Identifying neuropsychiatric disorders using unsupervised clustering methods: Data and code.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhao X
PROVIDER: S-EPMC6321965 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundIn microbiome data analysis, unsupervised clustering is often used to identify naturally occurring clusters, which can then be assessed for associations with characteristics of interest. In this work, we systematically compared beta diversity and clustering methods commonly used in microbiome analyses. We applied these to four published datasets where highly distinct microbiome profiles could be seen between sample groups, as well a clinical dataset with less clear separation between groups.ResultsAlthough no single method outperformed the others consistently, we did identify the key scenarios where certain methods can underperform. Specifically, the Bray Curtis (BC) metric resulted in poor clustering in a dataset where high-abundance OTUs were relatively rare. In contrast, the unweighted UniFrac (UU) metric clustered poorly on dataset with a high prevalence of low-abundance OTUs. To explore these hypotheses about BC and UU, we systematically modified the properties of the poorly performing datasets and found that this approach resulted in improved BC and UU performance. Based on these observations, we rationally combined BC and UU to generate a novel metric. We tested its performance while varying the relative contributions of each metric and also compared it with another combined metric, the generalized UniFrac distance. The proposed metric showed high performance across all datasets.ConclusionsOur systematic evaluation of clustering performance in these five datasets demonstrates that there is no existing clustering method that universally performs best across all datasets. We propose a combined metric of BC and UU that capitalizes on the complementary strengths of the two metrics. Video abstract.
| S-EPMC8817542 | biostudies-literature
Project description:BackgroundFraud, Waste, and Abuse (FWA) in medical claims have a negative impact on the quality and cost of healthcare. A major component of FWA in claims is procedure code overutilization, where one or more prescribed procedures may not be relevant to a given diagnosis and patient profile, resulting in unnecessary and unwarranted treatments and medical payments. This study aims to identify such unwarranted procedures from millions of healthcare claims. In the absence of labeled examples of unwarranted procedures, the study focused on the application of unsupervised machine learning techniques.MethodsExperiments were conducted with deep autoencoders to find claims containing anomalous procedure codes indicative of FWA, and were compared against a baseline density-based clustering model. Diagnoses, procedures, and demographic data associated with healthcare claims were used as features for the models. A dataset of one hundred thousand claims sampled from a larger claims database is used to initially train and tune the models, followed by experimentations on a dataset with thirty-three million claims. Experimental results show that the autoencoder model, when trained with a novel feature-weighted loss function, outperforms the density-based clustering approach in finding potential outlier procedure codes.ResultsGiven the unsupervised nature of our experiments, model performance was evaluated using a synthetic outlier test dataset, and a manually annotated outlier test dataset. Precision, recall and F1-scores on the synthetic outlier test dataset for the autoencoder model trained on one hundred thousand claims were 0.87, 1.0 and 0.93, respectively, while the results for these metrics on the manually annotated outlier test dataset were 0.36, 0.86 and 0.51, respectively. The model performance on the manually annotated outlier test dataset improved further when trained on the larger thirty-three million claims dataset with precision, recall and F1-scores of 0.48, 0.90 and 0.63, respectively.ConclusionsThis study demonstrates the feasibility of leveraging unsupervised, deep-learning methods to identify potential procedure overutilization from healthcare claims.
| S-EPMC10536726 | biostudies-literature
Project description:Multiple sclerosis (MS) can be divided into four phenotypes based on clinical evolution. The pathophysiological boundaries of these phenotypes are unclear, limiting treatment stratification. Machine learning can identify groups with similar features using multidimensional data. Here, to classify MS subtypes based on pathological features, we apply unsupervised machine learning to brain MRI scans acquired in previously published studies. We use a training dataset from 6322 MS patients to define MRI-based subtypes and an independent cohort of 3068 patients for validation. Based on the earliest abnormalities, we define MS subtypes as cortex-led, normal-appearing white matter-led, and lesion-led. People with the lesion-led subtype have the highest risk of confirmed disability progression (CDP) and the highest relapse rate. People with the lesion-led MS subtype show positive treatment response in selected clinical trials. Our findings suggest that MRI-based subtypes predict MS disability progression and response to treatment and may be used to define groups of patients in interventional trials.
| S-EPMC8024377 | biostudies-literature
Project description:We present a systematic approach for the identification of statistically relevant conformational macrostates of organic molecules from molecular dynamics trajectories. The approach applies to molecules characterized by an arbitrary number of torsional degrees of freedom and enables the transferability of the macrostates definition across different environments. We formulate a dissimilarity measure between molecular configurations that incorporates information on the characteristic energetic cost associated with transitions along all relevant torsional degrees of freedom. Such metric is employed to perform unsupervised clustering of molecular configurations based on the Fast Search and Find of Density Peaks algorithm. We apply this method to investigate the equilibrium conformational ensemble of Sildenafil, a conformationally complex pharmaceutical compound, in different environments including the crystal bulk, the gas phase, and three different solvents (acetonitrile, 1-butanol, and toluene). We demonstrate that while Sildenafil can adopt more than 100 metastable conformational configurations, only 12 are significantly populated across all of the environments investigated. Despite the complexity of the conformational space, we find that the most abundant conformers in solution are the closest to the conformers found in the most common Sildenafil crystal phase.
| S-EPMC8278389 | biostudies-literature
Project description:The widespread adoption of online courses opens opportunities for analysing learner behaviour and optimising web-based learning adapted to observed usage. Here, we introduce a mathematical framework for the analysis of time-series of online learner engagement, which allows the identification of clusters of learners with similar online temporal behaviour directly from the raw data without prescribing a priori subjective reference behaviours. The method uses a dynamic time warping kernel to create a pair-wise similarity between time-series of learner actions, and combines it with an unsupervised multiscale graph clustering algorithm to identify groups of learners with similar temporal behaviour. To showcase our approach, we analyse task completion data from a cohort of learners taking an online post-graduate degree at Imperial Business School. Our analysis reveals clusters of learners with statistically distinct patterns of engagement, from distributed to massed learning, with different levels of regularity, adherence to pre-planned course structure and task completion. The approach also reveals outlier learners with highly sporadic behaviour. A posteriori comparison against student performance shows that, whereas high-performing learners are spread across clusters with diverse temporal engagement, low performers are located significantly in the massed learning cluster, and our unsupervised clustering identifies low performers more accurately than common machine learning classification methods trained on temporal statistics of the data. Finally, we test the applicability of the method by analysing two additional data sets: a different cohort of the same course, and time-series of different format from another university.
| S-EPMC6722089 | biostudies-literature
Project description:Exome sequencing in diabetes presents a diagnostic challenge because depending on frequency, functional impact, and genomic and environmental contexts, HNF1A variants can cause maturity-onset diabetes of the young (MODY), increase type 2 diabetes risk, or be benign. A correct diagnosis matters as it informs on treatment, progression, and family risk. We describe a multi-dimensional functional dataset of 73 HNF1A missense variants identified in exomes of 12,940 individuals. Our aim was to develop an analytical framework for stratifying variants along the HNF1A phenotypic continuum to facilitate diagnostic interpretation. HNF1A variant function was determined by four different molecular assays. Structure of the multi-dimensional dataset was explored using principal component analysis, k-means, and hierarchical clustering. Weights for tissue-specific isoform expression and functional domain were integrated. Functionally annotated variant subgroups were used to re-evaluate genetic diagnoses in national MODY diagnostic registries. HNF1A variants demonstrated a range of behaviors across the assays. The structure of the multi-parametric data was shaped primarily by transactivation. Using unsupervised learning methods, we obtained high-resolution functional clusters of the variants that separated known causal MODY variants from benign and type 2 diabetes risk variants and led to reclassification of 4% and 9% of HNF1A variants identified in the UK and Norway MODY diagnostic registries, respectively. Our proof-of-principle analyses facilitated informative stratification of HNF1A variants along the continuum, allowing improved evaluation of clinical significance, management, and precision medicine in diabetes clinics. Transcriptional activity appears a superior readout supporting pursuit of transactivation-centric experimental designs for high-throughput functional screens.
| S-EPMC7536579 | biostudies-literature
Project description:The rapid emergence of novel psychoactive substances (NPS) poses new challenges and requirements for forensic testing/analysis techniques. This paper aims to explore the application of unsupervised clustering of NPS compounds' infrared spectra. Two statistical measures, Pearson and Spearman, were used to quantify the spectral similarity and to generate similarity matrices for hierarchical clustering. The correspondence of spectral similarity clustering trees to the commonly used structural/pharmacological categorization was evaluated and compared to the clustering generated using 2D/3D molecular fingerprints. Hybrid model feature selections were applied using different filter-based feature ranking algorithms developed for unsupervised clustering tasks. Since Spearman tends to overestimate the spectral similarity based on the overall pattern of the full spectrum, the clustering result shows the highest degree of improvement from having the nondiscriminative features removed. The loading plots of the first two principal components of the optimal feature subsets confirmed that the most important vibrational bands contributing to the clustering of NPS compounds were selected using non-negative discriminative feature selection (NDFS) algorithms.
| S-EPMC8638022 | biostudies-literature
Project description:BackgroundSearching for similarities in a set of biological data is intrinsically difficult due to possible data points that should not be clustered, or that should group within several clusters. Under these hypotheses, hierarchical agglomerative clustering is not appropriate. Moreover, if the dataset is not known enough, like often is the case, supervised classification is not appropriate either.ResultsCLAG (for CLusters AGgregation) is an unsupervised non hierarchical clustering algorithm designed to cluster a large variety of biological data and to provide a clustered matrix and numerical values indicating cluster strength. CLAG clusterizes correlation matrices for residues in protein families, gene-expression and miRNA data related to various cancer types, sets of species described by multidimensional vectors of characters, binary matrices. It does not ask to all data points to cluster and it converges yielding the same result at each run. Its simplicity and speed allows it to run on reasonably large datasets.ConclusionsCLAG can be used to investigate the cluster structure present in biological datasets and to identify its underlying graph. It showed to be more informative and accurate than several known clustering methods, as hierarchical agglomerative clustering, k-means, fuzzy c-means, model-based clustering, affinity propagation clustering, and not to suffer of the convergence problem proper to this latter.
| S-EPMC3519615 | biostudies-literature
Project description:Deep neural networks (DNN) have shown their success through computer vision tasks such as object detection, classification, and segmentation of image data including clinical and biological data. However, supervised DNNs require a large volume of labeled data to train and great effort to tune hyperparameters. The goal of this study is to segment cardiac images in movie data into objects of interest and a noisy background. This task is one of the essential tasks before statistical analysis of the images. Otherwise, the statistical values such as means, medians, and standard deviations can be erroneous. In this study, we show that the combination of unsupervised and supervised machine learning can automatize this process and find objects of interest accurately. We used the fact that typical clinical/biological data contain only limited kinds of objects. We solve this problem at the pixel level. For example, if there is only one object in an image, there are two types of pixels: object pixels and background pixels. We can expect object pixels and background pixels are quite different and they can be grouped using unsupervised clustering methods. In this study, we used the k-means clustering method. After finding object pixels and background pixels using unsupervised clustering methods, we used these pixels as training data for supervised learning. In this study, we used logistic regression and support vector machine. The combination of the unsupervised method and the supervised method can find objects of interest and segment images accurately without predefined thresholds or manually labeled data.
| S-EPMC9019745 | biostudies-literature
Project description:BackgroundThe high diversity and complexity of the microbial community make it a formidable challenge to identify and quantify the large number of proteins expressed in the community. Conventional metaproteomics approaches largely rely on accurate identification of the MS/MS spectra to their corresponding short peptides in the digested samples, followed by protein inference and subsequent taxonomic and functional analysis of the detected proteins. These approaches are dependent on the availability of protein sequence databases derived either from sample-specific metagenomic data or from public repositories. Due to the incompleteness and imperfections of these protein sequence databases, and the preponderance of homologous proteins expressed by different bacterial species in the community, this computational process of peptide identification and protein inference is challenging and error-prone, which hinders the comparison of metaproteomes across multiple samples.ResultsWe developed metaSpectraST, an unsupervised and database-independent metaproteomics workflow, which quantitatively profiles and compares metaproteomics samples by clustering experimentally observed MS/MS spectra based on their spectral similarity. We applied metaSpectraST to fecal samples collected from littermates of two different mother mice right after weaning. Quantitative proteome profiles of the microbial communities of different mice were obtained without any peptide-spectrum identification and used to evaluate the overall similarity between samples and highlight any differentiating markers. Compared to the conventional database-dependent metaproteomics analysis, metaSpectraST is more successful in classifying the samples and detecting the subtle microbiome changes of mouse gut microbiomes post-weaning. metaSpectraST could also be used as a tool to select the suitable biological replicates from samples with wide inter-individual variation.ConclusionsmetaSpectraST enables rapid profiling of metaproteomic samples quantitatively, without the need for constructing the protein sequence database or identification of the MS/MS spectra. It maximally preserves information contained in the experimental MS/MS spectra by clustering all of them first and thus is able to better profile the complex microbial communities and highlight their functional changes, as compared with conventional approaches. tag the videobyte in this section as ESM4 Video Abstract.
| S-EPMC10405559 | biostudies-literature