Innovative infrastructure to access Brazilian fungal diversity using deep learning
Ontology highlight
ABSTRACT:
SUBMITTER: Chaves T
PROVIDER: S-EPMC11243970 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Evidence-based STI (science, technology, and innovation) policy making requires accurate indicators of innovation in order to promote economic growth. However, traditional indicators from patents and questionnaire-based surveys often lack coverage, granularity as well as timeliness and may involve high data collection costs, especially when conducted at a large scale. Consequently, they struggle to provide policy makers and scientists with the full picture of the current state of the innovation system. In this paper, we propose a first approach on generating web-based innovation indicators which may have the potential to overcome some of the shortcomings of traditional indicators. Specifically, we develop a method to identify product innovator firms at a large scale and very low costs. We use traditional firm-level indicators from a questionnaire-based innovation survey (German Community Innovation Survey) to train an artificial neural network classification model on labelled (product innovator/no product innovator) web texts of surveyed firms. Subsequently, we apply this classification model to the web texts of hundreds of thousands of firms in Germany to predict whether they are product innovators or not. We then compare these predictions to firm-level patent statistics, survey extrapolation benchmark data, and regional innovation indicators. The results show that our approach produces reliable predictions and has the potential to be a valuable and highly cost-efficient addition to the existing set of innovation indicators, especially due to its coverage and regional granularity.
| S-EPMC8016297 | biostudies-literature
Project description:Citrus farming is one of the major agricultural sectors of Pakistan and currently represents almost 30% of total fruit production, with its highest concentration in Punjab. Although economically important, citrus crops like sweet orange, grapefruit, lemon, and mandarins face various diseases like canker, scab, and black spot, which lower fruit quality and yield. Traditional manual disease diagnosis is not only slow, less accurate, and expensive but also relies heavily on expert intervention. To address these issues, this research examines the implementation of an automated disease classification system using deep learning and optimal feature selection. The system incorporates data augmentation and transfer learning with pre-trained models such as DenseNet-201 and AlexNet to improve diagnostic accuracy, efficiency, and cost-effectiveness. Experimental results on a citrus leaves dataset show an impressive 99.6% classification accuracy. The proposed framework outperforms existing methods, offering a robust and scalable solution for disease detection in citrus farming, contributing to more sustainable agricultural practices.
| S-EPMC11753642 | biostudies-literature
Project description:Sepsis is a major cause of morbidity and mortality worldwide, and is caused by bacterial infection in a majority of cases. However, fungal sepsis often carries a higher mortality rate both due to its prevalence in immunocompromised patients as well as delayed recognition. Using chest x-rays, associated radiology reports, and structured patient data from the MIMIC-IV clinical dataset, the authors present a machine learning methodology to differentiate between bacterial, fungal, and viral sepsis. Model performance shows AUCs of 0.81, 0.83, 0.79 for detecting bacterial, fungal, and viral sepsis respectively, with best performance achieved using embeddings from image reports and structured clinical data. By improving early detection of an often missed causative septic agent, predictive models could facilitate earlier treatment of non-bacterial sepsis with resultant associated mortality reduction.
| S-EPMC10120799 | biostudies-literature
Project description:The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiological agent responsible for coronavirus disease 2019 (COVID-19), has affected the lives of billions and killed millions of infected people. This virus has been demonstrated to have different outcomes among individuals, with some of them presenting a mild infection, while others present severe symptoms or even death. The identification of the molecular states related to the severity of a COVID-19 infection has become of the utmost importance to understanding the differences in critical immune response. In this study, we computationally processed a set of publicly available single-cell RNA-Seq (scRNA-Seq) data of 12 Bronchoalveolar Lavage Fluid (BALF) samples diagnosed as having a mild, severe, or no infection, and generated a high-quality dataset that consists of 63,734 cells, each with 23,916 genes. We extended the cell-type and sub-type composition identification and our analysis showed significant differences in cell-type composition in mild and severe groups compared to the normal. Importantly, inflammatory responses were dramatically elevated in the severe group, which was evidenced by the significant increase in macrophages, from 10.56% in the normal group to 20.97% in the mild group and 34.15% in the severe group. As an indicator of immune defense, populations of T cells accounted for 24.76% in the mild group and decreased to 7.35% in the severe group. To verify these findings, we developed several artificial neural networks (ANNs) and graph convolutional neural network (GCNN) models. We showed that the GCNN models reach a prediction accuracy of the infection of 91.16% using data from subtypes of macrophages. Overall, our study indicates significant differences in the gene expression profiles of inflammatory response and immune cells of severely infected patients.
| S-EPMC9777824 | biostudies-literature
Project description:Deep-sea hydrothermal ecosystems are considered oases of life in oceans. Since the discovery of these ecosystems in the late 1970s, many endemic species of Bacteria, Archaea, and other organisms, such as annelids and crabs, have been described. Considerable knowledge has been acquired about the diversity of (micro)organisms in these ecosystems, but the diversity of fungi has not been studied to date. These organisms are considered key organisms in terrestrial ecosystems because of their ecological functions and especially their ability to degrade organic matter. The lack of knowledge about them in the sea reflects the widely held belief that fungi are terrestrial organisms. The first inventory of such organisms in deep-sea hydrothermal environments was obtained in this study. Fungal diversity was investigated by analyzing the small-subunit rRNA gene sequences amplified by culture-independent PCR using DNA extracts from hydrothermal samples and from a culture collection that was established. Our work revealed an unsuspected diversity of species in three of the five fungal phyla. We found a new branch of Chytridiomycota forming an ancient evolutionary lineage. Many of the species identified are unknown, even at higher taxonomic levels in the Chytridiomycota, Ascomycota, and Basidiomycota. This work opens the way to new studies of the diversity, ecology, and physiology of fungi in oceans and might stimulate new prospecting for biomolecules. From an evolutionary point of view, the diversification of fungi in the oceans can no longer be ignored.
| S-EPMC2765129 | biostudies-literature
Project description:The agricultural sector faces several difficulties today in ensuring the safety of food supply, including water scarcity. This study presents the design and development of a low-cost and full-featured fog-IoT/AI system targeted towards smallholder farmer communities (SFCs). However, the smallholder community is hesitant to adopt technology-based solutions. There are many overwhelming reasons for this, but the high cost, implementation complexity, and malfunctioning sensors cause inappropriate decisions. The PRIMA INTEL-IRRIS project aims to make digital and innovative agricultural technologies more appealing and available to these communities by advancing the intelligent irrigation "in-the-box" concept. Considered a vital resource, collected data are used to detect anomalies or abnormal behavior, providing information about an occurrence or a node failure. To prevent agro-field data leakage, this paper presents an innovative, smart, and sustainable low-cost irrigation system that employs artificial intelligence (AI) techniques to analyze anomalies and problems in water usage. The sensor anomaly can be detected using an autoencoder (AE) and a generative adversarial network (GAN). We will feed the autoencoders' anomaly detection models with time series records from the datasets and replace detected anomalies with the reconstructed outputs. When integrated with an IoT platform, this methodology is a tool for easing the labeling of sensor anomalies and can help create supervised datasets for future research. In addition, anomalies can be corrected by prediction models based on deep learning approaches, applying CNN/BiLSTM architecture. The results show that AEs outperform the GANs, achieving an accuracy of 90%, 95%, and 97% for soil moisture, air temperature, and air humidity, respectively. The proposed system is designed to ensure that the data are of high quality and reliable enough to make sound decisions compared to the existing platforms.
| S-EPMC10892454 | biostudies-literature
Project description:ObjectiveThis study develops and evaluates multimodal machine learning models for differentiating bacterial and fungal keratitis using a prospective representative dataset from South India.DesignMachine learning classifier training and validation study.ParticipantsFive hundred ninety-nine subjects diagnosed with acute infectious keratitis at Aravind Eye Hospital in Madurai, India.MethodsWe developed and compared 3 prediction models to distinguish bacterial and fungal keratitis using a prospective, consecutively-collected, representative dataset gathered over a full calendar year (the MADURAI dataset). These models included a clinical data model, a computer vision model using the EfficientNet architecture, and a multimodal model combining both imaging and clinical data. We partitioned the MADURAI dataset into 70% train/validation and 30% test sets. Model training was performed with fivefold cross-validation. We also compared the performance of the MADURAI-trained computer vision model against a model with identical architecture but trained on a preexisting dataset collated from multiple prior bacterial and fungal keratitis randomized clinical trials (RCTs) (the RCT-trained computer vision model).Main outcome measuresThe primary evaluation metric was the area under the precision-recall curve (AUPRC). Secondary metrics included area under the receiver operating characteristic curve (AUROC), accuracy, and F1 score.ResultsThe MADURAI-trained computer vision model outperformed the clinical data model and the RCT-trained computer vision model on the hold-out test set, with an AUPRC 0.94 (95% confidence interval: 0.92-0.96), AUROC 0.81 (0.76-0.85), accuracy 77%, and F1 score 0.85. The multimodal model did not substantially improve performance compared with the computer vision model.ConclusionsThe best-performing machine learning classifier for infectious keratitis was a computer vision model trained using the MADURAI dataset. These findings suggest that image-based deep learning could significantly enhance diagnostic capabilities for infectious keratitis and emphasize the importance of using prospective, consecutively-collected, representative data for machine learning model training and evaluation.Financial disclosuresProprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
| S-EPMC11758206 | biostudies-literature
Project description:Molecular techniques using fungal DNA barcoding (ITS) and other markers have been key to identifying the biodiversity of different geographic areas, mainly in megadiverse countries. Here, we provide an overview of the fungal diversity in Brazil based on DNA markers of phylogenetic importance generated since 1996. We retrieved fungal sequences of ITS, LSU, SSU, tef1-α, β-tubulin, rpb1, rpb2, actin, chitin synthase, and ATP6 from GenBank using different field keywords that indicated their origin in Brazil. A total of 19,440 sequences were recovered. ITS is the most representative marker (11,209 sequences), with 70.1% belonging to Ascomycota, 18.6% Basidiomycota, 10.2% unidentified, 1.1% Mucoromycota, two sequences of Olpidium bornovanus (Fungi incertae sedis), one sequence of Blastocladiomycota (Allomyces arbusculus), and one sequence of Chytridiomycota (Batrachochytrium dendrobatidis). Considering the sequences of all selected markers, only the phyla Cryptomycota and Entorrhizomycota were not represented. Based on ITS, using a cutoff of 98%, all sequences comprise 3047 OTUs, with the majority being Ascomycota (2088 OTUs) and Basidiomycota (681 OTUs). Previous numbers based mainly on morphological and bibliographical data revealed 5264 fungal species from Brazil, with a predominance of Basidiomycota (2741 spp.) and Ascomycota (1881 spp.). The unidentified ITS sequences not assigned to a higher taxonomic level represent 1.61% of all ITS sequences sampled and correspond to 38 unknown class-level lineages (75% cutoff). A maximum likelihood phylogeny based on LSU illustrates the fungal classes occurring in Brazil.
| S-EPMC7203393 | biostudies-literature
Project description:Fungi are the principal degraders of biomass in most terrestrial ecosystems. In contrast to surface environments, deep-sea environmental gene libraries have suggested that fungi are rare and non-diverse in high-pressure marine environments. Here, we report the diversity of fungi from 11 deep-sea samples from around the world representing depths from 1,500 to 4,000 m (146-388 atm) and two shallower water column samples (250 and 500m). We sequenced 239 clones from 10 fungal-specific 18S rRNA gene libraries constructed from these samples, from which we detected only 18 fungal 18S-types in deep-sea samples. Our phylogenetic analyses show that a total of only 32 fungal 18S-types have so far been recovered from deep-sea habitats, and our results suggest that fungi, in general, are relatively rare in the deep-sea habitats we sampled. The fungal diversity detected suggests that deep-sea environments host an evolutionarily diverse array of fungi dominated by groups of distantly related yeasts, although four putative filamentous fungal 18S-types were detected. The majority of our new sequences branch close to known fungi found in surface environments. This pattern contradicts the proposal that deep-sea and hydrothermal vent habitats represent ancient ecosystems, and demonstrates a history of frequent dispersal between terrestrial and deep-sea habitats.
| S-EPMC2293941 | biostudies-literature
Project description:The power sector is one of the most important engineering sectors, with a lot of equipment that needs to be appropriately maintained, often spread over large areas. With the recent advances in deep learning techniques, many applications can be developed that could be used to automate the power line inspection process, replacing previously manual activities. However, in addition to these novel algorithms, this approach requires specialized datasets, collections that have been properly curated and labeled with the help of experts in the field. When it comes to visual inspection processes, these data are mainly images of various types. This paper consists of two main parts. The first one presents information about datasets used in machine learning, especially deep learning. The need to create domain datasets is justified using the example of the collection of data on power infrastructure objects, and the selected repositories of different collections are compared. In addition, selected collections of digital image data are characterized in more detail. The latter part of the review also discusses the use of an original dataset containing 2630 high-resolution labeled images of power line insulators and comments on the potential applications of this collection.
| S-EPMC10459611 | biostudies-literature