Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Xiaorui Su
Computer Science > Artificial Intelligence
When a user question is underspecified, a capable model should recognize that its context is insufficient, identify the missing information, ask for it, and respond only once that information determines a unique answer. We formalize multi-turn information seeking as solving a k-underspecified constraint satisfaction problem, where k is the number of variables jointly required to determine the target and therefore measures the degree of missing information.
Impact of Different Degrees of Liver Iron Concentration on MRI Feature Assessment and LI-RADS v2018 Category Assignment for Hepatocellular Carcinoma
Sue Cao, Li Jianwen, and Xiaorui Su have contributed equally to this work. , , , et al., “Impact of Different Degrees of Liver Iron Concentration on MRI Feature Assessment and LI-RADS v2018 Category Assignment for Hepatocellular Carcinoma,” Journal of Magnetic Resonance Imaging (2026): 1–19, https://doi.org/10.1002/jmri.70415. Conflicts of Interest The authors declare no conflicts of interest.
Structural basis and immunogenic efficacy of porcine circovirus type 3 virus-like particle
Abstract Porcine circovirus type 3 (PCV3) is an emerging swine pathogen associated with reproductive failure and systemic inflammation, but vaccines for related PCV2 provide limited cross-protection. Here, we determine high-resolution cryo-EM structures of PCV3 capsid protein assembled into virus-like particles (VLPs) and of PCV3 VLPs bound to the PCV3-specific antibody 2B5.
Embeddings of clinical codes enable knowledge-grounded AI in medicine
Abstract Standardization of electronic health records (EHRs) has enabled the use of clinical codes in AI. We introduce ClinVec, an embedding store that provides embeddings for 153,166 clinical codes and concepts across eight vocabularies.
Metabolic Dysfunction-associated Steatotic Liver Disease Diminishes the Efficacy of miR-125b-5p-engineered MSC Therapy for Hepatocellular Carcinoma via HK2 Upregulation: A Multimodal Theranostic Study
Hepatocellular carcinoma (HCC) accounts for approximately 85% of primary liver cancers and remains a major global health burden, with an increasing incidence worldwide. In 2020, liver cancer was the sixth most commonly diagnosed malignancy and the third leading cause of cancer-related death, with approximately 906,000 new cases and 830,000 deaths.
CCK2R regulates METH-induced CPP acquisition within VTA-BLA-BNST circuit in male mice
Abstract Methamphetamine (METH) addiction is a severe public health issue driven by maladaptive neuroplasticity in reward circuits. Cholecystokinin (CCK), a neuropeptide abundant in the ventral tegmental area (VTA), modulates addiction-related behaviors through its receptors (CCK1R/CCK2R), yet its role in METH-induced conditioned place preference (CPP) remains unclear.
Tumor glioneuronal mixoide con mutación PDGFRA p.K385: hallazgos radiológicos de 2 casos
Ayuda Buscar en la ayuda Buscar en la ayuda Tumor glioneuronal mixoide con mutación PDGFRA p.K385: hallazgos radiológicos de 2 casos Anrong Zeng [1] ; Xiaorui Su [2] ; Wei Hu [1] ; Qiang Yue [1] [1] Department of Radiology, West China Hospital of Sichuan University, Chengdu, China [2] Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China Localización: Neurocirugía: Órgano oficial de la Sociedad Española de Neurocirugía, ISSN...
Interpretability-guided RNA N6-methyladenosine modification site prediction with invertible neural networks - Communications Biology
Abstract As one of the most common and abundant post-transcriptional modifications, N6-methyladenosine (m6A) has been extensively studied for its essential regulatory role in gene expression and cell functions. The location of m6A RNA modification sites, however, remains a challenging problem, because of the inability to characterize m6A modified sites at a multi-scale level in their native RNA context.
Interpretable identification of cancer genes across biological networks via transformer-powered graph representation learning - Nature Biomedical Engineering
Abstract Graph representation learning has been leveraged to identify cancer genes from biological networks. However, its applicability is limited by insufficient interpretability and generalizability under integrative network analysis.
MRI characteristics of H3 G34-mutant diffuse hemispheric gliomas and possible differentiation from IDH-wild-type glioblastomas in adolescents and young adults in: Journal of Neurosurgery: Pediatrics - Ahead of print Journals
Correspondence Qiang Yue: West China Hospital of Sichuan University, Chengdu Sichuan, China. scu_yq@163.com. INCLUDE WHEN CITING Published online December 29, 2023; DOI: 10.3171/2023.10.PEDS23235. Disclosures The authors report no conflict of interest concerning the materials or methods used in this study or the findings specified in this paper. *H.S., J.G., and X.S. contributed equally to this work.
An Improved Graph Isomorphism Network for Accurate Prediction of Drug-Drug Interactions
3.5. Results In this section, we evaluate all baselines with the above six evaluation metrics by quantitatively measuring their performance on two benchmark datasets, respectively. In Table 2, we present the results of all the models, where several things can be noted. First of all, LINE and SDNE are network embedding (NE)-based algorithms, and they solve DDI problems through conventional network representation learning methods, such as MF and RW.
A geometric deep learning framework for drug repositioning over heterogeneous information networks
Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website.
An improved graph representation learning method for drug-target interaction prediction over heterogeneous biological information graph
New Results doi: https://doi.org/10.1101/2022.06.30.498357 Abstract The prediction task of the relationships between drugs and targets plays a significant role in the process of new drug discovery. Computational-based strategies for predicting drug-target interactions (DTIs) are regarded as a high-efficiency way. Moreover, recent studies adopted a graph neural network (GNN) to discover underlying DTIs and achieved better performance.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Xiaorui
Contact Xiaorui, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack