Filters








53,633 Hits in 6.9 sec

Integrative High Dimensional Multiple Testing with Heterogeneity under Data Sharing Constraints [article]

Molei Liu, Yin Xia, Kelly Cho, Tianxi Cai
2020 arXiv   pre-print
The challenge is even more pronounced with additional data sharing constraints under which only summary data but not individual level data can be shared across different sites.  ...  However, integrative analysis of high dimensional data from multiple studies is challenging in the presence of between study heterogeneity.  ...  In addition to high dimensionality, attentions to both heterogeneity and data sharing constraints are needed to perform meta-analysis of multiple electronic health records linked genomic studies.  ... 
arXiv:2004.00816v3 fatcat:dx25d32bj5cmll6spnlc6xojze

Optimisation of System Throughput Exploiting Tasks Heterogeneity on Space Shared FPGAs

Umar Ibrahim Minhas, Roger Woods, Georgios Karakonstantis
2019 2019 International Conference on Field-Programmable Technology (ICFPT)  
Furthermore, SPM facilitates creation of bitstreams from a high-level, OpenCL, easy adaptation by programmers and flexible integration in software based heterogeneous data centres.  ...  PRR vs SPM Due to the size of the device under test (DUT) and area available for PRRs, the space sharing is limited to a cluster of 2 tasks. For SPM, up to 3 tasks can be fit at one time.  ... 
doi:10.1109/icfpt47387.2019.00067 dblp:conf/icfpt/MinhasWK19 fatcat:vvp4owmm45behfs6kemodzekce

A Network Integration Approach for Drug-Target Interaction Prediction and Computational Drug Repositioning from Heterogeneous Information [article]

Yunan Luo, Xinbin Zhao, Jingtian Zhou, Jinglin Yang, Yanqing Zhang, Wenhua Kuang, Jian Peng, Ligong Chen, Jianyang Zeng
2017 bioRxiv   pre-print
In this work, we integrate diverse drug-related information, including drugs, proteins, diseases and side-effects, together with their interactions, associations or similarities, to construct a heterogeneous  ...  Systematic integration of these heterogeneous data not only serves as a promising tool for identifying new drug-target interactions (DTIs), which is an important step in drug development, but also provides  ...  Integration of heterogeneous network information. The above dimensionality reduction framework can be naturally extended to integrate multiple network data from heterogeneous sources.  ... 
doi:10.1101/100305 fatcat:3b4r33zftndq3ek7rjyoagakja

Individual Data Protected Integrative Regression Analysis of High-dimensional Heterogeneous Data [article]

Tianxi Cai, Molei Liu, Yin Xia
2020 arXiv   pre-print
Integrative analysis of multiple heterogeneous studies is, however, highly challenging in the ultra high dimensional setting.  ...  Under sparse regression models that are assumed to be similar yet not identical across studies, we propose in this paper a novel integrative estimation procedure for data-Shielding High-dimensional Integrative  ...  In addition to high dimensional features, EHR data analysis encounters privacy constraints in that individual-level data typically cannot be shared across local hospital sites, which makes the challenge  ... 
arXiv:1902.06115v3 fatcat:bynmldmfyrbsnatzccjijzabq4

Cell scale host-pathogen modeling: another branch in the evolution of constraint-based methods

Neema Jamshidi, Anu Raghunathan
2015 Frontiers in Microbiology  
Constraint-based models have become popular methods for systems biology as they enable the integration of complex, disparate datasets in a biologically cohesive framework that also supports the description  ...  Virchow, a nineteenth century co-founder of pathology is credited with describing pathology as "physiology with obstacles" and specifying a "diseased state" as a quantitative deviation from normal function  ...  The heterogeneity of omic data (biological constraints) and their integration is represented in parallel with the phenotypic solution space of the high dimensional host-pathogen model derived from physicochemical  ... 
doi:10.3389/fmicb.2015.01032 pmid:26500611 pmcid:PMC4594423 fatcat:gvmvprvaijffplzoehyku7fwnq

Physically-aware HW-SW partitioning for reconfigurable architectures with partial dynamic reconfiguration

Sudarshan Banerjee, Elaheh Bozorgzadeh, Nikil Dutt
2005 Proceedings of the 42nd annual conference on Design automation - DAC '05  
We demonstrate that our heuristic generates high-quality schedules by comparing the results with the exact formulation for small tests and a popular, but placementuanaware scheduling heuristic for larger  ...  We present a physically aware hardware-software (HW-SW) scheme for minimizing application execution time under HW resource constraints, where the HW is a reconfigurable architecture with partial dynamic  ...  As an example, we consider post-routing timing data obtained from synthesizing a 2-dimensional DCT (discrete cosine transform) under columnar placement and routing constraints on the Virtex-II chip XC2V2000  ... 
doi:10.1145/1065579.1065667 dblp:conf/dac/BanerjeeBD05 fatcat:vuj6elaqjfhrzmimg24cjq4yya

Targeting Underrepresented Populations in Precision Medicine: A Federated Transfer Learning Approach [article]

Sai Li, Tianxi Cai, Rui Duan
2021 arXiv   pre-print
In this paper, we propose a two-way data integration strategy that integrates heterogeneous data from diverse populations and from multiple healthcare institutions via a federated transfer learning approach  ...  With only a small number of communications across participating sites, the proposed method can achieve performance comparable to the pooled analysis where individual-level data are directly pooled together  ...  On the other hand, under data sharing constraints, most federated learning methods focus on settings where the true models are the same across studies.  ... 
arXiv:2108.12112v1 fatcat:qyiu23zltrgazfkvppobbeeqvu

A multi-network integration approach for measuring disease similarity based on ncRNA regulation and heterogeneous information

Ningyi Zhang, Tianyi Zang
2022 BMC Bioinformatics  
Encoder (AE) and improved AE model is proposed to extract constraints and low-dimensional feature representations.  ...  Results In this article, we proposed a novel method, ImpAESim, a framework integrating multiple networks embedding to learn compact feature representations and disease similarity calculation.  ...  data sources (e.g., disease-gene associations, lncRNA-gene associations, miRNA-gene associations) but also copes with the noisy and high-dimensional nature of large-scale biological data by utilizing  ... 
doi:10.1186/s12859-022-04613-1 pmid:35255810 pmcid:PMC8902705 fatcat:a4f2knjwrfakngmhcfb5nml3ki

Learning from Data Heterogeneity: Algorithms and Applications

Jingrui He
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
In this paper, along with multiple real applications, we will briefly review state-of-the-art techniques for learning from data heterogeneity, and demonstrate their performance at addressing these real  ...  It refers to any inhomogeneity in the data, and can be present in a variety of forms, corresponding to different types of data heterogeneity, such as task/view/instance/oracle heterogeneity.  ...  Acknowledgments This work is supported by National Science Foundation under Grant No. IIS-1552654, ONR under Grant No. N00014-15-1-2821, and an IBM Faculty Award.  ... 
doi:10.24963/ijcai.2017/735 dblp:conf/ijcai/He17 fatcat:zx4vxacv45e6pn66hsnzwb4p7u

Multi-view Subspace Clustering Analysis for Aggregating Multiple Heterogeneous Omics Data

Qianqian Shi, Bing Hu, Tao Zeng, Chuanchao Zhang
2019 Frontiers in Genetics  
data types, thereby comprehensively capturing the underlying heterogeneity of samples.  ...  The combinations of molecules responsible for different phenotypes form multiple embedded (expression) subspaces, thus identifying the intrinsic data structure is challenging by regular integration methods  ...  But the pair-wise clustering-based methods, i.e., SNF and ANF, obviously can't recognize the multiple manifolds embedded in high-dimensional space.  ... 
doi:10.3389/fgene.2019.00744 pmid:31497031 pmcid:PMC6712585 fatcat:3npxnejrsvf6hb4f3jxwx2slyy

Learning Clinical Outcomes from Heterogeneous Genomic Data Sources [article]

Safoora Yousefi, Amirreza Shaban, Mohamed Amgad, Ramraj Chandradevan, Lee A. D. Cooper
2019 arXiv   pre-print
one to combine multiple cohorts and outcomes in training.  ...  In this paper, we show that neural networks can be trained to predict clinical outcomes using heterogeneous genomic data sources via multi-task learning and adversarial representation learning, allowing  ...  Heterogeneity of available genomic datasets due to technical and sample biases poses challenges to integrating multiple data sources.  ... 
arXiv:1904.01637v1 fatcat:hev2iy3zafdejgarzvhhqlmgfe

Shingle 2.0 manual

Adam Candy
2017 Figshare  
This test problem BRML description contains the following comment: A monochromatic raster image with the word 'Shingle' and five small islands developed as a mask.  ...  Image of output spatial discretisation automatically generated by the Shingle verification test engine.  ...  Readers here can import more complex heterogeneous data, including GIS projects with multiple layers containing a wide range of data types, for example.  ... 
doi:10.6084/m9.figshare.5659378.v1 fatcat:pydaoko62baivd4aygkd3sk56q

Integration and transfer learning of single-cell transcriptomes via cFIT

Minshi Peng, Yue Li, Brie Wamsley, Yuting Wei, Kathryn Roeder
2021 Proceedings of the National Academy of Sciences of the United States of America  
The model parameters are learned under an iterative nonnegative matrix factorization (NMF) framework and then used for synchronized integration from across-domain assays.  ...  In addition, the model enables transferring via low-rank matrix from more informative data to allow for precise identification in data of lower quality.  ...  We model the scRNA-seq data via a high-dimensional linear model with a latent low-dimensional structure.  ... 
doi:10.1073/pnas.2024383118 pmid:33658382 fatcat:d5habjbhtjhqznh3rnrdn4vz4m

Shingle 2.0: generalising self-consistent and automated domain discretisation for multi-scale geophysical models [article]

Adam S. Candy, Julie D. Pietrzak
2017 arXiv   pre-print
This additionally provides a method to accurately record these constraints, using high-level natural language based abstractions, that enables full accounts of provenance, sharing and distribution.  ...  It introduces a generalised, extensible, self-documenting approach to carefully describe, and necessarily fully, the constraints over the heterogeneous parameter space that determine how a domain is spatially  ...  Readers here can import more complex heterogeneous data, including GIS projects with multiple layers containing a wide range of data types, for example.  ... 
arXiv:1703.08504v1 fatcat:zlejf27jqvayhpabullyms5fje

Physically-aware HW-SW partitioning for reconfigurable architectures with partial dynamic reconfiguration

S. Banerjee, E. Bozorgzadeh, N. Dutt
2005 Proceedings. 42nd Design Automation Conference, 2005.  
We demonstrate that our heuristic generates high-quality schedules by comparing the results with the exact formulation for small tests and a popular, but placementuanaware scheduling heuristic for larger  ...  We present a physically aware hardware-software (HW-SW) scheme for minimizing application execution time under HW resource constraints, where the HW is a reconfigurable architecture with partial dynamic  ...  As an example, we consider post-routing timing data obtained from synthesizing a 2-dimensional DCT (discrete cosine transform) under columnar placement and routing constraints on the Virtex-II chip XC2V2000  ... 
doi:10.1109/dac.2005.193828 fatcat:hqgzewiyxzh6nf45msj63sp64e
« Previous Showing results 1 — 15 out of 53,633 results