References of "Geurts, Pierre"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailCollaborative analysis of multi-gigapixel imaging data using Cytomine
Marée, Raphaël ULg; Rollus, Loïc; Stévens, Benjamin et al

in Bioinformatics (2016)

Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of ... [more ▼]

Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of multidisciplinary teams for large-scale image-based studies. It uses web development methodologies and machine learning in order to readily organize, explore, share, and analyze (semantically and quantitatively) multi-gigapixel imaging data over the internet. We illustrate how it has been used in several biomedical applications. Availability: Cytomine (http://www.cytomine.be/) is freely available under an open-source license from http://github.com/cytomine/. A documentation wiki (http://doc.cytomine.be) and a demo server (http://demo.cytomine.be) are also available. [less ▲]

Detailed reference viewed: 49 (13 ULg)
Full Text
Peer Reviewed
See detailTowards Generic Image Classification using Tree-based Learning: an Extensive Empirical Study
Marée, Raphaël ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

in Pattern Recognition Letters (2016)

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are ... [more ▼]

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are the extraction of random subwindows described by raw pixel intensity values and the use of ensemble of extremely randomized trees to directly classify images or to learn image features. The influence of method parameters and variants is thoroughly evaluated so as to provide baselines and guidelines for future studies. Detailed results are provided on 80 publicly available datasets that depict very diverse types of images (more than 3800 image classes and over 1.5 million images). [less ▲]

Detailed reference viewed: 160 (30 ULg)
Peer Reviewed
See detailCirculating microRNA-based screening tool for breast cancer
Freres, Pierre ULg; Wenric, Stéphane ULg; Boukerroucha, Meriem et al

in Oncotarget (2015)

Circulating microRNAs (miRNAs) are increasingly recognized as powerful biomarkers in several pathologies, including breast cancer. Here, their plasmatic levels were measured to be used as an alternative ... [more ▼]

Circulating microRNAs (miRNAs) are increasingly recognized as powerful biomarkers in several pathologies, including breast cancer. Here, their plasmatic levels were measured to be used as an alternative screening procedure to mammography for breast cancer diagnosis. A plasma miRNA profile was determined by RT-qPCR in a cohort of 378 women. A diagnostic model was designed based on the expression of 8 miRNAs measured first in a profiling cohort composed of 41 primary breast cancers and 45 controls, and further validated in diverse cohorts composed of 108 primary breast cancers, 88 controls, 35 breast cancers in remission, 31 metastatic breast cancers and 30 gynecologic tumors. A receiver operating characteristic curve derived from the 8-miRNA random forest based diagnostic tool exhibited an area under the curve of 0.81. The accuracy of the diagnostic tool remained unchanged considering age and tumor stage. The miRNA signature correctly identified patients with metastatic breast cancer. The use of the classification model on cohorts of patients with breast cancers in remission and with gynecologic cancers yielded prediction distributions similar to that of the control group. Using a multivariate supervised learning method and a set of 8 circulating miRNAs, we designed an accurate, minimally invasive screening tool for breast cancer. [less ▲]

Detailed reference viewed: 51 (15 ULg)
Full Text
Peer Reviewed
See detailRating Network Paths for Locality-Aware Overlay Construction and Routing
Du, Wei; Liao, Yongjun ULg; Tao, Narisu et al

in IEEE/ACM Transactions on Networking (2015), 23(5), 1661-1673

This paper investigates the rating of network paths, i.e. acquiring quantized measures of path properties such as round-trip time and available bandwidth. Comparing to finegrained measurements, coarse ... [more ▼]

This paper investigates the rating of network paths, i.e. acquiring quantized measures of path properties such as round-trip time and available bandwidth. Comparing to finegrained measurements, coarse-grained ratings are appealing in that they are not only informative but also cheap to obtain. Motivated by this insight, we firstly address the scalable acquisition of path ratings by statistical inference. By observing similarities to recommender systems, we examine the applicability of solutions to recommender system and show that our inference problem can be solved by a class of matrix factorization techniques. A technical contribution is an active and progressive inference framework that not only improves the accuracy by selectively measuring more informative paths but also speeds up the convergence for available bandwidth by incorporating its measurement methodology. Then, we investigate the usability of rating-based network measurement and inference in applications. A case study is performed on whether locality awareness can be achieved for overlay networks of Pastry and BitTorrent using inferred ratings. We show that such coarse-grained knowledge can improve the performance of peer selection and that finer granularities do not always lead to larger improvements. [less ▲]

Detailed reference viewed: 223 (17 ULg)
Full Text
Peer Reviewed
See detailCerebral functional connectivity periodically (de)synchronizes with anatomical constraints
Liegeois, Raphaël ULg; Ziegler, Erik; Bahri, Mohamed Ali ULg et al

in Brain Structure and Function (2015)

This paper studies the link between resting-state functional connectivity (FC), measured by the correlations of the fMRI BOLD time courses, and structural connectivity (SC), estimated through fiber ... [more ▼]

This paper studies the link between resting-state functional connectivity (FC), measured by the correlations of the fMRI BOLD time courses, and structural connectivity (SC), estimated through fiber tractography. Instead of a static analysis based on the correlation between SC and the FC averaged over the entire fMRI time series, we propose a dynamic analysis, based on the time evolution of the correlation between SC and a suitably windowed FC. Assessing the statistical significance of the time series against random phase permutations, our data show a pronounced peak of significance for time window widths around 20-30 TR (40-60 sec). Using the appropriate window width, we show that FC patterns oscillate between phases of high modularity, primarily shaped by anatomy, and phases of low modularity, primarily shaped by inter-network connectivity. Building upon recent results in dynamic FC, this emphasizes the potential role of SC as a transitory architecture between different highly connected resting state FC patterns. Finally, we show that networks implied in consciousness-related processes, such as the default mode network (DMN), contribute more to these brain-level fluctuations compared to other networks, such as the motor or somatosensory networks. This suggests that the fluctuations between FC and SC are capturing mind-wandering effects. [less ▲]

Detailed reference viewed: 75 (16 ULg)
Full Text
Peer Reviewed
See detailClassifying pairs with trees for supervised biological network inference
Schrynemackers, Marie ULg; Wehenkel, Louis ULg; Madan Babu, Mohan et al

in Molecular Biosystems (2015), 11(8), 2116-2125

Networks are ubiquitous in biology, and computational approaches have been largely investigated for their inference. In particular, supervised machine learning methods can be used to complete a partially ... [more ▼]

Networks are ubiquitous in biology, and computational approaches have been largely investigated for their inference. In particular, supervised machine learning methods can be used to complete a partially known network by integrating various measurements. Two main supervised frameworks have been proposed: the local approach, which trains a separate model for each network node, and the global approach, which trains a single model over pairs of nodes. Here, we systematically investigate, theoretically and empirically, the exploitation of tree-based ensemble methods in the context of these two approaches for biological network inference. We first formalize the problem of network inference as a classification of pairs, unifying in the process homogeneous and bipartite graphs and discussing two main sampling schemes. We then present the global and the local approaches, extending the latter for the prediction of interactions between two unseen network nodes, and discuss their specializations to tree-based ensemble methods, highlighting their interpretability and drawing links with clustering techniques. Extensive computational experiments are carried out with these methods on various biological networks that clearly highlight that these methods are competitive with existing methods. [less ▲]

Detailed reference viewed: 89 (27 ULg)
Full Text
Peer Reviewed
See detailPhenotype Classification of Zebrafish Embryos by Supervised Learning
Jeanray, Nathalie ULg; Marée, Raphaël ULg; Pruvot, Benoist et al

in PLoS ONE (2015), 10(1), 01169891-20

Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances ... [more ▼]

Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances on embryo survival and development are generally evaluated manually through microscopic observation by an expert and documented by several typical photographs. Here, we present a methodology to automatically classify brightfield images of wildtype zebrafish embryos according to their defects by using an image analysis approach based on supervised machine learning. We show that, compared to manual classification, automatic classification results in 90 to 100 % agreement with consensus voting of biological experts in nine out of eleven considered defects in 3 days old zebrafish larvae. Automation of the analysis and classification of zebrafish embryo pictures reduces the workload and time required for the biological expert and increases the reproducibility and objectivity of this classification. [less ▲]

Detailed reference viewed: 71 (20 ULg)
Full Text
Peer Reviewed
See detailErratum: Elevated basal levels of circulating activated platelets predict ICU-acquired sepsis and mortality: a prospective study.
Layios, N.; Delierneux, Céline ULg; Hego, A. et al

in Critical care (London, England) (2015), 19(1), 301

Detailed reference viewed: 22 (2 ULg)
Full Text
Peer Reviewed
See detailErratum: Prospective immune profiling in critically ill adults: before, during and after severe sepsis and septic shock.
Layios, N.; GOSSET, Christian ULg; Delierneux, Céline ULg et al

in Critical care (London, England) (2015), 19(1), 300

Detailed reference viewed: 14 (4 ULg)
Full Text
Peer Reviewed
See detailEvaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge
Ching Wei, Wang; Cheng-Ta, Huang; Meng-Che, Hsieh et al

in IEEE Transactions on Medical Imaging (2015)

Detailed reference viewed: 47 (4 ULg)
Full Text
Peer Reviewed
See detailA Membrane-Type-1 Matrix Metalloproteinase (MT1-MMP) - Discoidin Domain Receptor 1 Axis Regulates Collagen-Induced Apoptosis in Breast Cancer Cells.
Assent, Delphine; Bourgot, Isabelle ULg; Hennuy, Benoît ULg et al

in PloS one (2015), 10(3), 0116006

During tumour dissemination, invading breast carcinoma cells become confronted with a reactive stroma, a type I collagen-rich environment endowed with anti-proliferative and pro-apoptotic properties. To ... [more ▼]

During tumour dissemination, invading breast carcinoma cells become confronted with a reactive stroma, a type I collagen-rich environment endowed with anti-proliferative and pro-apoptotic properties. To develop metastatic capabilities, tumour cells must acquire the capacity to cope with this novel microenvironment. How cells interact with and respond to their microenvironment during cancer dissemination remains poorly understood. To address the impact of type I collagen on the fate of tumour cells, human breast carcinoma MCF-7 cells were cultured within three-dimensional type I collagen gels (3D COL1). Using this experimental model, we have previously demonstrated that membrane type-1 matrix metalloproteinase (MT1-MMP), a proteinase overexpressed in many aggressive tumours, promotes tumour progression by circumventing the collagen-induced up-regulation of BIK, a pro-apoptotic tumour suppressor, and hence apoptosis. Here we performed a transcriptomic analysis to decipher the molecular mechanisms regulating 3D COL1-induced apoptosis in human breast cancer cells. Control and MT1-MMP expressing MCF-7 cells were cultured on two-dimensional plastic plates or within 3D COL1 and a global transcriptional time-course analysis was performed. Shifting the cells from plastic plates to 3D COL1 activated a complex reprogramming of genes implicated in various biological processes. Bioinformatic analysis revealed a 3D COL1-mediated alteration of key cellular functions including apoptosis, cell proliferation, RNA processing and cytoskeleton remodelling. By using a panel of pharmacological inhibitors, we identified discoidin domain receptor 1 (DDR1), a receptor tyrosine kinase specifically activated by collagen, as the initiator of 3D COL1-induced apoptosis. Our data support the concept that MT1-MMP contributes to the inactivation of the DDR1-BIK signalling axis through the cleavage of collagen fibres and/or the alteration of DDR1 receptor signalling unit, without triggering a drastic remodelling of the transcriptome of MCF-7 cells. [less ▲]

Detailed reference viewed: 38 (5 ULg)
Full Text
See detailTowards generic image classification: an extensive empirical study
Marée, Raphaël ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

E-print/Working paper (2014)

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are ... [more ▼]

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are the extraction of random subwindows described by raw pixel intensity values and the use of ensemble of extremely randomized trees to directly classify images or to learn image features. The influence of method parameters and variants is thoroughly evaluated so as to provide baselines and guidelines for future studies. Detailed results are provided on 80 publicly available datasets that depict very diverse types of images (more than 3800 image classes and over 1.5 million images). [less ▲]

Detailed reference viewed: 143 (13 ULg)
Full Text
Peer Reviewed
See detailMapping Gene Regulatory Networks in Drosophila Eye Development by Large-Scale Transcriptome Perturbations and Motif Inference
Potier, Delphine; Davie, Kristofer; Hulselmans, Gert et al

in Cell Reports (2014), 9(6), 2290-2303

Genome control is operated by transcription factors (TFs) controlling their target genes by binding to promoters and enhancers. Conceptually, the interactions between TFs, their binding sites, and their ... [more ▼]

Genome control is operated by transcription factors (TFs) controlling their target genes by binding to promoters and enhancers. Conceptually, the interactions between TFs, their binding sites, and their functional targets are represented by gene regulatory networks (GRNs). Deciphering in vivo GRNs underlying organ development in an unbiased genome-wide setting involves identifying both functional TF-gene interactions and physical TF-DNA interactions. To reverse engineer the GRNs of eye development in Drosophila, we performed RNA-seq across 72 genetic perturbations and sorted cell types and inferred a coexpression network. Next, we derived direct TF-DNA interactions using computational motif inference, ultimately connecting 241 TFs to 5,632 direct target genes through 24,926 enhancers. Using this network, we found network motifs, cis-regulatory codes, and regulators of eye development. We validate the predicted target regions of Grainyhead by ChIP-seq and identify this factor as a general cofactor in the eye network, being bound to thousands of nucleosome-free regions. [less ▲]

Detailed reference viewed: 64 (14 ULg)
Full Text
Peer Reviewed
See detailRandom forests with random projections of the output space for high dimensional multi-label classification
Joly, Arnaud ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

in Machine Learning and Knowledge Discovery in Databases (2014, September 15)

We adapt the idea of random projections applied to the out- put space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can ... [more ▼]

We adapt the idea of random projections applied to the out- put space, so as to enhance tree-based ensemble methods in the context of multi-label classification. We show how learning time complexity can be reduced without affecting computational complexity and accuracy of predictions. We also show that random output space projections may be used in order to reach different bias-variance tradeoffs, over a broad panel of benchmark problems, and that this may lead to improved accuracy while reducing significantly the computational burden of the learning stage. [less ▲]

Detailed reference viewed: 254 (63 ULg)
Full Text
Peer Reviewed
See detailSimple connectome inference from partial correlation statistics in calcium imaging
Sutera, Antonio ULg; Joly, Arnaud ULg; François-Lavet, Vincent ULg et al

in Proceedings of Connectomics 2014 (ECML 2014) (2014, June)

In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to ... [more ▼]

In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation statistics. This paper summarises the methodology that led us to win the Connectomics Challenge, proposes a simplified version of our method, and finally compares our results with respect to other inference methods. [less ▲]

Detailed reference viewed: 626 (149 ULg)
Full Text
Peer Reviewed
See detailExploiting SNP Correlations within Random Forest for Genome-Wide Association Studies
Botta, Vincent ULg; Louppe, Gilles ULg; Geurts, Pierre ULg et al

in PLoS ONE (2014)

The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however ... [more ▼]

The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however, are usually based on univariate hypothesis tests and therefore can account neither for correlations due to linkage disequilibrium nor for combinations of several markers. To discover and leverage such potential multivariate interactions, we propose in this work an extension of the Random Forest algorithm tailored for structured GWAS data. In terms of risk prediction, we show empirically on several GWAS datasets that the proposed T-Trees method significantly outperforms both the original Random Forest algorithm and standard linear models, thereby suggesting the actual existence of multivariate non-linear effects due to the combinations of several SNPs. We also demonstrate that variable importances as derived from our method can help identify relevant loci. Finally, we highlight the strong impact that quality control procedures may have, both in terms of predictive power and loci identification. [less ▲]

Detailed reference viewed: 192 (15 ULg)