Generative artificial intelligence in the design of therapeutic peptides and small molecules
Graph neural networks in the prediction of small molecule properties
Use of AI in biomedical imaging and signal analysis
Use of deep learning prediction methods in scoliosis research
Gene signature prediction in microarray expression data
Exploring the association between time series features and forecasting by temporal aggregation using machine learning
When a forecast of the total value over several time periods ahead is required, forecasters are presented with two temporal aggregation (TA) approaches to produce required forecasts: i) aggregated forecast (AF) or ii) aggregate data using non-overlapping temporal aggregation (AD). Often, the recommendation is to aggregate data to a frequency relevant to the decision the eventual forecast will support and then produce the forecast. However, this might not be always the best choice and we argue that both AF and AD approaches may outperform each other in different situations. Moreover, there is a lack of evidence on what indicators may determine the superiority of each approach. We design and execute an empirical experiment framework to first explore the performance of these approaches using monthly time series of M4 competition dataset. We further turn the problem into a classification supervised learning by constructing a database consisting of features of each time series as predictor and model class labelled as AF/AD as response/outcome. We then build machine learning algorithms to investigate the association between time series features and the performance of AF and AD. Our findings suggest that both AF and AD approaches may not consistently generate accurate results for every individual series. AF is shown to be significantly better than AD for the monthly M4 time series, especially for longer horizons. We build several machine learning approaches using a set of extracted time series features as input to predict accurately whether AD or AF should be used. We find out that Random Forest (RF) is the most accurate approach in correctly classifying the outcome assessed both by statistical measures such as misclassification error, F-statistics, area under the curve, and a utility measure. The RF approach reveals that curvature, nonlinearity, seas_pacf, unitroot_pp, mean, ARCHM.LM, Coefficient of Variation, stability, linearity, and max_level_shif are among the most important features in driving the predictions of the model. Our findings indicate that the strength of trend, ARCH.LM, hurst, autocorrelation lag 1, unitroot_pp, and seas_pacf may favour AF approach, while lumpiness, entropy, nonlinearity, curvature, and strength of seasonality may increase the chance of AD performing better. We conclude the study by summarising the findings and present an agenda for further research.
A new algorithm for fetal heart rate detection: Fractional order calculus approach
A new modified Pan-Tompkins’ (mPT) method for fetal heart rate detection is presented. The mPT method is based on the hypothesis that optimal fractional order derivative and optimal window width of the moving average filter would enable efficient estimation of fetal heart rate from surface abdominal electrophysiological recordings with relatively low signal-to-noise ratios.
The algorithm is tested on signals recorded from the abdomen of pregnant women available from the PhysioNet Computing in Cardiology Challenge database. Fetal heart rate detection is performed on 10-s long segments selected by the estimation of signal-to-noise ratios (the extravagance of the fetal QRS peak to its surroundings and to the whole signal; and the mean ratio of fetal and maternal QRS peaks) and on the manually selected segments.
The best results are obtained via criteria based on the extravagance of the fetal QRS peak to its surroundings that reached average sensitivity of 97%, positive predictive value of 97%, error rate of ∼3.5%, and F1 score of 97%. The obtained averaged optimal parameters for mPT are 0.51 for fractional order and 24.5 ms for the window width of the moving average filter.
Cilia metasurfaces for electronically programmable microfluidic manipulation
Cilial pumping is a powerful strategy used by biological organisms to control and manipulate fluids at the microscale. However, despite numerous recent advances in optically, magnetically and electrically driven actuation, development of an engineered cilial platform with the potential for applications has remained difficult to realize. Here we report on active metasurfaces of electronically actuated artificial cilia that can create arbitrary flow patterns in liquids near a surface. We first create voltage-actuated cilia that generate non-reciprocal motions to drive surface flows at tens of microns per second at actuation voltages of 1 volt. We then show that a cilia unit cell can locally create a range of elemental flow geometries. By combining these unit cells, we create an active cilia metasurface that can generate and switch between any desired surface flow pattern. Finally, we integrate the cilia with a light-powered complementary metal–oxide–semiconductor (CMOS) clock circuit to demonstrate wireless operation. As a proof of concept, we use this circuit to output voltage pulses with various phase delays to demonstrate improved pumping efficiency using metachronal waves. These powerful results, demonstrated experimentally and confirmed using theoretical computations, illustrate a pathway towards fine-scale microfluidic manipulation, with applications from microfluidic pumping to microrobotic locomotion.
Microswimmers in vortices: dynamics and trapping
Biological and artificial microswimmers often self-propel in external flows of vortical nature; relevant examples include algae in small-scale ocean eddies, spermatozoa in uterine peristaltic flows and bacteria in microfluidic devices. A recent experiment has shown that swimming bacteria in model vortices are expelled from the vortex all the way to a well-defined depletion zone (A. Sokolov and I. S. Aranson, Rapid expulsion of microswimmers by a vortical flow. Nat. Commun., 2016, 7, 11114). In this paper, we propose a theoretical model to investigate the dynamics of elongated microswimmers in elementary vortices, namely active particles in two- and three-dimensional rotlets. A deterministic model first reveals the existence of bounded orbits near the centre of the vortex and unbounded orbits elsewhere. We further discover a conserved quantity of motion that allows us to map the phase space according to the type of the orbit (bounded vs unbounded). We next introduce translational and rotational noise into the system. Using a Fokker–Planck formalism, we quantify the quality of trapping near the centre of the vortex by examining the probability of escape and the mean time of escape from the region of deterministically bounded orbits. We finally show how to use these findings to formulate a prediction for the radius of the depletion zone, which compares favourably with the experiments (A. Sokolov and I. S. Aranson, Rapid expulsion of microswimmers by a vortical flow. Nat. Commun., 2016, 7, 11114).
Memristive circuit-based model of central pattern generator to reproduce spinal neuronal activity in walking pattern
Existing methods of neurorehabilitation include invasive or non-invasive stimulators that are usually simple digital generators with manually set parameters like pulse width, period, burst duration, and frequency of stimulation series. An obvious lack of adaptation capability of stimulators, as well as poor biocompatibility and high power consumption of prosthetic devices, highlights the need for medical usage of neuromorphic systems including memristive devices. The latter are electrical devices providing a wide range of complex synaptic functionality within a single element. In this study, we propose the memristive schematic capable of self-learning according to bio-plausible spike-timing-dependant plasticity to organize the electrical activity of the walking pattern generated by the central pattern generator.
An ontology-based module of the information system ScolioMedIS for 3D digital diagnosis of adolescent scoliosis
Conventional information systems are built on top of a relational database. The main weakness of these systems is impossibility to define stable data schema ahead when the knowledge of the system is evolving and dynamic. The widely accepted alternatives to relational databases are ontologies that can be used for designing information systems. Many research papers describe various methods for improving reliability and precision in generating the type of the Lenke classification based on the image processing techniques or a computer program, but all of them require radiograph images. The main objective of this paper is to demonstrate the development of an ontology-based module of the information system ScolioMedIS for adolescent idiopathic scoliosis (AIS) diagnosis and monitoring, which uses optical 3D methods to determine the Lenke classification of AIS and to avoid harmful effects of traditional radiation diagnosis.