A novel feature selection strategy for enhanced biomedical event extraction using the Turku system.
Ontology highlight
ABSTRACT:
SUBMITTER: Xia J
PROVIDER: S-EPMC3997098 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers. The feature extraction method is tested on both the N-MNIST (Neuromorphic-MNIST) benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage.
| S-EPMC7146588 | biostudies-literature
Project description:BackgroundBiomedical event extraction is a fundamental and in-demand technology that has attracted substantial interest from many researchers. Previous works have heavily relied on manual designed features and external NLP packages in which the feature engineering is large and complex. Additionally, most of the existing works use the pipeline process that breaks down a task into simple sub-tasks but ignores the interaction between them. To overcome these limitations, we propose a novel event combination strategy based on hybrid deep neural networks to settle the task in a joint end-to-end manner.ResultsWe adapted our method to several annotated corpora of biomedical event extraction tasks. Our method achieved state-of-the-art performance with noticeable overall F1 score improvement compared to that of existing methods for all of these corpora.ConclusionsThe experimental results demonstrated that our method is effective for biomedical event extraction. The combination strategy can reconstruct complex events from the output of deep neural networks, while the deep neural networks effectively capture the feature representation from the raw text. The biomedical event extraction implementation is available online;http://www.Predictorxin/event_extraction;http://2013.bionlp-st.org/tasks;http://nactem.ac.uk/MLEE/.Otherwise, please provide alternatives.
| S-EPMC7006190 | biostudies-literature
Project description:The Golgi Apparatus (GA) is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP), a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE) is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF) module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew's Correlation Coefficient (MCC) of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions.
| S-EPMC4783950 | biostudies-literature
Project description:MotivationRecent neural approaches on event extraction from text mainly focus on flat events in general domain, while there are less attempts to detect nested and overlapping events. These existing systems are built on given entities and they depend on external syntactic tools.ResultsWe propose an end-to-end neural nested event extraction model named DeepEventMine that extracts multiple overlapping directed acyclic graph structures from a raw sentence. On the top of the bidirectional encoder representations from transformers model, our model detects nested entities and triggers, roles, nested events and their modifications in an end-to-end manner without any syntactic tools. Our DeepEventMine model achieves the new state-of-the-art performance on seven biomedical nested event extraction tasks. Even when gold entities are unavailable, our model can detect events from raw text with promising performance.Availability and implementationOur codes and models to reproduce the results are available at: https://github.com/aistairc/DeepEventMine.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC7750964 | biostudies-literature
Project description:MotivationRelation extraction (RE) is a crucial process to deal with the amount of text published daily, e.g. to find missing associations in a database. RE is a text mining task for which the state-of-the-art approaches use bidirectional encoders, namely, BERT. However, state-of-the-art performance may be limited by the lack of efficient external knowledge injection approaches, with a larger impact in the biomedical area given the widespread usage and high quality of biomedical ontologies. This knowledge can propel these systems forward by aiding them in predicting more explainable biomedical associations. With this in mind, we developed K-RET, a novel, knowledgeable biomedical RE system that, for the first time, injects knowledge by handling different types of associations, multiple sources and where to apply it, and multi-token entities.ResultsWe tested K-RET on three independent and open-access corpora (DDI, BC5CDR, and PGR) using four biomedical ontologies handling different entities. K-RET improved state-of-the-art results by 2.68% on average, with the DDI Corpus yielding the most significant boost in performance, from 79.30% to 87.19% in F-measure, representing a P-value of 2.91×10-12.Availability and implementationhttps://github.com/lasigeBioTM/K-RET.
| S-EPMC10112952 | biostudies-literature
Project description:ObjectiveThe US Vaccine Adverse Event Reporting System (VAERS) collects spontaneous reports of adverse events following vaccination. Medical officers review the reports and often apply standardized case definitions, such as those developed by the Brighton Collaboration. Our objective was to demonstrate a multi-level text mining approach for automated text classification of VAERS reports that could potentially reduce human workload.DesignWe selected 6034 VAERS reports for H1N1 vaccine that were classified by medical officers as potentially positive (N(pos)=237) or negative for anaphylaxis. We created a categorized corpus of text files that included the class label and the symptom text field of each report. A validation set of 1100 labeled text files was also used. Text mining techniques were applied to extract three feature sets for important keywords, low- and high-level patterns. A rule-based classifier processed the high-level feature representation, while several machine learning classifiers were trained for the remaining two feature representations.MeasurementsClassifiers' performance was evaluated by macro-averaging recall, precision, and F-measure, and Friedman's test; misclassification error rate analysis was also performed.ResultsRule-based classifier, boosted trees, and weighted support vector machines performed well in terms of macro-recall, however at the expense of a higher mean misclassification error rate. The rule-based classifier performed very well in terms of average sensitivity and specificity (79.05% and 94.80%, respectively).ConclusionOur validated results showed the possibility of developing effective medical text classifiers for VAERS reports by combining text mining with informative feature selection; this strategy has the potential to reduce reviewer workload considerably.
| S-EPMC3168300 | biostudies-literature
Project description:BackgroundWheat is an important food crop globally, and timely prediction of wheat yield in breeding efforts can improve selection efficiency. Traditional yield prediction method based on secondary traits is time-consuming, costly, and destructive. It is urgent to develop innovative methods to improve selection efficiency and accelerate genetic gains in the breeding cycle.ResultsCrop yield prediction using remote sensing has gained popularity in recent years. This paper proposed a novel ensemble feature selection (EFS) method to improve yield prediction from hyperspectral data. For this, 207 wheat cultivars and breeding lines were grown under full and limited irrigation treatments respectively, and their canopy hyperspectral reflectance was measured at the flowering, early grain filling (EGF), mid grain filling (MGF), and late grain filling (LGF) stages. Then, 115 vegetation indices were extracted from the hyperspectral reflectance and combined with four feature selection methods, i.e., mean decrease impurity (MDI), Boruta, FeaLect, and RReliefF to train deep neural network (DNN) models for yield prediction. Next, a learning framework was developed by combining the predicted values of the selected and the full features using multiple linear regression (MLR). The results show that the selected features contributed to higher yield prediction accuracy than the full features, and the MDI method performed well across growth stages, with a mean R2 ranging from 0.634 to 0.666 (mean RMSE = 0.926-0.967 t ha-1). Also, the proposed EFS method outperformed all the individual feature selection methods across growth stages, with a mean R2 ranging from 0.648 to 0.679 (mean RMSE = 0.911-0.950 t ha-1).ConclusionsThe proposed EFS method can improve grain yield prediction from hyperspectral data and can be used to assist wheat breeders in earlier decision-making.
| S-EPMC9641855 | biostudies-literature
Project description:Gene expression, often determined by single nucleotide polymorphisms, short repeated sequences known as short tandem repeats (STRs), structural variants, and environmental factors, provides means for an organism to produce gene products necessary to live. Variation in expression levels, sometimes known as enrichment patterns, has been associated with disease progression. Thus, the STR enrichment patterns have recently gained interest as potential genetic markers for disease progression. However, to the best of our knowledge, we are unaware of any study that evaluates and explores STRs, particularly trinucleotide sequences, as machine learning features for classifying neurological disease genes for the purpose of discovering genetic features. Thus, in this paper, we proposed a new metric and a novel feature extraction and selection algorithm based on statistically significant STR-based features and their respective enrichment patterns to create a statistically significant feature set. The proposed new metric has shown that the neurological disease family genes have a non-random AA, AT, TA, TG, and TT enrichment pattern. This is an important result, as it supports prior research that has established that certain trinucleotides, such as AAT, ATA, ATT, TAT, and TTA, are favored during protein misfolding. In contrast, trinucleotides, such as TAA, TAG, and TGA, are favored during premature termination codon mutations as they are stop codons. This suggests that the metric has the potential to identify patterns that may be genetic features in a sample of neurological genes. Moreover, the practical performance and high prediction results of the statistically significant STR-based feature set indicate that variations in STR enrichment patterns can distinguish neurological disease genes. In conclusion, the proposed approach may have the potential to discover differential genetic features for other diseases.
| S-EPMC9922266 | biostudies-literature
Project description:Binary classification is a widely employed problem to facilitate the decisions on various biomedical big data questions, such as clinical drug trials between treated participants and controls, and genome-wide association studies (GWASs) between participants with or without a phenotype. A machine learning model is trained for this purpose by optimizing the power of discriminating samples from two groups. However, most of the classification algorithms tend to generate one locally optimal solution according to the input dataset and the mathematical presumptions of the dataset. Here we demonstrated from the aspects of both disease classification and feature selection that multiple different solutions may have similar classification performances. So the existing machine learning algorithms may have ignored a horde of fishes by catching only a good one. Since most of the existing machine learning algorithms generate a solution by optimizing a mathematical goal, it may be essential for understanding the biological mechanisms for the investigated classification question, by considering both the generated solution and the ignored ones.
| S-EPMC5634418 | biostudies-literature
Project description:With an increasing demand for stringent security systems, automated identification of individuals based on biometric methods has been a major focus of research and development over the last decade. Biometric recognition analyses unique physiological traits or behavioral characteristics, such as an iris, face, retina, voice, fingerprint, hand geometry, keystrokes or gait. The iris has a complex and unique structure that remains stable over a person's lifetime, features that have led to its increasing interest in its use for biometric recognition. In this study, we proposed a technique incorporating Principal Component Analysis (PCA) based on Discrete Wavelet Transformation (DWT) for the extraction of the optimum features of an iris and reducing the runtime needed for iris template classification. The idea of using DWT behind PCA is to reduce the resolution of the iris template. DWT converts an iris image into four frequency sub-bands. One frequency sub-band instead of four has been used for further feature extraction by using PCA. Our experimental evaluation demonstrates the efficient performance of the proposed technique.
| S-EPMC7924705 | biostudies-literature