Human Campylobacter spp. infections in Italy.

PURPOSE: Campylobacter is a frequent cause of enteric infections with common antimicrobial resistance issues. The most recent reports of campylobacteriosis in Italy include data from 2013 to 2016. We aimed to provide national epidemiological and microbiological data on human Campylobacter infections in Italy during the period 2017-2021. METHODS: Data was collected from 19 Hospitals in 13 Italian Regions. Bacterial identification was performed by mass spectrometry. Antibiograms were determined with Etest or Kirby-Bauer (EUCAST criteria). RESULTS: In total, 5419 isolations of Campylobacter spp. were performed. The most common species were C. jejuni (n = 4535, 83.7%), followed by C. coli (n = 732, 13.5%) and C. fetus (n = 34, 0.6%). The mean age of patients was 34.61 years and 57.1% were males. Outpatients accounted for 54% of the cases detected. Campylobacter were isolated from faeces in 97.3% of cases and in 2.7% from blood. C. fetus was mostly isolated from blood (88.2% of cases). We tested for antimicrobial susceptibility 4627 isolates (85.4%). Resistance to ciprofloxacin and tetracyclines was 75.5% and 54.8%, respectively; resistance to erythromycin was 4.8%; clarithromycin 2% and azithromycin 2%. 50% of C. jejuni and C. coli were resistant to ≥ 2 antibiotics. Over the study period, resistance to ciprofloxacin and tetracyclines significantly decreased (p < 0.005), while resistance to macrolides remained stable. CONCLUSION: Campylobacter resistance to fluoroquinolones and tetracyclines in Italy is decreasing but is still high, while macrolides retain good activity.

Keeping Pathologists in the Loop and an Adaptive F1-Score Threshold Method for Mitosis Detection in Canine Perivascular Wall Tumours.

Performing a mitosis count (MC) is the diagnostic task of histologically grading canine Soft Tissue Sarcoma (cSTS). However, mitosis count is subject to inter- and intra-observer variability. Deep learning models can offer a standardisation in the process of MC used to histologically grade canine Soft Tissue Sarcomas. Subsequently, the focus of this study was mitosis detection in canine Perivascular Wall Tumours (cPWTs). Generating mitosis annotations is a long and arduous process open to inter-observer variability. Therefore, by keeping pathologists in the loop, a two-step annotation process was performed where a pre-trained Faster R-CNN model was trained on initial annotations provided by veterinary pathologists. The pathologists reviewed the output false positive mitosis candidates and determined whether these were overlooked candidates, thus updating the dataset. Faster R-CNN was then trained on this updated dataset. An optimal decision threshold was applied to maximise the F1-score predetermined using the validation set and produced our best F1-score of 0.75, which is competitive with the state of the art in the canine mitosis domain.

Wound recovery efficacy of retinol based-micellar formulations in an organotypic skin wound model.

Impairment of the skin's structural integrity initially results in acute wounds which can become chronic if timely wound closure is not achieved. Chronic wounds (CWs) affect more than 1% of the global population with increasing cases of this condition due to the ageing population. Current wound management relies on debridement, hyperbaric oxygen, antibiotics, and wound dressings, which lack early intervention and specificity. Herein, antibiotics-free retinol-based micellar formulations (RMF) were made and their wound healing efficacy were investigated in vitro. Five different formulations with retinol contents of 0.3% and 1% against a placebo were topically applied to an organotypic full-thickness skin wound model (FT-SWM, MatTek®) with a 3 mm punch wound, and maintained in an incubator for 6 days. The histological analysis of the FT-SWM was conducted at depths of 60 µm and 80 µm. It was found that all the micellar retinol formulations accelerated wound bed contraction, with 0.3% RMF demonstrating the highest efficacy. At the depths of 60 µm and 80 µm, the 0.3% RMF exhibited inner wound diameter contraction of 58% and 77%, respectively, in comparison to the placebo showing 15% and 8%. The RMF significantly accelerated wound healing and can thus be a potential early intervention for speedy wound recovery. It should be pointed out that these results were obtained based on a small sample size and a large sample size will be explored to further validate the results.

Significant differences in the caecal bacterial microbiota of red and grey squirrels in Britain.

Introduction. Red squirrel populations have declined in the UK since the introduction of the grey squirrel, due to resource competition and grey squirrels carrying a squirrelpox virus that is fatal to red squirrels.Hypothesis/Gap Statement. It is not known if the gut microbiota of the two species is similar and if this could impact the survival of red squirrels.Aim. The aim of this study was to profile the caecal microbiota of red and grey squirrels obtained opportunistically from a conservation programme in North Wales.Methodology. Bacterial DNA was extracted from ten red and ten grey squirrels and sent for 16S rRNA sequencing. Three samples from red squirrels returned less than 5000 reads, and so were not carried forward for further analyses.Results. Samples taken from the caeca of red squirrels had significantly lower bacterial diversity and a higher percentage of Bacilli bacteria when compared to samples from grey squirrels. When the abundance of bacterial groups across all levels of phylogenetic classifications was compared between the two groups of squirrels, grey squirrels had a higher abundance of bacteria belonging to the families S24-7, RF39 and Rikenellaceae. Escherichia coli with resistance to amoxicillin/clavulanic acid was identified in all samples. Cefotaxime resistance was identified in two samples from grey squirrels along with sulfamethoxazole/trimethoprim in one of these samples.Conclusion. Clear differences between the caecal microbiota of the two species of squirrel were identified, which could potentially impact their overall health and ability to compete for resources.

A mathematical, classical stratification modeling approach to disentangling the impact of weather on infectious diseases: A case study using spatio-temporally disaggregated Campylobacter surveillance data for England and Wales.

Disentangling the impact of the weather on transmission of infectious diseases is crucial for health protection, preparedness and prevention. Because weather factors are co-incidental and partly correlated, we have used geography to separate out the impact of individual weather parameters on other seasonal variables using campylobacteriosis as a case study. Campylobacter infections are found worldwide and are the most common bacterial food-borne disease in developed countries, where they exhibit consistent but country specific seasonality. We developed a novel conditional incidence method, based on classical stratification, exploiting the long term, high-resolution, linkage of approximately one-million campylobacteriosis cases over 20 years in England and Wales with local meteorological datasets from diagnostic laboratory locations. The predicted incidence of campylobacteriosis increased by 1 case per million people for every 5° (Celsius) increase in temperature within the range of 8°-15°. Limited association was observed outside that range. There were strong associations with day-length. Cases tended to increase with relative humidity in the region of 75-80%, while the associations with rainfall and wind-speed were weaker. The approach is able to examine multiple factors and model how complex trends arise, e.g. the consistent steep increase in campylobacteriosis in England and Wales in May-June and its spatial variability. This transparent and straightforward approach leads to accurate predictions without relying on regression models and/or postulating specific parameterisations. A key output of the analysis is a thoroughly phenomenological description of the incidence of the disease conditional on specific local weather factors. The study can be crucially important to infer the elusive mechanism of transmission of campylobacteriosis; for instance, by simulating the conditional incidence for a postulated mechanism and compare it with the phenomenological patterns as benchmark. The findings challenge the assumption, commonly made in statistical models, that the transformed mean rate of infection for diseases like campylobacteriosis is a mere additive and combination of the environmental variables.

Corrigendum: VIDIIA Hunter: a low-cost, smartphone connected, artificial intelligence-assisted COVID-19 rapid diagnostic platform approved for medical use in the UK.

[This corrects the article DOI: 10.3389/fmolb.2023.1144001.].

Anti-persister efficacy of colistin and meropenem against uropathogenic Escherichia coli is dependent on environmental conditions.

Antibiotic persistence is a phenomenon observed when genetically susceptible cells survive long-term exposure to antibiotics. These 'persisters' are an intrinsic component of bacterial populations and stem from phenotypic heterogeneity. Persistence to antibiotics is a concern for public health globally, as it increases treatment duration and can contribute to treatment failure. Furthermore, there is a growing array of evidence that persistence is a 'stepping-stone' for the development of genetic antimicrobial resistance. Urinary tract infections (UTIs) are a major contributor to antibiotic consumption worldwide, and are known to be both persistent (i.e. affecting the host for a prolonged period) and recurring. Currently, in clinical settings, routine laboratory screening of pathogenic isolates does not determine the presence or the frequency of persister cells. Furthermore, the majority of research undertaken on antibiotic persistence has been done on lab-adapted bacterial strains. In the study presented here, we characterized antibiotic persisters in a panel of clinical uropathogenic Escherichia coli isolates collected from hospitals in the UK and Australia. We found that a urine-pH mimicking environment not only induces higher levels of antibiotic persistence to meropenem and colistin than standard laboratory growth conditions, but also results in rapid development of transient colistin resistance, regardless of the genetic resistance profile of the isolate. Furthermore, we provide evidence for the presence of multiple virulence factors involved in stress resistance and biofilm formation in the genomes of these isolates, whose activities have been previously shown to contribute to the formation of persister cells.

VIDIIA Hunter diagnostic platform: a low-cost, smartphone connected, artificial intelligence-assisted COVID-19 rapid diagnostics approved for medical use in the UK.

Introduction: Accurate and rapid diagnostics paired with effective tracking and tracing systems are key to halting the spread of infectious diseases, limiting the emergence of new variants and to monitor vaccine efficacy. The current gold standard test (RT-qPCR) for COVID-19 is highly accurate and sensitive, but is time-consuming, and requires expensive specialised, lab-based equipment. Methods: Herein, we report on the development of a SARS-CoV-2 (COVID-19) rapid and inexpensive diagnostic platform that relies on a reverse-transcription loop-mediated isothermal amplification (RT-LAMP) assay and a portable smart diagnostic device. Automated image acquisition and an Artificial Intelligence (AI) deep learning model embedded in the Virus Hunter 6 (VH6) device allow to remove any subjectivity in the interpretation of results. The VH6 device is also linked to a smartphone companion application that registers patients for swab collection and manages the entire process, thus ensuring tests are traced and data securely stored. Results: Our designed AI-implemented diagnostic platform recognises the nucleocapsid protein gene of SARS-CoV-2 with high analytical sensitivity and specificity. A total of 752 NHS patient samples, 367 confirmed positives for coronavirus disease (COVID-19) and 385 negatives, were used for the development and validation of the test and the AI-assisted platform. The smart diagnostic platform was then used to test 150 positive clinical samples covering a dynamic range of clinically meaningful viral loads and 250 negative samples. When compared to RT-qPCR, our AI-assisted diagnostics platform was shown to be reliable, highly specific (100%) and sensitive (98-100% depending on viral load) with a limit of detection of 1.4 copies of RNA per µL in 30 min. Using this data, our CE-IVD and MHRA approved test and associated diagnostic platform has been approved for medical use in the United Kingdom under the UK Health Security Agency's Medical Devices (Coronavirus Test Device Approvals, CTDA) Regulations 2022. Laboratory and in-silico data presented here also indicates that the VIDIIA diagnostic platform is able to detect the main variants of concern in the United Kingdom (September 2023). Discussion: This system could provide an efficient, time and cost-effective platform to diagnose SARS-CoV-2 and other infectious diseases in resource-limited settings.

Development of a loop-mediated isothermal amplification (LAMP)-based electrochemical test for rapid detection of SARS-CoV-2.

Rapid, reliable, sensitive, portable, and accurate diagnostics are required to control disease outbreaks such as COVID-19 that pose an immense burden on human health and the global economy. Here we developed a loop-mediated isothermal amplification (LAMP)-based electrochemical test for the detection of SARS-CoV-2 that causes COVID-19. The test is based on the oxidation-reduction reaction between pyrophosphates (generated from positive LAMP reaction) and molybdate that is detected by cyclic voltammetry using inexpensive and disposable carbon screen printed electrodes. Our test showed higher sensitivity (detecting as low as 5.29 RNA copies/µL) compared to the conventional fluorescent reverse transcriptase (RT)-LAMP. We validated our tests using human serum and saliva spiked with SARS-CoV-2 RNA and clinical (saliva and nasal-pharyngeal) swab samples demonstrating 100% specificity and 93.33% sensitivity. Our assay provides a rapid, specific, and sensitive test with an electrochemical readout in less than 45 min that could be adapted for point-of-care settings.

Alteration of the Chicken Upper Respiratory Microbiota, Following H9N2 Avian Influenza Virus Infection.

Several studies have highlighted the importance of the gut microbiota in developing immunity against viral infections in chickens. We have previously shown that H9N2 avian influenza A virus (AIV) infection retards the diversity of the natural colon-associated microbiota, which may further influence chicken health following recovery from infection. The effects of influenza infection on the upper respiratory tract (URT) microbiota are largely unknown. Here, we showed that H9N2 AIV infection lowers alpha diversity indices in the acute phase of infection in the URT, largely due to the family Lactobacillaceae being highly enriched during this time in the respiratory microbiota. Interestingly, microbiota diversity did not return to levels similar to control chickens in the recovery phase after viral shedding had ceased. Beta diversity followed a similar trend following the challenge. Lactobacillus associate statistically with the disturbed microbiota of infected chickens at the acute and recovery phases of infection. Additionally, we studied age-related changes in the respiratory microbiota during maturation in chickens. From 7 to 28 days of age, species richness and evenness were observed to advance over time as the microbial composition evolved. Maintaining microbiota homeostasis might be considered as a potential therapeutic target to prevent or aid recovery from H9N2 AIV infection.

Preventing bacterial disease in poultry in the post-antibiotic era: a case for innate immunity modulation as an alternative to antibiotic use.

The widespread use of antibiotics in the poultry industry has led to the emergence of antibiotic-resistant bacteria, which pose a significant health risk to humans and animals. These public health concerns, which have led to legislation limiting antibiotic use in animals, drive the need to find alternative strategies for controlling and treating bacterial infections. Modulation of the avian innate immune system using immunostimulatory compounds provides a promising solution to enhance poultry immune responses to a broad range of bacterial infections without the risk of generating antibiotic resistance. An array of immunomodulatory compounds have been investigated for their impact on poultry performance and immune responses. However, further research is required to identify compounds capable of controlling bacterial infections without detrimentally affecting bird performance. It is also crucial to determine the safety and effectiveness of these compounds in conjunction with poultry vaccines. This review provides an overview of the various immune modulators known to enhance innate immunity against avian bacterial pathogens in chickens, and describes the mechanisms involved.

The manganese carbonyl complex [Mn(CO)3(tqa-κ3N)]Br: A novel antimicrobial agent with the potential to treat avian pathogenic Escherichia coli (APEC) infections.

The development of alternatives to antibiotics is essential for the treatment of animal infections and as a measure to reduce the selective pressure on antibiotics that are critical for human medicine. Metal complexes have been highlighted for their antimicrobial activity against several bacterial pathogens. In particular, manganese carbonyl complexes have shown efficacy against multidrug-resistant Gram-negative pathogens, and relatively low cytotoxicity against avian macrophages and in wax moth larval models. They are thus potential candidates for deployment against Avian Pathogenic Escherichia coli (APEC), the aetiological agent of avian colibacillosis, which results in severe animal welfare issues and financial losses worldwide. This study aimed to determine the efficacy of [Mn(CO)3(tqa-κ3N)]Br in Galleria mellonella and chick models of infection against APEC. The results demonstrated in vitro and in vivo antibacterial activity against all antibiotic-resistant APEC test isolates screened in the study.

A multi-country One Health foodborne outbreak simulation exercise: cross-sectoral cooperation, data sharing and communication.

Introduction: The awareness of scientists and policy makers regarding the requirement for an integrated One Health (OH) approach in responding to zoonoses has increased in recent years. However, there remains an overall inertia in relation to the implementation of practical cross-sector collaborations. Foodborne outbreaks of zoonotic diseases continue to affect the European population despite stringent regulations, evidencing the requirement for better 'prevent, detect and response' strategies. Response exercises play an essential role in the improvement of crisis management plans, providing the opportunity to test practical intervention methodologies in a controlled environment. Methods: The One Health European Joint Programme simulation exercise (OHEJP SimEx) aimed at practicing the OH capacity and interoperability across public health, animal health and food safety sectors in a challenging outbreak scenario. The OHEJP SimEx was delivered through a sequence of scripts covering the different stages of a Salmonella outbreak investigation at a national level, involving both the human food chain and the raw pet feed industry. Results: A total of 255 participants from 11 European countries (Belgium, Denmark, Estonia, Finland, France, Italy, Norway, Poland, Portugal, Sweden, the Netherlands) took part in national level two-day exercises during 2022. National evaluations identified common recommendations to countries aiming to improve their OH structure to establish formal communication channels between sectors, implement a common data sharing platform, harmonize laboratory procedures, and reinforce inter-laboratory networks within countries. The large proportion of participants (94%) indicated significant interest in pursuing a OH approach and desire to work more closely with other sectors. Discussion: The OHEJP SimEx outcomes will assist policy makers in implementing a harmonized approach to cross-sector health-related topics, by highlighting the benefits of cooperation, identifying gaps in the current strategies and suggesting actions required to better address foodborne outbreaks. Furthermore, we summarize recommendations for future OH simulation exercises, which are essential to continually test, challenge and improve national OH strategies.

Non-Antibiotic Compounds Synergistically Kill Chronic Wound-Associated Bacteria and Disrupt Their Biofilms.

Chronic wounds and their treatment present a significant burden to patients and healthcare systems alike, with their management further complicated by bacterial infection. Historically, antibiotics have been deployed to prevent and treat infections, but the emergence of bacterial antimicrobial resistance and the frequent development of biofilms within the wound area necessitates the identification of novel treatment strategies for use within infected chronic wounds. Here, several non-antibiotic compounds, polyhexamethylene biguanide (PHMB), curcumin, retinol, polysorbate 40, ethanol, and D-α-tocopheryl polyethylene glycol succinate 1000 (TPGS) were screened for their antibacterial and antibiofilm capabilities. The minimum inhibitory concentration (MIC) and crystal violet (CV) biofilm clearance against two bacteria frequently associated with infected chronic wounds, Staphylococcus aureus and Pseudomonas aeruginosa, were determined. PHMB was observed to have highly effective antibacterial activity against both bacteria, but its ability to disperse biofilms at MIC levels was variable. Meanwhile, TPGS had limited inhibitory activity but demonstrated potent antibiofilm properties. The subsequent combination of these two compounds in a formulation resulted in a synergistic enhancement of their capability to kill both S. aureus and P. aeruginosa and disperse their biofilms. Collectively, this work highlights the utility of combinatory approaches to the treatment of infected chronic wounds where bacterial colonization and biofilm formation remains significant issues.

Genome-wide association reveals host-specific genomic traits in Escherichia coli.

BACKGROUND: Escherichia coli is an opportunistic pathogen which colonizes various host species. However, to what extent genetic lineages of E. coli are adapted or restricted to specific hosts and the genomic determinants of such adaptation or restriction is poorly understood. RESULTS: We randomly sampled E. coli isolates from four countries (Germany, UK, Spain, and Vietnam), obtained from five host species (human, pig, cattle, chicken, and wild boar) over 16 years, from both healthy and diseased hosts, to construct a collection of 1198 whole-genome sequenced E. coli isolates. We identified associations between specific E. coli lineages and the host from which they were isolated. A genome-wide association study (GWAS) identified several E. coli genes that were associated with human, cattle, or chicken hosts, whereas no genes associated with the pig host could be found. In silico characterization of nine contiguous genes (collectively designated as nan-9) associated with the human host indicated that these genes are involved in the metabolism of sialic acids (Sia). In contrast, the previously described sialic acid regulon known as sialoregulon (i.e. nanRATEK-yhcH, nanXY, and nanCMS) was not associated with any host species. In vitro growth experiments with a Δnan-9 E. coli mutant strain, using the sialic acids 5-N-acetylneuraminic acid (Neu5Ac) and N-glycolylneuraminic acid (Neu5Gc) as sole carbon source, showed impaired growth behaviour compared to the wild-type. CONCLUSIONS: This study provides an extensive analysis of genetic determinants which may contribute to host specificity in E. coli. Our findings should inform risk analysis and epidemiological monitoring of (antimicrobial resistant) E. coli.

Rapid culture-independent loop-mediated isothermal amplification detection of antimicrobial resistance markers from environmental water samples.

Environmental water is considered one of the main vehicles for the transmission of antimicrobial resistance (AMR), posing an increasing threat to humans and animals health. Continuous efforts are being made to eliminate AMR; however, the detection of AMR pathogens from water samples often requires at least one culture step, which is time-consuming and can limit sensitivity. In this study, we employed comparative genomics to identify the prevalence of AMR genes within among: Escherichia coli, Klebsiella, Salmonella enterica and Acinetobacter, using publicly available genomes. The mcr-1, blaKPC (KPC-1 to KPC-4 alleles), blaOXA-48, blaOXA-23 and blaVIM (VIM-1 and VIM-2 alleles) genes are of great medical and veterinary significance, thus were selected as targets for the development of isothermal loop-mediated amplification (LAMP) detection assays. We also developed a rapid and sensitive sample preparation method for an integrated culture-independent LAMP-based detection from water samples. The developed assays successfully detected the five AMR gene markers from pond water within 1 h and were 100% sensitive and specific with a detection limit of 0.0625 µg/mL and 10 cfu/mL for genomic DNA and spiked bacterial cells, respectively. The integrated detection can be easily implemented in resource-limited areas to enhance One Health AMR surveillances and improve diagnostics.

Inflammatory Responses Induced by the Monophasic Variant of Salmonella Typhimurium in Pigs Play a Role in the High Shedder Phenotype and Fecal Microbiota Composition.

Pigs infected with Salmonella may excrete large amounts of Salmonella, increasing the risk of spread of this pathogen in the food chain. Identifying Salmonella high shedder pigs is therefore required to mitigate this risk. We analyzed immune-associated markers and composition of the gut microbiota in specific-pathogen-free pigs presenting different shedding levels after an oral infection with Salmonella. Immune response was studied through total blood cell counts, production of anti-Salmonella antibodies and cytokines, and gene expression quantification. Total Salmonella shedding for each pig was estimated and hierarchical clustering was used to cluster pigs into high, intermediate, and low shedders. Gut microbiota compositions were assessed using 16S rRNA microbial community profiling. Comparisons were made between control and inoculated pigs, then between high and low shedders pigs. Prior to infection, high shedders had similar immunological profiles compared to low shedders. As soon as 1 day postinoculation (dpi), significant differences on the cytokine production level and on the expression level of several host genes related to a proinflammatory response were observed between high and low shedders. Infection with Salmonella induced an early and profound remodeling of the immune response in all pigs, but the intensity of the response was stronger in high shedders. In contrast, low shedders seroconverted earlier than high shedders. Just after induction of the proinflammatory response (at 2 dpi), some taxa of the fecal microbiota were specific to the shedding phenotypes. This was related to the enrichment of several functional pathways related to anaerobic respiration in high shedders. In conclusion, our data show that the immune response to Salmonella modifies the fecal microbiota and subsequently could be responsible for shedding phenotypes. Influencing the gut microbiota and reducing intestinal inflammation could be a strategy for preventing Salmonella high shedding in livestock. IMPORTANCE Salmonellosis remains the most frequent human foodborne zoonosis after campylobacteriosis and pork meat is considered one of the major sources of human foodborne infections. At the farm, host heterogeneity in pig infection is problematic. High Salmonella shedders contribute more significantly to the spread of this foodborne pathogen in the food chain. The identification of predictive biomarkers for high shedders could help to control Salmonella in pigs. The purpose of the present study was to investigate why some pigs become super shedders and others low shedders. We thus investigated the differences in the fecal microbial composition and the immune response in orally infected pigs presenting different Salmonella shedding patterns. Our data show that the proinflammatory response induced by S. Typhimurium at 1 dpi could be responsible for the modification of the fecal microbiota composition and functions observed mainly at 2 and 3 dpi and to the low and super shedder phenotypes.

Detection of Necrosis in Digitised Whole-Slide Images for Better Grading of Canine Soft-Tissue Sarcomas Using Machine-Learning.

The definitive diagnosis of canine soft-tissue sarcomas (STSs) is based on histological assessment of formalin-fixed tissues. Assessment of parameters, such as degree of differentiation, necrosis score and mitotic score, give rise to a final tumour grade, which is important in determining prognosis and subsequent treatment modalities. However, grading discrepancies are reported to occur in human and canine STSs, which can result in complications regarding treatment plans. The introduction of digital pathology has the potential to help improve STS grading via automated determination of the presence and extent of necrosis. The detected necrotic regions can be factored in the grading scheme or excluded before analysing the remaining tissue. Here we describe a method to detect tumour necrosis in histopathological whole-slide images (WSIs) of STSs using machine learning. Annotated areas of necrosis were extracted from WSIs and the patches containing necrotic tissue fed into a pre-trained DenseNet161 convolutional neural network (CNN) for training, testing and validation. The proposed CNN architecture reported favourable results, with an overall validation accuracy of 92.7% for necrosis detection which represents the number of correctly classified data instances over the total number of data instances. The proposed method, when vigorously validated represents a promising tool to assist pathologists in evaluating necrosis in canine STS tumours, by increasing efficiency, accuracy and reducing inter-rater variation.

Rectified Classifier Chains for Prediction of Antibiotic Resistance From Multi-Labelled Data With Missing Labels.

Predicting Antimicrobial Resistance (AMR) from genomic data has important implications for human and animal healthcare, and especially given its potential for more rapid diagnostics and informed treatment choices. With the recent advances in sequencing technologies, applying machine learning techniques for AMR prediction have indicated promising results. Despite this, there are shortcomings in the literature concerning methodologies suitable for multi-drug AMR prediction and especially where samples with missing labels exist. To address this shortcoming, we introduce a Rectified Classifier Chain (RCC) method for predicting multi-drug resistance. This RCC method was tested using annotated features of genomics sequences and compared with similar multi-label classification methodologies. We found that applying the eXtreme Gradient Boosting (XGBoost) base model to our RCC model outperformed the second-best model, XGBoost based binary relevance model, by 3.3% in Hamming accuracy and 7.8% in F1-score. Additionally, we note that in the literature machine learning models applied to AMR prediction typically are unsuitable for identifying biomarkers informative of their decisions; in this study, we show that biomarkers contributing to AMR prediction can also be identified using the proposed RCC method. We expect this can facilitate genome annotation and pave the path towards identifying new biomarkers indicative of AMR.