Drug repurposing-identifying new therapeutic uses for approved drugs-is often a serendipitous and opportunistic endeavour to expand the use of drugs diseases. The clinical utility drug-repurposing artificial intelligence (AI) models remains limited because these focus narrowly on diseases which some already exist. Here we introduce TxGNN, graph foundation model zero-shot drug repurposing, identifying candidates even with treatment options or no existing drugs. Trained medical knowledge...

Designers need to consider not only perceptual effectiveness but also visual styles when creating an infographic. This process can be difficult and time consuming for professional designers, mention non-expert users, leading the demand automated infographics design. As a first step, we focus on timeline infographics, which have been widely used centuries. We contribute end-to-end approach that automatically extracts extensible template from bitmap image. Our adopts deconstruction...

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations achieve a better design, development, and evaluation visualizations. This branch studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt for visualizations, structured understanding integration ML4VIS needed. In this article, we systematically survey 88 aiming answer two motivating questions: <italic...

Recent advances in mobile augmented reality (AR) techniques have shed new light on personal visualization for their advantages of fitting within routines, situating a real-world context, and arousing users' interests. However, enabling non-experts to create data AR environments is challenging given the lack tools that allow in-situ design while supporting binding content. Most existing authoring require working computers or manually creating each virtual object modifying its visual...

This paper presents an authoring environment for augmenting static visualizations with virtual content in augmented reality. Augmenting can leverage the best of both physical and digital worlds, but its creation currently involves different tools devices, without any means to explicitly design debug simultaneously. To address these issues, we that seamlessly integrates all steps a deployment workflow through main features: i) extension Vega, ii) preview, iii) hints facilitate valid...

The combination of diverse data types and analysis tasks in genomics has resulted the development a wide range visualization techniques tools. However, most existing tools are tailored to specific problem or type offer limited customization, making it challenging optimize visualizations for new datasets. To address this challenge, we designed Gosling-a grammar interactive scalable visualization. Gosling balances expressiveness comprehensive multi-scale with accessibility domain scientists....

Node-link diagrams are widely used to facilitate network explorations. However, when using a graph drawing technique visualize networks, users often need tune different algorithm-specific parameters iteratively by comparing the corresponding results in order achieve desired visual effect. This trial and error process is tedious time-consuming, especially for non-expert users. Inspired powerful data modelling prediction capabilities of deep learning techniques, we explore possibility applying...

Third‐party logistics (3PL) user–provider integration is attracting increasing attention from both academics and practitioners. However, it remains unclear how best to adopt governance mechanisms safeguard 3PL (e.g., information sharing process coordination). Based on transaction cost economics social exchange theory, this study examined the individual joint effects of contractual detailed contracts contract application) relational trust norms) for operational performance. We conducted a...

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated (AutoML) methods have been developed to automatically search for good models. Due huge model space, it is impossible try all Users tend distrust automatic results increase budget as much they can, thereby undermining efficiency AutoML. address these issues, we design implement ATMSeer, an interactive visualization tool that supports users in refining space AutoML analyzing results....

Graph Neural Networks (GNNs) aim to extend deep learning techniques graph data and have achieved significant progress in analysis tasks (e.g., node classification) recent years. However, similar other neural networks like Convolutional (CNNs) Recurrent (RNNs), GNNs behave a black box with their details hidden from model developers users. It is therefore difficult diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs RNNs, little research has addressed the...

The increasing reliance on Large Language Models (LLMs) for health information seeking can pose severe risks due to the potential misinformation and complexity of these topics. This paper introduces KNOWNET a visualization system that integrates LLMs with Knowledge Graphs (KG) provide enhanced accuracy structured exploration. Specifically, accuracy, extracts triples (e.g., entities their relations) from LLM outputs maps them into validated supported evidence in external KGs. For exploration,...

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness machine learning. How can we decide whether different treatments are reasonable or discriminatory? In this paper, investigate discrimination learning from a visual analytics perspective propose an interactive visualization tool, DiscriLens, to support more comprehensive analysis. To reveal detailed information on algorithmic...

Abstract A blockchain is a decentralized distributed public database. It does not have central authority to maintain this database by running cryptographic protocol with nodes. Bitcoin currently the hottest item in blockchain, and node can verify transaction content package it into block. The guarantees consistency of books through underlying consensus agreement. These algorithms are different because algorithm security assumptions from actual requirements. This paper sorts compares various...

Visual designs can be complex in modern data visualization systems, which poses special challenges for explaining them to the non-experts. However, few if any presentation tools are tailored this purpose. In study, we present Narvis, a slideshow authoring tool designed introducing visualizations Narvis targets two types of end-users: teachers, experts who produce tutorials visualization, and students, non-experts try understand through tutorials. We an analysis requirements close discussions...

Abstract Titanium dioxide (TiO 2 ) is an attractive anode material for energy storage devices due to its low-volume-change and high safety. However, TiO anodes usually suffer from poor electrical ionic conductivity, thus causing dramatic degradation of electrochemical performance at rapid charge/discharge rates, which has hindered use in devices. Here, we present a novel strategy address this main obstacle via using nanoarchitectured consisting mesoporous wrapped carbon on tunnel-like etched...

Latent vectors extracted by machine learning (ML) are widely used in data exploration (e.g., t-SNE) but suffer from a lack of interpretability. While previous studies employed disentangled representation (DRL) to enable more interpretable exploration, they often overlooked the potential mismatches between concepts humans and semantic dimensions learned DRL. To address this issue, we propose Drava, visual analytics system that supports users 1) relating with DRL identifying mismatches, 2)...

Recent advancements have enabled tissue samples to be profiled at the unprecedented level of detail a single cell. Analysis single-cell data has life scientists generate hypotheses and make discoveries that are relevant understanding disease developing therapeutics. Large-scale profiling efforts underway with aim 'atlas' resources catalog cellular archetypes including biomarkers spatial locations. While problem visualization is not new, increasing size, resolution, heterogeneity atlas...

While many visualizations are built for domain users (e.g., biologists, machine learning developers), understanding how used in the has long been a challenging task. Previous research relied on either interviewing limited number of or reviewing relevant application papers visualization community, neither which provides comprehensive insight into ``in wild'' specific domain. This paper aims to fill this gap by examining potential using Large Language Models (LLM) analyze usage literature. We...

Recent advancements have enabled tissue samples to be profiled at the unprecedented level of detail a single cell. Analysis single-cell data has life scientists generate hypotheses and make discoveries that are relevant understanding disease developing therapeutics. Large-scale profiling efforts underway with aim 'atlas' resources catalog cellular archetypes including biomarkers spatial locations. While problem visualization is not new, increasing size, resolution, heterogeneity atlas...

A comprehensive and comprehensible summary of existing deep neural networks (DNNs) helps practitioners understand the behaviour evolution DNNs, offers insights for architecture optimization, sheds light on working mechanisms DNNs. However, this is hard to obtain because complexity diversity DNN architectures. To address issue, we develop Genealogy, an interactive visualization tool, offer a visual representative DNNs their evolutionary relationships. Genealogy enables users learn from...