Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 23.189
Filtrar
1.
Environ Monit Assess ; 193(11): 699, 2021 Oct 07.
Artículo en Inglés | MEDLINE | ID: mdl-34622348

RESUMEN

In response to the Minamata Convention on Mercury, international organizations, governments, nonprofit organizations, and other institutions as well as individuals have worked to promote the development and implementation of safe and environmentally healthy practices, processes, and products. It is expected that the accumulation of mercury in the natural environment will decrease in volume each year. However, even after Hg ceases to be used, the Hg already accumulated in forests will continue to pose an ecological risk. Forest fires are serious events, partly because they release accumulated Hg from the environment. In this study, the effects of forest fires on the accumulation and chemical species of Hg in soil, related to the mobilization of Hg, were investigated. The research was conducted in secondary forests located near artisanal small-scale gold mining sites, where Hg is used for the amalgamation of gold in Camarines Norte, Philippines. The results showed that the original Hg accumulation level in the burned forest was not as high as that in the control forest, and that burn severity might have affected only the surface soil (0-5 cm). However, the proportion of water-soluble Hg, which was derived from ash, was increased by fire. Therefore, it is suggested that forest fires not only increase the release of Hg into the atmosphere but also increase the outflow risk to the aquatic system through rainfall.


Asunto(s)
Mercurio , Incendios Forestales , Monitoreo del Ambiente , Oro , Humanos , Mercurio/análisis , Minería , Suelo
2.
BMC Bioinformatics ; 22(1): 482, 2021 Oct 04.
Artículo en Inglés | MEDLINE | ID: mdl-34607568

RESUMEN

BACKGROUND: Blood cancers (BCs) are responsible for over 720 K yearly deaths worldwide. Their prevalence and mortality-rate uphold the relevance of research related to BCs. Despite the availability of different resources establishing Disease-Disease Associations (DDAs), the knowledge is scattered and not accessible in a straightforward way to the scientific community. Here, we propose SicknessMiner, a biomedical Text-Mining (TM) approach towards the centralization of DDAs. Our methodology encompasses Named Entity Recognition (NER) and Named Entity Normalization (NEN) steps, and the DDAs retrieved were compared to the DisGeNET resource for qualitative and quantitative comparison. RESULTS: We obtained the DDAs via co-mention using our SicknessMiner or gene- or variant-disease similarity on DisGeNET. SicknessMiner was able to retrieve around 92% of the DisGeNET results and nearly 15% of the SicknessMiner results were specific to our pipeline. CONCLUSIONS: SicknessMiner is a valuable tool to extract disease-disease relationship from RAW input corpus.


Asunto(s)
Aprendizaje Profundo , Minería de Datos , Conocimiento
3.
Comput Intell Neurosci ; 2021: 3597051, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34603430

RESUMEN

With the rapid development of artificial intelligence in recent years, the research on image processing, text mining, and genome informatics has gradually deepened, and the mining of large-scale databases has begun to receive more and more attention. The objects of data mining have also become more complex, and the data dimensions of mining objects have become higher and higher. Compared with the ultra-high data dimensions, the number of samples available for analysis is too small, resulting in the production of high-dimensional small sample data. High-dimensional small sample data will bring serious dimensional disasters to the mining process. Through feature selection, redundancy and noise features in high-dimensional small sample data can be effectively eliminated, avoiding dimensional disasters and improving the actual efficiency of mining algorithms. However, the existing feature selection methods emphasize the classification or clustering performance of the feature selection results and ignore the stability of the feature selection results, which will lead to unstable feature selection results, and it is difficult to obtain real and understandable features. Based on the traditional feature selection method, this paper proposes an ensemble feature selection method, Random Bits Forest Recursive Clustering Eliminate (RBF-RCE) feature selection method, combined with multiple sets of basic classifiers to carry out parallel learning and screen out the best feature classification results, optimizes the classification performance of traditional feature selection methods, and can also improve the stability of feature selection. Then, this paper analyzes the reasons for the instability of feature selection and introduces a feature selection stability measurement method, the Intersection Measurement (IM), to evaluate whether the feature selection process is stable. The effectiveness of the proposed method is verified by experiments on several groups of high-dimensional small sample data sets.


Asunto(s)
Inteligencia Artificial , Macrodatos , Algoritmos , Minería de Datos , Tecnología
4.
Washington, D.C.; PAHO; 2021-10-06. (PAHO/EIH/IS/21-032).
en Inglés | PAHO-IRIS | ID: phr-54958

RESUMEN

The PAHO Digital Transformation Toolkit was created with the aim of offering managerial, technical, knowledge, communication, and academic resources to all those health professionals, decisionmakers, and institutions dedicated to strengthening health information systems. Its guiding vision is that of achieving universal access to health and universal health coverage in the Region through access to good-quality data, strategic information, and digital health tools for decision-making and well-being. The category of technical tools within the PAHO Digital Transformation Toolkit is based on offering documents that facilitate implementation of policies, recommendations, data governance frameworks, monitoring and evaluation frameworks, analysis, and other rapid evaluation tools for the Information Systems for Health initiative in countries.


Asunto(s)
Sistemas de Información , Sistemas de Información en Salud , Medicina Basada en la Evidencia , Política Informada por la Evidencia , Información , Gestión de la Información , Tecnología de la Información , Minería de Datos , Gestión del Conocimiento , Macrodatos , Ciencia de los Datos
5.
Biomedica ; 41(Sp. 2): 37-47, 2021 Oct 15.
Artículo en Español | MEDLINE | ID: mdl-34669277

RESUMEN

La minería ha tenido una gran influencia en las sociedades humanas, permeando por igual las riquezas del suelo y la cultura, lo que ha tenido profundas implicaciones para los individuos dedicados a esta labor y para los lugares en los que se lleva a cabo. En el presente artículo, se describen las características socioculturales y de sanidad, así como las enfermedades más frecuentes en las minas de oro de Marmato (Caldas) durante el siglo XIX. Las precarias condiciones de salubridad y las enfermedades tropicales infecciosas persistieron en la población durante todo el siglo.

6.
BMC Bioinformatics ; 22(1): 500, 2021 Oct 16.
Artículo en Inglés | MEDLINE | ID: mdl-34656098

RESUMEN

BACKGROUND: Identifying human protein-phenotype relationships has attracted researchers in bioinformatics and biomedical natural language processing due to its importance in uncovering rare and complex diseases. Since experimental validation of protein-phenotype associations is prohibitive, automated tools capable of accurately extracting these associations from the biomedical text are in high demand. However, while the manual annotation of protein-phenotype co-mentions required for training such models is highly resource-consuming, extracting millions of unlabeled co-mentions is straightforward. RESULTS: In this study, we propose a novel deep semi-supervised ensemble framework that combines deep neural networks, semi-supervised, and ensemble learning for classifying human protein-phenotype co-mentions with the help of unlabeled data. This framework allows the ability to incorporate an extensive collection of unlabeled sentence-level co-mentions of human proteins and phenotypes with a small labeled dataset to enhance overall performance. We develop PPPredSS, a prototype of our proposed semi-supervised framework that combines sophisticated language models, convolutional networks, and recurrent networks. Our experimental results demonstrate that the proposed approach provides a new state-of-the-art performance in classifying human protein-phenotype co-mentions by outperforming other supervised and semi-supervised counterparts. Furthermore, we highlight the utility of PPPredSS in powering a curation assistant system through case studies involving a group of biologists. CONCLUSIONS: This article presents a novel approach for human protein-phenotype co-mention classification based on deep, semi-supervised, and ensemble learning. The insights and findings from this work have implications for biomedical researchers, biocurators, and the text mining community working on biomedical relationship extraction.


Asunto(s)
Redes Neurales de la Computación , Aprendizaje Automático Supervisado , Minería de Datos , Humanos , Fenotipo
7.
Zhongguo Zhen Jiu ; 41(10): 1166-70, 2021 Oct 12.
Artículo en Chino | MEDLINE | ID: mdl-34628752

RESUMEN

OBJECTIVE: To analyze the rules of acupoint and medication selection of acupoint application therapy for functional constipation (FC) by data mining technology. METHODS: The clinical research literature regarding acupoint application therapy for FC from published to February 26, 2020 was searched in CNKI, VIP, Wanfang, SinoMed and PubMed. The prescriptions were extracted, and by using SPSS24.0 and SPSS Modeler14.0 software, the use of high-frequency acupoints and medication was summarized. The association rule analysis, cluster analysis and core prescription analysis of acupoints and medication were analyzed. RESULTS: A total of 122 prescriptions of acupoint application therapy were included, involving 32 acupoints. The core prescription of acupoints was Tianshu (ST 25), Dachangshu (BL 25), Shenque (CV 8) and Guanyuan (CV 4). The high-frequency meridians mainly included conception vessel, yangming stomach meridian of foot and taiyang bladder meridian of foot. The core prescription of medication was rheum officinale, mirabilite, immature bitter orange, mangnolia officinalis, common aucklandia root and borneol. CONCLUSION: The use of local acupoint and regulating-qi and purgating medication is an important principle of acupoint application therapy for FC.


Asunto(s)
Terapia por Acupuntura , Meridianos , Puntos de Acupuntura , Estreñimiento/tratamiento farmacológico , Minería de Datos , Humanos
8.
J Environ Manage ; 300: 113797, 2021 Dec 15.
Artículo en Inglés | MEDLINE | ID: mdl-34649315

RESUMEN

Although the mining area has been restored, the environmental problems caused by years of large-scale oil shale mining are still continuing, coupled with the intensive distribution of the surrounding petrochemical industry, posing a serious threat to the local ecological environment. In this study, we investigated eight heavy metals (Cu, Ni, Pb, Cd, As, Cr, Mn and Zn) contamination and distribution around mining area, evaluated the potential risks of environment, identified the main sources of metal pollution and performed source apportionment. The results showed that the original north and south dumps were seriously polluted, and the CF values were significantly higher than other sampling sites. Ni, Zn and Mn have high coefficients of variation, which may be greatly affected by human factors and especially the waste slag piled up. The concentration of heavy metals in the water was lower than in the soil; soil particles, pH, Eh and acid mine drainage influence the variation of heavy metal concentrations. As and Cd have very high RAC values, and accordingly they were mainly present in the exchangeable and reduced fractions. Mn was exposed to higher ecological risks, followed by Pb, although there were high loads on carbonate bound and oxidizable fractions. APCS-MLL receptor model was used to identify and apportionment three main sources of contamination. The mean contribution rates of industrial activity, atmospheric deposition and mixed sources accounted for 39.77%, 22.24% and 37.99%, respectively. Cluster analysis further classified the metal pollution sources according to the spatial distance of sampling points.


Asunto(s)
Metales Pesados , Contaminantes del Suelo , China , Monitoreo del Ambiente , Humanos , Metales Pesados/análisis , Minería , Medición de Riesgo , Suelo , Contaminantes del Suelo/análisis
9.
Sensors (Basel) ; 21(19)2021 Oct 05.
Artículo en Inglés | MEDLINE | ID: mdl-34640949

RESUMEN

In recent years, massive open online courses (MOOCs) have received widespread attention owing to their flexibility and free access, which has attracted millions of online learners to participate in courses. With the wide application of MOOCs in educational institutions, a large amount of learners' log data exist in the MOOCs platform, and this lays a solid data foundation for exploring learners' online learning behaviors. Using data mining techniques to process these log data and then analyze the relationship between learner behavior and academic performance has become a hot topic of research. Firstly, this paper summarizes the commonly used predictive models in the relevant research fields. Based on the behavior log data of learners participating in 12 courses in MOOCs, an entropy-based indicator quantifying behavior change trends is proposed, which explores the relationships between behavior change trends and learners' academic performance. Next, we build a set of behavioral features, which further analyze the relationships between behaviors and academic performance. The results demonstrate that entropy has a certain correlation with the corresponding behavior, which can effectively represent the change trends of behavior. Finally, to verify the effectiveness and importance of the predictive features, we choose four benchmark models to predict learners' academic performance and compare them with the previous relevant research results. The results show that the proposed feature selection-based model can effectively identify the key features and obtain good prediction performance. Furthermore, our prediction results are better than the related studies in the performance prediction based on the same Xuetang MOOC platform, which demonstrates that the combination of the selected learner-related features (behavioral features + behavior entropy) can lead to a much better prediction performance.


Asunto(s)
Rendimiento Académico , Educación a Distancia , Minería de Datos , Bases de Datos Factuales , Entropía
10.
BMC Bioinformatics ; 22(1): 426, 2021 Sep 08.
Artículo en Inglés | MEDLINE | ID: mdl-34496758

RESUMEN

BACKGROUND: A considerable number of data mining approaches for biomedical data analysis, including state-of-the-art associative models, require a form of data discretization. Although diverse discretization approaches have been proposed, they generally work under a strict set of statistical assumptions which are arguably insufficient to handle the diversity and heterogeneity of clinical and molecular variables within a given dataset. In addition, although an increasing number of symbolic approaches in bioinformatics are able to assign multiple items to values occurring near discretization boundaries for superior robustness, there are no reference principles on how to perform multi-item discretizations. RESULTS: In this study, an unsupervised discretization method, DI2, for variables with arbitrarily skewed distributions is proposed. Statistical tests applied to assess differences in performance confirm that DI2 generally outperforms well-established discretizations methods with statistical significance. Within classification tasks, DI2 displays either competitive or superior levels of predictive accuracy, particularly delineate for classifiers able to accommodate border values. CONCLUSIONS: This work proposes a new unsupervised method for data discretization, DI2, that takes into account the underlying data regularities, the presence of outlier values disrupting expected regularities, as well as the relevance of border values. DI2 is available at https://github.com/JupitersMight/DI2.


Asunto(s)
Algoritmos , Minería de Datos , Biología Computacional
11.
Environ Monit Assess ; 193(10): 632, 2021 Sep 07.
Artículo en Inglés | MEDLINE | ID: mdl-34490524

RESUMEN

In southern South America, Brazil, in the state of Santa Catarina, the neglect and lack of environmental supervision during coal mining caused the contamination of surface and groundwater by acid mine drainage (AMD). By the force of the local law, environmental reclamation actions in these abandoned areas have been carried. A scientific work of monitoring and assessment of the water resources within these areas has never been developed, as the efficacy of the reclamation strategies has never been discussed. This work aims to fill this gap by presenting and analyzing the environmental reclamation strategy of a former degraded coal mining area and its impacts on local water resources. The water monitoring plan in Area IV's was carried out in groundwater, and in lentic (ponds) and lotic (rivers) environments of surface waters, fourteen monitoring campaigns were conducted. The results showed that upstream and downstream river points have different water qualities, with the downstream points having poorer water quality, still affected by past mining activities. From the surface water perspective, the reclaiming method adopted was effective in three of the four ponds, presenting problems only in the downstream one. Two hypotheses were proposed; the first hypothesis is that contamination happens due to leaching of the material that still remains on the ponds' banks into the water. Another hypothesis is that the contamination comes from the upstream groundwater inflow into the pond, which runs through the entire area before reaching the pond. Those results serve to further access the actual monitoring perspectives as well as to better develop future reclaiming strategies.


Asunto(s)
Minas de Carbón , Agua Subterránea , Contaminantes Químicos del Agua , Brasil , Carbón Mineral/análisis , Monitoreo del Ambiente , Minería , Contaminantes Químicos del Agua/análisis , Recursos Hídricos
12.
BMC Public Health ; 21(1): 1607, 2021 09 01.
Artículo en Inglés | MEDLINE | ID: mdl-34470630

RESUMEN

BACKGROUND: The first half of 2020 has been marked as the era of COVID-19 pandemic which affected the world globally in almost every aspect of the daily life from societal to economical. To prevent the spread of COVID-19, countries have implemented diverse policies regarding Non-Pharmaceutical Intervention (NPI) measures. This is because in the first stage countries had limited knowledge about the virus and its contagiousness. Also, there was no effective medication or vaccines. This paper studies the effectiveness of the implemented policies and measures against the deaths attributed to the virus between January and May 2020. METHODS: Data from the European Centre for Disease Prevention and Control regarding the identified cases and deaths of COVID-19 from 48 countries have been used. Additionally, data concerning the NPI measures related policies implemented by the 48 countries and the capacity of their health care systems was collected manually from their national gazettes and official institutes. Data mining, time series analysis, pattern detection, machine learning, clustering methods and visual analytics techniques have been applied to analyze the collected data and discover possible relationships between the implemented NPIs and COVID-19 spread and mortality. Further, we recorded and analyzed the responses of the countries against COVID-19 pandemic, mainly in urban areas which are over-populated and accordingly COVID-19 has the potential to spread easier among humans. RESULTS: The data mining and clustering analysis of the collected data showed that the implementation of the NPI measures before the first death case seems to be very effective in controlling the spread of the disease. In other words, delaying the implementation of the NPI measures to after the first death case has practically little effect on limiting the spread of the disease. The success of implementing the NPI measures further depends on the way each government monitored their application. Countries with stricter policing of the measures seems to be more effective in controlling the transmission of the disease. CONCLUSIONS: The conducted comparative data mining study provides insights regarding the correlation between the early implementation of the NPI measures and controlling COVID-19 contagiousness and mortality. We reported a number of useful observations that could be very helpful to the decision makers or epidemiologists regarding the rapid implementation and monitoring of the NPI measures in case of a future wave of COVID-19 or to deal with other unknown infectious pandemics. Regardless, after the first wave of COVID-19, most countries have decided to lift the restrictions and return to normal. This has resulted in a severe second wave in some countries, a situation which requires re-evaluating the whole process and inspiring lessons for the future.


Asunto(s)
COVID-19 , Pandemias , Minería de Datos , Gobierno , Humanos , Pandemias/prevención & control , SARS-CoV-2
13.
Chemosphere ; 282: 131163, 2021 Nov.
Artículo en Inglés | MEDLINE | ID: mdl-34470177

RESUMEN

Cemented paste backfill (CPB) technology is beneficial to the recycling of solid wastes and sustainable development in mines. However, the wetting-drying cycle caused by water intrusion and goaf drainage has a great influence on the waterproof and support performance of CPB. In this study, the hydraulic and mechanical properties of CPB samples under wetting-drying cycles were studied by permeability tests, nuclear magnetic resonance (NMR) tests and uniaxial compression tests. The results show that with the increasing number of wetting-drying cycles, the porosity and permeability of CPB samples increase; the porosity and permeability of CPB samples with small particle size distribution and cementing strength are more sensitive to the increasing number of wetting-drying cycles. During the wetting-drying cycles, the uniaxial compressive strength and elastic modulus of CPB samples gradually deteriorate. This effect is more significant for CPB samples with the smaller particle size distribution and cementing strength. According to the periodic destruction of CPB cemented structures caused by wetting-drying cycles, the deterioration process of mechanical properties of CPB samples can be divided into two stages: initial deterioration stage and re-deterioration stage. The microstructure analysis of CPB samples was used to verify the periodic destruction of the cemented structures. Finally, protective measures of CPB were proposed to ensure the stability of CPB. The CPB with large particle size distribution and cementing strength should be adopted. Besides, the filling rate and the monitoring condition of the goaf can be strengthend to reduce and even avoid wetting-drying cycles.


Asunto(s)
Residuos Sólidos , Sulfuros , Materiales de Construcción , Minería , Reciclaje
14.
Zhongguo Zhong Yao Za Zhi ; 46(15): 4016-4022, 2021 Aug.
Artículo en Chino | MEDLINE | ID: mdl-34472279

RESUMEN

The tumor prescriptions contained in Dictionary of Tumor Formulas, Compendium of Good Tumor Formulas, Chinese Pharmacopoeia, Ministry of Health Drug Standards for Chinese Medicine Formulas and National Compilation of Standards for Proprietary Chinese Medicines were selected and organized to construct a database for tumor prescriptions, and the data mining techniques were applied to investigate the prescription regularity of colorectal cancer prescriptions. The formula data were extracted after screening in strict accordance with the inclusion and exclusion criteria, and were then analyzed with Microsoft Excel 2010 for frequency statistics, Apriori block provided by SPSS Clementine 12.0 software for correlation rule analysis, and arules and arulesViz packages in R 4.0.2 software for correlation rule visualization. In addition, SPSS 18.0 software was used for cluster analysis and factor analysis, in which cluster analysis was performed by Ochiai algorithm with bicategorical variables in systematic clustering method and factor analysis was performed mainly with principal component analysis. A total of 285 prescriptions were included in the statistical analysis, and the frequency statistics showed that 43 herbs had been used more than 16 times. The association rules analysis showed that 26 high-frequency me-dicine pair rules were obtained, and the association rules for those dispelling evil spirits, strengthening the body, resolving stasis, dispelling dampness, etc. were visualized. In the cluster analysis, we generated a dendrogram from which 7 groups of traditional Chinese medicines with homogeneity were extracted. 10 common factors were obtained in the factor analysis. The types of herbal medicines involved in the colorectal cancer prescription included anti-cancer antidotes, strengthening and tonifying medicines, blood-regulating medicines, and expectorant medicines, corresponding to the treatment for eliminating evil spirits, strengthening, resolving stasis, and expectorating dampness. The prescriptions for anti-cancer detoxification were normally based on the pairs composed of Scutellaria barbata-Hedyotis diffusa and Sophora flavescens, Sargentodoxa cuneata, S. barbata, often combined with stasis relieving drug and dampness eliminating drug, reflecting the characteristics of treatment for both toxicity and stasis, dampness and toxicity simultaneously. The prescriptions for strengthening the righteousness and tonifying the deficiency were composed of Astragalus membranaceus and Atractylodes macrocephala mainly, exerting the effect of benefiting Qi, strengthening the spleen and drying dampness, tonifying kidney and essence, tonifying blood and invigorating blood. Meanwhile, anti-cancer detoxification medicines shall be reduced as much as possible. The compatibility of the medicines for the intestinal tract reflected the principle of using the right medicine for the right condition and eliminating evil spirits or strengthening the body, as appropriate.


Asunto(s)
Neoplasias Colorrectales , Medicamentos Herbarios Chinos , Neoplasias Colorrectales/tratamiento farmacológico , Minería de Datos , Prescripciones de Medicamentos , Medicamentos Herbarios Chinos/uso terapéutico , Humanos , Medicina China Tradicional
15.
Med Ref Serv Q ; 40(3): 329-336, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34495798

RESUMEN

The explosive growth of digital information in recent years has amplified the information overload experienced by today's health-care professionals. In particular, the wide variety of unstructured text makes it difficult for researchers to find meaningful data without spending a considerable amount of time reading. Text mining can be used to facilitate better discoverability and analysis, and aid researchers in identifying critical trends and connections. This column will introduce key text-mining terms, recent use cases of biomedical text mining, and current applications for this technology in medical libraries.


Asunto(s)
Investigación Biomédica/tendencias , COVID-19 , Recolección de Datos/tendencias , Minería de Datos/tendencias , Informe de Investigación/tendencias , Investigación Biomédica/estadística & datos numéricos , Recolección de Datos/estadística & datos numéricos , Minería de Datos/estadística & datos numéricos , Predicción , Humanos
16.
Talanta ; 235: 122740, 2021 Dec 01.
Artículo en Inglés | MEDLINE | ID: mdl-34517608

RESUMEN

Illicit fentanyl and analogues have been involved in many fatalities and cases of intoxication across the United States over the last decade, and are becoming a health concern in Europe. New potent analogues emerge onto the drug market every year to circumvent analytical detection and legislation, and little pharmacological/toxicological data are available when the substances first appear. However, pharmacokinetic data are crucial to determine specific biomarkers of consumption in clinical and forensic settings, considering the low active doses and the rapid metabolism of fentanyl analogues. Phenylfentanyl is a novel analogue that was first detected in seized material in 2017, and little is currently known about this substance and its metabolism. We studied phenylfentanyl metabolic fate using in silico predictions with GLORYx freeware, human hepatocyte incubations, and liquid chromatography-high-resolution tandem mass spectrometry (LC-HRMS/MS). We applied a specific targeted/untargeted workflow using data-mining software to allow the rapid and partially automated screening of LC-HRMS/MS raw data. Approximately 90,000 substances were initially individuated after 3-h incubation with hepatocytes, and 115 substances were automatically selected for a manual check by the operators. Finally, 13 metabolites, mostly produced by N-dealkylation, amide hydrolysis, oxidation, and combinations thereof, were identified. We suggest phenylnorfentanyl as the main biological marker of phenylfentanyl use, and we proposed the inclusion of its fragmentation pattern in mzCloud and HighResNPS online libraries. Other major metabolites include N-Phenyl-1-(2-phenylethyl)-4-piperidinamine (4-ANPP), 1-(2-phenylethyl)-4-piperidinol, and other non-specific metabolites. Phase II transformations were infrequent, and the hydrolysis of the biological samples is not required to increase the detection capability of non-conjugated metabolites. The overall workflow is easily adaptable for the metabolite profiling of other novel psychoactive substances.


Asunto(s)
Minería de Datos , Microsomas Hepáticos , Cromatografía Liquida , Simulación por Computador , Humanos , Detección de Abuso de Sustancias , Flujo de Trabajo
17.
Annu Rev Biomed Data Sci ; 4: 313-339, 2021 07 20.
Artículo en Inglés | MEDLINE | ID: mdl-34465169

RESUMEN

The COVID-19 (coronavirus disease 2019) pandemic has had a significant impact on society, both because of the serious health effects of COVID-19 and because of public health measures implemented to slow its spread. Many of these difficulties are fundamentally information needs; attempts to address these needs have caused an information overload for both researchers and the public. Natural language processing (NLP)-the branch of artificial intelligence that interprets human language-can be applied to address many of the information needs made urgent by the COVID-19 pandemic. This review surveys approximately 150 NLP studies and more than 50 systems and datasets addressing the COVID-19 pandemic. We detail work on four core NLP tasks: information retrieval, named entity recognition, literature-based discovery, and question answering. We also describe work that directly addresses aspects of the pandemic through four additional tasks: topic modeling, sentiment and emotion analysis, caseload forecasting, and misinformation detection. We conclude by discussing observable trends and remaining challenges.


Asunto(s)
COVID-19/epidemiología , Almacenamiento y Recuperación de la Información/métodos , Procesamiento de Lenguaje Natural , Comunicación , Minería de Datos/métodos , Conjuntos de Datos como Asunto , Emociones , Humanos , Descubrimiento del Conocimiento , Pandemias , Publicaciones Periódicas como Asunto , Programas Informáticos
18.
BMC Bioinformatics ; 22(1): 432, 2021 Sep 10.
Artículo en Inglés | MEDLINE | ID: mdl-34507528

RESUMEN

BACKGROUND: Interactions of microbes and diseases are of great importance for biomedical research. However, large-scale of microbe-disease interactions are hidden in the biomedical literature. The structured databases for microbe-disease interactions are in limited amounts. In this paper, we aim to construct a large-scale database for microbe-disease interactions automatically. We attained this goal via applying text mining methods based on a deep learning model with a moderate curation cost. We also built a user-friendly web interface that allows researchers to navigate and query required information. RESULTS: Firstly, we manually constructed a golden-standard corpus and a sliver-standard corpus (SSC) for microbe-disease interactions for curation. Moreover, we proposed a text mining framework for microbe-disease interaction extraction based on a pretrained model BERE. We applied named entity recognition tools to detect microbe and disease mentions from the free biomedical texts. After that, we fine-tuned the pretrained model BERE to recognize relations between targeted entities, which was originally built for drug-target interactions or drug-drug interactions. The introduction of SSC for model fine-tuning greatly improved detection performance for microbe-disease interactions, with an average reduction in error of approximately 10%. The MDIDB website offers data browsing, custom searching for specific diseases or microbes, and batch downloading. CONCLUSIONS: Evaluation results demonstrate that our method outperform the baseline model (rule-based PKDE4J) with an average [Formula: see text]-score of 73.81%. For further validation, we randomly sampled nearly 1000 predicted interactions by our model, and manually checked the correctness of each interaction, which gives a 73% accuracy. The MDIDB webiste is freely avaliable throuth http://dbmdi.com/index/.


Asunto(s)
Investigación Biomédica , Minería de Datos , Aprendizaje Automático , Publicaciones
19.
Comput Intell Neurosci ; 2021: 6734345, 2021.
Artículo en Inglés | MEDLINE | ID: mdl-34512744

RESUMEN

Since the reform and opening up, China's regional economy has developed rapidly. However, due to different starting points of economic development caused by the traditional distribution of productive forces and the differences in regions, resources, technologies, and policies, the level of economic development in different regions is uneven. Clustering analysis is a data mining method that clusters or classifies entities according to their characteristics and then discovers the whole spatial distribution law of datasets and typical patterns. It is of great significance to classify, compare, and study the economic development level of different regions in order to formulate the regional economic development strategy. In this paper, a self-organizing feature map (SOM) neural network with the hybrid genetic algorithm is used to cluster the differences of regional economic development, the clustering results are evaluated, and the empirical results are good. From this, some meaningful conclusions can be drawn, which can provide reference for the decision-making of coordinating regional economic development.


Asunto(s)
Desarrollo Económico , Redes Neurales de la Computación , Algoritmos , China , Análisis por Conglomerados , Minería de Datos
20.
J Hazard Mater ; 416: 125863, 2021 08 15.
Artículo en Inglés | MEDLINE | ID: mdl-34492811

RESUMEN

Arsenic (As) adsorbed on Fe oxyhydroxides (adsorbent) is widely occurring in many environmental settings such as in acid mine drainage systems or in the hydrometallurgical operations to form Fe-As coprecipitates. However, the influence of the reaction media and the drying treatment on the microstructure of the directly formed adsorbents at various pHs was still not fully understood. In this work, As adsorption behaviors on various forms of Fe oxyhydroxides were systematically investigated by using XRD, FTIR, Raman, XANES, and HRTEM. The results revealed that at weak acidic pH, more As could adsorbed on the suspension adsorbent formed in sulfate and chloride media than that in nitrate media, possibly due to the microstructure alteration of the adsorbent in the presence of sulfate and chloride. Besides, the increasing crystallinity of the Fe oxyhydroxides and the aggregation effect after drying were the major reasons why less As could be hold by the dried adsorbents than that of the corresponding suspension adsorbents. These findings could shed more light on the nature of the Fe oxyhydroxides which may be helpful for more precisely predicting the fate of some toxic metal(loid)s in the environment.


Asunto(s)
Arsénico , Adsorción , Arsénico/análisis , Minería , Nitratos
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...