The article presents work on developing a software application for test creation using artificial intelligence and large language models. Its main goal is to optimize the educators’ work by automating the process of test generation and evaluation, with the tests being stored for subsequent analysis and use. The application can generate test questions based on specified criteria such as difficulty level, Bloom’s taxonomy level, question type, style and format, feedback inclusion, and more, thereby providing opportunities to enhance the adaptability and efficiency of the learning process. It is developed on the Google Firebase platform, utilizing the ChatGPT API, and also incorporates cloud computing to ensure scalability and data reliability.

Research on food-derived bioactive peptides is expanding and the need for a convenient online platform that combines a foolproof and intuitive user interface with a reliable database and tools for prediction and analysis is rising. In this regard, this paper presents an open-access web-based platform PepLab (Peptides Laboratory). The database contains 2764 peptide sequence entries, grouped into sixteen classes according to their biological activity and into seven classes according to the source from which they were derived. Moreover, it includes bioinformatic tools for their processing and analysis. The DMpep tool allows extracting information about a number of physicochemical characteristics of a peptide or a set of peptides, including those that are not recorded in the database. The main advantages of PepLab are a user-friendly interface, a responsive design, and optimized search engines for better visibility on the Internet. Prediction of non-reported activity is available based on amino acid sequence analysis. In addition, users can download data and results in a convenient format (text and/or graphic) that was limited in the existing platforms. In this way, the presented PepLab platform will be helpful for researchers from various fields—bioinformatics, pharmaceuticals, food sciences, dietetics, biotechnology, analytical chemistry, etc.

A large number of researchers spend a lot of time searching for the most efficient neural network to solve a given problem. The procedure of configuration, training, testing, and comparison for expected performance is applied to each experimental neural network. The configuration parameters—training methods, transfer functions, number of hidden layers, number of neurons, number of epochs, and tolerable error—have multiple possible values. Setting guidelines for appropriate parameter values would shorten the time required to create an efficient neural network, facilitate researchers, and provide a tool to improve the performance of automated neural network search methods. The task considered in this paper is related to the determination of upper bounds for the number of hidden layers and the number of neurons in them for approximating artificial neural networks trained with algorithms using the Jacobi matrix in the error function. The derived formulas for the upper limits of the number of hidden layers and the number of neurons in them are proved theoretically, and the presented experiments confirm their validity. They show that the search for an efficient neural network can focus below certain upper bounds, and above them, it becomes pointless. The formulas provide researchers with a useful auxiliary tool in the search for efficient neural networks with optimal topology. They are applicable to neural networks trained with methods such as Levenberg–Marquardt, Gauss–Newton, Bayesian regularization, scaled conjugate gradient, BFGS quasi-Newton, etc., which use the Jacobi matrix.

Pedagogical patterns describe teaching ideas that can be applied in different ways in teaching in different disciplines, and for different types of students. They are a tool for sharing experience and good practices between teachers. The use of pedagogical patterns in online learning is a challenge that can be met by using an appropriate software system for learning management. The article proposes a model of educational objects, suitable for software imple-mentation, which we call pedagogical pattern instances, or for short - in-stances. One instance combines specific learning content with additional fea-tures. Learning content can have different “views” that present knowledge in different ways, for example, through text files of presentations, audio or video content, interactive content, etc. Logical categories of characteristics and activities form the “aspects” of the instance, such as methodology, adap-tivity, assessment, etc. The proposed pattern instance model is flexible. It can be expanded with new features and adapted to specific goals and designs. The paper also outlines a conceptual framework of an e-learning software system using the presented model of a pattern instance.