatic cellular function. Inconsistencies in the ubiquitination process may lead to tumorigenesis. Ubiquitin-specific peptidases are attractive therapeutic targets in different cancers and are being evaluated for clinical development. Ubiquitin-specific peptidase 37 (USP37) is one of the least studied members of the USP family. USP37 controls numerous aspects of oncogenesis, including stabilizing many different oncoproteins. Recent work highlights the role of USP37 in stimulating the epithelial-mesenchymal transition and metastasis in lung and breast cancer by stabilizing SNAI1 and stimulating the sonic hedgehog pathway, respectively. Several aspects of USP37 biology in cancer cells are yet unclear and are an active area of research. This review emphasizes the importance of USP37 in cancer and how identifying its molecular targets and signalling networks in various cancer types can help advance cancer therapeutics. Show less

Plasma HDL-cholesterol and apolipoprotein A-I (apoA-I) levels are strongly inversely associated with cardiovascular disease. However, the structure and protein composition of HDL particles is complex, as native and synthetic discoidal and spherical HDL particles can have from two to five apoA-I molecules per particle. To fully understand structure-function relationships of HDL, a method is required that is capable of directly determining the number of apolipoprotein molecules in heterogeneous HDL particles. Chemical cross-linking followed by SDS polyacrylamide gradient gel electrophoresis has been previously used to determine apolipoprotein stoichiometry in HDL particles. However, this method yields ambiguous results due to effects of cross-linking on protein conformation and, subsequently, its migration pattern on the gel. Here, we describe a new method based on cross-linking chemistry followed by MALDI mass spectrometry that determines the absolute mass of the cross-linked complex, thereby correctly determining the number of apolipoprotein molecules in a given HDL particle. Using well-defined, homogeneous, reconstituted apoA-I-containing HDL, apoA-IV-containing HDL, as well as apoA-I/apoA-II-containing HDL, we have validated this method. The method has the capability to determine the molecular ratio and molecular composition of apolipoprotein molecules in complex reconstituted HDL particles. Show less