Knowledge-Guided Disentangled Representation Learning for Recommender Systems

In recommender systems, it is essential to understand the underlying factors that affect user-item interaction. Recently, several studies have utilized disentangled representation learning to discover such hidden factors from user-item interaction data, which shows promising results. However, without any external guidance signal, the learned disentangled representations lack clear meanings, and are easy to suffer from the data sparsity issue. In light of these challenges, we study how to leverage knowledge graph (KG) to guide the disentangled representation learning in recommender systems. The purpose for incorporating KG is twofold, making the disentangled representations interpretable and resolving data sparsity issue. However, it is not straightforward to incorporate KG for improving disentangled representations, because KG has very different data characteristics compared with user-item interactions. We propose a novel K nowledge-guided D isentangled R epresentations approach ( KDR ) to utilizing KG to guide the disentangled representation learning in recommender systems. The basic idea, is to first learn more interpretable disentangled dimensions (explicit disentangled representations) based on structural KG, and then align implicit disentangled representations learned from user-item interaction with the explicit disentangled representations. We design a novel alignment strategy based on mutual information maximization. It enables the KG information to guide the implicit disentangled representation learning, and such learned disentangled representations will correspond to semantic information derived from KG. Finally, the fused disentangled representations are optimized to improve the recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model in terms of both performance and interpretability.

The phantom steering effect in Q&A websites

Virtual rewards, such as badges, are commonly used in online platforms as incentives for promoting contributions from a userbase. It is widely accepted that such rewards “steer” people’s behaviour towards increasing their rate of contributions before obtaining the reward. This paper provides a new probabilistic model of user behaviour in the presence of threshold rewards, such a badges. We find, surprisingly, that while steering does affect a minority of the population, the majority of users do not change their behaviour around the achievement of these virtual rewards. In particular, we find that only approximately 5–30% of Stack Overflow users who achieve the rewards appear to respond to the incentives. This result is based on the analysis of thousands of users’ activity patterns before and after they achieve the reward. Our conclusion is that the phenomenon of steering is less common than has previously been claimed. We identify a statistical phenomenon, termed “Phantom Steering”, that can account for the interaction data of the users who do not respond to the reward. The presence of phantom steering may have contributed to some previous conclusions about the ubiquity of steering. We conduct a qualitative survey of the users on Stack Overflow which supports our results, suggesting that the motivating factors behind user behaviour are complex, and that some of the online incentives used in Stack Overflow may not be solely responsible for changes in users’ contribution rates.

New human-computer interaction regulations for ship safe driving based on multi-mode data interconnection

Based on the analysis of the multi-mode data of ship mechatronics and the new human-computer interaction regulations for safety driving, a new safety driving regulation based on multi-mode data is put forward. The new regulations for ship safe driving use mechanical and electrical data to form small-world data interconnection. Artificial intelligence and human-computer interaction operation information are used to integrate and communicate, and human-computer interaction data are incorporated to standardize driving behavior to integrate historical driving data, and finally, the standardized automatic self-driving is formed. The new human-computer interaction regulations formed by the safe driving system make it possible to solve and optimize the ship safe driving mode.

Smell Detection Agent Optimisation Framework and Systems Biology Approach to Detect Dys-Regulated Subnetwork in Cancer Data

Network biology has become a key tool in unravelling the mechanisms of complex diseases. Detecting dys-regulated subnetworks from molecular networks is a task that needs efficient computational methods. In this work, we constructed an integrated network using gene interaction data as well as protein–protein interaction data of differentially expressed genes derived from the microarray gene expression data. We considered the level of differential expression as well as the topological weight of proteins in interaction network to quantify dys-regulation. Then, a nature-inspired Smell Detection Agent (SDA) optimisation algorithm is designed with multiple agents traversing through various paths in the network. Finally, the algorithm provides a maximum weighted module as the optimum dys-regulated subnetwork. The analysis is performed for samples of triple-negative breast cancer as well as colorectal cancer. Biological significance analysis of module genes is also done to validate the results. The breast cancer subnetwork is found to contain i) valid biomarkers including PIK3CA, PTEN, BRCA1, AR and EGFR; ii) validated drug targets TOP2A, CDK4, HDAC1, IL6, BRCA1, HSP90AA1 and AR; iii) synergistic drug targets EGFR and BIRC5. Moreover, based on the weight values assigned to nodes in the subnetwork, PLK1, CTNNB1, IGF1, AURKA, PCNA, HSPA4 and GAPDH are proposed as drug targets for further studies. For colorectal cancer module, the analysis revealed the occurrence of approved drug targets TYMS, TOP1, BRAF and EGFR. Considering the higher weight values, HSP90AA1, CCNB1, AKT1 and CXCL8 are proposed as drug targets for experimentation. The derived subnetworks possess cancer-related pathways as well. The SDA-derived breast cancer subnetwork is compared with that of tools such as MCODE and Minimum Spanning Tree, and observed a higher enrichment (75%) of significant elements. Thus, the proposed nature-inspired algorithm is a novel approach to derive the optimum dys-regulated subnetwork from huge molecular network.

Predicting genes associated with RNA methylation pathways using machine learning

RNA methylation plays an important role in functional regulation of RNAs, and has thus attracted an increasing interest in biology and drug discovery. Here, we collected and collated transcriptomic, proteomic, structural and physical interaction data from the Harmonizome database, and applied supervised machine learning to predict novel genes associated with RNA methylation pathways in human. We selected five types of classifiers, which we trained and evaluated using cross-validation on multiple training sets. The best models reached 88% accuracy based on cross-validation, and an average 91% accuracy on the test set. Using protein-protein interaction data, we propose six molecular sub-networks linking model predictions to previously known RNA methylation genes, with roles in mRNA methylation, tRNA processing, rRNA processing, but also protein and chromatin modifications. Our study exemplifies how access to large omics datasets joined by machine learning methods can be used to predict gene function.

Reducing Loneliness Among Aging Adults: The Roles of Personal Voice Assistants and Anthropomorphic Interactions

The perception of feeling lonely is an influential factor in determining quality of life among aging adults. As the US Census Bureau projects that the number of Americans ages 65 and older will double by 2060, reducing loneliness is imperative. Personal voice assistants (PVAs) such as Amazon's Echo offer the ease-of-use of voice control with a friendly, helpful artificial intelligence. This study aimed to understand the influence of a PVA on loneliness reduction among adults of advanced ages, i.e., 75+, and explore anthropomorphism as a potential underlying mechanism. Participants (N = 16) ages 75 or older used an Amazon Echo PVA for 8 weeks in an independent living facility in the Midwest. Surveys were used to collect information about perceived loneliness, and PVA interaction data was recorded and analyzed. Participants consistently exceeded the required daily interactions. As hypothesized, after the first 4 weeks of the intervention, aging adults reported significantly lower loneliness (baseline mean = 2.22, SD = 0.42; week 4 mean = 1.99, SD = 0.45, Z = −2.45, and p = 0.01). Four dominant anthropomorphic themes emerged after thematic analysis of the entire 8 weeks' PVA interaction data (Cohen's Kappa = 0.92): (1) greetings (user-initiated, friendly phrases); (2) comments/questions (user-initiated, second-person pronoun), (3) polite interactions (user-initiated, direct-name friendly requests), (4) reaction (user response to Alexa). Relational greetings predicted loneliness reductions in the first 4 weeks and baseline loneliness predicted relational greetings with the PVA during the entire 8 weeks, suggesting that anthropomorphization of PVAs may play a role in mitigating loneliness in aging adults.

Drug Repurposing Using Modularity Clustering in Drug-Drug Similarity Networks Based on Drug–Gene Interactions

Drug repurposing is a valuable alternative to traditional drug design based on the assumption that medicines have multiple functions. Computer-based techniques use ever-growing drug databases to uncover new drug repurposing hints, which require further validation with in vitro and in vivo experiments. Indeed, such a scientific undertaking can be particularly effective in the case of rare diseases (resources for developing new drugs are scarce) and new diseases such as COVID-19 (designing new drugs require too much time). This paper introduces a new, completely automated computational drug repurposing pipeline based on drug–gene interaction data. We obtained drug–gene interaction data from an earlier version of DrugBank, built a drug–gene interaction network, and projected it as a drug–drug similarity network (DDSN). We then clustered DDSN by optimizing modularity resolution, used the ATC codes distribution within each cluster to identify potential drug repurposing candidates, and verified repurposing hints with the latest DrugBank ATC codes. Finally, using the best modularity resolution found with our method, we applied our pipeline to the latest DrugBank drug–gene interaction data to generate a comprehensive drug repurposing hint list.