Usual response of organism to viral or bacterial invasion represents antibodies production, qualitative and quantitative changes in composition of biological fluids. These changes influence conformation and surface characteristics of macromolecules (proteins), which become apparent in sessile drying drops, when they form aggregates due to salting-out effect and sediment. The bottom adsorption layers change their adhesive and viscoelastic properties in time depending on fluid composition and structure. The aim of this study was verification the idea of using this phenomenon in rapid vet diagnostics. Milk, blood and serum samples of 183 cows were tested using Drop Drying Technology (DDT). A drop of tested fluid dried on a polished quartz plate, oscillated with constant frequency-60 kHz. Mechanical properties of the drop changed during drying, influenced the electrical conductivity of the quartz plate. This signal was converted to the Acoustical-Mechanical Impedance (AMI) and displayed as a curve in coordinates AMI vs. Time. Shape of the AMI curve reflected this dynamics, and was used as a target for quantitative comparison between * Corresponding author. T. A. Yakhno et al. 2 control and infected animals. Frequency analysis of the estimated parameters of the curves was performed using features of the Excel program. Powerful method of artificial neural network processing of the experimental data was also tested in this work as a possible tool for future development. Significant differences between control, Bovine leucosis virus positive (BLV+) and Bovine tuberculin positive (BTub+) cattle groups were obtained using all biological fluids-blood, serum and milk. We fixed also a season shift of the data, but distinction between groups still remained. In serum and milk some features of the AMI curves were more stable, and retained diagnostic properties when combined winter and spring databases. Further development of DDT is proposed.
The ability to perform de novo protein design will allow researchers to expand the variety of available proteins. By designing synthetic structures computationally, they can utilise more structures than those available in the Protein Data Bank, design structures that are not found in nature, or direct the design of proteins to acquire a specific desired structure. While some researchers attempt to design proteins from first physical and thermodynamic principals, we decided to attempt to test whether it is possible to perform de novo helical protein design of just the backbone statistically using machine learning by building a model that uses a long short-term memory (LSTM) architecture. The LSTM model used only the φ and ψ angles of each residue from an augmented dataset of only helical protein structures. Though the network’s generated backbone structures were not perfect, they were idealised and evaluated post generation where the non-ideal structures were filtered out and the adequate structures kept. The results were successful in developing a logical, rigid, compact, helical protein backbone topology. This paper is a proof of concept that shows it is possible to generate a novel helical backbone topology using an LSTM neural network architecture using only the φ and ψ angles as features. The next step is to attempt to use these backbone topologies and sequence design them to form complete protein structures.
The ability to perform de novo protein design will allow researchers to expand the variety of available proteins. By designing synthetic structures computationally, they can utilise more structures than those available in the Protein Data Bank, design structures that are not found in nature, or direct the design of proteins to acquire a specific desired structure. While some researchers attempt to design proteins from first physical and thermodynamic principals, we decided to attempt to test whether it is possible to perform de novo helical protein design of just the backbone statistically using machine learning by building a model that uses a long short-term memory (LSTM) architecture. The LSTM model used only the φ and ψ angles of each residue from an augmented dataset of only helical protein structures. Though the network’s generated backbone structures were not perfect, they were idealised and evaluated post generation where the non-ideal structures were filtered out and the adequate structures kept. The results were successful in developing a logical, rigid, compact, helical protein backbone topology. This paper is a proof of concept that shows it is possible to generate a novel helical backbone topology using an LSTM neural network architecture using only the φ and ψ angles as features. The next step is to attempt to use these backbone topologies and sequence design them to form complete protein structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.