The recent advances in pervasive sensing technologies have enabled us to monitor and analyze the multi-channel electroencephalogram (EEG) signals of epilepsy patients to prevent serious outcomes ...caused by epileptic seizures. To avoid manual visual inspection from long-term EEG readings, automatic EEG seizure detection has garnered increasing attention among researchers. In this paper, we present a unified multi-view deep learning framework to capture brain abnormalities associated with seizures based on multi-channel scalp EEG signals. The proposed approach is an end-to-end model that is able to jointly learn multi-view features from both unsupervised multi-channel EEG reconstruction and supervised seizure detection via spectrogram representation. We construct a new autoencoder-based multi-view learning model by incorporating both inter and intra correlations of EEG channels to unleash the power of multi-channel information. By adding a channel-wise competition mechanism in the training phase, we propose a channel-aware seizure detection module to guide our multi-view structure to focus on important and relevant EEG channels. To validate the effectiveness of the proposed framework, extensive experiments against nine baselines, including both traditional handcrafted feature extraction and conventional deep learning methods, are carried out on a benchmark scalp EEG dataset. Experimental results show that the proposed model is able to achieve higher average accuracy and f1-score at 94.37% and 85.34%, respectively, using 5-fold subject-independent cross validation, demonstrating a powerful and effective method in the task of EEG seizure detection.
Comprehensive molecular profiling of various cancers and other diseases has generated vast amounts of multi-omics data. Each type of -omics data corresponds to one feature space, such as gene ...expression, miRNA expression, DNA methylation, etc. Integrating multi-omics data can link different layers of molecular feature spaces and is crucial to elucidate molecular pathways underlying various diseases. Machine learning approaches to mining multi-omics data hold great promises in uncovering intricate relationships among molecular features. However, due to the "big p, small n" problem (i.e., small sample sizes with high-dimensional features), training a large-scale generalizable deep learning model with multi-omics data alone is very challenging.
We developed a method called Multi-view Factorization AutoEncoder (MAE) with network constraints that can seamlessly integrate multi-omics data and domain knowledge such as molecular interaction networks. Our method learns feature and patient embeddings simultaneously with deep representation learning. Both feature representations and patient representations are subject to certain constraints specified as regularization terms in the training objective. By incorporating domain knowledge into the training objective, we implicitly introduced a good inductive bias into the machine learning model, which helps improve model generalizability. We performed extensive experiments on the TCGA datasets and demonstrated the power of integrating multi-omics data and biological interaction networks using our proposed method for predicting target clinical variables.
To alleviate the overfitting problem in deep learning on multi-omics data with the "big p, small n" problem, it is helpful to incorporate biological domain knowledge into the model as inductive biases. It is very promising to design machine learning models that facilitate the seamless integration of large-scale multi-omics data and biomedical domain knowledge for uncovering intricate relationships among molecular features and clinical features.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
A Survey on Causal Inference Yao, Liuyi; Chu, Zhixuan; Li, Sheng ...
ACM transactions on knowledge discovery from data,
06/2021, Letnik:
15, Številka:
5
Journal Article
Recenzirano
Odprti dostop
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy, and economics, for decades. Nowadays, estimating causal effect from ...observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine, and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
•Affinity Network Fusion and Semi-supervised Learning for Multi-omic Integration.•Extensive Experiments and Promising Results on GDC Harmonized Cancer Genomic Datasets.•Few-shot Semi-supervised Model ...Achieving 90% Test Set Accuracy by Training Only 1% Data.
Defining subtypes of complex diseases such as cancer and stratifying patient groups with the same disease but different subtypes for targeted treatments is important for personalized and precision medicine. Approaches that incorporate multi-omic data are more advantageous to those using only one data type for patient clustering and disease subtype discovery. However, it is challenging to integrate multi-omic data as they are heterogeneous and noisy. In this paper, we present Affinity Network Fusion (ANF) to integrate multi-omic data for patient clustering. ANF first constructs patient affinity networks for each omic data type, and then calculates a fused network for spectral clustering. We applied ANF to a processed harmonized cancer dataset downloaded from GDC data portal consisting of 2193 patients, and generated promising results on clustering patients into correct disease types. Moreover, we developed a semi-supervised model combining ANF and neural network for few-shot learning. In several cases, the model can achieve greater than 90% accuracy on test set with training less than 1% of the data. This demonstrates the power of ANF in learning a good representation of patients, and shows the great potential of semi-supervised learning in cancer patient clustering. .
Abstract
Motivation
MEDLINE is the primary bibliographic database maintained by National Library of Medicine (NLM). MEDLINE citations are indexed with Medical Subject Headings (MeSH), which is a ...controlled vocabulary curated by the NLM experts. This greatly facilitates the applications of biomedical research and knowledge discovery. Currently, MeSH indexing is manually performed by human experts. To reduce the time and monetary cost associated with manual annotation, many automatic MeSH indexing systems have been proposed to assist manual annotation, including DeepMeSH and NLM’s official model Medical Text Indexer (MTI). However, the existing models usually rely on the intermediate results of other models and suffer from efficiency issues. We propose an end-to-end framework, MeSHProbeNet (formerly named as xgx), which utilizes deep learning and self-attentive MeSH probes to index MeSH terms. Each MeSH probe enables the model to extract one specific aspect of biomedical knowledge from an input article, thus comprehensive biomedical information can be extracted with different MeSH probes and interpretability can be achieved at word level. MeSH terms are finally recommended with a unified classifier, making MeSHProbeNet both time efficient and space efficient.
Results
MeSHProbeNet won the first place in the latest batch of Task A in the 2018 BioASQ challenge. The result on the last test set of the challenge is reported in this paper. Compared with other state-of-the-art models, such as MTI and DeepMeSH, MeSHProbeNet achieves the highest scores in all the F-measures, including Example Based F-Measure, Macro F-Measure, Micro F-Measure, Hierarchical F-Measure and Lowest Common Ancestor F-measure. We also intuitively show how MeSHProbeNet is able to extract comprehensive biomedical knowledge from an input article.
We demonstrate a facile procedure to efficiently prepare Prussian blue nanocubes/reduced graphene oxide (PBNCs/rGO) nanocomposite by directly mixing Fe
3+
and Fe(CN)
6
3
in the presence of GO in ...polyethyleneimine aqueous solution, resulting in a novel acetylcholinesterase (AChE) biosensor for detection of organophosphorus pesticides (OPs). The obtained nanocomposite was characterized by X-ray photoelectron spectroscopy (XPS), transmission electron microscopy (TEM) and energy-dispersive X-ray (EDX) microanalysis. It was clearly observed that the nanosheet has been decorated with cubic PB nanoparticles and nearly all the nanoparticles are distributed uniformly only on the surface of the reduced GO. No isolated PB nanoparticles were observed, indicating the strong interaction between PB nanocubes and the reduced GO and the formation of PBNCs/rGO nanocomposite. The obtained PBNCs/rGO based AChE biosensor make the peak potential shift negatively to 220 mV. The over-potential decreases 460 mV compared to that on a bare electrode, suggesting that PBNCs/rGO has a high electrocatalytic activity towards the oxidation of thiocholine. The AChE biosensor shows rapid response and high sensitivity for detection of monocrotophos with a linear range from 1.0 to 600 ng mL
1
and a detection limit of 0.1 ng mL
1
. These results suggest that the PBNCs/rGO hybrids nanocomposite exhibited high electrocatalytic activity towards the oxidation of thiocholine, which lead to the sensitive detection of OP pesticides.
A facile procedure for synthesis of Prussian blue nanocubes/reduced graphene oxide nanocomposite results in a novel acetylcholinesterase biosensor for detection of organophosphorus pesticides.
Anthocyanin synthesis is affected by many factors, among which temperature is an important environmental factor. Eggplant is usually exposed to high temperatures during the cultivation season in ...Shanghai, China. Therefore,RNA -seq analysis was used to determine the effects of high-temperature stress on gene expression in the anthocyanin biosynthetic pathway of eggplant (Solanum melongena L.).
We tested the heat-resistant cultivar 'Tewangda'. The plants were incubated at 38 °C and 45 °C, and the suitable temperature for eggplant growth was used as a control. The treatment times were 3 h and 6 h. The skin of the eggplant was taken for transcriptome sequencing, qRT-PCR assays and bioinformatic analysis. The results showed that 770 genes were differentially expressed between different treatments. Gene Ontology (GO) database and Kyoto Encyclopedia of Genes and Genomes (KEGG) database analyses identified 16 genes related to anthocyanin biosynthesis, among which CHSB was upregulated. Other genes, including BHLH62, MYB380, CHI3, CHI, CCOAOMT, AN3, ACT-2, HST, 5MA-T1, CYP75A2, ANT17, RT, PAL2, and anthocyanin 5-aromatic acyltransferase were downregulated. In addition, the Myb family transcription factor PHL11 was upregulated in the CK 3 h vs 45 °C 3 h, CK 3 h vs 38 °C 3 h, and CK 6 h vs 38 °C 6 h comparisons, and the transcription factor bHLH35 was upregulated in the CK 3 h vs 38 °C 3 h and CK 6 h vs 38 °C 6 h comparisons.
These results indicated that high temperature will downregulate most of the genes in the anthocyanin biosynthetic pathway of eggplant. Our data have a reference value for the heat resistance mechanism of eggplant and can provide directions for molecular breeding of heat-resistant germplasm with anthocyanin content in eggplant.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Enzymes of the chalcone synthase (CHS) family participate in the synthesis of multiple secondary metabolites in plants, fungi and bacteria. CHS showed a significant correlation with the accumulation ...patterns of anthocyanin. The peel color, which is primarily determined by the content of anthocyanin, is an economically important trait for eggplants that is affected by heat stress. A total of 7 CHS (SmCHS1-7) putative genes were identified in a genome-wide analysis of eggplants (S. melongena L.). The SmCHS genes were distributed on 7 scaffolds and were classified into 3 clusters. Phylogenetic relationship analysis showed that 73 CHS genes from 7 Solanaceae species were classified into 10 groups. SmCHS5, SmCHS6 and SmCHS7 were continuously down-regulated under 38°C and 45°C treatment, while SmCHS4 was up-regulated under 38°C but showed little change at 45°C in peel. Expression profiles of key anthocyanin biosynthesis gene families showed that the PAL, 4CL and AN11 genes were primarily expressed in all five tissues. The CHI, F3H, F3'5'H, DFR, 3GT and bHLH1 genes were expressed in flower and peel. Under heat stress, the expression level of 52 key genes were reduced. In contrast, the expression patterns of eight key genes similar to SmCHS4 were up-regulated at a treatment of 38°C for 3 hour. Comparative analysis of putative CHS protein evolutionary relationships, cis-regulatory elements, and regulatory networks indicated that SmCHS gene family has a conserved gene structure and functional diversification. SmCHS showed two or more expression patterns, these results of this study may facilitate further research to understand the regulatory mechanism governing peel color in eggplants.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The landmark report by de Bold et al. in 1981 signified the heart as one of the endocrine organs involved in fluid and salt balance (de Bold AJ, Borenstein HB, Veress AT, Sonnenberg H.
28: 89-94, ...1981). Atrial natriuretic peptide (ANP) and brain natriuretic peptide (BNP) are secreted from cardiomyocytes in response to cardiac stretch as in the case of heart failure, whereas C-type natriuretic peptide (CNP) is secreted from endothelial and renal cells in response to cytokines and endothelium-dependent agonists, such as acetylcholine. Binding ANP or BNP to natriuretic peptide receptor A induces cyclic guanylyl monophosphate as second messenger in the target cells to mediate the following: natriuresis; water diuresis; increasing glomerular filtration rate; decreasing systemic sympathetic activities; plasma volume; cardiac output and blood pressure; and curbing mitoses of heart fibroblasts and hypertrophy of cardiovascular muscle cells. ANP, BNP, and CNP are cleared from the bloodstream by natriuretic peptide receptor C and degraded by an ectoenzyme called neprilysin (NEP). The plasma levels of BNP are typically >100 pg/ml in patients with congestive heart failure. Sacubitril/valsartan is an angiotensin receptor NEP inhibitor that prevents the clinical progression of surviving patients with heart failure more effectively than enalapril, an angiotensin-converting enzyme inhibitor. A thorough understanding of the renal and cardiovascular effects of natriuretic peptides is of major importance for first-year medical students to gain insight into the significance of plasma levels of BNP in patients with heart failure.
A protein-protein interaction (PPI) network is a biomolecule relationship network that plays an important role in biological activities. Studies of functional modules in a PPI network contribute ...greatly to the understanding of biological mechanism. With the development of life science and computing science, a great amount of PPI data has been acquired by various experimental and computational approaches, which presents a significant challenge of detecting functional modules in a PPI network. To address this challenge, many functional module detecting methods have been developed. In this survey, we first analyze the existing problems in detecting functional modules and discuss the countermeasures in the data preprocess and postprocess. Second, we introduce some special metrics for distance or graph developed in clustering process of proteins. Third, we give a classification system of functional module detecting methods and describe some existing detection methods in each category. Fourth, we list databases in common use and conduct performance comparisons of several typical algorithms by popular measurements. Finally, we present the prospects and references for researchers engaged in analyzing PPI networks.