A comparison of extrinsic clustering evaluation metrics based on formal constraints

Amigó, Enrique; Gonzalo, Julio; Artiles, Javier; Verdejo, Felisa

doi:10.1007/s10791-009-9106-z

Cited by 205 publications

(307 citation statements)

References 1 publication

Supporting

Mentioning

300

Contrasting

Unclassified

Order By: Relevance

“…We summarize the baseline levels of performance provided by these optimal classifications in Table 1 using three statistics: pairwise precision, pairwise recall, and pairwise F-measure (Amigó, Gonzalo, Artiles, & Verdejo, 2009). Pairwise refers to the fact that the statistics are constructed by examining every pair of data points and asking whether the two are in the same class (according to either the fitted model or the ideal model).…”

Section: Resultsmentioning

confidence: 99%

A Single‐Stage Approach to Learning Phonological Categories: Insights From Inuktitut

Dillon¹,

Dunbar

Idsardi

2012

Cognitive Science

View full text Add to dashboard Cite

To acquire one’s native phonological system, language-specific phonological categories and relationships must be extracted from the input. The acquisition of the categories and relationships have each in their own right been the focus of intense research. However, it is remarkable that research on the acquisition of categories and the relations between them have proceeded, for the most part, independent of one another. We argue that this has led to the implicit view that phonological acquisition is a ‘two-stage’ process: phonetic categories are first acquired, and then subsequently mapped onto abstract phoneme categories. We present simulations that suggest two problems with this view: first, the learner might mistake the phoneme-level categories for phonetic-level categories and thus be unable to learn the relationships between phonetic-level categories; on the other hand, the learner might construct inaccurate phonetic-level representations that prevent it from finding regular relations among them. We suggest an alternative conception of the phonological acquisition problem that sidesteps this apparent inevitability, and acquires phonemic categories in a single stage. Using acoustic data from Inuktitut, we show that this model reliably converges on a set of phoneme-level categories and phonetic-level relations among subcategories, without making use of a lexicon.

show abstract

Section: Resultsmentioning

confidence: 99%

A Single‐Stage Approach to Learning Phonological Categories: Insights From Inuktitut

Dillon¹,

Dunbar

Idsardi

2012

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Clonal genotypes were obtained by inferring the occurrence of the mutation on the branches of the clonal tree. The clustering accuracy of each method was measured using adjusted rand index and B-cubed F-score (Amigó et al, 2009) for datasets without and with doublets respectively. The genotyping performance was measured using Hamming distance (number of entries differing) between the true and inferred genotypes.…”

Section: Benchmarking On Simulated Datasetsmentioning

confidence: 99%

SiCloneFit: Bayesian inference of population structure, genotype,and phylogeny of tumor clones from single-cell genome sequencing data

Zafar

Navin

Chen

et al. 2018

Preprint

View full text Add to dashboard Cite

keywords intra-tumor heterogeneity, clonal phylogeny, single-cell sequencing, finite-site model of evolution, Bayesian inference 1 Abstract Accumulation and selection of somatic mutations in a Darwinian framework result in intra-tumor heterogeneity (ITH) that poses significant challenges to the diagnosis and clinical therapy of cancer. Identification of the tumor cell populations (clones) and reconstruction of their evolutionary relationship can elucidate this heterogeneity. Recently developed single-cell DNA sequencing (SCS) technologies promise to resolve ITH to a single-cell level. However, technical errors in SCS datasets, including false-positives (FP), false-negatives (FN) due to allelic dropout and cell doublets, significantly complicate these tasks. Here, we propose a non-parametric Bayesian method that reconstructs the clonal populations as clusters of single cells, genotypes of each clone and the evolutionary relationships between the clones. It employs a tree-structured Chinese restaurant process as the prior on the number and composition of clonal populations. The evolution of the clonal populations is modeled by a clonal phylogeny and a finite-site model of evolution to accountfor potential mutation recurrence and losses. We probabilistically account for FP and FN errors, and cell doublets are modeled by employing a Beta-binomial distribution. We develop a Gibbs sampling algorithm comprising of partial reversible-jump and partial Metropolis-Hastings updates to explore the joint posterior space of all parameters. The performance of our method on synthetic and experimental datasets suggests that joint reconstruction of tumor clones and clonal phylogeny under a finite-site model of evolution leads to more accurate inferences. Our method is the first to enable this joint reconstruction in a fully Bayesian framework, thus providing measures of support of the inferences it makes.

show abstract

“…Let a be the number of pairs of cells correctly partitioned into the same class by the clustering method; b be the number of pairs of cells partitioned into the same cluster but in fact belong to di erent classes; c be the number of pairs of cells partitioned into di erent clusters but belongs to the same class; and d be the number of pairs of cells correctly partitioned into di erent clusters. Then the Adjusted Rand Index [50], the Jaccard index [51], and the Fowlkes-Mallows index [52] can be de ned as + c) ; and the Purity [53] can be calculated as…”

Section: Evaluating the Stability Of Gene Listsmentioning

confidence: 99%

Evaluating stably expressed genes in single cells

Lin

Ghazanfar

Strbenac

et al. 2017

Preprint

View full text Add to dashboard Cite

Housekeeping genes are critical for understanding the core transcriptome and instrumental in data normalisation given their stable expression in different tissues and cells. Previous studies defined housekeeping genes using bulk transcriptome data. With recent advances in single-cell RNA-sequencing (scRNA-seq), it is now possible to identify steadily expressed genes across individual cells. Here we introduce the concept of housekeeping index and a framework for assessing housekeeping genes at the single-cell level using high-resolution scRNA-seq data. We apply our approach on two scRNA-seq datasets from early mammalian development and evaluate derived housekeeping genes on ten additional scRNA-seq datasets from diverse cell/tissue types.

show abstract

A comparison of extrinsic clustering evaluation metrics based on formal constraints

Cited by 205 publications

References 1 publication

A Single‐Stage Approach to Learning Phonological Categories: Insights From Inuktitut

A Single‐Stage Approach to Learning Phonological Categories: Insights From Inuktitut

SiCloneFit: Bayesian inference of population structure, genotype,and phylogeny of tumor clones from single-cell genome sequencing data

Evaluating stably expressed genes in single cells

Contact Info

Product

Resources

About