MOTIVATION: Accurate cancer subtyping is critically important for cancer treatment due to significant molecular heterogeneity. While existing methods with multi-omics integration have achieved some success in cancer subtype identification by leveraging the rich information provided by multi-omics data, most approaches remain limited by an overemphasis on cross-omics consistency at the expense of intra-omics specificity. Furthermore, a two-step scheme is often adopted to extract cluster structure from a consistency matrix or a continuous indicator matrix by k-means, which inevitably leads to information loss and unstable clusters. RESULTS: To overcome these issues, we propose seOMLR, a one-step multi-view latent representation method with self-weighted ensemble learning for cancer subtyping. Using relaxed exclusivity constraints and consistency regularization terms, seOMLR exploits the specificity and consistency of multi-omics data by building a sparse low-rank self-representation framework. Simultaneously, a self-weighted ensemble strategy is introduced to adaptively incorporate prior subtyping information from other methods, indirectly promoting specificity and consistency learning. Moreover, the discrete clustering structure is subsequently extracted via spectral rotation to avoid information loss and cluster instability. Through joint iterative optimization of fusion and clustering, seOMLR enhances subtyping accuracy. Experiments on both simulated datasets and eight real multi-omics cancer datasets from TCGA demonstrate that seOMLR outperforms competing methods, achieving efficient multi-omics data fusion and providing computational framework support for cancer subtyping research. AVAILABILITY AND IMPLEMENTATION: Supplementary data are available at Bioinformatics online.

In this paper, we propose KGenre, a knowledge-embedded music representation learning framework for improved genre classification. We construct the knowledge graph from the metadata in the open-source FMA-medium and OpenMIC-2018 datasets, with no extra information/effort required. KGenre then mines the correlation between different genres from the knowledge graph and embeds such correlation in audio representation. To our knowledge, KGenre is the first method fusing the audio with high-level knowledge for music genre classification. Experimental results demonstrate the embedded knowledge can effectively enhance the audio feature representation, and the genre classification performance surpasses the state-of-the-art methods.

More and more brands are utilizing online word-of-mouth recommendations to promote their products and using product ingredients more widely in marketing communications. However, no research has explored how recommendation terms (ingredient vs. function) for functional products affects consumers' attitudes. Through one pilot study and four experiments, it was found that consumers hold the lay belief that “ingredient = professional.” For functional products, consumers' purchase intentions and product evaluations are higher when ingredient (vs. function) are labelled, with perceived trustworthiness playing a mediating role. In addition, the domain knowledge of the information sender moderates the focal effect. Theoretically, this research contributes to the literature on both lay beliefs and word-of-mouth marketing by proposing a new lay belief, and by exploring the effect of recommendation terms on consumers' attitudes. Practically, this research can guide marketers in the appropriate use of product ingredient for word-of-mouth marketing.

The messenger-based social network (Msg-SN), e.g. WeChat Moments, has emerged as a new type of social networking with unique characteristics. Msg-SN plays a strikingly important role in people’s daily lives and has gradually become a battleground for advertisers to win consumers. This is especially the case in China. Unlike conventional social network sites (SNSs), Msg-SN offers a semi-closed space in which traditional advertising strategy based on Key Opinion Leaders may become infeasible. Drawing from self-construal theory, this study offers a new angle to understand the antecedents of advertising involvement in the context of Msg-SN. It conducted an empirical study with respondents from users of WeChat Moments, which reveals the different impacts of each facet of a user’s self-construal, including interdependent self-construal (InterSC), independent self-construal (IndepSC) and individualist self-construal (IndivSC), on adverting involvement, partially mediated by frequency of user activities. This study enriches the research of advertising involvement in the context of Msg-SN from a new angle. It also offers practical implications for marketers to achieve highly targeted advertising according to psychographic segmentations.

The discovery of cancer subtypes has become much-researched topic in oncology. Dividing cancer patients into subtypes can provide personalized treatments for heterogeneous patients. High-throughput technologies provide multiple omics data for cancer subtyping. Integration of multi-view data is used to identify cancer subtypes in many computational methods, which obtain different subtypes for the same cancer, even using the same multi-omics data. To a certain extent, these subtypes from distinct methods are related, which may have certain guiding significance for cancer subtyping. It is a challenge to effectively utilize the valuable information of distinct subtypes to produce more accurate and reliable subtypes. A weighted ensemble sparse latent representation (subtype-WESLR) is proposed to detect cancer subtypes on heterogeneous omics data. Using a weighted ensemble strategy to fuse base clustering obtained by distinct methods as prior knowledge, subtype-WESLR projects each sample feature profile from each data type to a common latent subspace while maintaining the local structure of the original sample feature space and consistency with the weighted ensemble and optimizes the common subspace by an iterative method to identify cancer subtypes. We conduct experiments on various synthetic datasets and eight public multi-view datasets from The Cancer Genome Atlas. The results demonstrate that subtype-WESLR is better than competing methods by utilizing the integration of base clustering of exist methods for more precise subtypes.