Multinomial Mixture Research Articles

Distinct lung microbiota associate with HIV-associated chronic lung disease in children

Chronic lung disease (CLD) is a common co-morbidity for HIV-positive children and adolescents on antiretroviral therapy (ART) in sub-Saharan Africa. In this population, distinct airway microbiota may differentially confer risk of CLD. In a cross-sectional study of 202 HIV-infected children aged 6–16 years in Harare, Zimbabwe, we determined the association of sputum microbiota composition (using 16S ribosomal RNA V4 gene region sequencing) with CLD defined using clinical, spirometric, or radiographic criteria. Forty-two percent of children were determined to have CLD according to our definition. Dirichlet multinomial mixtures identified four compositionally distinct sputum microbiota structures. Patients whose sputum microbiota was dominated by Haemophilus, Moraxella or Neisseria (HMN) were at 1.5 times higher risk of CLD than those with Streptococcus or Prevotella (SP)-dominated microbiota (RR = 1.48, p = 0.035). Cell-free products of HMN sputum microbiota induced features of epithelial disruption and inflammatory gene expression in vitro, indicating enhanced pathogenic potential of these CLD-associated microbiota. Thus, HIV-positive children harbor distinct sputum microbiota, with those dominated by Haemophilus, Moraxella or Neisseria associated with enhanced pathogenesis in vitro and clinical CLD.

A reliable cross-site user generated content modeling method based on topic model

Nowadays, social network sites (SNSs) have been significant platforms for content sharing in our daily life. With the emergence of different kinds of social network sites and users’ diverse needs for content sharing, their content sharing practices are generally taken place in multiple SNSs. To construct models that can characterize users’ content sharing practices in a composite context constituted by multiple social network sites (cross-site user generated content modeling) has been an emerging research topic in web data mining and human behavior research. However, previous methods such as Dirichlet Multinomial Mixture model (DMM), Biterm Topic Model (BTM), Twitter-LDA and MultiLDA have limited representation ability or are based on unreliable assumption, which cannot characterize the user generated content (UGC) accurately from the perspective of multiple SNSs. In this paper, we first conduct an empirical study to investigate the characteristics of users’ content sharing practices in cross-site context, based on which we propose a more reliable cross-site UGC model named CrossSite-LDA (C-LDA). We then evaluate the performances of the C-LDA model with four state-of-the-art models based on the two data sets sampled from Weibo–Douban and Facebook–Twitter. Results show that the C-LDA has better performances in perplexity, word coherence, topic KL divergence, UCI and UMass metrics compared with existing models, which suggests its superior accuracy on modeling users’ content characteristics in cross-site context.

The world cancer patient population (WCPP): An updated standard for international comparisons of population-based survival

PurposeThis study addresses the need for a global cancer patient-based standard population that adjusts for the expected age structure of different cancers, thus aiding the comparison of survival estimates worldwide. MethodsCounts of age-specific incidence for 36 cancer sites in 185 countries for the year 2018 were extracted from IARC’s GLOBOCAN database of national estimates. We used a multinomial mixture regression to identify clusters of cancer sites with similar age-specific profiles. ResultsAn updated standard entitled the World Cancer Patient Population (WCPP) is presented, derived from the current estimated global numbers of cancer patients that comprises three sets of age-specific weights. Around two-thirds of cancer sites were described by a unique standard, representing the majority of epithelial cancers more often diagnosed at older age groups. The two other standards represent a number of non-epithelial cancer types, and cancers common at younger and older age groups, respectively. ConclusionThe WCPP proposed here provides a contemporary and global means to estimate age-standardised survival for international benchmarking purposes.

Abstract 1121: Baseline oral microbiota profiles associated with all-cancer incidence in a cohort of non-smoking Mexican American women

Abstract Background: We previously demonstrated an association of age and acculturation with oral microbiota among non-smoking women enrolled in a Texas cohort of first and second generation immigrants of Mexican origin. Given the increasing evidence that the oral microbiome is involved in obesity, diabetes and cancer risk, as well as the lack of data in Mexican Americans, we prospectively investigated baseline oral microbiota profiles in relation to all-cancer incidence. Methods: We characterized the 16Sv4 rDNA microbiome in oral mouthwash samples collected at baseline from a representative subset of 369 non-smoking women, aged 20-78 years, enrolled in the MD Anderson Mano a Mano Mexican American (MA) cohort study. Using Dirichlet multinomial mixtures (DMM) modeling, we previously identified three microbial communities or clusters in our sample uniquely characterized by Streptococcus, Fusobacterium and Prevotella. We evaluated within (alpha) and between sample (beta) diversity by incident cancer status and applied Linear Discriminant Analysis (LDA) Effect Size analysis (LEfSe) to assess differentially abundant taxa. Results: Over 8.9 median years of follow-up, 31 incident cancer cases were identified and verified with the Texas Cancer Registry. In addition to advanced age and higher acculturation, a prior history of cardiovascular disease and multiple cardiometabolic risk factors (obesity, diabetes, high cholesterol, hypertension) were associated with higher all-cancer incidence in this subset of non-smoking women. With the exception of country of birth and following adjustment for age, none of these were strongly associated with the oral microbiome. Higher overall diversity of the oral microbiota, as assessed by Shannon diversity index, was observed among women diagnosed with cancer over follow-up, as compared to those who were not (age-adjusted Pdiff=0.0003). We observed potentially distinct biological communities, as measured by weighted UniFrac distance (Pdiff =0.001), and several differentially abundant taxa by incident cancer status. Fusobacterium, Campylobacter, Prevotella, Dialister and Atopobium were higher among women who developed cancer, while Streptococcus was enriched among women who did not develop cancer (LDA>=3, P<0.01). Moreover, we observed increased odds of developing cancer among women in the Prevotella vs. Streptococcus cluster (age-adjusted OR=3.08, 95%CI=1.14, 8.35, P=0.02). Conclusions: To our knowledge, this is the first look at oral microbiota and cancer risk in Mexican American women. Our findings support the potential of the more readily accessible oral microbiota as a promising biomarker of cancer risk in non-smoking women. Citation Format: Xiaotao Zhang, Kristi L. Hoffman, Qiong Dong, Kplola Y. Elhor Gbito, Shine Chang, Joseph Petrosino, Carrie R. Daniel-MacDougall. Baseline oral microbiota profiles associated with all-cancer incidence in a cohort of non-smoking Mexican American women [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 1121.

Topography of the respiratory tract bacterial microbiota in cattle

BackgroundBacterial bronchopneumonia (BP) is the leading cause of morbidity and mortality in cattle. The nasopharynx is generally accepted as the primary source of pathogenic bacteria that cause BP. However, it has recently been shown in humans that the oropharynx may act as the primary reservoir for pathogens that reach the lung. The objective was therefore to describe the bacterial microbiota present along the entire cattle respiratory tract to determine which upper respiratory tract (URT) niches may contribute the most to the composition of the lung microbiota.MethodsSeventeen upper and lower respiratory tract locations were sampled from 15 healthy feedlot steer calves. Samples were collected using a combination of swabs, protected specimen brushes, and saline washes. DNA was extracted from each sample and the 16S rRNA gene (V3-V4) was sequenced. Community composition, alpha-diversity, and beta-diversity were compared among sampling locations.ResultsMicrobiota composition differed across sampling locations, with physiologically and anatomically distinct locations showing different relative abundances of 1137 observed sequence variants (SVs). An analysis of similarities showed that the lung was more similar to the nasopharynx (R-statistic = 0.091) than it was to the oropharynx (R-statistic = 0.709) or any other URT sampling location. Five distinct metacommunities were identified across all samples after clustering at the genus level using Dirichlet multinomial mixtures. This included a metacommunity found primarily in the lung and nasopharynx that was dominated by Mycoplasma. Further clustering at the SV level showed a shared metacommunity between the lung and nasopharynx that was dominated by Mycoplasma dispar. Other metacommunities found in the nostrils, tonsils, and oral microbiotas were dominated by Moraxella, Fusobacterium, and Streptococcus, respectively.ConclusionsThe nasopharyngeal bacterial microbiota is most similar to the lung bacterial microbiota in healthy cattle and therefore may serve as the primary source of bacteria to the lung. This finding indicates that the nasopharynx is likely the most important location that should be targeted when doing bovine respiratory microbiota research.4oDYTht3cF8JKr3LU-_s_YVideo abstract.

Short Text Topic Modeling Techniques, Applications, and Performance: A Survey

Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm.

Use of Strong Habitat–Abundance Relationships in Assessing Population Status of Cryptic Fishes: An Example Using the Harlequin Darter

AbstractUnderstanding trends in abundance is important to fisheries conservation, but techniques for estimating streamwide abundance of cryptic fishes with strong habitat–abundance relationships are not well established and need further development. We developed techniques for addressing this need using the Harlequin Darter Etheostoma histrio, a small, cryptic freshwater fish associated with submerged wood in streams. Our objectives were to (1) determine how Harlequin Darter abundance and the amount of submerged wood were related at sampled sites and (2) use this relationship to estimate Harlequin Darter abundance at unsampled sites and extrapolate Harlequin Darter abundance estimates and associated uncertainty streamwide. We conducted a mark–recapture study to estimate abundance of Harlequin Darters in 25‐m stream reaches at 24 sites in Big Escambia Creek (BEC) and 18 sites in Pine Barren Creek (PBC) (Escambia River tributaries in northwestern Florida). The number of wood pieces (submerged wood ≥1.5 m long and ≥0.25 m in circumference) in both creeks was counted and mapped using side‐scan sonar and a geographic information system. Harlequin Darter and wood data were used in a Bayesian multinomial mixture model to estimate site abundance of Harlequin Darters, to determine the relationship between wood and Harlequin Darter abundance, and to extrapolate Harlequin Darter abundance streamwide. We found a positive relationship between wood and Harlequin Darter abundance in both creeks, and there were more wood pieces in PBC than in BEC. Streamwide abundance of Harlequin Darters was greater in PBC than in BEC. The extrapolated streamwide abundance estimates were 9,369 Harlequin Darters (95% credible interval = 6,668–13,402) in PBC and 7,439 Harlequin Darters (95% credible interval = 4,493–11,226) in BEC. Our methods effectively estimated abundance of a small, cryptic fish that uses complex wood habitat. In addition, our findings may assist in the conservation of the Harlequin Darter.

Meta-analysis of 16S rRNA Microbial Data Identified Distinctive and Predictive Microbiota Dysbiosis in Colorectal Carcinoma Adjacent Tissue.

As research focusing on the colorectal cancer fecal microbiome using shotgun sequencing continues, increasing evidence has supported correlations between colorectal carcinomas (CRCs) and fecal microbiome dysbiosis. However, large-scale on-site and off-site (surrounding adjacent) tissue microbiome characterization of CRC was underrepresented. Here, considering each taxon as a feature, we demonstrate a machine learning-based method to investigate tissue microbial differences among CRC, colorectal adenoma (CRA), and healthy control groups using 16S rRNA data sets retrieved from 15 studies. A total of 2,099 samples were included and analyzed in case-control comparisons. Multiple methods, including differential abundance analysis, random forest classification, cooccurrence network analysis, and Dirichlet multinomial mixture analysis, were conducted to investigate the microbial signatures. We showed that the dysbiosis of the off-site tissue of colonic cancer was distinctive and predictive. The AUCs (areas under the curve) were 80.7%, 96.0%, and 95.8% for CRC versus healthy control random forest models using stool, tissue, and adjacent tissue samples and 69.9%, 91.5%, and 89.5% for the corresponding CRA models, respectively. We also found that the microbiota ecologies of the surrounding adjacent tissues of CRC and CRA were similar to their on-site counterparts according to network analysis. Furthermore, based on the enterotyping of tissue samples, the cohort-specific microbial signature might be the crux in addressing classification generalization problems. Despite cohort heterogeneity, the dysbiosis of lesion-adjacent tissues might provide us with further perspectives in demonstrating the role of the microbiota in colorectal cancer tumorigenesis.IMPORTANCE Turbulent fecal and tissue microbiome dysbiosis of colorectal carcinoma and adenoma has been identified, and some taxa have been proven to be carcinogenic. However, the microbiomes of surrounding adjacent tissues of colonic cancerous tissues were seldom investigated uniformly on a large scale. Here, we characterize the microbiome signatures and dysbiosis of various colonic cancer sample groups. We found a high correlation between colorectal carcinoma adjacent tissue microbiomes and their on-site counterparts. We also discovered that the microbiome dysbiosis in adjacent tissues could discriminate colorectal carcinomas from healthy controls effectively. These results extend our knowledge on the microbial profile of colorectal cancer tissues and highlight microbiota dysbiosis in the surrounding tissues. They also suggest that microbial feature variations of cancerous lesion-adjacent tissues might help to reveal the microbial etiology of colonic cancer and could ultimately be applied for diagnostic and screening purposes.

Evaluation of web service clustering using Dirichlet Multinomial Mixture model based approach for Dimensionality Reduction in service representation

In recent years, mainly the functionality of services are described in a short natural text language. Keyword-based searching for web service discovery is not efficient for providing relevant results. When services are clustered according to the similarity, then it reduces search space and due to that search time is also reduced in the web service discovery process. So in the domain of web service clustering, basically topic modeling techniques like Latent Dirichlet Allocation (LDA), Correlated Topic Model (CTM), Hierarchical Dirichlet Processing (HDP), etc. are adopted for dimensionality reduction and feature representation of services in vector space. But as the services are described in the form of short text, so these techniques are not efficient due to lack of occurring words, limited content, etc. In this paper, the performance of web service clustering is evaluated by applying various topic modeling techniques with different clustering algorithms on the crawled dataset from ProgrammableWeb repository. Gibbs Sampling algorithm for Dirichlet Multinomial Mixture (GSDMM) model is proposed as a dimensionality reduction and feature representation of services to overcome the limitations of short text clustering. Results show that GSDMM with K-Means or Agglomerative clustering is outperforming all other methods. The performance of clustering is evaluated based on three extrinsic and two intrinsic evaluation criteria. Dimensionality reduction achieved by GSDMM is 90.88%, 88.84%, and 93.13% on three real-time crawled datasets, which is satisfactory as the performance of clustering is also enhanced by deploying this technique.

Targeted aspects oriented topic modeling for short texts

Topic modeling has demonstrated its value in short text topic discovery. For this task, a common way adopted by many topic models is to perform a full analysis to find all the possible topics. However, these topic models overlook the importance of deeper topics, leading to confusing topics discovered. In practice, people always tend to find more focused topics on some special aspects (or events), rather than a set of coarse topics. Therefore, in this paper, we propose a novel method, Targeted Aspects Oriented Topic Modeling (TATM), to discover more focused topics on specific aspects in short texts. Specifically, each short text is assigned to only one targeted aspect derived from an enhanced Dirichlet Multinomial Mixture process (E-DMM). This process helps group similar words as many as possible, which achieves topic homogeneity. In addition, TATM discovers the topics for each targeted aspect from as many angles as possible by performing target-level modeling, which achieves topic completeness. Thus, TATM can make a balance between the two conflicting properties without employing any additional information or pre-trained knowledge. The extensive experiments conducted on five real-world datasets demonstrate that our proposed model can effectively discover more focused and complete topics, and it outperforms the state-of-the-art baselines.

A Sticky Multinomial Mixture Model of Strand-Coordinated Mutational Processes in Cancer.

SummaryThe characterization of mutational processes in terms of their signatures of activity relies mostly on the assumption that mutations in a given cancer genome are independent of one another. Recently, it was discovered that certain segments of mutations, termed processive groups, occur on the same DNA strand and are generated by a single process or signature. Here we provide a first probabilistic model of mutational signatures that accounts for their observed stickiness and strand coordination. The model conditions on the observed strand for each mutation and allows the same signature to generate a run of mutations. It can both use known signatures or learn new ones. We show that this model provides a more accurate description of the properties of mutagenic processes than independent-mutation achieving substantially higher likelihood on held-out data. We apply this model to characterize the processivity of mutagenic processes across multiple types of cancer.

OP20 The gut microbiota during biological therapy for inflammatory bowel disease

Abstract Background The expansion of therapeutic options in IBD brought forward a need to personalise treatment. Gut inflammation in inflammatory bowel disease (IBD) patients has been associated with reduced microbial richness and abundance of SCFA producers. We aimed to explore the longitudinal impact of treatment on the inflammatory burden and faecal microbiota in patients with CD and UC, treated with anti-tumour necrosis factor (anti-TNF) therapy, vedolizumab (VDZ) or ustekinumab (UST). Methods We analysed faecal samples from 349 IBD patients (112 UC, 237 CD) initiating biological therapy (anti-TNF; VDZ; UST), regardless baseline disease activity, between 2010 and 2019 at a tertiary referral centre. Samples were collected at week 0, 14 and 24. Microbiota phylogenetic profiling was conducted by 16S rRNA gene sequencing and faecal cell counts were determined using flow cytometry. Moisture levels were measured using lyophilisation. Disease activity and response were assessed by faecal calprotectin (FCal). Statistics were performed in R, v3.5.1. Enterotyping was based on the Dirichlet multinomial mixtures approach. Results Faecal microbiota profiles showed high diversity, with samples classified into all four enterotypes (Fig1), although Bact2 was 6- to 10-fold more prevalent in patients compared with controls (Fig2). The variation in faecal microbiota composition was explained (multivariate dbRDA) by diagnosis (R2 = 1.2%, p = 1.00E−04), timepoint (R2 = 0.52, p = 0.006), significantly by age, gender and faecal moisture. The full model only explained 2.85% of the microbiota variation. A slight non-significant decrease in the Bact2 enterotype prevalence was observed in the CD, but not in the UC cohort, during treatment. A significant decrease in FCal concentrations (w0 vs. 14, UC p = 5.12E-08, CD p = 2.56E−08; week 0 vs. 24: CD p = 4.86E-08) was observed with treatment, accompanied by a significant increase in cellcounts (w0 vs. 14: UC p = 0.024, CD p = 0.0022; week 0 vs. 24: CD p = 0.0201) (Figure 3). No significant change in Bact2 prevalence was found during treatment. Only treatment-associated variables—week of treatment (p = 2.4E−18), diagnosis (0.0005) and timepoint (p = 0.0073)—were significant predictors for response, while microbiota-associated variables (enterotype, cell counts and faecal moisture) not. Baseline samples were associated with higher FCal levels. This suggests that the response time of the microbiota to treatment may be higher than the host inflammatory response. Conclusion The prevalence of the inflammatory Bact2 enterotype was 5- to 10-fold higher in CD and UC patients as compared with controls. Although initiation of biological therapies leads to a decrease in inflammation levels as witnessed by faecal calprotectin and increase in microbial richness, a shift in enterotypes did not occur.

Topic Modeling for Short Texts via Word Embedding and Document Correlation

Topic modeling is a widely studied foundational and interesting problem in the text mining domains. Conventional topic models based on word co-occurrences infer the hidden semantic structure from a corpus of documents. However, due to the limited length of short text, data sparsity impedes the inference process of conventional topic models and causes unsatisfactory results on short texts. In fact, each short text usually contains a limited number of topics, and understanding semantic content of short text needs to the relevant background knowledge. Inspired by the observed information, we propose a regularized non-negative matrix factorization topic model for short texts, named TRNMF. The proposed model leverages pre-trained distributional vector representation of words to overcome the data sparsity problem of short texts. Meanwhile, the method employs the clustering mechanism under document-to-topic distributions during the topic inference by using Gibbs Sampling Dirichlet Multinomial Mixture model. TRNMF integrates successfully both word co-occurrence regularization and sentence similarity regularization into topic modeling for short texts. Through extensive experiments on constructed real-world short text corpus, experimental results show that TRNMF can achieve better results than the state-of-the-art methods in term of topic coherence measure and text classification task.

Collaborative Online Edge Caching With Bayesian Clustering in Wireless Networks

In this article, we study the edge caching problem by considering the heterogeneous context with unknown users’ preferences. The cache provider (CP) can personalize the users’ storage based on available data to maximize the overall cache hit rate, accounting for the dynamic natures of both mobile edge cache scenarios and the users’ preferences. Toward this end, we introduce an online Bayesian clustering caching algorithm for the CP to autonomously learn the users’ interactive cache hit data in a collaborative way while maintaining sustainable scalability. Specifically, a Bayesian generative framework called the Dirichlet multinomial mixture (DMM) model is used to describe the uncertainty about the latent number of users’ clusters, each of which consists of the users with the same preference. Then, a dynamic clustering policy is proposed to obtain both the underlying mapping of users to clusters and the preferences of each cluster by using a collapsed Gibbs sampling algorithm. Subsequently, cache decisions are made according to the generated mappings by extending the traditional cache bandit algorithm to a new bandit mechanism with clusters of arms, capable of expediting the learning process between the exploitation and exploration. We theoretically characterize the value of dynamic Bayesian clustering for the long-term edge caching scenario with respect to the regret incurred by the noncluster schemes. Finally, using a real-world data set, our numerical results show that the proposed scheme outperforms the caching algorithms without clustering in the uncertain network scenario.

Vaginal microbiome diversity and preterm birth: results of a nested case–control study in Peru

PurposePreterm birth (PTB) is a major cause of neonatal mortality. The vaginal microbiome is associated with PTB, but results vary across racial/ethnic populations. Some evidence suggests gestational age affects this association. We investigated these associations in a novel population, conducting a post hoc analysis assessing if associations differed between women swabbed at different gestational ages. MethodsWe compared vaginal microbiomes from women with PTB (n = 25) to a random sample of women with term births (n = 100) among participants in the Pregnancy Outcomes, Maternal and Infant Study, conducted in Lima, Peru. Using DADA2, we identified taxa from 16S DNA sequencing and used Dirichlet multinomial mixture models to group into community state types (CSTs). ResultsIf gestational age at sampling was not considered, no CST (diverse, Lactobacillus-dominated or Lactobacillus iners–dominated), was associated with PTB. Among women sampled before 12 weeks' gestation, women with Lactobacillus-dominated CSTs were less likely to have a PTB than those with a diverse CST. Among those swabbed between 12 and 16 weeks' gestation, the reverse was true. ConclusionsOur study supports previous literature suggesting that what constitutes a healthy vaginal microbiome varies by race/ethnicity. Longitudinal studies are necessary to disentangle effects of vaginal microbiome differences over gestation.

An operator theoretic approach to nonparametric mixture models

When estimating finite mixture models, it is common to make assumptions on the mixture components, such as parametric assumptions. In this work, we make no distributional assumptions on the mixture components and instead assume that observations from the mixture model are grouped, such that observations in the same group are known to be drawn from the same mixture component. We precisely characterize the number of observations $n$ per group needed for the mixture model to be identifiable, as a function of the number $m$ of mixture components. In addition to our assumption-free analysis, we also study the settings where the mixture components are either linearly independent or jointly irreducible. Furthermore, our analysis considers two kinds of identifiability, where the mixture model is the simplest one explaining the data, and where it is the only one. As an application of these results, we precisely characterize identifiability of multinomial mixture models. Our analysis relies on an operator-theoretic framework that associates mixture models in the grouped-sample setting with certain infinite-dimensional tensors. Based on this framework, we introduce a general spectral algorithm for recovering the mixture components.

An Exploratory Diagnostic Model for Ordinal Responses with Binary Attributes: Identifiability and Estimation.

Diagnostic models (DMs) provide researchers and practitioners with tools to classify respondents into substantively relevant classes. DMs are widely applied to binary response data; however, binary response models are not applicable to the wealth of ordinal data collected by educational, psychological, and behavioral researchers. Prior research developed confirmatory ordinal DMs that require expert knowledge to specify the underlying structure. This paper introduces an exploratory DM for ordinal data. In particular, we present an exploratory ordinal DM, which uses a cumulative probit link along with Bayesian variable selection techniques to uncover the latent structure. Furthermore, we discuss new identifiability conditions for structured multinomial mixture models with binary attributes. We provide evidence of accurate parameter recovery in a Monte Carlo simulation study across moderate to large sample sizes. We apply the model to twelve items from the public-use, Early Childhood Longitudinal Study, Kindergarten Class of 1998-1999 approaches to learning and self-description questionnaire and report evidence to support a three-attribute solution with eight classes to describe the latent structure underlying the teacher and parent ratings. In short, the developed methodology contributes to the development of ordinal DMs and broadens their applicability to address theoretical and substantive issues more generally across the social sciences.

Dirichlet Multinomial Mixture with Variational Manifold Regularization: Topic Modeling over Short Texts

Conventional topic models suffer from a severe sparsity problem when facing extremely short texts such as social media posts. The family of Dirichlet multinomial mixture (DMM) can handle the sparsity problem, however, they are still very sensitive to ordinary and noisy words, resulting in inaccurate topic representations at the document level. In this paper, we alleviate this problem by preserving local neighborhood structure of short texts, enabling to spread topical signals among neighboring documents, so as to correct the inaccurate topic representations. This is achieved by using variational manifold regularization, constraining the close short texts should have similar variational topic representations. Upon this idea, we propose a novel Laplacian DMM (LapDMM) topic model. During the document graph construction, we further use the word mover’s distance with word embeddings to measure document similarities at the semantic level. To evaluate LapDMM, we compare it against the state-of-theart short text topic models on several traditional tasks. Experimental results demonstrate that our LapDMM achieves very significant performance gains over baseline models, e.g., achieving even about 0.2 higher scores on clustering and classification tasks in many cases.

X-DMM: Fast and Scalable Model Based Text Clustering

Text clustering is a widely studied problem in the text mining domain. The Dirichlet Multinomial Mixture (DMM) model based clustering algorithms have shown good performance to cope with high dimensional sparse text data, obtaining reasonable results in both clustering accuracy and computational efficiency. However, the time complexity of DMM model training is proportional to the average document length and the number of clusters, making it inefficient for scaling up to long text and large corpora, which is common in realworld applications such as documents organization, retrieval and recommendation. In this paper, we leverage a symmetric prior setting for Dirichlet distribution, and build indices to decrease the time complexity of the sampling-based training for DMM from O(K∗L) to O(K∗U), where K is the number of clusters, L the average length of document, and U the average number of unique words in each document. We introduce a Metropolis-Hastings sampling algorithm, which further reduces the sampling time complexity from O(K∗U) to O(U) in the nearly-to-convergence training stages. Moreover, we also parallelize the DMM model training to obtain a further acceleration by using an uncollapsed Gibbs sampler. We combine all these optimizations into a highly efficient implementation, called X-DMM, which enables the DMM model to scale up for long and large-scale text clustering. We evaluate the performance of X-DMM on several real world datasets, and the experimental results show that XDMM achieves substantial speed up compared with existing state-of-the-art algorithms without clustering accuracy degradation.

The development and ecology of the Japanese macaque gut microbiome from weaning to early adolescence in association with diet.

Previously we have shown that the Japanese macaque gut microbiome differs not by obesity per se, but rather in association with high-fat diet (HFD) feeding. This held true for both pregnant dams, as well as their 1-year-old offspring, even when weaned onto a control diet. Here we aimed to examine the stability of the gut microbiome over time and in response to maternal and postweaning HFD feeding from 6 months of age, and at 1 and 3 years of age. In both cross-sectional and longitudinal specimens, we performed analysis of the V4 hypervariable region of the 16S rRNA gene on anus swabs collected from pregnant dams and their juveniles at age 6 months to 3 years (n = 55). Extracted microbial DNA was subjected to 16S-amplicon-based metagenomic sequencing on the Illumina MiSeq platform. We initially identified 272 unique bacterial genera, and multidimensional scaling revealed samples to cluster by age and diet exposures. Dirichlet multinomial mixture modeling of microbiota abundances enabled identification of two predominant enterotypes to which samples sorted, characterized primarily by Treponema abundance, or lack thereof. Approximating the time of initial weaning (6 months), the Japanese macaque offspring microbiome underwent a significant state type transition which stabilized from 1 to 3 years of age. However, we also found the low abundance Treponema enterotype to be strongly associated with HFD exposure, be it during gestation/lactation or in the postweaning interval. Examination of taxonomic co-occurrences revealed samples within the low Treponema cluster were relatively permissive (allowing for increased interactions between microbiota) whereas samples within the high Treponema cluster were relatively exclusionary (suggesting decreased interactions amongst microbiota). Taken together, these findings suggest that Treponemes are keystone species in the developing gut microbiome of the gut, and susceptible to HFD feeding in their relative abundance.