Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 15.981
Filtrar
1.
Sci Rep ; 12(1): 7166, 2022 May 03.
Artigo em Inglês | MEDLINE | ID: mdl-35504931

RESUMO

The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications. However, due to the nature of such deep black-boxed models, concerns about interpretability, fairness, and biases in healthcare scenarios where human lives are at stake call for a careful and thorough examination of both datasets and models. In this work, we focus on MIMIC-IV (Medical Information Mart for Intensive Care, version IV), the largest publicly available healthcare dataset, and conduct comprehensive analyses of interpretability as well as dataset representation bias and prediction fairness of deep learning models for in-hospital mortality prediction. First, we analyze the interpretability of deep learning mortality prediction models and observe that (1) the best-performing interpretability method successfully identifies critical features for mortality prediction on various prediction models as well as recognizing new important features that domain knowledge does not consider; (2) prediction models rely on demographic features, raising concerns in fairness. Therefore, we then evaluate the fairness of models and do observe the unfairness: (1) there exists disparate treatment in prescribing mechanical ventilation among patient groups across ethnicity, gender and age; (2) models often rely on racial attributes unequally across subgroups to generate their predictions. We further draw concrete connections between interpretability methods and fairness metrics by showing how feature importance from interpretability methods can be beneficial in quantifying potential disparities in mortality predictors. Our analysis demonstrates that the prediction performance is not the only factor to consider when evaluating models for healthcare applications, since high prediction performance might be the result of unfair utilization of demographic features. Our findings suggest that future research in AI models for healthcare applications can benefit from utilizing the analysis workflow of interpretability and fairness as well as verifying if models achieve superior performance at the cost of introducing bias.


Assuntos
Aprendizado Profundo , Benchmarking , Cuidados Críticos , Previsões , Mortalidade Hospitalar , Humanos
2.
Nat Commun ; 13(1): 2423, 2022 May 03.
Artigo em Inglês | MEDLINE | ID: mdl-35505052

RESUMO

The molecular determinants of tissue composition of the human brain remain largely unknown. Recent genome-wide association studies (GWAS) on this topic have had limited success due to methodological constraints. Here, we apply advanced whole-brain analyses on multi-shell diffusion imaging data and multivariate GWAS to two large scale imaging genetic datasets (UK Biobank and the Adolescent Brain Cognitive Development study) to identify and validate genetic association signals. We discover 503 unique genetic loci that have impact on multiple regions of human brain. Among them, more than 79% are validated in either of two large-scale independent imaging datasets. Key molecular pathways involved in axonal growth, astrocyte-mediated neuroinflammation, and synaptogenesis during development are found to significantly impact the measured variations in tissue-specific imaging features. Our results shed new light on the biological determinants of brain tissue composition and their potential overlap with the genetic basis of neuropsychiatric disorders.


Assuntos
Benchmarking , Estudo de Associação Genômica Ampla , Adolescente , Encéfalo/diagnóstico por imagem , Encéfalo/metabolismo , Cognição , Loci Gênicos , Estudo de Associação Genômica Ampla/métodos , Humanos
3.
Appl Clin Inform ; 13(2): 431-438, 2022 03.
Artigo em Inglês | MEDLINE | ID: mdl-35508197

RESUMO

OBJECTIVE: The purpose of this study is to evaluate the ability of three metrics to monitor for a reduction in performance of a chronic kidney disease (CKD) model deployed at a pediatric hospital. METHODS: The CKD risk model estimates a patient's risk of developing CKD 3 to 12 months following an inpatient admission. The model was developed on a retrospective dataset of 4,879 admissions from 2014 to 2018, then run silently on 1,270 admissions from April to October, 2019. Three metrics were used to monitor its performance during the silent phase: (1) standardized mean differences (SMDs); (2) performance of a "membership model"; and (3) response distribution analysis. Observed patient outcomes for the 1,270 admissions were used to calculate prospective model performance and the ability of the three metrics to detect performance changes. RESULTS: The deployed model had an area under the receiver-operator curve (AUROC) of 0.63 in the prospective evaluation, which was a significant decrease from an AUROC of 0.76 on retrospective data (p = 0.033). Among the three metrics, SMDs were significantly different for 66/75 (88%) of the model's input variables (p <0.05) between retrospective and deployment data. The membership model was able to discriminate between the two settings (AUROC = 0.71, p <0.0001) and the response distributions were significantly different (p <0.0001) for the two settings. CONCLUSION: This study suggests that the three metrics examined could provide early indication of performance deterioration in deployed models' performance.


Assuntos
Aprendizado de Máquina , Insuficiência Renal Crônica , Benchmarking , Criança , Feminino , Hospitalização , Humanos , Masculino , Insuficiência Renal Crônica/diagnóstico , Estudos Retrospectivos
4.
PLoS One ; 17(5): e0268110, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35522678

RESUMO

INTRODUCTION: Academia uses scholarly metrics, such as the h-index, to make hiring, promotion, and funding decisions. These high-stakes decisions require that those using scholarly metrics be able to recognize, interpret, critically assess and effectively and ethically use them. This study aimed to characterize educational videos about the h-index to understand available resources and provide recommendations for future educational initiatives. METHODS: The authors analyzed videos on the h-index posted to YouTube. Videos were identified by searching YouTube and were screened by two authors. To code the videos the authors created a coding sheet, which assessed content and presentation style with a focus on the videos' educational quality based on Cognitive Load Theory. Two authors coded each video independently with discrepancies resolved by group consensus. RESULTS: Thirty-one videos met inclusion criteria. Twenty-one videos (68%) were screencasts and seven used a "talking head" approach. Twenty-six videos defined the h-index (83%) and provided examples of how to calculate and find it. The importance of the h-index in high-stakes decisions was raised in 14 (45%) videos. Sixteen videos (52%) described caveats about using the h-index, with potential disadvantages to early researchers the most prevalent (n = 7; 23%). All videos incorporated various educational approaches with potential impact on viewer cognitive load. A minority of videos (n = 10; 32%) displayed professional production quality. DISCUSSION: The videos featured content with potential to enhance viewers' metrics literacies such that many defined the h-index and described its calculation, providing viewers with skills to recognize and interpret the metric. However, less than half described the h-index as an author quality indicator, which has been contested, and caveats about h-index use were inconsistently presented, suggesting room for improvement. While most videos integrated practices to facilitate balancing viewers' cognitive load, few (32%) were of professional production quality. Some videos missed opportunities to adopt particular practices that could benefit learning.


Assuntos
Mídias Sociais , Benchmarking , Aprendizagem , Gravação em Vídeo
5.
Genome Biol ; 23(1): 110, 2022 May 06.
Artigo em Inglês | MEDLINE | ID: mdl-35524317

RESUMO

Variant benchmarking is often performed by comparing a test callset to a gold standard set of variants. In repetitive regions of the genome, it may be difficult to establish what is the truth for a call, for example, when different alignment scoring metrics provide equally supported but different variant calls on the same data. Here, we provide an alternative approach, TT-Mars, that takes advantage of the recent production of high-quality haplotype-resolved genome assemblies by providing false discovery rates for variant calls based on how well their call reflects the content of the assembly, rather than comparing calls themselves.


Assuntos
Polimorfismo de Nucleotídeo Único , Software , Benchmarking , Genoma , Haplótipos , Sequenciamento de Nucleotídeos em Larga Escala
6.
PLoS One ; 17(5): e0267759, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35507631

RESUMO

Effective conservation actions require effective population monitoring. However, accurately counting animals in the wild to inform conservation decision-making is difficult. Monitoring populations through image sampling has made data collection cheaper, wide-reaching and less intrusive but created a need to process and analyse this data efficiently. Counting animals from such data is challenging, particularly when densely packed in noisy images. Attempting this manually is slow and expensive, while traditional computer vision methods are limited in their generalisability. Deep learning is the state-of-the-art method for many computer vision tasks, but it has yet to be properly explored to count animals. To this end, we employ deep learning, with a density-based regression approach, to count fish in low-resolution sonar images. We introduce a large dataset of sonar videos, deployed to record wild Lebranche mullet schools (Mugil liza), with a subset of 500 labelled images. We utilise abundant unlabelled data in a self-supervised task to improve the supervised counting task. For the first time in this context, by introducing uncertainty quantification, we improve model training and provide an accompanying measure of prediction uncertainty for more informed biological decision-making. Finally, we demonstrate the generalisability of our proposed counting framework through testing it on a recent benchmark dataset of high-resolution annotated underwater images from varying habitats (DeepFish). From experiments on both contrasting datasets, we demonstrate our network outperforms the few other deep learning models implemented for solving this task. By providing an open-source framework along with training data, our study puts forth an efficient deep learning template for crowd counting aquatic animals thereby contributing effective methods to assess natural populations from the ever-increasing visual data.


Assuntos
Aprendizado Profundo , Animais , Benchmarking , Ecossistema , Peixes , Incerteza
8.
Zhongguo Zhong Yao Za Zhi ; 47(9): 2430-2439, 2022 May.
Artigo em Chinês | MEDLINE | ID: mdl-35531690

RESUMO

A total of 15 batches of the substance reference of Guizhi Jia Gegen Decoction(GZGGD) were prepared and the characteristic fingerprints of them were established. Furthermore, the similarity of the fingerprints and peak attributes were explored. The extraction rate, and the content and the transfer rate ranges of the index components, puerarin, paeoniflorin, liquiritin, and ammonium glycyrrhizate were determined for the analysis of the quality value transfer. The result demonstrated that the fingerprints of the 15 batches of the samples showed high similarity(>0.99). A total of 15 characteristic peaks were identified from the fingerprints, with 10 for Puerariae Lobatae Radix, 1 for Cinnamomi Ramulus, 2 for Paeoniae Radix Alba, and 2 for Glycyrrhizae Radix et Rhizoma. The content of puerarin was 11.05-18.35 mg·g~(-1) and the average transfer rate was 21.27%-39.49%. The corresponding figures were 7.95-10.90 mg·g~(-1) and 23.28%-43.23% for paeoniflorin, 3.25-4.95 mg·g~(-1) and 32.31%-61.27% for ammonium glycyrrhizate, and 3.65-5.80 mg·g~(-1) and 14.57%-27.05% for liquiritin. The extraction rate of the 15 batches of samples was in the range of 16.85%-21.78%. In this paper, the quality value transfer of the substance reference of GZGGD was analyzed based on characteristic fingerprint, content of index components, and the extraction rate. This study is expected to lay a basis for the quality control and further development of GZGGD.


Assuntos
Compostos de Amônio , Medicamentos de Ervas Chinesas , Paeonia , Benchmarking , Cromatografia Líquida de Alta Pressão
9.
Zhongguo Zhong Yao Za Zhi ; 47(8): 2090-2098, 2022 Apr.
Artigo em Chinês | MEDLINE | ID: mdl-35531725

RESUMO

The methods for determining the characteristic chromatogram and index components content of Xuanfu Daizhe Decoction were established to provide a scientific basis for the quality evaluation of substance benchmarks and preparations. Eighteen batches of Xuanfu Daizhe Decoction were prepared with the decoction pieces of different batches and of the same batch were prepared respectively, and the HPLC characteristic chromatograms of these samples were established. The similarities of the chromatographic fingerprints were analyzed. With liquiritin, glycyrrhizic acid, 6-gingerol, ginsenoside Rg_1, and ginsenoside Re as index components, the high performance liquid chromatography was established for content determination with no more than 70%-130% of the mass average as the limit. The results showed that there were 19 characteristic peaks corresponding to the characteristic chromatograms of 18 batches of Xuanfu Daizhe Decoction, including 8 peaks representing liquiritin, 1,5-O-dicaffeoylqunic acid, ginsenoside Rg_1, ginsenoside Re, 1-O-acetyl britannilactone, ginsenoside Rb_1, glycyrrhizic acid, and 6-gingerol, and the fingerprint similarity was greater than 0.97. The contents of liquiritin, glycyrrhizic acid, 6-gingerol, and ginsenosides Rg_1 + Re in the prepared Xuanfu Daizhe Decoction samples were 0.53%-0.86%, 0.61%-1.2%, 0.023%-0.068%, and 0.33%-0.66%, respectively. Except for several batches, most batches of Xuanfu Daizhe Decoction showed stable contents of index components, with no discrete values. The characteristic chromatograms and index components content characterized the information of Inulae Flos, Ginseng Radix et Rhizoma, Glycyrrhizae Radix et Rhizoma, and Zingiberis Rhizoma Recens in Xuanfu Daizhe Decoction. This study provides a scientific basis for the further research on the key chemical properties of substance benchmark and preparations of Xuanfu Daizhe Decoction.


Assuntos
Medicamentos de Ervas Chinesas , Ginsenosídeos , Benchmarking , Cromatografia Líquida de Alta Pressão , Medicamentos de Ervas Chinesas/química , Ginsenosídeos/análise , Ácido Glicirrízico/análise , Controle de Qualidade
10.
Zhongguo Zhong Yao Za Zhi ; 47(8): 2099-2108, 2022 Apr.
Artigo em Chinês | MEDLINE | ID: mdl-35531726

RESUMO

According to the polarity of different components in Sanpian Decoction, two fingerprints were established. Then the substance benchmark freeze-dried powder of 15 batches of Sanpian Decoction was prepared, followed by the determination of the fingerprints, index component content, and dry extract rates, the identification of attribution of characteristic peaks, and the calculation of similarities between these fingerprints and the reference(R), the content and transfer rate ranges of ferulic acid, sinapine thiocyanate, liquiritin, and glycyrrhizic acid, and the dry extract rate range. The results showed that the similarities of 15 batches of the substance benchmark fingerprints with R were all greater than 0.900.Further summarization of the characteristic peaks revealed that there were a total of 20 characteristic peaks in fingerprint 1, among which, eight were from Sinapis Semen, four from Paeoniae Radix Alba, six from Chuanxiong Rhizoma, and two from Glycyrrhizae Radix et Rhizoma. A total of 16 characteristic peaks were observed in fingerprint 2, including one from Sinapis Semen, three from Paeoniae Radix Alba, eight from Chuanxiong Rhizoma, and four from Glycyrrhizae Radix et Rhizoma. The average dry extract rate of 15 batches of substance benchmarks was 18.25%, with a dry extract rate range of 16.28%-20.76%. The index component content and transfer rate ranges were listed as follows: 0.15%-0.18% and 38.81%-58.05% for ferulic acid; 0.26%-0.42% and 36.51%-51.02% for sinapine thiocyanate; 0.09%-0.15% and 48.80%-76.61% for liquiritin; 0.13%-0.24% and 23.45%-35.61% for glycyrrhizic acid. The fingerprint, dry extract rate, and index component content determination was combined for analyzing the quality value transfer of substance benchmarks in the classic prescription Sanpian Decoction.The established quality evaluation method for the substance benchmarks was stable and feasible, which has provided a basis for the quality control of Sanpian Decoction and the follow-up development of related preparations.


Assuntos
Medicamentos de Ervas Chinesas , Paeonia , Benchmarking , Cromatografia Líquida de Alta Pressão , Ácido Glicirrízico/análise , Controle de Qualidade , Tiocianatos
11.
Comput Intell Neurosci ; 2022: 8323962, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35498187

RESUMO

Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey.


Assuntos
Aprendizado Profundo , Benchmarking , Atividades Humanas , Humanos , Redes Neurais de Computação , Reconhecimento Psicológico
12.
Comput Intell Neurosci ; 2022: 7261551, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35498207

RESUMO

Shadow detection and removal play an important role in the field of computer vision and pattern recognition. Shadow will cause some loss and interference to the information of moving objects, resulting in the performance degradation of subsequent computer vision tasks such as moving object detection or image segmentation. In this paper, each image is regarded as a small sample, and then a method based on material matching of intelligent computing between image regions is proposed to detect and remove image shadows. In shadow detection, the proposed method can be directly used for detection without training and ensures the consistency of similar regions to a certain extent. In shadow removal, the proposed method can minimize the influence of shadow removal operation on other features in the shadow region. The experiments on the benchmark dataset demonstrate that the proposed approach achieves a promising performance, and its improvement is more than 6% in comparison with several advanced shadow detection methods.


Assuntos
Benchmarking , Inteligência
13.
World Neurosurg ; 161: 251-264, 2022 May.
Artigo em Inglês | MEDLINE | ID: mdl-35505542

RESUMO

BACKGROUND: With the advent of personalized and stratified medicine, there has been much discussion about predictive modeling and the role of classical regression in modern medical research. We describe and distinguish the goals in these 2 frameworks for analysis. METHODS: The assumptions underlying and utility of classical regression are reviewed for continuous and binary outcomes. The tenets of predictive modeling are then discussed and contrasted. Principles are illustrated by simulation and through application of methods to a neurosurgical study. RESULTS: Classical regression can be used for insights into causal mechanisms if careful thought is given to the role of variables of interest and potential confounders. In predictive modeling, interest lies more in accuracy of predictions and so alternative metrics are used to judge adequacy of models and methods; methods which average predictions over several contending models can improve predictive performance but these do not admit a single risk score. CONCLUSIONS: Both classical regression and predictive modeling have important roles in modern medical research. Understanding the distinction between the 2 frameworks for analysis is important to place them in their appropriate context and interpreting findings from published studies appropriately.


Assuntos
Pesquisa Biomédica , Benchmarking , Simulação por Computador , Humanos
14.
Cancer Biomark ; 33(4): 467-478, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35491771

RESUMO

BACKGROUND: Given the growing interest in using microRNAs (miRNAs) as biomarkers of early disease, establishment of robust protocols and platforms for miRNA quantification in biological fluids is critical. OBJECTIVE: The goal of this multi-center pilot study was to evaluate the reproducibility of NanoString nCounter™ technology when analyzing the abundance of miRNAs in plasma and cystic fluid from patients with pancreatic lesions. METHODS: Using sample triplicates analyzed across three study sites, we assessed potential sources of variability (RNA isolation, sample processing/ligation, hybridization, and lot-to-lot variability) that may contribute to suboptimal reproducibility of miRNA abundance when using nCounter™, and evaluated expression of positive and negative controls, housekeeping genes, spike-in genes, and miRNAs. RESULTS: Positive controls showed a high correlation across samples from each site (median correlation coefficient, r> 0.9). Most negative control probes had expression levels below background. Housekeeping and spike-in genes each showed a similar distribution of expression and comparable pairwise correlation coefficients of replicate samples across sites. A total of 804 miRNAs showed a similar distribution of pairwise correlation coefficients between replicate samples (p= 0.93). After normalization and selecting miRNAs with expression levels above zero in 80% of samples, 55 miRNAs were identified; heatmap and principal component analysis revealed similar expression patterns and clustering in replicate samples. CONCLUSIONS: Findings from this pilot investigation suggest the nCounter platform can yield reproducible results across study sites. This study underscores the importance of implementing quality control procedures when designing multi-center evaluations of miRNA abundance.


Assuntos
MicroRNA Circulante , MicroRNAs , Benchmarking , MicroRNA Circulante/genética , Perfilação da Expressão Gênica/métodos , Humanos , MicroRNAs/genética , Projetos Piloto , Controle de Qualidade , Reprodutibilidade dos Testes
15.
Sci Robot ; 7(66): eabm5954, 2022 May 04.
Artigo em Inglês | MEDLINE | ID: mdl-35507682

RESUMO

Aerial robots are widely deployed, but highly cluttered environments such as dense forests remain inaccessible to drones and even more so to swarms of drones. In these scenarios, previously unknown surroundings and narrow corridors combined with requirements of swarm coordination can create challenges. To enable swarm navigation in the wild, we develop miniature but fully autonomous drones with a trajectory planner that can function in a timely and accurate manner based on limited information from onboard sensors. The planning problem satisfies various task requirements including flight efficiency, obstacle avoidance, and inter-robot collision avoidance, dynamical feasibility, swarm coordination, and so on, thus realizing an extensible planner. Furthermore, the proposed planner deforms trajectory shapes and adjusts time allocation synchronously based on spatial-temporal joint optimization. A high-quality trajectory thus can be obtained after exhaustively exploiting the solution space within only a few milliseconds, even in the most constrained environment. The planner is finally integrated into the developed palm-sized swarm platform with onboard perception, localization, and control. Benchmark comparisons validate the superior performance of the planner in trajectory quality and computing time. Various real-world field experiments demonstrate the extensibility of our system. Our approach evolves aerial robotics in three aspects: capability of cluttered environment navigation, extensibility to diverse task requirements, and coordination as a swarm without external facilities.


Assuntos
Robótica , Esportes , Algoritmos , Benchmarking , Humanos , Distúrbios da Fala
16.
Comput Intell Neurosci ; 2022: 3558385, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-35371240

RESUMO

In many fields, including management, computer, and communication, Large-Scale Global Optimization (LSGO) plays a critical role. It has been applied to various applications and domains. At the same time, it is one of the most challenging optimization problems. This paper proposes a novel memetic algorithm (called MPCE & SSALS) based on multiparent evolution and adaptive local search to address the LSGO problems. In MPCE & SSALS, a multiparent crossover operation is used for global exploration, while a step-size adaptive local search is utilized for local exploitation. A new offspring is generated by recombining four parents. In the early stage of the algorithm execution, global search and local search are performed alternately, and the population size gradually decreases to 1. In the later stage, only local searches are performed for the last individual. Experiments were conducted on 15 benchmark functions of the CEC'2013 benchmark suite for LSGO. The results were compared with four state-of-the-art algorithms, demonstrating that the proposed MPCE & SSALS algorithm is more effective.


Assuntos
Algoritmos , Benchmarking , Comunicação , Simulação por Computador
17.
Sci Rep ; 12(1): 5979, 2022 Apr 08.
Artigo em Inglês | MEDLINE | ID: mdl-35395867

RESUMO

Clinicians and software developers need to understand how proposed machine learning (ML) models could improve patient care. No single metric captures all the desirable properties of a model, which is why several metrics are typically reported to summarize a model's performance. Unfortunately, these measures are not easily understandable by many clinicians. Moreover, comparison of models across studies in an objective manner is challenging, and no tool exists to compare models using the same performance metrics. This paper looks at previous ML studies done in gastroenterology, provides an explanation of what different metrics mean in the context of binary classification in the presented studies, and gives a thorough explanation of how different metrics should be interpreted. We also release an open source web-based tool that may be used to aid in calculating the most relevant metrics presented in this paper so that other researchers and clinicians may easily incorporate them into their research.


Assuntos
Inteligência Artificial , Benchmarking , Humanos , Aprendizado de Máquina , Software
18.
Sci Rep ; 12(1): 5962, 2022 Apr 08.
Artigo em Inglês | MEDLINE | ID: mdl-35396371

RESUMO

Swarm intelligence algorithm is an important evolutionary computation method that optimizes the objective function by imitating the behaviors of various organisms in nature. A two-stage swarm intelligence algorithm named spider pheromone coordination algorithm (SPC) is proposed in this paper. SPC tries to explore as many feasible solutions as possible on the cobweb at the positioning stage. It simulates the release and reception of different pheromones between spiders at the hunting stage, and then spiders move towards prey under the co-action of winds and pheromones. Different from the existing algorithms, SPC simulates the process that spiders accomplish intra-species communications through different pheromones and considers the impact on spider wind movement. A large number of typical benchmark functions are used in comparative numerical experiments to verify the performances of SPC. Experiments are made to compare SPC with a series of swarm intelligence algorithms, showing that SPC has higher convergence accuracy and stronger global searchability, effectively keeping the diversity of feasible solutions.


Assuntos
Feromônios , Aranhas , Algoritmos , Animais , Benchmarking
19.
J Exp Biol ; 225(7)2022 Apr 01.
Artigo em Inglês | MEDLINE | ID: mdl-35403696

RESUMO

Applications of key technologies in biomedical research, such as qRT-PCR or LC-MS-based proteomics, are generating large biological (-omics) datasets which are useful for the identification and quantification of biomarkers in any research area of interest. Genome, transcriptome and proteome databases are already available for a number of model organisms including vertebrates and invertebrates. However, there is insufficient information available for protein sequences of certain invertebrates, such as the great pond snail Lymnaea stagnalis, a model organism that has been used highly successfully in elucidating evolutionarily conserved mechanisms of memory function and dysfunction. Here, we used a bioinformatics approach to designing and benchmarking a comprehensive central nervous system (CNS) proteomics database (LymCNS-PDB) for the identification of proteins from the CNS of Lymnaea by LC-MS-based proteomics. LymCNS-PDB was created by using the Trinity TransDecoder bioinformatics tool to translate amino acid sequences from mRNA transcript assemblies obtained from a published Lymnaea transcriptomics database. The blast-style MMSeq2 software was used to match all translated sequences to UniProtKB sequences for molluscan proteins, including those from Lymnaea and other molluscs. LymCNS-PDB contains 9628 identified matched proteins that were benchmarked by performing LC-MS-based proteomics analysis with proteins isolated from the Lymnaea CNS. MS/MS analysis using the LymCNS-PDB database led to the identification of 3810 proteins. Only 982 proteins were identified by using a non-specific molluscan database. LymCNS-PDB provides a valuable tool that will enable us to perform quantitative proteomics analysis of protein interactomes involved in several CNS functions in Lymnaea, including learning and memory and age-related memory decline.


Assuntos
Biologia Computacional , Lymnaea , Animais , Benchmarking , Sistema Nervoso Central , Cromatografia Líquida , Lymnaea/genética , Proteínas/metabolismo , Espectrometria de Massas em Tandem
20.
Sensors (Basel) ; 22(7)2022 Mar 30.
Artigo em Inglês | MEDLINE | ID: mdl-35408261

RESUMO

Few-shot learning (FSL) is of great significance to the field of machine learning. The ability to learn and generalize using a small number of samples is an obvious distinction between artificial intelligence and humans. In the FSL domain, most graph neural networks (GNNs) focus on transferring labeled sample information to an unlabeled query sample, ignoring the important role of semantic information during the classification process. Our proposed method embeds semantic information of classes into a GNN, creating a word embedding distribution propagation graph network (WPGN) for FSL. We merge the attention mechanism with our backbone network, use the Mahalanobis distance to calculate the similarity of classes, select the Funnel ReLU (FReLU) function as the activation function of the Transform layer, and update the point graph and word embedding distribution graph. In extensive experiments on FSL benchmarks, compared with the baseline model, the accuracy of the WPGN on the 5-way-1/2/5 shot tasks increased by 9.03, 4.56, and 4.15%, respectively.


Assuntos
Inteligência Artificial , Redes Neurais de Computação , Benchmarking , Humanos , Aprendizado de Máquina , Semântica
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...