The expansion of textual data, stemming from various sources such as online product reviews and scholarly publications on scientific discoveries, has created a significant demand for the extraction of succinct yet comprehensive information. While many methods have been proposed for automatic keyword extraction in unsupervised and fully supervised settings, effectively leveraging a partial list of known keywords, such as author-specified keywords or Twitter hashtags, remains under-explored. This work aims to enhance both the effectiveness and scalability of semi-supervised keyword extraction. We propose a novel variational Bayesian semi-supervised (VBSS) method that builds upon recent Bayesian advancement in the field, replacing computationally expensive posterior sampling with variational inference and data augmentation. This leads to closed-form updates and substantial speedups, particularly for long texts. Our numerical results show that the VBSS method not only improves performance on longer texts but also offers better control over false discovery rates compared to state-of-the-art keyword extraction techniques.

This article provides an in-depth review of computational methods for predicting transcriptional regulators (TRs) with query gene sets. Identification of TRs is of utmost importance in many biological applications, including but not limited to elucidating biological development mechanisms, identifying key disease genes, and predicting therapeutic targets. Various computational methods based on next-generation sequencing (NGS) data have been developed in the past decade, yet no systematic evaluation of NGS-based methods has been offered. We classified these methods into two categories based on shared characteristics, namely library-based and region-based methods. We further conducted benchmark studies to evaluate the accuracy, sensitivity, coverage, and usability of NGS-based methods with molecular experimental datasets. Results show that BART, ChIP-Atlas, and Lisa have relatively better performance. Besides, we point out the limitations of NGS-based methods and explore potential directions for further improvement.

MOTIVATION: Non-informative or diffuse prior distributions are widely employed in Bayesian data analysis to maintain objectivity. However, when meaningful prior information exists and can be identified, using an informative prior distribution to accurately reflect current knowledge may lead to superior outcomes and great efficiency. RESULTS: We propose MetaNorm, a Bayesian algorithm for normalizing NanoString nCounter gene expression data. MetaNorm is based on RCRnorm, a powerful method designed under an integrated series of hierarchical models that allow various sources of error to be explained by different types of probes in the nCounter system. However, a lack of accurate prior information, weak computational efficiency, and instability of estimates that sometimes occur weakens the approach despite its impressive performance. MetaNorm employs priors carefully constructed from a rigorous meta-analysis to leverage information from large public data. Combined with additional algorithmic enhancements, MetaNorm improves RCRnorm by yielding more stable estimation of normalized values, better convergence diagnostics and superior computational efficiency. AVAILABILITY AND IMPLEMENTATION: R Code for replicating the meta-analysis and the normalization function can be found at github.com/jbarth216/MetaNorm.

MOTIVATION: We propose a drug recommendation model that integrates information from both structured data (patient demographic information) and unstructured texts (patient reviews). It is based on multitask learning to predict review ratings of several satisfaction-related measures for a given medicine, where related tasks can learn from each other for prediction. The learned models can then be applied to new patients for drug recommendation. This is fundamentally different from most recommender systems in e-commerce, which do not work well for new customers (referred to as the cold-start problem). To extract information from review texts, we employ both topic modeling and sentiment analysis. We further incorporate variable selection into the model via Bayesian LASSO, which aims to filter out irrelevant features. To our best knowledge, this is the first Bayesian multitask learning method for ordinal responses. We are also the first to apply multitask learning to medicine recommendation. The sample code and data are made available at GitHub: https://github.com/thrushcyc-github/BMull. RESULTS: We evaluate the proposed method on two sets of drug reviews involving 17 depression/high blood pressure-related drugs. Overall, our method performs better than existing benchmark methods in terms of accuracy and AUC (area under the receiver operating characteristic curve). It is effective even with a small sample size and only a few available features, and more robust to possible noninformative covariates. Due to our model explainability, insights generated from our model may work as a useful reference for doctors. In practice, however, a final decision should be carefully made by combining the information from the proposed recommender with doctors' domain knowledge and past experience. AVAILABILITY AND IMPLEMENTATION: The sample code and data are publicly available at GitHub: https://github.com/thrushcyc-github/BMull.

In the era of big data, people benefit from the existence of tremendous amounts of information. However, availability of said information may pose great challenges. For instance, one big challenge is how to extract useful yet succinct information in an automated fashion. As one of the first few efforts, keyword extraction methods summarize an article by identifying a list of keywords. Many existing keyword extraction methods focus on the unsupervised setting, with all keywords assumed unknown. In reality, a (small) subset of the keywords may be available for a particular article. To use such information, we propose a rigorous probabilistic model based on a semisupervised setup. Our method incorporates the graph-based information of an article into a Bayesian framework via an informative prior so that our model facilitates formal statistical inference, which is often absent from existing methods. To overcome the difficulty arising from high-dimensional posterior sampling, we develop two Markov chain Monte Carlo algorithms based on Gibbs samplers and compare their performance using benchmark data. We use a false discovery rate (FDR)-based approach for selecting the number of keywords, whereas the existing methods use ad hoc threshold values. Our numerical results show that the proposed method compared favorably with state-of-the-art methods for keyword extraction. History: Accepted by Ramaswamy Ramesh, Area Editor for Data Science and Machine Learning. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1283 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2021.0234 ) at ( http://dx.doi.org/10.5281/zenodo.7348935 ).

Early detection of cancers has been much explored due to its paramount importance in biomedical fields. Among different types of data used to answer this biological question, studies based on T cell receptors (TCRs) are under recent spotlight due to the growing appreciation of the roles of the host immunity system in tumor biology. However, the one-to-many correspondence between a patient and multiple TCR sequences hinders researchers from simply adopting classical statistical/machine learning methods. There were recent attempts to model this type of data in the context of multiple instance learning (MIL). Despite the novel application of MIL to cancer detection using TCR sequences and the demonstrated adequate performance in several tumor types, there is still room for improvement, especially for certain cancer types. Furthermore, explainable neural network models are not fully investigated for this application. In this article, we propose multiple instance neural networks based on sparse attention (MINN-SA) to enhance the performance in cancer detection and explainability. The sparse attention structure drops out uninformative instances in each bag, achieving both interpretability and better predictive performance in combination with the skip connection. Our experiments show that MINN-SA yields the highest area under the ROC curve scores on average measured across 10 different types of cancers, compared to existing MIL approaches. Moreover, we observe from the estimated attentions that MINN-SA can identify the TCRs that are specific for tumor antigens in the same T cell repertoire.

We propose a novel supervised dimension-reduction method called supervised t-distributed stochastic neighbor embedding (St-SNE) that achieves dimension reduction by preserving the similarities of data points in both feature and outcome spaces. The proposed method can be used for both prediction and visualization tasks with the ability to handle high-dimensional data. We show through a variety of data sets that when compared with a comprehensive list of existing methods, St-SNE has superior prediction performance in the ultrahigh-dimensional setting in which the number of features p exceeds the sample size n and has competitive performance in the p ≤ n setting. We also show that St-SNE is a competitive visualization tool that is capable of capturing within-cluster variations. In addition, we propose a penalized Kullback–Leibler divergence criterion to automatically select the reduced-dimension size k for St-SNE. Summary of Contribution: With the fast development of data collection and data processing technologies, high-dimensional data have now become ubiquitous. Examples of such data include those collected from environmental sensors, personal mobile devices, and wearable electronics. High-dimensionality poses great challenges for data analytics routines, both methodologically and computationally. Many machine learning algorithms may fail to work for ultrahigh-dimensional data, where the number of the features p is (much) larger than the sample size n. We propose a novel method for dimension reduction that can (i) aid the understanding of high-dimensional data through visualization and (ii) create a small set of good predictors, which is especially useful for prediction using ultrahigh-dimensional data.

MOTIVATION: Recent studies have shown that RNA-sequencing (RNA-seq) can be used to measure mRNA of sufficient quality extracted from formalin-fixed paraffin-embedded (FFPE) tissues to provide whole-genome transcriptome analysis. However, little attention has been given to the normalization of FFPE RNA-seq data, a key step that adjusts for unwanted biological and technical effects that can bias the signal of interest. Existing methods, developed based on fresh-frozen or similar-type samples, may cause suboptimal performance. RESULTS: We proposed a new normalization method, labeled MIXnorm, for FFPE RNA-seq data. MIXnorm relies on a two-component mixture model, which models non-expressed genes by zero-inflated Poisson distributions and models expressed genes by truncated normal distributions. To obtain maximum likelihood estimates, we developed a nested EM algorithm, in which closed-form updates are available in each iteration. By eliminating the need for numerical optimization in the M-step, the algorithm is easy to implement and computationally efficient. We evaluated MIXnorm through simulations and cancer studies. MIXnorm makes a significant improvement over commonly used methods for RNA-seq expression data. AVAILABILITY AND IMPLEMENTATION: R code available at https://github.com/S-YIN/MIXnorm. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Rank aggregation (RA), the process of combining multiple ranked lists into a single ranking, has played an important role in integrating information from individual genomic studies that address the same biological question. In previous research, attention has been focused on aggregating full lists. However, partial and/or top ranked lists are prevalent because of the great heterogeneity of genomic studies and limited resources for follow-up investigation. To be able to handle such lists, some ad hoc adjustments have been suggested in the past, but how RA methods perform on them (after the adjustments) has never been fully evaluated. In this article, a systematic framework is proposed to define different situations that may occur based on the nature of individually ranked lists. A comprehensive simulation study is conducted to examine the performance characteristics of a collection of existing RA methods that are suitable for genomic applications under various settings simulated to mimic practical situations. A non-small cell lung cancer data example is provided for further comparison. Based on our numerical results, general guidelines about which methods perform the best/worst, and under what conditions, are provided. Also, we discuss key factors that substantially affect the performance of the different methods.

BACKGROUND: Gene regulatory networks reveal how genes work together to carry out their biological functions. Reconstructions of gene networks from gene expression data greatly facilitate our understanding of underlying biological mechanisms and provide new opportunities for biomarker and drug discoveries. In gene networks, a gene that has many interactions with other genes is called a hub gene, which usually plays an essential role in gene regulation and biological processes. In this study, we developed a method for reconstructing gene networks using a partial correlation-based approach that incorporates prior information about hub genes. Through simulation studies and two real-data examples, we compare the performance in estimating the network structures between the existing methods and the proposed method. RESULTS: In simulation studies, we show that the proposed strategy reduces errors in estimating network structures compared to the existing methods. When applied to Escherichia coli, the regulation network constructed by our proposed ESPACE method is more consistent with current biological knowledge than the SPACE method. Furthermore, application of the proposed method in lung cancer has identified hub genes whose mRNA expression predicts cancer progress and patient response to treatment. CONCLUSIONS: We have demonstrated that incorporating hub gene information in estimating network structures can improve the performance of the existing methods.

MOTIVATION: Identification of altered pathways that are clinically relevant across human cancers is a key challenge in cancer genomics. Precise identification and understanding of these altered pathways may provide novel insights into patient stratification, therapeutic strategies and the development of new drugs. However, a challenge remains in accurately identifying pathways altered by somatic mutations across human cancers, due to the diverse mutation spectrum. We developed an innovative approach to integrate somatic mutation data with gene networks and pathways, in order to identify pathways altered by somatic mutations across cancers. RESULTS: We applied our approach to The Cancer Genome Atlas (TCGA) dataset of somatic mutations in 4790 cancer patients with 19 different types of tumors. Our analysis identified cancer-type-specific altered pathways enriched with known cancer-relevant genes and targets of currently available drugs. To investigate the clinical significance of these altered pathways, we performed consensus clustering for patient stratification using member genes in the altered pathways coupled with gene expression datasets from 4870 patients from TCGA, and multiple independent cohorts confirmed that the altered pathways could be used to stratify patients into subgroups with significantly different clinical outcomes. Of particular significance, certain patient subpopulations with poor prognosis were identified because they had specific altered pathways for which there are available targeted therapies. These findings could be used to tailor and intensify therapy in these patients, for whom current therapy is suboptimal. AVAILABILITY AND IMPLEMENTATION: The code is available at: http://www.taehyunlab.org CONTACT: [email protected] or [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Much research effort has been devoted to the identification of enriched gene sets for microarray experiments. However, identified gene sets are often found to be inconsistent among independent studies. This is probably owing to the noisy data of microarray experiments coupled with small sample sizes of individual studies. Therefore, combining information from multiple studies is likely to improve the detection of truly enriched gene classes. As more and more data become available, it calls for statistical methods to integrate information from multiple studies, also known as meta-analysis, to improve the power of identifying enriched gene sets. RESULTS: We propose a Bayesian model that provides a coherent framework for joint modeling of both gene set information and gene expression data from multiple studies, to improve the detection of enriched gene sets by leveraging information from different sources available. One distinct feature of our method is that it directly models the gene expression data, instead of using summary statistics, when synthesizing studies. Besides, the proposed model is flexible and offers an appropriate treatment of between-study heterogeneities that frequently arise in the meta-analysis of microarray experiments. We show that under our Bayesian model, the full posterior conditionals all have known distributions, which greatly facilitates the MCMC computation. Simulation results show that the proposed method can improve the power of gene set enrichment meta-analysis, as opposed to existing methods developed by Shen and Tseng (2010, Bioinformatics, 26, 1316-1323), and it is not sensitive to mild or moderate deviations from the distributional assumption for gene expression data. We illustrate the proposed method through an application of combining eight lung cancer datasets for gene set enrichment analysis, which demonstrates the usefulness of the method. AVAILABILITY: http://qbrc.swmed.edu/software/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Recently, firms have experienced severe disasters that caused major supply disruptions. In this paper we study the strategies of dual sourcing and inventory management of a manufacturer facing disrupted supplies. Although abundant research has been conducted in this field, researchers rarely address the problem in the presence of information asymmetry or imperfection, which occurs because unstable supplies are often highly volatile and unpredictable in early stages. Without accurate and prompt forecasts of upstream supplies, it is difficult for a manufacturer to manage the disruption risks in an optimal manner. Here, a Bayesian model is proposed to dynamically update the knowledge of supply risks, which uses Dirichlet prior distributions to achieve mathematical tractability in Bayesian updating. Optimal-sourcing strategies are studied under this framework. Simulation results show that the proposed approach is effective in cost reduction and robust in reacting to imperfect or incomplete initial knowledge of disruptions.

Phishing continue to be one of the most drastic attacks causing both financial institutions and customers huge monetary losses. Nowadays mobile devices are widely used to access the Internet and therefore access financial and confidential data. However, unlike PCs and wired devices, such devices lack basic defensive applications to protect against various types of attacks. In consequence, phishing has evolved to target mobile users in Vishing and SMishing attacks recently. This study presents a client-server distributed architecture to detect phishing e-mails by taking advantage of automatic variable selection in Bayesian Additive Regression Trees (BART). When combined with other classifiers, BART improves their predictive accuracy. Further the overall architecture proves to leverage well in resource constrained environments.

MOTIVATION: Advances in technology have made different microarray platforms available. Among the many, Illumina BeadArrays are relatively new and have captured significant market share. With BeadArray technology, high data quality is generated from low sample input at reduced cost. However, the analysis methods for Illumina BeadArrays are far behind those for Affymetrix oligonucleotide arrays, and so need to be improved. RESULTS: In this article, we consider the problem of background correction for BeadArray data. One distinct feature of BeadArrays is that for each array, the noise is controlled by over 1000 bead types conjugated with non-specific oligonucleotide sequences. We extend the robust multi-array analysis (RMA) background correction model to incorporate the information from negative control beads, and consider three commonly used approaches for parameter estimation, namely, non-parametric, maximum likelihood estimation (MLE) and Bayesian estimation. The proposed approaches, as well as the existing background correction methods, are compared through simulation studies and a data example. We find that the maximum likelihood and Bayes methods seem to be the most promising. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Spam is considered an invasion of privacy. Its changeable structures and variability raise the need for new spam classification techniques. The present study proposes using Bayesian additive regression trees (BART) for spam classification and evaluates its performance against other classification methods, including logistic regression, support vector machines, classification and regression trees, neural networks, random forests, and naive Bayes. BART in its original form is not designed for such problems, hence we modify BART and make it applicable to classification problems. We evaluate the classifiers using three spam datasets; Ling-Spam, PU1, and Spambase to determine the predictive accuracy and the false positive rate.