RESUMEN
BackgroundAs increasing antibiotic resistance in Acinetobacter baumannii poses a global healthcare challenge, understanding its evolution is crucial for effective control strategies.AimWe aimed to evaluate the epidemiology, antimicrobial susceptibility and main resistance mechanisms of Acinetobacter spp. in Spain in 2020, and to explore temporal trends of A. baumannii.MethodsWe collected 199 single-patient Acinetobacter spp. clinical isolates in 2020 from 18 Spanish tertiary hospitals. Minimum inhibitory concentrations (MICs) for nine antimicrobials were determined. Short-read sequencing was performed for all isolates, and targeted long-read sequencing for A. baumannii. Resistance mechanisms, phylogenetics and clonality were assessed. Findings on resistance rates and infection types were compared with data from 2000 and 2010.ResultsCefiderocol and colistin exhibited the highest activity against A. baumannii, although colistin susceptibility has significantly declined over 2 decades. A. non-baumannii strains were highly susceptible to most tested antibiotics. Of the A. baumannii isolates, 47.5% (56/118) were multidrug-resistant (MDR). Phylogeny and clonal relationship analysis of A. baumannii revealed five prevalent international clones, notably IC2 (ST2, n = 52; ST745, n = 4) and IC1 (ST1, n = 14), and some episodes of clonal dissemination. Genes bla OXA-23, bla OXA-58 and bla OXA-24/40 were identified in 49 (41.5%), eight (6.8%) and one (0.8%) A. baumannii isolates, respectively. ISAba1 was found upstream of the gene (a bla OXA-51-like) in 10 isolates.ConclusionsThe emergence of OXA-23-producing ST1 and ST2, the predominant MDR lineages, shows a pivotal shift in carbapenem-resistant A. baumannii (CRAB) epidemiology in Spain. Coupled with increased colistin resistance, these changes underscore notable alterations in regional antimicrobial resistance dynamics.
Asunto(s)
Infecciones por Acinetobacter , Acinetobacter baumannii , Humanos , Colistina/farmacología , beta-Lactamasas/genética , Proteína 1 Similar al Receptor de Interleucina-1 , Infecciones por Acinetobacter/tratamiento farmacológico , Infecciones por Acinetobacter/epidemiología , Antibacterianos/farmacología , Acinetobacter baumannii/genética , Genómica , Pruebas de Sensibilidad Microbiana , Proteínas Bacterianas/genéticaRESUMEN
Drug hypersensitivity reactions (DHRs) to platinum-based compounds (PCs) are on the rise, and their personalized and safe management is essential to enable first-line treatment for these cancer patients. This study aimed to evaluate the usefulness of the basophil activation test by flow cytometry (BAT-FC) and the newly developed sIgE-microarray and BAT-microarray in diagnosing IgE-mediated hypersensitivity reactions to PCs. A total of 24 patients with DHRs to PCs (20 oxaliplatin and four carboplatin) were evaluated: thirteen patients were diagnosed as allergic with positive skin tests (STs) or drug provocation tests (DPTs), six patients were diagnosed as non-allergic with negative STs and DPTs, and five patients were classified as suspected allergic because DPTs could not be performed. In addition, four carboplatin-tolerant patients were included as controls. The BAT-FC was positive in 2 of 13 allergic patients, with a sensitivity of 15.4% and specificity of 100%. However, the sIgE- and BAT-microarray were positive in 11 of 13 DHR patients, giving a sensitivity of over 84.6% and a specificity of 90%. Except for one patient, all samples from the non-allergic and control groups were negative for sIgE- and BAT-microarray. Our experience indicated that the sIgE- and BAT-microarray could be helpful in the endophenotyping of IgE-mediated hypersensitivity reactions to PCs and may provide an advance in decision making for drug provocation testing.
Asunto(s)
Hipersensibilidad a las Drogas , Hipersensibilidad Inmediata , Poliquetos , Fármacos Sensibilizantes a Radiaciones , Tionas , Humanos , Animales , Prueba de Desgranulación de los Basófilos , Compuestos de Platino , Carboplatino/efectos adversos , Hipersensibilidad a las Drogas/diagnóstico , Antineoplásicos Alquilantes , Inmunoglobulina ERESUMEN
In the first wave of COVID-19, up to 20% of patients had skin lesions with variable characteristics. There is no clear evidence of the involvement of the SARS-CoV-2 virus in all cases; some of these lesions may be secondary to drug hypersensitivity. To analyze the possible cause of the skin lesions, we performed a complete allergology study on 11 patients. One year after recovery from COVID-19, we performed a lymphocyte transformation test (LTT) and Th1/Th2 cytokine secretion assays for PBMCs. We included five nonallergic patients treated with the same drugs without lesions. Except for one patient who had an immediate reaction to azithromycin, all patients had a positive LTT result for at least one of the drugs tested (azithromycin, clavulanic acid, hydroxychloroquine, lopinavir, and ritonavir). None of the nonallergic patients had a positive LTT result. We found mixed Th1/Th2 cytokine secretion (IL-4, IL-5, IL-13, and IFN-γ) in patients with skin lesions corresponding to mixed drug hypersensitivity type IVa and IVb. In all cases, we identified a candidate drug as the culprit for skin lesions during SARS-CoV-2 infection, although only three patients had a positive drug challenge. Therefore, it would be reasonable to recommend avoiding the drug in question in all cases.
Asunto(s)
COVID-19 , Hipersensibilidad a las Drogas , Humanos , Azitromicina/efectos adversos , Activación de Linfocitos , SARS-CoV-2 , Hipersensibilidad a las Drogas/diagnóstico , Hipersensibilidad a las Drogas/etiología , Citocinas , Prueba de COVID-19RESUMEN
Providing the visual complexity of an image in terms of impact or aesthetic preference can be of great applicability in areas such as psychology or marketing. To this end, certain areas such as Computer Vision have focused on identifying features and computational models that allow for satisfactory results. This paper studies the application of recent ML models using input images evaluated by humans and characterized by features related to visual complexity. According to the experiments carried out, it was confirmed that one of these methods, Correlation by Genetic Search (CGS), based on the search for minimum sets of features that maximize the correlation of the model with respect to the input data, predicted human ratings of image visual complexity better than any other model referenced to date in terms of correlation, RMSE or minimum number of features required by the model. In addition, the variability of these terms were studied eliminating images considered as outliers in previous studies, observing the robustness of the method when selecting the most important variables to make the prediction.
RESUMEN
BACKGROUND: To date, the molecular mechanisms that underlie residual feed intake (RFI) in pigs are unknown. Results from different genome-wide association studies and gene expression analyses are not always consistent. The aim of this research was to use machine learning to identify genes associated with feed efficiency (FE) using transcriptomic (RNA-Seq) data from pigs that are phenotypically extreme for RFI. METHODS: RFI was computed by considering within-sex regression on mean metabolic body weight, average daily gain, and average backfat gain. RNA-Seq analyses were performed on liver and duodenum tissue from 32 high and 33 low RFI pigs collected at 153 d of age. Machine-learning algorithms were used to predict RFI class based on gene expression levels in liver and duodenum after adjusting for batch effects. Genes were ranked according to their contribution to the classification using the permutation accuracy importance score in an unbiased random forest (RF) algorithm based on conditional inference. Support vector machine, RF, elastic net (ENET) and nearest shrunken centroid algorithms were tested using different subsets of the top rank genes. Nested resampling for hyperparameter tuning was implemented with tenfold cross-validation in the outer and inner loops. RESULTS: The best classification was obtained with ENET using the expression of 200 genes in liver [area under the receiver operating characteristic curve (AUROC): 0.85; accuracy: 0.78] and 100 genes in duodenum (AUROC: 0.76; accuracy: 0.69). Canonical pathways and candidate genes that were previously reported as associated with FE in several species were identified. The most remarkable pathways and genes identified were NRF2-mediated oxidative stress response and aldosterone signalling in epithelial cells, the DNAJC6, DNAJC1, MAPK8, PRKD3 genes in duodenum, and melatonin degradation II, PPARα/RXRα activation, and GPCR-mediated nutrient sensing in enteroendocrine cells and SMOX, IL4I1, PRKAR2B, CLOCK and CCK genes in liver. CONCLUSIONS: ML algorithms and RNA-Seq expression data were found to provide good performance for classifying pigs into high or low RFI groups. Classification was better with gene expression data from liver than from duodenum. Genes associated with FE in liver and duodenum tissue that can be used as predictive biomarkers for this trait were identified.
Asunto(s)
Fenómenos Fisiológicos Nutricionales de los Animales/genética , Perfilación de la Expresión Génica/métodos , Aprendizaje Automático , Porcinos/genética , Transcriptoma , Alimentación Animal , Animales , Cruzamiento/métodos , Porcinos/fisiologíaAsunto(s)
Alérgenos , Hipersensibilidad , Animales , Humanos , Carboxipeptidasa B , Erizos , Vesículas Secretoras , LectinasRESUMEN
Signaling proteins are an important topic in drug development due to the increased importance of finding fast, accurate and cheap methods to evaluate new molecular targets involved in specific diseases. The complexity of the protein structure hinders the direct association of the signaling activity with the molecular structure. Therefore, the proposed solution involves the use of protein star graphs for the peptide sequence information encoding into specific topological indices calculated with S2SNet tool. The Quantitative Structure-Activity Relationship classification model obtained with Machine Learning techniques is able to predict new signaling peptides. The best classification model is the first signaling prediction model, which is based on eleven descriptors and it was obtained using the Support Vector Machines-Recursive Feature Elimination (SVM-RFE) technique with the Laplacian kernel (RFE-LAP) and an AUROC of 0.961. Testing a set of 3114 proteins of unknown function from the PDB database assessed the prediction performance of the model. Important signaling pathways are presented for three UniprotIDs (34 PDBs) with a signaling prediction greater than 98.0%.
Asunto(s)
Péptidos y Proteínas de Señalización Intracelular/química , Aprendizaje Automático , Bases de Datos de Proteínas , Humanos , Relación Estructura-Actividad Cuantitativa , Transducción de Señal/fisiologíaRESUMEN
Due to the importance of hot-spots (HS) detection and the efficiency of computational methodologies, several HS detecting approaches have been developed. The current paper presents new models to predict HS for protein-protein and protein-nucleic acid interactions with better statistics compared with the ones currently reported in literature. These models are based on solvent accessible surface area (SASA) and genetic conservation features subjected to simple Bayes networks (protein-protein systems) and a more complex multi-objective genetic algorithm-support vector machine algorithms (protein-nucleic acid systems). The best models for these interactions have been implemented in two free Web tools.
Asunto(s)
Biología Computacional/métodos , ADN/metabolismo , Proteínas/metabolismo , ARN/metabolismo , Solventes/química , Algoritmos , ADN/química , Internet , Modelos Moleculares , Conformación de Ácido Nucleico , Unión Proteica , Conformación Proteica , Proteínas/química , ARN/química , Máquina de Vectores de Soporte , Propiedades de SuperficieRESUMEN
Block-matching techniques have been widely used in the task of estimating displacement in medical images, and they represent the best approach in scenes with deformable structures such as tissues, fluids, and gels. In this article, a new iterative block-matching technique-based on successive deformation, search, fitting, filtering, and interpolation stages-is proposed to measure elastic displacements in two-dimensional polyacrylamide gel electrophoresis (2D-PAGE) images. The proposed technique uses different deformation models in the task of correlating proteins in real 2D electrophoresis gel images, obtaining an accuracy of 96.6% and improving the results obtained with other techniques. This technique represents a general solution, being easy to adapt to different 2D deformable cases and providing an experimental reference for block-matching algorithms.
Asunto(s)
Electroforesis en Gel Bidimensional/métodos , Procesamiento de Imagen Asistido por Computador/métodos , Modelos Teóricos , Proteómica/métodos , AlgoritmosRESUMEN
The cell death (CD) is a dynamic biological function involved in physiological and pathological processes. Due to the complexity of CD, there is a demand for fast theoretical methods that can help to find new CD molecular targets. The current work presents the first classification model to predict CD-related proteins based on Markov Mean Properties. These protein descriptors have been calculated with the MInD-Prot tool using the topological information of the amino acid contact networks of the 2423 protein chains, five atom physicochemical properties and the protein 3D regions. The Machine Learning algorithms from Weka were used to find the best classification model for CD-related protein chains using all 20 attributes. The most accurate algorithm to solve this problem was K*. After several feature subset methods, the best model found is based on only 11 variables and is characterized by the Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.992 and the true positive rate (TP Rate) of 88.2% (validation set). 7409 protein chains labeled with "unknown function" in the PDB Databank were analyzed with the best model in order to predict the CD-related biological activity. Thus, several proteins have been predicted to have CD-related function in Homo sapiens: 3DRX-involved in virus-host interaction biological process, protein homooligomerization; 4DWF-involved in cell differentiation, chromatin modification, DNA damage response, protein stabilization; 1IUR-involved in ATP binding, chaperone binding; 1J7D-involved in DNA double-strand break processing, histone ubiquitination, nucleotide-binding oligomerization; 1UTU-linked with DNA repair, regulation of transcription; 3EEC-participating to the cellular membrane organization, egress of virus within host cell, class mediator resulting in cell cycle arrest, negative regulation of ubiquitin-protein ligase activity involved in mitotic cell cycle and apoptotic process. Other proteins from bacteria predicted as CD-related are 2G3V - a CAG pathogenicity island protein 13 from Helicobacter pylori, 4G5A - a hypothetical protein in Bacteroides thetaiotaomicron, 1YLK-involved in the nitrogen metabolism of Mycobacterium tuberculosis, and 1XSV - with possible DNA/RNA binding domains. The results demonstrated the possibility to predict CD-related proteins using molecular information encoded into the protein 3D structure. Thus, the current work demonstrated the possibility to predict new molecular targets involved in cell-death processes.
Asunto(s)
Cadenas de Markov , Proteínas/clasificación , Algoritmos , Muerte Celular , Bases de Datos de Proteínas , Estándares de ReferenciaRESUMEN
This study aimed to develop a robust classification scheme for stratifying patients based on vaginal microbiome. By employing consensus clustering analysis, we identified four distinct clusters using a cohort that includes individuals diagnosed with Bacterial Vaginosis (BV) as well as control participants, each characterized by unique patterns of microbiome species abundances. Notably, the consistent distribution of these clusters was observed across multiple external cohorts, such as SRA022855, SRA051298, PRJNA208535, PRJNA797778, and PRJNA302078 obtained from public repositories, demonstrating the generalizability of our findings. We further trained an elastic net model to predict these clusters, and its performance was evaluated in various external cohorts. Moreover, we developed VIBES, a user-friendly R package that encapsulates the model for convenient implementation and enables easy predictions on new data. Remarkably, we explored the applicability of this new classification scheme in providing valuable insights into disease progression, treatment response, and potential clinical outcomes in BV patients. Specifically, we demonstrated that the combined output of VIBES and VALENCIA scores could effectively predict the response to metronidazole antibiotic treatment in BV patients. Therefore, this study's outcomes contribute to our understanding of BV heterogeneity and lay the groundwork for personalized approaches to BV management and treatment selection.
RESUMEN
The enantioselective Brønsted acid-catalyzed α-amidoalkylation reaction is a useful procedure is for the production of new drugs and natural products. In this context, Chiral Phosphoric Acid (CPA) catalysts are versatile catalysts for this type of reactions. The selection and design of new CPA catalysts for different enantioselective reactions has a dual interest because new CPA catalysts (tools) and chiral drugs or materials (products) can be obtained. However, this process is difficult and time consuming if approached from an experimental trial and error perspective. In this work, an Heuristic Perturbation-Theory and Machine Learning (HPTML) algorithm was used to seek a predictive model for CPA catalysts performance in terms of enantioselectivity in α-amidoalkylation reactions with R2 = 0.96 overall for training and validation series. It involved a Monte Carlo sampling of > 100,000 pairs of query and reference reactions. In addition, the computational and experimental investigation of a new set of intermolecular α-amidoalkylation reactions using BINOL-derived N-triflylphosphoramides as CPA catalysts is reported as a case of study. The model was implemented in a web server called MATEO: InterMolecular Amidoalkylation Theoretical Enantioselectivity Optimization, available online at: https://cptmltool.rnasa-imedir.com/CPTMLTools-Web/mateo . This new user-friendly online computational tool would enable sustainable optimization of reaction conditions that could lead to the design of new CPA catalysts along with new organic synthesis products.
RESUMEN
Peptide microarrays are a powerful tool to identify linear epitopes of food allergens in a high-throughput manner. The main advantages of the microarray-based immunoassay are as follows: the possibility to assay thousands of targets simultaneously, the requirement of a low volume of serum, the more robust statistical analysis, and the possibility to test simultaneously several immunoglobulin subclasses. Among them, the last one has a special interest in the field of food allergy, because the development of tolerance to food allergens has been associated with a decrease in IgE and an increase in IgG4 levels against linear epitopes. However, the main limitation to the clinical use of microarray is the automated analysis of the data. Recent studies mapping the linear epitopes of food allergens with peptide microarray immunoassays have identified peptide biomarkers that can be used for early diagnosis of food allergies and to predict their severity or the self-development of tolerance. Using this approach, we have worked on epitope mapping of the two most important food allergens in the Spanish population, cow's milk, and chicken eggs. The final aim of these studies is to define subsets of peptides that could be used as biomarkers to improve the diagnosis and prognosis of food allergies. This chapter describes the protocol to produce microarrays using a library of overlapping peptides corresponding to the primary sequences of food allergens and data acquisition and analysis of IgE and IgG4 binding epitopes.
Asunto(s)
Hipersensibilidad a los Alimentos , Inmunoglobulina G , Alérgenos , Animales , Biomarcadores , Bovinos , Mapeo Epitopo/métodos , Epítopos , Femenino , Hipersensibilidad a los Alimentos/diagnóstico , Inmunoensayo/métodos , Inmunoglobulina E/metabolismo , PéptidosRESUMEN
This article seeks to provide a snapshot of the security of Wi-Fi access points in the metropolitan area of A Coruña. First, we discuss the options for obtaining a tool that allows the collection and storage of auditable information from Wi-Fi networks, from location to signal strength, security protocol or the list of connected clients. Subsequently, an analysis is carried out aimed at identifying password patterns in Wi-Fi networks with WEP, WPA and WPA2 security protocols. For this purpose, a password recovery tool called Hashcat was used to execute dictionary or brute force attacks, among others, with various word collections. The coverage of the access points in which passwords were decrypted is displayed on a heat map that represents various levels of signal quality depending on the signal strength. From the handshakes obtained, and by means of brute force, we will try to crack as many passwords as possible in order to create a targeted and contextualized dictionary both by geographical location and by the nature of the owner of the access point. Finally, we will propose a contextualized grammar that minimizes the size of the dictionary with respect to the most used ones and unifies the decryption capacity of the combination of all of them.
RESUMEN
Inflammatory bowel disease (IBD) is a chronic disease with unknown pathophysiological mechanisms. There is evidence of the role of microorganims in this disease development. Thanks to the open access to multiple omics data, it is possible to develop predictive models that are able to prognosticate the course and development of the disease. The interpretability of these models, and the study of the variables used, allows the identification of biological aspects of great importance in the development of the disease. In this work we generated a metagenomic signature with predictive capacity to identify IBD from fecal samples. Different Machine Learning models were trained, obtaining high performance measures. The predictive capacity of the identified signature was validated in two external cohorts. More precisely a cohort containing samples from patients suffering Ulcerative Colitis and another from patients suffering Crohn's Disease, the two major subtypes of IBD. The results obtained in this validation (AUC 0.74 and AUC = 0.76, respectively) show that our signature presents a generalization capacity in both subtypes. The study of the variables within the model, and a correlation study based on text mining, identified different genera that play an important and common role in the development of these two subtypes.
RESUMEN
Carbapenem resistance is increasing among Gram-negative bacteria, including the genus Acinetobacter. This study aimed to characterize, for the first time, the development of carbapenem resistance in clinical isolates of Acinetobacter junii and Acinetobacter nosocomialis conferred by the acquisition of a plasmid-borne blaOXA-24/40 gene and also to characterize the dissemination of this gene between species of Acinetobacter. Carbapenem-resistant A. nosocomialis HUAV-AN66 and A. junii HUAV-AJ77 strains were isolated in the Arnau de Vilanova Hospital (Spain). The genomes were sequenced, and in silico analysis were performed to characterize the genetic environment and the OXA-24/40 transmission mechanism. Antibiotic MICs were determined, and horizontal transfer assays were conducted to evaluate interspecies transmission of OXA-24/40. Carbapenems MICs obtained were ≥64 mg/L for HUAV-AN66 and HUAV-AJ77. Genome analysis revealed the presence in both strains of a new plasmid, designated pHUAV/OXA-24/40, harboring the carbapenem-resistance gene blaOXA-24/40 and flanked by sequences XerC/XerD. pHUAV/OXA-24/40 was successfully transferred from A. nosocomialis and A. junii to a carbapenem-susceptible A. baumannii strain, thus conferring carbapenem resistance. A second plasmid (pHUAV/AMG-R) was identified in both clinical isolates for the successful horizontal transfer of pHUAV/OXA-24/40. blaOXA-24/40-carrying plasmids of the GR12 group and showing high identity with pHUAV/OXA-24/40 were identified in at least 8 Acinetobacter species. In conclusion the carbapenemase OXA-24/40 is described for the first time in A. nosocomialis and A. junii. In both isolates the blaOXA-24/40 gene was located in the GR12 pHUAV/OXA-24/40 plasmid. GR12 plasmids are implicated in the dissemination and spread of carbapenem resistance among Acinetobacter species. IMPORTANCE Acinetobacter baumannii is one of the most relevant pathogens in terms of antibiotic resistance. The main resistance mechanisms are the carbapenem-hydrolyzing class D ß-lactamases (CHDLs), especially OXA-23 and OXA-24/40. In addition to A. baumannii, there are other species within the genus Acinetobacter, which in general exhibit much lower resistance rates. In this work we characterize for the first time two clinical isolates of Acinetobacter nosocomialis and Acinetobacter junii, isolated in the same hospital, carrying the carbapenemase OXA-24/40 and displaying high resistance rates to carbapenems. By means of bioinformatics analysis we have also been able to characterize the mechanism by which this carbapenemase is horizontally transferred interspecies of Acinetobacter spp. The dissemination of carbapenemase OXA-24/40 between non-baumannii Acinetobacter species is concerning since it prevents the use of most ß-lactam antibiotics in the fight against these resistant isolates.
Asunto(s)
Infecciones por Acinetobacter/microbiología , Acinetobacter/efectos de los fármacos , Acinetobacter/genética , Antibacterianos/farmacología , Carbapenémicos/farmacología , Transferencia de Gen Horizontal , Acinetobacter/enzimología , Proteínas Bacterianas/genética , Proteínas Bacterianas/metabolismo , Farmacorresistencia Bacteriana , Genoma Bacteriano , Genómica , Humanos , Pruebas de Sensibilidad Microbiana , Plásmidos/genética , Plásmidos/metabolismo , beta-Lactamasas/genética , beta-Lactamasas/metabolismoRESUMEN
In recent years, machine learning (ML) researchers have changed their focus towards biological problems that are difficult to analyse with standard approaches. Large initiatives such as The Cancer Genome Atlas (TCGA) have allowed the use of omic data for the training of these algorithms. In order to study the state of the art, this review is provided to cover the main works that have used ML with TCGA data. Firstly, the principal discoveries made by the TCGA consortium are presented. Once these bases have been established, we begin with the main objective of this study, the identification and discussion of those works that have used the TCGA data for the training of different ML approaches. After a review of more than 100 different papers, it has been possible to make a classification according to following three pillars: the type of tumour, the type of algorithm and the predicted biological problem. One of the conclusions drawn in this work shows a high density of studies based on two major algorithms: Random Forest and Support Vector Machines. We also observe the rise in the use of deep artificial neural networks. It is worth emphasizing, the increase of integrative models of multi-omic data analysis. The different biological conditions are a consequence of molecular homeostasis, driven by both protein coding regions, regulatory elements and the surrounding environment. It is notable that a large number of works make use of genetic expression data, which has been found to be the preferred method by researchers when training the different models. The biological problems addressed have been classified into five types: prognosis prediction, tumour subtypes, microsatellite instability (MSI), immunological aspects and certain pathways of interest. A clear trend was detected in the prediction of these conditions according to the type of tumour. That is the reason for which a greater number of works have focused on the BRCA cohort, while specific works for survival, for example, were centred on the GBM cohort, due to its large number of events. Throughout this review, it will be possible to go in depth into the works and the methodologies used to study TCGA cancer data. Finally, it is intended that this work will serve as a basis for future research in this field of study.
RESUMEN
In recent years, microbiota has become an increasingly relevant factor for the understanding and potential treatment of diseases. In this work, based on the data reported by the largest study of microbioma in the world, a classification model has been developed based on Machine Learning (ML) capable of predicting the country of origin (United Kingdom vs United States) according to metagenomic data. The data were used for the training of a glmnet algorithm and a Random Forest algorithm. Both algorithms obtained similar results (0.698 and 0.672 in AUC, respectively). Furthermore, thanks to the application of a multivariate feature selection algorithm, eleven metagenomic genres highly correlated with the country of origin were obtained. An in-depth study of the variables used in each model is shown in the present work.
Asunto(s)
Aprendizaje Automático , Metagenómica , Algoritmos , Reino Unido , Estados UnidosRESUMEN
Peptide microarrays have been used to study protein-protein interaction, enzyme-substrate profiling, epitope mapping, vaccine development, and immuno-profiling. Unlike proteins, peptides are cheap to produce, and can be produced in a high-throughput manner, in a reliable and consistent procedure that reduces batch-to-batch variability. All this provides the peptide microarrays a great potential in the development of new diagnostic tools. Noncontact printing, such as piezoelectric systems, results in a considerable advance in protein and peptide microarray production. In particular, they improve drop deposition, sample distribution, quality control, and flexibility in substrate deposition and eliminate cross-contamination and carryover. These features contribute to creating reproducible assays and generating more reliable data. Here we describe the methods and materials for epitope mapping of food allergens using peptide microarrays produced with a noncontact piezoelectric microarray printer.