Yu Xu

Yu Xu

Auto-generated profile, based on publicly available information

Yu Xu

Department of Computer Science, Hong Kong Baptist University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 November 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
YXYu Xu
Yu Xu
CWChonghao Wang
Chonghao Wang
KXKe Xu
Ke Xu
YDYi Ding
Yi Ding
ALAiping Lyu
Aiping Lyu
LZLu Zhang
Lu Zhang
A bstract: In silico transcription factor and DNA (TF-DNA) binding affinity prediction plays a vital role in examining TF binding preferences and understanding gene regulation. The existing tools employ TF-DNA binding profiles from in vitro high-throughput technologies to predict TF-DNA binding affinity. However, TFs tend to bind to sequences in open chromatin regions in vivo , such TF binding preference is seldomly considered by these existing tools. In this study, we developed TRAFICA, an open chromatin language model to predict TF-DNA binding affinity by integrating the characteristics of sequences from open chromatin regions in ATAC-seq experiments and in vitro TF-DNA binding profiles from high-throughput technologies. We applied self-supervised learning to pre-train TRAFICA on over 13 million nucleotide sequences from the peaks in ATAC-seq experiments to learn the TF binding preference in vivo . TRAFICA was further fine-tuned using the TF-DNA binding profiles from PBM and HT-SELEX technologies to learn the association between TFs and their target DNA sequences. We observed that TRAFICA significantly outperformed both machine learning-based and deep learning-based tools in predicting in vitro and in vivo TF-DNA binding affinity. These findings indicate that considering the characteristics of sequences from open chromatin regions could significantly improve TF-DNA binding affinity prediction, particularly when limited TF-DNA binding profiles from high-throughput technologies are available for specific TFs.

20 May 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
YXYu Xu
Yu Xu
BZBohao Zou
Bohao Zou
GXGuoxiang Xie
Guoxiang Xie
TCTianlu Chen
Tianlu Chen
WJWei Jia
Wei Jia
A(Alzheimer Disease Metabolomics Consortium (ADMC)
Alzheimer Disease Metabolomics Consortium (ADMC)
Metabolomic aging clocks estimate biological age by modeling metabolite concentrations, thereby capturing aging signals from healthspan and adverse outcomes. However, existing clocks generally assume homogeneous aging trajectories and yield only a single age acceleration metric, limiting their capacity to capture inter-individual metabolic heterogeneity and characterize nuanced individual-level representations. To address these limitations, we proposed MetAgeFormer, a transformer-based metabolomic model pre-trained on nuclear magnetic resonance (NMR) metabolomic profiles from over 430,000 participants in UK Biobank via self-supervised learning. This large-scale pre-training enables MetAgeFormer to learn a metabolomic representation space that captures the complex, nonlinear structure of systemic metabolism as reflected in NMR data. Building on MetAge-Former, we developed a mortality-informed metabolomic aging clock by fine-tuning an attached survival module, deriving age acceleration that demonstrates significant associations with multiple age-related diseases and factors. We further validated zero-shot transfer in the independent Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. More importantly, we utilized embeddings generated by MetAgeFormer to identify 13 distinct metabolic subtypes and consolidated them into four meta-subtypes with markedly divergent susceptibility profiles for major age-related diseases, particularly type 2 diabetes and neurodegenerative disorders. This finding empirically demonstrated substantial metabolic heterogeneity across populations, persisting even at comparable levels of age acceleration. To enhance clinical applicability, we further employed contrastive learning to distill a lightweight model that approximates the learned metabolomic representation space using only 14 routine clinical blood test measurements as inputs. Both hold-out testing within UK Biobank and external validation in the China Health and Retirement Longitudinal Study replicated similar disease onset patterns across the identified subtypes, underscoring the robust generalizability of MetAgeFormer and supporting its translational potential as a scalable framework for metabolomic aging assessment and early disease risk stratification.

22 November 2024
Verified
Conference Paper
Open access
ZLZeming Li
Zeming Li
YXYu Xu
Yu Xu
DCDebajyoti Chowdhury
Debajyoti Chowdhury
HYHip Fung Yip
Hip Fung Yip
CWChonghao Wang
Chonghao Wang
LZLu Zhang
Lu Zhang
Predicting complex diseases using computational methods have rapidly evolved, which accelerates precision medicine, disease prevention, and so on. In past years, especially after emergence of genomics, major focus was inclined connecting genetic influence to complex diseases wherein many other essential factors such as environment, lifestyles, and so on were constantly neglected. In recent years, researchers have begun predicting disease risk scores by integrating genetic variants data and different lifestyle factors (alcohol intake, etc) and physical parameters (body mass index, age, etc). However, a potential missing link still exists there as most of those methods did not adequately address how to integrate the information from the medical history record that plays a crucial role in complex disease occurrence. In this paper, we have proposed Med-PRSIMD model that integrates genetic variants, lifestyle factors and medical history records to advance complex disease prediction. In this approach, we trained the Transformer model using causal language model pretraining task for extracting medical history records information. We have evaluated the prediction performance of our proposed Med-PRSIMD model on coronary artery disease, type 2 diabetes, and breast cancer patients' data obtained from the UK biobank. Med-PRSIMD achieved state-of-the-art performance compared to existing methods.

29 October 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
CWChonghao Wang
Chonghao Wang
YXYu Xu
Yu Xu
ZLZeming Li
Zeming Li
LZLouxin Zhang
Louxin Zhang
LZLu Zhang
Lu Zhang
Many phage proteins remain functionally uncharacterized despite advances in structural-similarity-based annotation. We introduce PhageFlare, a deep learning framework for predicting phage protein functions lacking significant structural matches to annotated references. Across three structure-disjoint benchmarks, where no significant Foldseek match was detected between training and test proteins (E-value thresholds of 10 − 3 , 10 − 4 , and 10 − 2 ), PhageFlare achieved macro-averaged F 1 scores of 0.871, 0.889, and 0.738 outperforming the strongest baseline (0.789, 0.814, and 0.732). Systematic evaluations demonstrated that protein language model selection critically influences performance, with ESM-C achieving stronger overall performance than ESM-2 and ProtBert. Embedding-guided case studies revealed local structural correspondences among proteins with limited global similarity. Applied to the efam and Metagenomic Gut Virus datasets, PhageFlare annotated 38.0% and 51.8% of proteins unresolved by Fold-seek, respectively. Furthermore, PhageFlare identified lysogenic potential in 1,866 prophage-designated genomes misclassified as lytic by BACPHLIP. These results show that PhageFlare complements structural-similarity-based annotation and expands functional discovery across viral dark matter.