Drug responses in cancer are diverse due to heterogenous genomic profiles. Drug responsiveness prediction is important in clinical response to specific cancer treatments. Recently, multi-class drug responsiveness models based on deep learning (DL) models using molecular fingerprints and mutation statuses have emerged. However, for multi-class models for drug responsiveness prediction, comparisons between convolution neural network (CNN) models (e.g., AlexNet and GoogLeNet) have not been performed. Therefore, in this study, we compared the two CNN models, GoogLeNet and AlexNet, along with the least absolute shrinkage and selection operator (LASSO) model as a baseline model. We constructed the models by taking drug molecular fingerprints of drugs and cell line mutation statuses, as input, to predict high-, intermediate-, and low-class for half-maximal inhibitory concentration (IC50) values of the drugs in the cancer cell lines. Additionally, we compared the models in breast cancer patients as well as in an independent gastric cancer cell line drug responsiveness data. We measured the model performance based on the area under receiver operating characteristic (ROC) curves (AUROC) value. In this study, we compared CNN models for multi-class drug responsiveness prediction. The AlexNet and GoogLeNet showed better performances in comparison to LASSO. Thus, DL models will be useful tools for precision oncology in terms of drug responsiveness prediction.

Cybersecurity increasingly relies on machine learning (ML) models to respond to and detect attacks. However, the rapidly changing data environment makes model life-cycle management after deployment essential. Real-time detection of drift signals from various threats is fundamental for effectively managing deployed models. However, detecting drift in unsupervised environments can be challenging. This study introduces a novel approach leveraging Shapley additive explanations (SHAP), a widely recognized explainability technique in ML, to address drift detection in unsupervised settings. The proposed method incorporates a range of plots and statistical techniques to enhance drift detection reliability and introduces a drift suspicion metric that considers the explanatory aspects absent in the current approaches. To validate the effectiveness of the proposed approach in a real-world scenario, we applied it to an environment designed to detect domain generation algorithms (DGAs). The dataset was obtained from various types of DGAs provided by NetLab. Based on this dataset composition, we sought to validate the proposed SHAP-based approach through drift scenarios that occur when a previously deployed model detects new data types in an environment that detects real-world DGAs. The results revealed that more than 90% of the drift data exceeded the threshold, demonstrating the high reliability of the approach to detect drift in an unsupervised environment. The proposed method distinguishes itself from existing approaches by employing explainable artificial intelligence (XAI)-based detection, which is not limited by model or system environment constraints. In conclusion, this paper proposes a novel approach to detect drift in unsupervised ML settings for cybersecurity. The proposed method employs SHAP-based XAI and a drift suspicion metric to improve drift detection reliability. It is versatile and suitable for various real-time data analysis contexts beyond DGA detection environments. This study significantly contributes to the ML community by addressing the critical issue of managing ML models in real-world cybersecurity settings. Our approach is distinguishable from existing techniques by employing XAI-based detection, which is not limited by model or system environment constraints. As a result, our method can be applied in critical domains that require adaptation to continuous changes, such as cybersecurity. Through extensive validation across diverse settings beyond DGA detection environments, the proposed method will emerge as a versatile drift detection technique suitable for a wide range of real-time data analysis contexts. It is also anticipated to emerge as a new approach to protect essential systems and infrastructures from attacks.

Protein kinases are central targets in drug discovery, yet early-stage development of potent and selective inhibitors remains challenging due to high experimental costs and limited interpretability of large-scale screening data. Here, we present DeepKinomeWeb, an integrated web-based platform that transforms competition-based high-throughput screening data into actionable insights for kinase inhibitor prioritization. Built upon our previously validated deep learning regression model, DeepKinome, the platform enables quantitative prediction of kinase–inhibitor binding affinities and provides panel-level visualization of selectivity landscapes, selectivity metric calculations, and integrated structural and physicochemical analyses. Through its user-friendly interface, DeepKinomeWeb supports rational, data-driven decision-making for biologists and medicinal chemists, lowering the barrier to systematic selectivity assessment in kinase inhibitor discovery. DeepKinomeWeb is freely available to all users without any login requirement at https://str.kribb.re.kr/deepkinome.

Mental disorders are highly prevalent among patients with chronic kidney disease (CKD); however, the causal effects of kidney dysfunction on specific brain volume traits and mental disorders remain underexplored. In this Mendelian randomization (MR) study, genetic instruments for kidney function and CKD, derived from genome-wide association studies (GWAS) in Chronic Kidney Disease Genetics and the UK Biobank (n = 1,201,909), were utilized for two-sample MR analysis in the discovery phase. Summary-level data from these GWAS provided exposure-outcome associations to calculate causal estimates using the inverse variance weighted method. Validation analysis was conducted using one-sample MR with individual-level data from the UK Biobank. Two-sample MR identified causal associations (odds ratios [ORs] as point estimates) between estimated glomerular filtration rate (exposures) and amygdala traits (outcomes), with ORs ranging from 0.559 to 0.723 (p < 0.05). Two-sample MR between CKD (exposures) and amygdala volume traits (outcomes) reported ORs ranging from 1.042 to 1.059 (p < 0.05). These associations also linked kidney dysfunction to an increased risk of depression, using two-sample MR across 507 brain volume and 242 mental disorder GWAS datasets. Leave-one-out analyses and pleiotropy tests, including MR Egger, supported the robustness of these findings. Validation analysis confirmed reproducibility using one-sample MR. Our results demonstrate that kidney dysfunction causally alters amygdala volume, increasing susceptibility to mental disorders such as depression. These findings highlight the kidney-brain axis and underscore the importance of integrating mental health screening and interventions into the clinical management of patients with CKD.