The collection of increasing amounts of data in health care has become relevant for pain therapy and research. This poses problems for analyses with classical approaches, which is why artificial intelligence (AI) and machine learning (ML) methods are being included into pain research. The current literature on AI and ML in the context of pain research was automatically searched and manually curated. Common machine learning methods and pain settings covered were evaluated. Further focus was on the origin of the publication and technical details, such as the included sample sizes of the studies analyzed with ML. Machine learning was identified in 475 publications from 18 countries, with 79% of the studies published since 2019. Most addressed pain conditions included low back pain, musculoskeletal disorders, osteoarthritis, neuropathic pain, and inflammatory pain. Most used ML algorithms included random forests and support vector machines; however, deep learning was used when medical images were involved in the diagnosis of painful conditions. Cohort sizes ranged from 11 to 2,164,872, with a mode at n = 100; however, deep learning required larger data sets often only available from medical images. Artificial intelligence and ML, in particular, are increasingly being applied to pain-related data. This report presents application examples and highlights advantages and limitations, such as the ability to process complex data, sometimes, but not always, at the cost of big data requirements or black-box decisions.

In order to survive, bacterial cells rely on precise spatiotemporal organization and coordination of essential processes such as cell growth, chromosome segregation, and cell division. Given the general lack of organelles, most bacteria are forced to depend on alternative localization mechanisms, such as, for example, geometrical cues. DivIVA proteins are widely distributed in mainly Gram-positive bacteria and were shown to bind the membrane, typically in regions of strong negative curvature, such as the cell poles and division septa. Here, they have been shown to be involved in a multitude of processes: from apical cell growth and chromosome segregation in actinobacteria to sporulation and inhibition of division re-initiation in firmicutes. Structural analyses revealed that DivIVA proteins can form oligomeric assemblies that constitute a scaffold for recruitment of other proteins. However, it remained unclear whether interaction with partner proteins influences DivIVA dynamics. Using structured illumination microscopy (SIM), single-particle tracking (SPT) microscopy, and fluorescent recovery after photobleaching (FRAP) experiments, we show that DivIVA from Corynebacterium glutamicum is mobilized by its binding partner ParB. In contrast, we show that the interaction between Bacillus subtilis DivIVA and its partner protein MinJ reduces DivIVA mobility. Furthermore, we show that the loss of the rod-shape leads to an increase in DivIVA dynamics in both organisms. Taken together, our study reveals the modulation of the polar scaffold protein by protein interactors and cell morphology. We reason that this leads to a very simple, yet robust way for actinobacteria to maintain polar growth and their rod-shape. In B. subtilis, however, the DivIVA protein is tailored towards a more dynamic function that allows quick relocalization from poles to septa upon division.

Clinical pharmacology research has always involved computational analysis. With the abundance of drug-related data available, the integration of artificial intelligence (AI) and machine learning (ML) methods has emerged as a promising way to enhance clinical pharmacology research. Based on an accepted definition of clinical pharmacology as a field of research dealing with all aspects of drug-human interactions, the analysis included publications from institutes specializing in clinical pharmacology. Research topics and the most used machine learning methods in clinical pharmacology were retrieved from the PubMed database and summarized. ML was identified in 674 publications attributed to clinical pharmacology research, with a significant increase in publication activity over the last decade. Notable research topics addressed by ML/AI included Covid-19-related clinical pharmacology research, clinical neuropharmacology, drug safety and risk assessment, clinical pharmacology related to cancer research, and antimicrobial and antiviral research unrelated to Covid-19. In terms of ML methods, neural networks, random forests, and support vector machines were frequently mentioned in the abstracts of the retrieved papers. ML, and AI in general, is increasingly being used in various research areas within clinical pharmacology. This report presents specific examples of applications and highlights the most used ML methods.

Knowledge discovery in biomedical data using supervised methods assumes that the data contain structure relevant to the class structure if a classifier can be trained to assign a case to the correct class better than by guessing. In this setting, acceptance or rejection of a scientific hypothesis may depend critically on the ability to classify cases better than randomly, without high classification performance being the primary goal. Random forests are often chosen for knowledge-discovery tasks because they are considered a powerful classifier that does not require sophisticated data transformation or hyperparameter tuning and can be regarded as a reference classifier for tabular numerical data. Here, we report a case where the failure of random forests using the default hyperparameter settings in the standard implementations of R and Python would have led to the rejection of the hypothesis that the data contained structure relevant to the class structure. After tuning the hyperparameters, classification performance increased from 56% to 65% balanced accuracy in R, and from 55% to 67% balanced accuracy in Python. More importantly, the 95% confidence intervals in the tuned versions were to the right of the value of 50% that characterizes guessing-level classification. Thus, tuning provided the desired evidence that the data structure supported the class structure of the data set. In this case, the tuning made more than a quantitative difference in the form of slightly better classification accuracy, but significantly changed the interpretation of the data set. This is especially true when classification performance is low and a small improvement increases the balanced accuracy to over 50% when guessing.

The search for novel drugs that efficiently eliminate prokaryotic pathogens is one of the most urgent health topics of our time. Robust evaluation methods for monitoring the antibiotic stress response in prokaryotes are therefore necessary for developing respective screening strategies. Besides advantages of common in vitro techniques, there is a growing demand for in vivo information based on imaging techniques that allow to screen antibiotic candidates in a dynamic manner. Gathering information from imaging data in a reproducible manner, robust data processing and analysis workflows demand advanced (semi-)automation and data management to increase reproducibility. Here we demonstrate a versatile and robust semi-automated image acquisition, processing and analysis workflow to investigate bacterial cell morphology in a quantitative manner. The presented workflow, A.D.I.C.T, covers aspects of experimental setup deployment, data acquisition and handling, image processing (e.g. ROI management, data transformation into binary images, background subtraction, filtering, projections) as well as statistical evaluation of the cellular stress response (e.g. shape measurement distributions, cell shape modeling, probability density evaluation of fluorescence imaging micrographs) towards antibiotic-induced stress, obtained from time-course experiments. The imaging workflow is based on regular brightfield images combined with live-cell imaging data gathered from bacteria, in our case from recombinant Shewanella cells, which are processed as binary images. The model organism expresses target proteins relevant for membrane-biogenesis that are functionally fused to respective fluorescent proteins. Data processing and analysis are based on customized scripts using ImageJ2/FIJI, Celltool and R packages that can be easily reproduced and adapted by users. Summing up, our approach aims at supporting life-scientists to establish their own imaging-pipeline in order to exploit their data as versatile as possible and in a reproducible manner.

Bacteria that are capable of organizing themselves as biofilms are an important public health issue. Knowledge discovery focusing on the ability to swarm and conquer the surroundings to form persistent colonies is therefore very important for microbiological research communities that focus on a clinical perspective. Here, we demonstrate how a machine learning workflow can be used to create useful models that are capable of discriminating distinct associated growth behaviors along distinct phenotypes. Based on basic gray-scale images, we provide a processing pipeline for binary image generation, making the workflow accessible for imaging data from a wide range of devices and conditions. The workflow includes a locally estimated regression model that easily applies to growth-related data and a shape analysis using identified principal components. Finally, we apply a density-based clustering application with noise (DBSCAN) to extract and analyze characteristic, general features explained by colony shapes and areas to discriminate distinct Bacillus subtilis phenotypes. Our results suggest that the differences regarding their ability to swarm and subsequently conquer the medium that surrounds them result in characteristic features. The differences along the time scales of the distinct latency for the colony formation give insights into the ability to invade the surroundings and therefore could serve as a useful monitoring tool.