Antibiotics offer an efficient means for managing diseases caused by bacterial pathogens. However, antibiotics are typically broad spectrum and they can indiscriminately kill beneficial microbes in body habitats such as the gut, deleteriously affecting the commensal gut microbiota. In addition, many bacteria have developed or are developing resistance to antibiotics, which complicates treatment and creates significant challenges in clinical medicine. Therefore, there is a real and urgent medical need to develop alternative antimicrobial approaches that will kill specific problem-causing bacteria without disturbing a normal, and often beneficial, gut microbiota. One such potential alternative approach is the use of lytic bacteriophages for managing bacterial infections, including those caused by multidrug-resistant pathogens. In the present study, we comparatively analysed the efficacy of a bacteriophage cocktail targeting Escherichia coli with that of a broad-spectrum antibiotic (ciprofloxacin) using an in vitro model of the small intestine. The parameters examined included (i) the impact on a specific, pre-chosen targeted E. coli strain, and (ii) the impact on a selected non-targeted bacterial population, which was chosen to represent a defined microbial consortium typical of a healthy small intestine. During these studies, we also examined stability of bacteriophages against various pH and bile concentrations commonly found in the intestinal tract of humans. The bacteriophage cocktail was slightly more stable in the simulated duodenum conditions compared to the simulated ileum (0.12 vs. 0.58 log decrease in phage titers, respectively). It was equally effective as ciprofloxacin in reducing E. coli in the simulated gut conditions (2–3 log reduction), but had much milder (none) impact on the commensal, non-targeted bacteria compared to the antibiotic.

The feeding of medicinal zinc oxide (ZnO) to weaner piglets will be phased out after 2022 in Europe, leaving pig producers without options to manage post-weaning disorders. This study assessed whether rapeseed meal, fermented alone (FRM) or co-fermented with a single (Ascophylum nodosum; FRMA), or two (A. nodossum and Saccharina latissima; FRMAS) brown macroalagae species, could improve weaner piglet performance and stimulate intestinal development as well as maturation of gut microbiota in the absence of in-feed zinc. Weaned piglets (n = 1240) were fed, during 28–85 days of age, a basal diet with no additives (negative control; NC), 2500 ppm in-feed ZnO (positive control; PC), FRM, FRMA or FRMAS. Piglets fed FRM and FRMA had a similar or numerically improved, respectively, production performance compared to PC piglets. Jejunal villus development was stimulated over NC in PC, FRM and FRMAS (gender-specific). FRM enhanced colon mucosal development and reduced signs of intestinal inflammation. All fermented feeds and PC induced similar changes in the composition and diversity of colon microbiota compared to NC. In conclusion, piglet performance, intestinal development and health indicators were sustained or numerically improved when in-feed zinc was replaced by FRM.

Maintenance of industrial reactors supported by deep learning driven ultrasound toMography eksploatacja reaktorów przeMysłowych ze wspoMaganieM toMografii ultradźwiękowej i algorytMów głębokiego uczeniaMonitoring of industrial processes is an important element ensuring the proper maintenance of equipment and high level of processes reliability. The presented research concerns the application of the deep learning method in the field of ultrasound tomography (UST). A novel algorithm that uses simultaneously multiple classification convolutional neural networks (CNNs) to generate monochrome 2D images was developed. In order to meet a compromise between the number of the networks and the number of all possible outcomes of a single network, it was proposed to divide the output image into 4-pixel clusters. Therefore, the number of required CNNs has been reduced fourfold and there are 16 distinct outcomes from single network. The new algorithm was first verified using simulation data and then tested on real data. The accuracy of image reconstruction exceeded 95%. The results obtained by using the new CNN clustered algorithm were compared with five popular machine learning algorithms: shallow Artificial Neural Network, Linear Support Vector Machine, Classification Tree, Medium k-Nearest Neighbor classification and Naive Bayes. Based on this comparison, it was found that the newly developed method of multiple convolutional neural networks (MCNN) generates the highest quality images.

There is a growing interest in understanding the fate and behaviour of probiotic microorganisms and bioactive compounds during passage of the human gastrointestinal tract (GIT). Here, we report the development of a small volume in vitro model called The smallest Intestine (TSI) with increased throughput focusing on simulating passage through the stomach and small intestine (SI). The basic TSI module consists of five reactors, with a working volume of 12 ml each. During the simulated passage through the SI, bile is absorbed and pH is adjusted to physiologically relevant values for duodenum, jejunum and ileum. A consortium of seven representative bacterial members of the ileum microbiota is included in the ileal stage of the model. The behaviour of three putative probiotic Lactobacillus strains during in vitro simulated upper GIT passage was tested in the model and results were compared to previous studies describing probiotic survival. It was found, that probiotic persistence is strongly related to whether food was ingested, but also to presence of the ileal microbiota, which significantly impacted probiotic survival. In conclusion, TSI allows testing a substantial number of samples, at low cost and short time, and is thus suitable as an in vitro screening platform.

This paper refers to the method of using the deep neural long-short-term memory (LSTM) network for the problem of electrocardiogram (ECG) signal classification. ECG signals contain a lot of subtle information analyzed by doctors to determine the type of heart dysfunction. Due to the large number of signal features that are difficult to identify, raw ECG data is usually not suitable for use in machine learning. The article presents how to transform individual ECG time series into spectral images for which two characteristics are determined, which are instantaneous frequency and spectral entropy. Feature extraction consists of converting the ECG signal into a series of spectral images using short-term Fourier transformation. Then the images were converted using Fourier transform again to two signals, which includes instantaneous frequency and spectral entropy. The data set transformed in this way was used to train the LSTM network. During the experiments, the LSTM networks were trained for both raw and spectrally transformed data. Then, the LSTM networks trained in this way were compared with each other. The obtained results prove that the transformation of input signals into images can be an effective method of improving the quality of classifiers based on deep learning.