ABSTRACT
The rapid proliferation of data across diverse fields has accentuated the importance of accurate imputation for missing values. This task is crucial for ensuring data integrity and deriving meaningful insights. In response to this challenge, we present Xputer, a novel imputation tool that adeptly integrates Non-negative Matrix Factorization (NMF) with the predictive strengths of XGBoost. One of Xputer's standout features is its versatility: it supports zero imputation, enables hyperparameter optimization through Optuna, and allows users to define the number of iterations. For enhanced user experience and accessibility, we have equipped Xputer with an intuitive Graphical User Interface (GUI) ensuring ease of handling, even for those less familiar with computational tools. In performance benchmarks, Xputer often outperforms IterativeImputer in terms of imputation accuracy. Furthermore, Xputer autonomously handles a diverse spectrum of data types, including categorical, continuous, and Boolean, eliminating the need for prior preprocessing. Given its blend of performance, flexibility, and user-friendly design, Xputer emerges as a state-of-the-art solution in the realm of data imputation.
ABSTRACT
Leveraging the potential of machine learning and recognizing the broad applications of binary classification, it becomes essential to develop platforms that are not only powerful but also transparent, interpretable, and user friendly. We introduce alphaML, a user-friendly platform that provides clear, legible, explainable, transparent, and elucidative (CLETE) binary classification models with comprehensive customization options. AlphaML offers feature selection, hyperparameter search, sampling, and normalization methods, along with 15 machine learning algorithms with global and local interpretation. We have integrated a custom metric for hyperparameter search that considers both training and validation scores, safeguarding against under- or overfitting. Additionally, we employ the NegLog2RMSL scoring method, which uses both training and test scores for a thorough model evaluation. The platform has been tested using datasets from multiple domains and offers a graphical interface, removing the need for programming expertise. Consequently, alphaML exhibits versatility, demonstrating promising applicability across a broad spectrum of tabular data configurations.
ABSTRACT
Combination drug treatments are usually used in many diseases, including cancers and AIDS. This treatment strategy is known as one of the cornerstone in therapies, which potentially reduces drug toxicity and drug resistance and also enhances therapeutic efficacy. Before using a drug in treatment, several experimental studies are done in vivo and in vitro to ensure the drug's efficacy. In such experimental studies, the drug's efficacy is evaluated with the help of drug dose ratio. In the combination drug experimental studies, the efficacy of the drugs is quantified with the Combination Index (CI) value and then interpreted by various terminologies like synergy, additive, and antagonism. Several computational models have now been invented for the speedy identification of combination drug efficacy. Unfortunately, none of these models have predicted the atomic level interaction of the combination drug with the target protein. This type of intermolecular interaction can be identified with the help of docking software. In the proposed work, we try to identify the intermolecular interaction and efficacy of the combination drug Crzizotinib and Temozolomide in the target of EML4-ALK in NSCLC by in silico study. The result of the study was evaluated with drug properties and Complex Energy (CE) of the docked complex rather than using docking score and binding energy. From this study, we could understand that first, Crizotinib and then after the Temozolomide drug binded on the EML4-ALK protein complex, showed very least CE and also identified that the combination of Crizotinib and Temozolomide drug are more effective in NSCLC.Communicated by Ramaswamy H. Sarma.
