Consensus clustering for Bayesian mixture models

BACKGROUND

Cluster analysis is an integral part of precision medicine and systems biology, used to define groups of patients or biomolecules. Consensus clustering is an ensemble approach that is widely used in these areas, which combines the output from multiple runs of a non-deterministic clustering algorithm. Here we consider the application of consensus clustering to a broad class of heuristic clustering algorithms that can be derived from Bayesian mixture models (and extensions thereof) by adopting an early stopping criterion when performing sampling-based inference for these models. While the resulting approach is non-Bayesian, it inherits the usual benefits of consensus clustering, particularly in terms of computational scalability and providing assessments of clustering stability/robustness.

RESULTS

In simulation studies, we show that our approach can successfully uncover the target clustering structure, while also exploring different plausible clusterings of the data. We show that, when a parallel computation environment is available, our approach offers significant reductions in runtime compared to performing sampling-based Bayesian inference for the underlying model, while retaining many of the practical benefits of the Bayesian approach, such as exploring different numbers of clusters. We propose a heuristic to decide upon ensemble size and the early stopping criterion, and then apply consensus clustering to a clustering algorithm derived from a Bayesian integrative clustering method. We use the resulting approach to perform an integrative analysis of three 'omics datasets for budding yeast and find clusters of co-expressed genes with shared regulatory proteins. We validate these clusters using data external to the analysis.

CONCLUSTIONS

Our approach can be used as a wrapper for essentially any existing sampling-based Bayesian clustering implementation, and enables meaningful clustering analyses to be performed using such implementations, even when computational Bayesian inference is not feasible, e.g. due to poor exploration of the target density (often as a result of increasing numbers of features) or a limited computational budget that does not along sufficient samples to drawn from a single chain. This enables researchers to straightforwardly extend the applicability of existing software to much larger datasets, including implementations of sophisticated models such as those that jointly model multiple datasets.

Current trends in flow cytometry automated data analysis software

Automated flow cytometry (FC) data analysis tools for cell population identification and characterization are increasingly being used in academic, biotechnology, pharmaceutical, and clinical laboratories. The development of these computational methods is designed to overcome reproducibility and process bottleneck issues in manual gating, however, the take-up of these tools remains (anecdotally) low. Here, we performed a comprehensive literature survey of state-of-the-art computational tools typically published by research, clinical, and biomanufacturing laboratories for automated FC data analysis and identified popular tools based on literature citation counts. Dimensionality reduction methods ranked highly, such as generic t-distributed stochastic neighbor embedding (t-SNE) and its initial Matlab-based implementation for cytometry data viSNE. Software with graphical user interfaces also ranked highly, including PhenoGraph, SPADE1, FlowSOM, and Citrus, with unsupervised learning methods outnumbering supervised learning methods, and algorithm type popularity spread across K-Means, hierarchical, density-based, model-based, and other classes of clustering algorithms. Additionally, to illustrate the actual use typically within clinical spaces alongside frequent citations, a survey issued by UK NEQAS Leucocyte Immunophenotyping to identify software usage trends among clinical laboratories was completed. The survey revealed 53% of laboratories have not yet taken up automated cell population identification methods, though among those that have, Infinicyt software is the most frequently identified. Survey respondents considered data output quality to be the most important factor when using automated FC data analysis software, followed by software speed and level of technical support. This review found differences in software usage between biomedical institutions, with tools for discovery, data exploration, and visualization more popular in academia, whereas automated tools for specialized targeted analysis that apply supervised learning methods were more used in clinical settings.

Modeling neuroaffective biomarkers of drug addiction: A Bayesian nonparametric approach using dirichlet process mixtures

BACKGROUND

The properties of neurophysiological processes related to addiction have received much attention in the literature. However, empirical evidence of meaningful and useful characterization of these processes is limited. Recent studies have found that electrophysiological responses to emotional and drug-related cues can be used to create profiles that reliably predict smoking relapse.

NEW METHOD

This paper evaluates the validity of classifying electrophysiological responses into distinct profiles using a Bayesian dirichlet process mixture (DPM) model. The DPM is a Bayesian nonparametric (BNP) method to modeling unknown number of profiles characterized by uncertainty in cluster membership and in cluster number.

RESULTS

The DPM model confirmed previously identified neuroaffective reactivity profiles, but also revealed a finer level of granularity in the clustering. Specifically, in addition to the two clusters previously identified in the literature, the BNP methods identified a cluster of individuals showing similar responses to smoking, pleasant, neutral and unpleasant cues.

COMPARISON WITH EXISTING METHODS

BNP models provide an alternative to the k-mean clustering approach to modeling EEG-based neuroaffective profiles. Unlike k-means clustering, BNP models compute the probability that a subject belongs to a cluster while taking into consideration uncertainty in the number of clusters.

CONCLUSIONS

Our results confirm the reliability of the two clusters previously identified in these data, but also provide new insights by revealing a cluster that presented similar responses to stimuli with different contents. This finding may be related to the uncertainty in classification or overlapping brain-reactivity profiles.