Machine learning and applications in microbiology

Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry for differential identification of adult Schistosoma worms

BACKGROUND

Schistosomiasis is a major neglected tropical disease that affects up to 250 million individuals worldwide. The diagnosis of human schistosomiasis is mainly based on the microscopic detection of the parasite's eggs in the feces (i.e., for Schistosoma mansoni or Schistosoma japonicum) or urine (i.e., for Schistosoma haematobium) samples. However, these techniques have limited sensitivity, and microscopic expertise is waning outside endemic areas. Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has become the gold standard diagnostic method for the identification of bacteria and fungi in many microbiological laboratories. Preliminary studies have recently shown promising results for parasite identification using this method. The aims of this study were to develop and validate a species-specific database for adult Schistosoma identification, and to evaluate the effects of different storage solutions (ethanol and RNAlater) on spectra profiles.

METHODS

Adult worms (males and females) of S. mansoni and S. japonicum were obtained from experimentally infected mice. Species identification was carried out morphologically and by cytochrome oxidase 1 gene sequencing. Reference protein spectra for the creation of an in-house MALDI-TOF MS database were generated, and the database evaluated using new samples. We employed unsupervised (principal component analysis) and supervised (support vector machine, k-nearest neighbor, Random Forest, and partial least squares discriminant analysis) machine learning algorithms for the identification and differentiation of the Schistosoma species.

RESULTS

All the spectra were correctly identified by internal validation. For external validation, 58 new Schistosoma samples were analyzed, of which 100% (58/58) were correctly identified to genus level (log score values ≥ 1.7) and 81% (47/58) were reliably identified to species level (log score values ≥ 2). The spectra profiles showed some differences depending on the storage solution used. All the machine learning algorithms classified the samples correctly.

CONCLUSIONS

MALDI-TOF MS can reliably distinguish adult S. mansoni from S. japonicum.

Accuracy of mutual predictions of plant and microbial communities vary along a successional gradient in an alpine glacier forefield

Receding glaciers create virtually uninhabited substrates waiting for initial colonization of bacteria, fungi and plants. These glacier forefields serve as an ideal ecosystem for studying transformations in community composition and diversity over time and the interactions between taxonomic groups in a dynamic landscape. In this study, we investigated the relationships between the composition and diversity of bacteria, fungi, and plant communities as well as environmental factors along a successional gradient. We used random forest analysis assessing how well the composition and diversity of taxonomic groups and environmental factors mutually predict each other. We did not identify a single best indicator for all taxonomic and environmental properties, but found specific predictors to be most accurate for each taxon and environmental factor. The accuracy of prediction varied considerably along the successional gradient, highlighting the dynamic environmental conditions along the successional gradient that may also affect biotic interactions across taxa. This was also reflected by the high accuracy of predictions of plot age by all taxa. Next to plot age, our results indicate a strong importance of pH and temperature in structuring microbial and plant community composition. In addition, taxonomic groups predicted the community composition of each other more accurately than environmental factors, which may either suggest that these groups similarly respond to other not measured environmental factors or that direct interactions between taxa shape the composition of their communities. In contrast, diversity of taxa was not well predicted, suggesting that community composition of one taxonomic group is not a strong driver of the diversity of another group. Our study provides insights into the successional development of multidiverse communities shaped by complex interactions between taxonomic groups and the environment.

Identification of the mitophagy-related diagnostic biomarkers in hepatocellular carcinoma based on machine learning algorithm and construction of prognostic model

Background and aims

As a result of increasing numbers of studies most recently, mitophagy plays a vital function in the genesis of cancer. However, research on the predictive potential and clinical importance of mitophagy-related genes (MRGs) in hepatocellular carcinoma (HCC) is currently lacking. This study aimed to uncover and analyze the mitophagy-related diagnostic biomarkers in HCC using machine learning (ML), as well as to investigate its biological role, immune infiltration, and clinical significance.

Methods

In our research, by using Least absolute shrinkage and selection operator (LASSO) regression and support vector machine- (SVM-) recursive feature elimination (RFE) algorithm, six mitophagy genes (ATG12, CSNK2B, MTERF3, TOMM20, TOMM22, and TOMM40) were identified from twenty-nine mitophagy genes, next, the algorithm of non-negative matrix factorization (NMF) was used to separate the HCC patients into cluster A and B based on the six mitophagy genes. And there was evidence from multi-analysis that cluster A and B were associated with tumor immune microenvironment (TIME), clinicopathological features, and prognosis. After then, based on the DEGs (differentially expressed genes) between cluster A and cluster B, the prognostic model (riskScore) of mitophagy was constructed, including ten mitophagy-related genes (G6PD, KIF20A, SLC1A5, TPX2, ANXA10, TRNP1, ADH4, CYP2C9, CFHR3, and SPP1).

Results

This study uncovered and analyzed the mitophagy-related diagnostic biomarkers in HCC using machine learning (ML), as well as to investigate its biological role, immune infiltration, and clinical significance. Based on the mitophagy-related diagnostic biomarkers, we constructed a prognostic model(riskScore). Furthermore, we discovered that the riskScore was associated with somatic mutation, TIME, chemotherapy efficacy, TACE and immunotherapy effectiveness in HCC patients.

Conclusion

Mitophagy may play an important role in the development of HCC, and further research on this issue is necessary. Furthermore, the riskScore performed well as a standalone prognostic marker in terms of accuracy and stability. It can provide some guidance for the diagnosis and treatment of HCC patients.

Rapid classification of micro-particles using multi-angle dynamic light scatting and machine learning approach

The rapid classification of micro-particles has a vast range of applications in biomedical sciences and technology. In the given study, a prototype has been developed for the rapid detection of particle size using multi-angle dynamic light scattering and a machine learning approach by applying a support vector machine. The device consisted of three major parts: a laser light, an assembly of twelve sensors, and a data acquisition system. The laser light with a wavelength of 660 nm was directed towards the prepared sample. The twelve different photosensors were arranged symmetrically surrounding the testing sample to acquire the scattered light. The position of the photosensor was based on the Mie scattering theory to detect the maximum light scattering. In this study, three different spherical microparticles with sizes of 1, 2, and 4 μm were analyzed for the classification. The real-time light scattering signals were collected from each sample for 30 min. The power spectrum feature was evaluated from the acquired waveforms, and then recursive feature elimination was utilized to filter the features with the highest correlation. The machine learning classifiers were trained using the features with optimum conditions and the classification accuracies were evaluated. The results showed higher classification accuracies of 94.41%, 94.20%, and 96.12% for the particle sizes of 1, 2, and 4 μm, respectively. The given method depicted an overall classification accuracy of 95.38%. The acquired results showed that the developed system can detect microparticles within the range of 1-4 μm, with detection limit of 0.025 mg/ml. Therefore, the current study validated the performance of the device, and the given technique can be further applied in clinical applications for the detection of microbial particles.

Application of combined CRISPR screening for genetic and chemical-genetic interaction profiling in Mycobacterium tuberculosis

CRISPR screening, including CRISPR interference (CRISPRi) and CRISPR-knockout (CRISPR-KO) screening, has become a powerful technology in the genetic screening of eukaryotes. In contrast with eukaryotes, CRISPR-KO screening has not yet been applied to functional genomics studies in bacteria. Here, we constructed genome-scale CRISPR-KO and also CRISPRi libraries in Mycobacterium tuberculosis (Mtb). We first examined these libraries to identify genes essential for Mtb viability. Subsequent screening identified dozens of genes associated with resistance/susceptibility to the antitubercular drug bedaquiline (BDQ). Genetic and chemical validation of the screening results suggested that it provided a valuable resource to investigate mechanisms of action underlying the effects of BDQ and to identify chemical-genetic synergies that can be used to optimize tuberculosis therapy. In summary, our results demonstrate the potential for efficient genome-wide CRISPR-KO screening in bacteria and establish a combined CRISPR screening approach for high-throughput investigation of genetic and chemical-genetic interactions in Mtb.

Lactic Acid Bacteria as Potential Agents for Biocontrol of Aflatoxigenic and Ochratoxigenic Fungi

Aflatoxins (AF) and ochratoxin A (OTA) are fungal metabolites that have carcinogenic, teratogenic, embryotoxic, genotoxic, neurotoxic, and immunosuppressive effects in humans and animals. The increased consumption of plant-based foods and environmental conditions associated with climate change have intensified the risk of mycotoxin intoxication. This study aimed to investigate the abilities of eleven selected LAB strains to reduce/inhibit the growth of Aspergillus flavus, Aspergillus parasiticus, Aspergillus carbonarius, Aspergillus niger, Aspergillus welwitschiae, Aspergillus steynii, Aspergillus westerdijkiae, and Penicillium verrucosum and AF and OTA production under different temperature regiments. Data were treated by ANOVA, and machine learning (ML) models able to predict the growth inhibition percentage were built, and their performance was compared. All factors LAB strain, fungal species, and temperature significantly affected fungal growth and mycotoxin production. The fungal growth inhibition range was 0-100%. Overall, the most sensitive fungi to LAB treatments were P. verrucosum and A. steynii, while the least sensitive were A. niger and A. welwitschiae. The LAB strains with the highest antifungal activity were Pediococcus pentosaceus (strains S11sMM and M9MM5b). The reduction range for AF was 19.0% (aflatoxin B1)-60.8% (aflatoxin B2) and for OTA, 7.3-100%, depending on the bacterial and fungal strains and temperatures. The LAB strains with the highest anti-AF activity were the three strains of P. pentosaceus and Leuconostoc mesenteroides ssp. dextranicum (T2MM3), and those with the highest anti-OTA activity were Leuconostoc paracasei ssp. paracasei (3T3R1) and L. mesenteroides ssp. dextranicum (T2MM3). The best ML methods in predicting fungal growth inhibition were multilayer perceptron neural networks, followed by random forest. Due to anti-fungal and anti-mycotoxin capacity, the LABs strains used in this study could be good candidates as biocontrol agents against aflatoxigenic and ochratoxigenic fungi and AFL and OTA accumulation.

Development of a Prediction Method of Cell Density in Autotrophic/Heterotrophic Microorganism Mixtures by Machine Learning Using Absorbance Spectrum Data

Microflora is actively used to produce value-added materials in industry, and each cell density should be controlled for stable microflora use. In this study, a simple system evaluating the cell density was constructed with artificial intelligence (AI) using the absorbance spectra data of microflora. To set up the system, the prediction system for cell density based on machine learning was constructed using the spectra data as the feature from the mixture of Saccharomyces cerevisiae and Chlamydomonas reinhardtii. As the results of predicting cell density by extremely randomized trees, when the cell densities of S. cerevisiae and C. reinhardtii were shifted and fixed, the coefficient of determination (R²) was 0.8495; on the other hand, when the cell densities of S. cerevisiae and C. reinhardtii were fixed and shifted, the R² was 0.9232. To explain the prediction system, the randomized trees regressor of the decision tree-based ensemble learning method as the machine learning algorithm and Shapley additive explanations (SHAPs) as the explainable AI (XAI) to interpret the features contributing to the prediction results were used. As a result of the SHAP analyses, not only the optical density, but also the absorbance of the Soret and Q bands derived from the chloroplasts of C. reinhardtii could contribute to the prediction as the features. The simple cell density evaluating system could have an industrial impact.

Current advances and research prospects for agricultural and industrial uses of microbial strains available in world collections

Microorganisms are an important component of the ecosystem and have an enormous impact on human lives. Moreover, microorganisms are considered to have desirable effects on other co-existing species in a variety of habitats, such as agriculture and industries. In this way, they also have enormous environmental applications. Hence, collections of microorganisms with specific traits are a crucial step in developing new technologies to harness the microbial potential. Microbial culture collections (MCCs) are a repository for the preservation of a large variety of microbial species distributed throughout the world. In this context, culture collections (CCs) and microbial biological resource centres (mBRCs) are vital for the safeguarding and circulation of biological resources, as well as for the progress of the life sciences. Ex situ conservation of microorganisms tagged with specific traits in the collections is the crucial step in developing new technologies to harness their potential. Type strains are mainly used in taxonomic study, whereas reference strains are used for agricultural, biotechnological, pharmaceutical research and commercial work. Despite the tremendous potential in microbiological research, little effort has been made in the true sense to harness the potential of conserved microorganisms. This review highlights (1) the importance of available global microbial collections for man and (2) the use of these resources in different research and applications in agriculture, biotechnology, and industry. In addition, an extensive literature survey was carried out on preserved microorganisms from different collection centres using the Web of Science (WoS) and SCOPUS. This review also emphasizes knowledge gaps and future perspectives. Finally, this study provides a critical analysis of the current and future roles of microorganisms available in culture collections for different sustainable agricultural and industrial applications. This work highlights target-specific potential microbial strains that have multiple important metabolic and genetic traits for future research and use.

Clinical Microbiology in Detection and Identification of Emerging Microbial Pathogens: Past, Present and Future

Clinical microbiology has possessed a marvellous past, an important present and a bright future. Western medicine modernization started with the discovery of bacterial pathogens, and from then, clinical bacteriology became a cornerstone of diagnostics. Today, clinical microbiology uses standard techniques including Gram stain morphology, in vitro culture, antigen and antibody assays, and molecular biology both to establish a diagnosis and monitor the progression of microbial infections. Clinical microbiology has played a critical role in pathogen detection and characterization for emerging infectious diseases as evidenced by the ongoing COVID-19 pandemic. Revolutionary changes are on the way in clinical microbiology with the application of “-omic” techniques, including transcriptomics and metabolomics, and optimization of clinical practice configurations to improve outcomes of patients with infectious diseases.

Spatio-temporal spread and evolution of influenza A (H7N9) viruses

The influenza A (H7N9) virus has been seriously concerned for its potential to cause an influenza pandemic. To understand the spread and evolution process of the virus, a spatial and temporal Bayesian evolutionary analysis was conducted on 2,052 H7N9 viruses isolated during 2013 and 2018. It revealed that the H7N9 virus was probably emerged in a border area of Anhui Province in August 2012, approximately 6 months earlier than the first human case reported. Two major epicenters had been developed in the Yangtze River Delta and Peral River Delta regions by the end of 2013, and from where the viruses have also spread to other regions at an average speed of 6.57 km/d. At least 24 genotypes showing have been developed and each of them showed a distinct spatio-temporal distribution pattern. Furthermore, A random forest algorithm-based model has been developed to predict the occurrence risk of H7N9 virus. The model has a high overall forecasting precision (> 97%) and the monthly H7N9 occurrence risk for each county of China was predicted. These findings provide new insights for a comprehensive understanding of the origin, evolution, and occurrence risk of H7N9 virus. Moreover, our study also lays a theoretical basis for conducting risk-based surveillance and prevention of the disease.

Identification of the Diagnostic Biomarker VIPR1 in Hepatocellular Carcinoma Based on Machine Learning Algorithm

The purpose of this study was to identify the potential diagnostic biomarkers in hepatocellular carcinoma (HCC) by machine learning (ML) and to explore the significance of immune cell infiltration in HCC. From GEO datasets, the microarray datasets of HCC patients were obtained and downloaded. Differentially expressed genes (DEGs) were screened from five datasets of GSE57957, GSE84402, GSE112790, GSE113996, and GSE121248, totalling 125 normal liver tissues and 326 HCC tissues. In order to find the diagnostic indicators of HCC, the LASSO regression and the SVM-RFE algorithms were utilized. The prognostic value of VIPR1 was analyzed. Finally, the difference of immune cell infiltration between HCC tissues and normal liver tissues was evaluated by CIBERSORT algorithm. In this study, a total of 232 DEGs were identified in 125 normal liver tissues and 326 HCC tissues. 11 diagnostic markers were identified by LASSO regression and SVM-RFE algorithms. FCN2, ECM1, VIRP1, IGFALS, and ASPG genes with AUC>0.85 were regarded as candidate biomarkers with high diagnostic value, and the above results were verified in GSE36376. Survival analyses showed that VIPR1 and IGFALS were significantly correlated with the OS, while ASPG, ECM1, and FCN2 had no statistical significance with the OS. Multivariate assays indicated that VIPR1 gene could be used as an independent prognostic factor for HCC, while FCN2, ECM1, IGFALS, and ASPG could not be used as independent prognostic factors for HCC. Immune cell infiltration analyses showed that the expression of VIPR1 in HCC was positively correlated with the levels of several immune cells. Overall, VIPR1 gene can be used as a diagnostic feature marker of HCC and may be a potential target for the diagnosis and treatment of liver cancer in the future.

Evaluation of various distance computation methods for construction of haplotype-based phylogenies from large MLST dataset

Multi-locus sequence typing (MLST) is widely used to investigate genetic relationships among eukaryotic taxa, including parasitic pathogens. MLST analysis workflows typically involve construction of alignment-based phylogenetic trees - i.e., where tree structures are computed from nucleotide differences observed in a multiple sequence alignment (MSA). Notably, alignment-based phylogenetic methods require that all isolates/taxa are represented by a single sequence. When multiple loci are sequenced these sequences may be concatenated to produce one tree that includes information from all loci. Alignment-based phylogenetic techniques are robust and widely used yet possess some shortcomings, including how heterozygous sites are handled, intolerance for missing data (i.e., partial genotypes), and differences in the way insertions-deletions (indels) are scored/treated during tree construction. In certain contexts, 'haplotype-based' methods may represent a viable alternative to alignment-based techniques, as they do not possess the aforementioned limitations. This is namely because haplotype-based methods assess genetic similarity based on numbers of shared (i.e., intersecting) haplotypes as opposed to similarities in nucleotide composition observed in an MSA. For haplotype-based comparisons, choosing an appropriate distance statistic is fundamental, and several statistics are available to choose from. However, a comprehensive assessment of various available statistics for their ability to produce a robust haplotype-based phylogenetic reconstruction has not yet been performed. We evaluated seven distance statistics by applying them to extant MLST datasets from the gastrointestinal parasite Cyclospora cayetanensis and two species of pathogenic nematode of the genus Strongyloides. We compare the genetic relationships identified using each statistic to epidemiologic, geographic, and host metadata. We show that Barratt's heuristic definition of genetic distance was the most robust among the statistics evaluated. Consequently, it is proposed that Barratt's heuristic represents a useful approach for use in the context of challenging MLST datasets possessing features (i.e., high heterozygosity, partial genotypes, and indel or repeat-based polymorphisms) that confound or preclude the use of alignment-based methods.

ScanGrow: Deep Learning-Based Live Tracking of Bacterial Growth in Broth

Monitoring the growth of bacterial cultures is one of the most common techniques in microbiology. This is usually achieved by using expensive and bulky spectrophotometric plate readers which periodically measure the optical density of bacterial cultures during the incubation period. In this study, we present a completely novel way of obtaining bacterial growth curves based on the classification of scanned images of cultures rather than using spectrophotometric measurements. We trained a deep learning model with images of bacterial broths contained in microplates, and we integrated it into a custom-made software application that triggers a flatbed scanner to timely capture images, automatically processes the images, and represents all growth curves. The developed tool, ScanGrow, is presented as a low-cost and high-throughput alternative to plate readers, and it only requires a computer connected to a flatbed scanner and equipped with our open-source ScanGrow application. In addition, this application also assists in the pre-processing of data to create and evaluate new models, having the potential to facilitate many routine microbiological techniques.

DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

This work demonstrates and guides how to use a range of state-of-the-art artificial neural-networks to analyse bacterial microscopy images using the recently developed ZeroCostDL4Mic platform. We generated a database of image datasets used to train networks for various image analysis tasks and present strategies for data acquisition and curation, as well as model training. We showcase different deep learning (DL) approaches for segmenting bright field and fluorescence images of different bacterial species, use object detection to classify different growth stages in time-lapse imaging data, and carry out DL-assisted phenotypic profiling of antibiotic-treated cells. To also demonstrate the ability of DL to enhance low-phototoxicity live-cell microscopy, we showcase how image denoising can allow researchers to attain high-fidelity data in faster and longer imaging. Finally, artificial labelling of cell membranes and predictions of super-resolution images allow for accurate mapping of cell shape and intracellular targets. Our purposefully-built database of training and testing data aids in novice users' training, enabling them to quickly explore how to analyse their data through DL. We hope this lays a fertile ground for the efficient application of DL in microbiology and fosters the creation of tools for bacterial cell biology and antibiotic research.

Mapping Microbial Abundance and Prevalence to Changing Oxygen Concentration in Deep-Sea Sediments Using Machine Learning and Differential Abundance

Oxygen constitutes one of the strongest factors explaining microbial taxonomic variability in deep-sea sediments. However, deep-sea microbiome studies often lack the spatial resolution to study the oxygen gradient and transition zone beyond the oxic-anoxic dichotomy, thus leaving important questions regarding the microbial response to changing conditions unanswered. Here, we use machine learning and differential abundance analysis on 184 samples from 11 sediment cores retrieved along the Arctic Mid-Ocean Ridge to study how changing oxygen concentrations (1) are predicted by the relative abundance of higher taxa and (2) influence the distribution of individual Operational Taxonomic Units. We find that some of the most abundant classes of microorganisms can be used to classify samples according to oxygen concentration. At the level of Operational Taxonomic Units, however, representatives of common classes are not differentially abundant from high-oxic to low-oxic conditions. This weakened response to changing oxygen concentration suggests that the abundance and prevalence of highly abundant OTUs may be better explained by other variables than oxygen. Our results suggest that a relatively homogeneous microbiome is recruited to the benthos, and that the microbiome then becomes more heterogeneous as oxygen drops below 25 μM. Our analytical approach takes into account the oft-ignored compositional nature of relative abundance data, and provides a framework for extracting biologically meaningful associations from datasets spanning multiple sedimentary cores.

Using machine learning techniques to predict antimicrobial resistance in stone disease patients

PURPOSE

Artificial intelligence is part of our daily life and machine learning techniques offer possibilities unknown until now in medicine. This study aims to offer an evaluation of the performance of machine learning (ML) techniques, for predicting bacterial resistance in a urology department.

METHODS

Data were retrieved from laboratory information system (LIS) concerning 239 patients with urolithiasis hospitalized in the urology department of a tertiary hospital over a 1-year period (2019): age, gender, Gram stain (positive, negative), bacterial species, sample type, antibiotics and antimicrobial susceptibility. In our experiments, we compared several classifiers following a tenfold cross-validation approach on 2 different versions of our dataset; the first contained only information of Gram stain, while the second had knowledge of bacterial species.

RESULTS

The best results in the balanced dataset containing Gram stain, achieve a weighted average receiver operator curve (ROC) area of 0.768 and F-measure of 0.708, using a multinomial logistic regression model with a ridge estimator. The corresponding results of the balanced dataset, that contained bacterial species, achieve a weighted average ROC area of 0.874 and F-measure of 0.783, with a bagging classifier.

CONCLUSIONS

Artificial intelligence technology can be used for making predictions on antibiotic resistance patterns when knowing Gram staining with an accuracy of 77% and nearly 87% when identifying specific microorganisms. This knowledge can aid urologists prescribing the appropriate antibiotic 24-48 h before test results are known.

Machine Learning and Its Applications for Protozoal Pathogens and Protozoal Infectious Diseases

In recent years, massive attention has been attracted to the development and application of machine learning (ML) in the field of infectious diseases, not only serving as a catalyst for academic studies but also as a key means of detecting pathogenic microorganisms, implementing public health surveillance, exploring host-pathogen interactions, discovering drug and vaccine candidates, and so forth. These applications also include the management of infectious diseases caused by protozoal pathogens, such as Plasmodium, Trypanosoma, Toxoplasma, Cryptosporidium, and Giardia, a class of fatal or life-threatening causative agents capable of infecting humans and a wide range of animals. With the reduction of computational cost, availability of effective ML algorithms, popularization of ML tools, and accumulation of high-throughput data, it is possible to implement the integration of ML applications into increasing scientific research related to protozoal infection. Here, we will present a brief overview of important concepts in ML serving as background knowledge, with a focus on basic workflows, popular algorithms (e.g., support vector machine, random forest, and neural networks), feature extraction and selection, and model evaluation metrics. We will then review current ML applications and major advances concerning protozoal pathogens and protozoal infectious diseases through combination with correlative biology expertise and provide forward-looking insights for perspectives and opportunities in future advances in ML techniques in this field.

Interfacing Machine Learning and Microbial Omics: A Promising Means to Address Environmental Challenges

Microbial communities are ubiquitous and carry an exceptionally broad metabolic capability. Upon environmental perturbation, microbes are also amongst the first natural responsive elements with perturbation-specific cues and markers. These communities are thereby uniquely positioned to inform on the status of environmental conditions. The advent of microbial omics has led to an unprecedented volume of complex microbiological data sets. Importantly, these data sets are rich in biological information with potential for predictive environmental classification and forecasting. However, the patterns in this information are often hidden amongst the inherent complexity of the data. There has been a continued rise in the development and adoption of machine learning (ML) and deep learning architectures for solving research challenges of this sort. Indeed, the interface between molecular microbial ecology and artificial intelligence (AI) appears to show considerable potential for significantly advancing environmental monitoring and management practices through their application. Here, we provide a primer for ML, highlight the notion of retaining biological sample information for supervised ML, discuss workflow considerations, and review the state of the art of the exciting, yet nascent, interdisciplinary field of ML-driven microbial ecology. Current limitations in this sphere of research are also addressed to frame a forward-looking perspective toward the realization of what we anticipate will become a pivotal toolkit for addressing environmental monitoring and management challenges in the years ahead.

Combination of MALDI-TOF Mass Spectrometry and Machine Learning for Rapid Antimicrobial Resistance Screening: The Case of Campylobacter spp

While MALDI-TOF mass spectrometry (MS) is widely considered as the reference method for the rapid and inexpensive identification of microorganisms in routine laboratories, less attention has been addressed to its ability for detection of antimicrobial resistance (AMR). Recently, some studies assessed its potential application together with machine learning for the detection of AMR in clinical pathogens. The scope of this study was to investigate MALDI-TOF MS protein mass spectra combined with a prediction approach as an AMR screening tool for relevant foodborne pathogens, such as Campylobacter coli and Campylobacter jejuni. A One-Health panel of 224 C. jejuni and 116 C. coli strains was phenotypically tested for seven antimicrobial resistances, i.e., ciprofloxacin, erythromycin, tetracycline, gentamycin, kanamycin, streptomycin, and ampicillin, independently, and were submitted, after an on- and off-plate protein extraction, to MALDI Biotyper analysis, which yielded one average spectra per isolate and type of extraction. Overall, high performance was observed for classifiers detecting susceptible as well as ciprofloxacin- and tetracycline-resistant isolates. A maximum sensitivity and a precision of 92.3 and 81.2%, respectively, were reached. No significant prediction performance differences were observed between on- and off-plate types of protein extractions. Finally, three putative AMR biomarkers for fluoroquinolones, tetracyclines, and aminoglycosides were identified during the current study. Combination of MALDI-TOF MS and machine learning could be an efficient and inexpensive tool to swiftly screen certain AMR in foodborne pathogens, which may enable a rapid initiation of a precise, targeted antibiotic treatment.

LIM Tracker: a software package for cell tracking and analysis with advanced interactivity

Cell tracking is one of the most critical tools for time-lapse image analysis to observe cell behavior and cell lineages over a long period of time. However, the accompanying graphical user interfaces are often difficult to use and do not incorporate seamless manual correction, data analysis tools, or simple training set design tools if it is machine learning based. In this paper, we introduce our cell tracking software "LIM Tracker". This software has a conventional tracking function consisting of recognition processing and link processing, a sequential search-type tracking function based on pattern matching, and a manual tracking function. LIM Tracker enables the seamless use of these functions. In addition, the system incorporates a highly interactive and interlocking data visualization method, which displays analysis result in real time, making it possible to flexibly correct the data and reduce the burden of tracking work. Moreover, recognition functions with deep learning (DL) are also available, which can be used for a wide range of targets including stain-free images. LIM Tracker allows researchers to track living objects with good usability and high versatility for various targets. We present a tracking case study based on fluorescence microscopy images (NRK-52E/EKAREV-NLS cells or MCF-10A/H2B-iRFP-P2A-mScarlet-I-hGem-P2A-PIP-NLS-mNeonGreen cells) and phase contrast microscopy images (Glioblastoma-astrocytoma U373 cells). LIM Tracker is implemented as a plugin for ImageJ/Fiji. The software can be downloaded from https://github.com/LIMT34/LIM-Tracker .

Recent advances in microbial community analysis from machine learning of multiparametric flow cytometry data

Dynamic analysis of microbial composition is crucial for understanding community functioning and detecting dysbiosis. Compositional information is mostly obtained through sequencing of taxonomic markers or whole meta-genomes, which may be productively complemented by real-time quantitative community multiparametric flow cytometry data (FCM). Patterns and clusters in FCM community data can be distinguished and compared by unsupervised machine learning. Alternatively, FCM data from preselected individual strain phenotypes can be used for supervised machine-training in order to differentiate similar cell types within communities. Both types of machine learning can quantitatively deconvolute community FCM data sets and rapidly analyse global changes in response to treatment. Procedures may further be optimized for recurrent microbiome samples to simultaneously quantify physiological and compositional states.

BowSaw: Inferring Higher-Order Trait Interactions Associated With Complex Biological Phenotypes

Machine learning is helping the interpretation of biological complexity by enabling the inference and classification of cellular, organismal and ecological phenotypes based on large datasets, e.g., from genomic, transcriptomic and metagenomic analyses. A number of available algorithms can help search these datasets to uncover patterns associated with specific traits, including disease-related attributes. While, in many instances, treating an algorithm as a black box is sufficient, it is interesting to pursue an enhanced understanding of how system variables end up contributing to a specific output, as an avenue toward new mechanistic insight. Here we address this challenge through a suite of algorithms, named BowSaw, which takes advantage of the structure of a trained random forest algorithm to identify combinations of variables (“rules”) frequently used for classification. We first apply BowSaw to a simulated dataset and show that the algorithm can accurately recover the sets of variables used to generate the phenotypes through complex Boolean rules, even under challenging noise levels. We next apply our method to data from the integrative Human Microbiome Project and find previously unreported high-order combinations of microbial taxa putatively associated with Crohn’s disease. By leveraging the structure of trees within a random forest, BowSaw provides a new way of using decision trees to generate testable biological hypotheses.