Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing

Llinares-López, Felipe; Sugiyama, Mahito; Papaxanthos, Laetitia; Borgwardt, Karsten

doi:10.1145/2783258.2783363

Cited by 55 publications

(51 citation statements)

References 38 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other methods: While our work focuses on deriving information theoretic FS criteria that capture high-order feature interactions, there are studies in the literature that provide answers from other perspectives. For example, there is a recent group of works for significance pattern mining (Terada et al 2013;Llinares-López et al 2015;Papaxanthos et al 2016): finding groups of items (i.e. features) that occur statistically significant more often in one class than in the other, and rigorously controlling the family-wise error rate (FWER).…”

Section: Background On Feature Selectionmentioning

confidence: 99%

Efficient feature selection using shrinkage estimators

et al. 2019

View full text Add to dashboard Cite

Information theoretic feature selection methods quantify the importance of each feature by estimating mutual information terms to capture: the relevancy, the redundancy and the complementarity. These terms are commonly estimated by maximum likelihood, while an under-explored area of research is how to use shrinkage methods instead. Our work suggests a novel shrinkage method for data-efficient estimation of information theoretic terms. The small sample behaviour makes it particularly suitable for estimation of discrete distributions with large number of categories (bins). Using our novel estimators we derive a framework for generating feature selection criteria that capture any high-order feature interaction for redundancy and complementarity. We perform a thorough empirical study across datasets from diverse sources and using various evaluation measures. Our first finding is that our shrinkage based methods achieve better results, while they keep the same computational cost as the simple maximum likelihood based methods. Furthermore, under our framework we derive efficient novel high-order criteria that outperform state-of-the-art methods in various tasks.

show abstract

Section: Background On Feature Selectionmentioning

confidence: 99%

Efficient feature selection using shrinkage estimators

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In our setting, and due to the fact that all possible regions are considered, the computational considerations make it extremely challenging to naively apply permutation testing. Nevertheless, combining with the approach proposed in Llinares-López et al (2015b ), which uses Tarone’s method as a way to speed-up permutation testing, would be an interesting topic for future work. Enhancing with permutation testing would also have additional benefits, such as taking into account the dependence between test statistics to obtain less stringent significance thresholds, thereby increasing statistical power.…”

Section: Discussionmentioning

confidence: 99%

“…Tarone’s trick has been recently applied to (i) itemset mining ( Terada et al , 2013 ; Minato et al , 2014 ; Llinares-López et al , 2015b ), (ii) subgraph mining ( Sugiyama et al , 2015 ), and (iii) to mine associated genomic regions with the previously mentioned algorithm ( Llinares-López et al , 2015a ). However, none of these methods were able to incorporate covariates to correct for confounding.…”

Section: Problem Statementmentioning

confidence: 99%

Genome-wide genetic heterogeneity discovery with categorical covariates

et al. 2017

Self Cite

View full text Add to dashboard Cite

MotivationGenetic heterogeneity is the phenomenon that distinct genetic variants may give rise to the same phenotype. The recently introduced algorithm Fast Automatic Interval Search () enables the genome-wide search of candidate regions for genetic heterogeneity in the form of any contiguous sequence of variants, and achieves high computational efficiency and statistical power. Although can test all possible genomic regions for association with a phenotype, a key limitation is its inability to correct for confounders such as gender or population structure, which may lead to numerous false-positive associations.ResultsWe propose , a method that overcomes this problem by properly accounting for categorical confounders, while still retaining statistical power and computational efficiency. Experiments comparing with and multiple kinds of burden tests on simulated data, as well as on human and Arabidopsis samples, demonstrate that can drastically reduce genomic inflation and discover associations that are missed by standard burden tests.Availability and ImplementationAn R package is available on CRAN and the source code can be found at: https://www.bsse.ethz.ch/mlcb/research/bioinformatics-and-computational-biology/fastcmh.htmlSupplementary information Supplementary data are available at Bioinformatics online.

show abstract

“…Especially in the life sciences, however, it is essential to determine whether a detected pattern is also statistically significant within a particular dataset or class. This is the basic premise of significant pattern mining (SPM) algorithms, which have already been successfully employed in itemset mining and subgraph mining tasks ( Llinares-López et al , 2015 ). Recent work by Papaxanthos et al (2016) demonstrated their applicability in genome-wide association mapping.…”

Section: Statistical Shapelet Miningmentioning

confidence: 99%

Association mapping in biomedical time series via statistically significant shapelet mining

et al. 2018

Self Cite

View full text Add to dashboard Cite

MotivationMost modern intensive care units record the physiological and vital signs of patients. These data can be used to extract signatures, commonly known as biomarkers, that help physicians understand the biological complexity of many syndromes. However, most biological biomarkers suffer from either poor predictive performance or weak explanatory power. Recent developments in time series classification focus on discovering shapelets, i.e. subsequences that are most predictive in terms of class membership. Shapelets have the advantage of combining a high predictive performance with an interpretable component—their shape. Currently, most shapelet discovery methods do not rely on statistical tests to verify the significance of individual shapelets. Therefore, identifying associations between the shapelets of physiological biomarkers and patients that exhibit certain phenotypes of interest enables the discovery and subsequent ranking of physiological signatures that are interpretable, statistically validated and accurate predictors of clinical endpoints.ResultsWe present a novel and scalable method for scanning time series and identifying discriminative patterns that are statistically significant. The significance of a shapelet is evaluated while considering the problem of multiple hypothesis testing and mitigating it by efficiently pruning untestable shapelet candidates with Tarone’s method. We demonstrate the utility of our method by discovering patterns in three of a patient’s vital signs: heart rate, respiratory rate and systolic blood pressure that are indicators of the severity of a future sepsis event, i.e. an inflammatory response to an infective agent that can lead to organ failure and death, if not treated in time.Availability and implementationWe make our method and the scripts that are required to reproduce the experiments publicly available at https://github.com/BorgwardtLab/S3M.Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing

Cited by 55 publications

References 38 publications

Efficient feature selection using shrinkage estimators

Efficient feature selection using shrinkage estimators

Genome-wide genetic heterogeneity discovery with categorical covariates

Association mapping in biomedical time series via statistically significant shapelet mining

Contact Info

Product

Resources

About