In this work we describe a cyber-physical decision support system integrated into the process of researching and developing novel antifungal antibiotics, particularly polyene macrolide antibiotic derivatives. The methods and technologies used to develop the decision support system include modern methods of web-application development (client-server architecture utilizing microservices, asynchronous queues for processing longer tasks), modern methods for developing predictive models (recurrent neural networks), specialized deterministic algorithms, and thin interfaces. The cyber-physical system enables chemists-researchers to make better decisions when selecting potential antifungal drug candidates by predicting the properties of antifungal antibiotics. The models predict toxicity, reaching an average AUC of 0.86 across relevant assays as well as 0.02 mg/kg mean squared error for oral toxicity (LD50, rats). Antifungal activity is predicted using a deterministic algorithm, which was able to correctly separate a set of antifungal and non-antifungal drugs into their respective categories. The mathematical models were trained, tested, and validated on a set of antifungal antibiotic data. Testing showed the models’ accuracy and viability for predicting antifungal antibiotics’ properties.
In this chapter, we describe the algorithms for data processing applied as part of an intellectual analysis subsystem of a software system for predicting and researching the properties of antifungal antibiotics. These include models for predicting toxicity based on assays as well as acute oral toxicity. The mathematical models were trained, tested, and validated on different sets of antifungal antibiotic data. Testing showed the models’ accuracy and viability for predicting antifungal antibiotics’ properties.
Reactions of the tetraene macrolide antibiotic tetramycin B with p-substituted aromatic aldehydes and sodiumcyanoborohydride in the conditions of reaction of reductive amination resultedin formation of its N-benzyl derivatives.Physicochemical and medical and biological properties of obtained derivatives oftetramycin B were studied. Biological investigations showed that N-benzyl derivatives of tetramycin B were low toxicagents and possessed high antifungal activity. The pharmacological testsrevealed that the acute toxicity (LD50) of obtainedderivatives of tetramycin B was 7–8 times low as that of the startingantibiotic. The automated intellectual information system for optimal choice ofthe conditions for rational design, synthesis and using in medical practice ofnovel derivatives of polyene macrolide antibiotics was developed.
In this work we present a software system that enables antifungal antibiotic drug candidate toxicity and likelihood of drug binding prediction. The system is composed of a number of machine learning models and deterministic algorithms. Its implementation utilizes modern software development practices including a client-server architecture with a thin web-client. Testing showed the models’ accuracy and viability for predicting antifungal antibiotics’ properties.
The paper discusses a computer system for predicting antimycotic properties, which can predict a certain compound’s toxicity and useful properties based on its chemical structure, as well as find similar synthesis parameters from a compound synthesis methods database. The system contains two neural networks (to predict toxicity and useful behavior from molecular descriptors and the SMILES notation), a rule base for synthesizing novel antibiotics, as well as an antimycotic compound synthesis database. The system can help significantly lower the development cost for novel antibiotics. It has been tested using antifungal polyene macrolide antibiotics.
Development of a computer system integrating modern bio- and chem-information, and cognitive technologies, such as hybrid production-frame knowledge representation, neural networks, and graph databases. The project intends to provide intellectual analysis and rational selection for the synthesis parameters of antifungal drug preparations that is possible to create through synthesis or chemical modification.