Haixuan Yang
A5090395493- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Machine Learning in Bioinformatics
- Genomics and Phylogenetic Studies
- Complex Network Analysis Techniques
- Superconducting and THz Device Technology
- RNA Research and Splicing
- Cosmology and Gravitation Theories
- Radio Astronomy Observations and Technology
- Advanced Graph Neural Networks
- Face and Expression Recognition
- Numerical methods in engineering
- Dark Matter and Cosmic Phenomena
- Biomedical Text Mining and Ontologies
- Computational Drug Discovery Methods
- RNA and protein synthesis mechanisms
- Recommender Systems and Techniques
- Advanced Proteomics Techniques and Applications
- Neural Networks and Applications
- Gene Regulatory Network Analysis
- Domain Adaptation and Few-Shot Learning
- Rough Sets and Fuzzy Logic
- Expert finding and Q&A systems
- Soil, Finite Element Methods
- Vibration and Dynamic Analysis
Stanford University
2019-2025
Ollscoil na Gaillimhe – University of Galway
1993-2024
Applied Mathematics (United States)
2018
Second Affiliated Hospital of Guangzhou Medical University
2016-2017
Guangzhou Medical University
2016-2017
Royal Holloway University of London
2008-2014
University of Milan
2014
Chinese University of Hong Kong
2005-2008
Tianjin University
1982-1997
Data sparsity, scalability and prediction quality have been recognized as the three most crucial challenges that every collaborative filtering algorithm or recommender system confronts. Many existing approaches to systems can neither handle very large datasets nor easily deal with users who made few ratings even none at all. Moreover, traditional assume all are independent identically distributed; this assumption ignores social interactions connections among users. In view of exponential...
Automated annotation of protein function is challenging. As the number sequenced genomes rapidly grows, overwhelming majority products can only be annotated computationally. If computational predictions are to relied upon, it crucial that accuracy these methods high. Here we report results from first large-scale community-based critical assessment (CAFA) experiment. Fifty-four representing state art for prediction were evaluated on a target set 866 proteins 11 organisms. Two findings stand...
Cellular processes often depend on stable physical associations between proteins. Despite recent progress, knowledge of the composition human protein complexes remains limited. To close this gap, we applied an integrative global proteomic profiling approach, based chromatographic separation cultured cell extracts into more than one thousand biochemical fractions that were subsequently analyzed by quantitative tandem mass spectrometry, to systematically identify a network 13,993...
A major bottleneck in our understanding of the molecular underpinnings life is assignment function to proteins. While experiments provide most reliable annotation proteins, their relatively low throughput and restricted purview have led an increasing role for computational prediction. However, assessing methods protein prediction tracking progress field remain challenging.We conducted second critical assessment functional (CAFA), a timed challenge assess that automatically assign function....
Abstract Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation protein function. Results Here, we report on results third CAFA challenge, CAFA3, that featured expanded analysis over previous rounds, both in terms volume data analyzed types performed. In a novel major new development, predictions assessment goals drove some experimental assays, resulting functional annotations for...
We report on the design and performance of BICEP3 instrument its first three-year data set collected from 2016 to 2018. is a 52cm aperture, refracting telescope designed observe polarization cosmic microwave background (CMB) degree angular scales at 95GHz. It started science observation South Pole in with 2400 antenna-coupled transition-edge sensor (TES) bolometers. The receiver demonstrated new technologies such as large-diameter alumina optics, Zotefoam infrared filters, flux-activated...
For a given query raised by specific user, the Query Suggestion technique aims to recommend relevant queries which potentially suit information needs of that user. Due complexity Web structure and ambiguity users' inputs, most suggestion algorithms suffer from problem poor recommendation accuracy. In this paper, aiming at providing semantically for users, we develop novel, effective efficient two-level model mining clickthrough data, in form two bipartite graphs (user-query query-URL graphs)...
Abstract Motivation: Several measures have been recently proposed for quantifying the functional similarity between gene products according to well-structured controlled vocabularies where biological terms are organized in a tree or directed acyclic graph (DAG) structure. However, existing semantic ignore two important facts. First, when calculating terms, they disregard descendants of these terms. While this makes no difference ontology is tree, we shall show that it has consequences...
While the PageRank algorithm has proven to be very effective for ranking Web pages, rank scores of pages can manipulated. To handle manipulation problem and cast a new insight on structure, we propose called DiffusionRank. DiffusionRank is motivated by heat diffusion phenomena, which connected because activities flow imagined as flow, link from page another treated pipe an air-conditioner, embody structure underlying graph. Theoretically show that serve generalization when co-efficient γ...
Computational approaches for drug repurposing viral diseases have mainly focused on a small number of antivirals that directly target pathogens (virus centric therapies). In this work, we combine ideas from collaborative filtering and network medicine making predictions much larger set drugs could be repurposed host therapies, are aimed at interfering with cell factors required by pathogen. Our idea is to create matrices quantifying the perturbation viruses induce human protein interaction...
We present GOssTo, the Gene Ontology semantic similarity Tool, a user-friendly software system for calculating similarities between gene products according to Ontology. GOssTo is bundled with six measures, including both term- and graph-based has extension capabilities allow user add new similarities. Importantly, any measure, can also calculate Random Walk Contribution that been shown greatly improve accuracy of measures. very fast, easy use, it allows calculation on genomic scale in few...
Abstract The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation protein function. Here we report on results third CAFA challenge, CAFA3, that featured expanded analysis over previous rounds, both in terms volume data analyzed types performed. In a novel major new development, predictions assessment goals drove some experimental assays, resulting functional annotations for more than 1000...
Identifying the unintended effects of drugs (side effects) is a very important issue in pharmacological studies. The laboratory verification associations between and side requires costly, time-intensive research. Thus, an approach to predicting drug based on known effects, using computational model, highly desirable. To provide such we used openly available data resources model as bipartite graph. drug-drug network constructed word2vec where edges represent semantic similarity them. We...
In real-world machine learning applications, unlabeled training data are readily available, but labeled expensive and hard to obtain. Therefore, semi-supervised algorithms have gathered much attention. Previous studies in this area mainly focused on a classification problem, whereas regression has received less paper, we proposed novel algorithm using heat diffusion with boundary-condition that guarantees closed-form solution. Experiments from artificial real datasets business, biomedical,...
Abstract Motivation Post-market unexpected Adverse Drug Reactions (ADRs) are associated with significant costs, in both financial burden and human health. Due to the high cost time required run clinical trials, there is interest accurate computational methods that can aid prediction of ADRs for new drugs. As a machine learning task, ADR made more challenging due degree class imbalance existing do not successfully balance requirement detect minority cases (true positives ADR), as measured by...
Determining the association between tumor sample and gene is demanding because it requires a high cost for conducting genetic experiments. Thus, discovered further clinical verification validation. This entire mechanism time-consuming expensive. Due to this issue, predicting samples genes remain challenge in biomedicine.Here we present, computational model based on heat diffusion algorithm which can predict genes. We proposed 2-layered graph. In first layer, constructed graph of where these...
Abstract Design for assembly (DFA) is an important part of the concurrent engineering strategy reduction product manufacturing costs and lead times. In this paper principles DFA are outlined role features (especially feature-based design) in described. An architecture integrated DFA/CAPP system described, based on ongoing work BRITE project no. 4661 (DEFMAT) Hua Yang process planning.
Nonnegative Matrix Factorization (NMF) has proved to be an effective method for unsupervised clustering analysis of gene expression data. By the nonnegativity constraint, NMF provides a decomposition data matrix into two matrices that have been used analysis. However, is not unique. This allows different results obtained, resulting in interpretations decomposition. To alleviate this problem, some existing methods directly enforce uniqueness extent by adding regularization terms objective...