Tianyu Liu

Three-dimensional Virtual Adult Cardiomyocyte Transcriptomics

This paper introduces 3D-VirtualCM, a method to reconstruct full cardiomyocyte transcriptomes from spatial transcriptomic sections, revealing spatial and transcriptional heterogeneity in infarcted mouse hearts.

Pre-training Genomic Language Model with Variants for Better Modeling Functional Genomics

The paper introduces UKBioBERT, a DNA language model pre-trained on UK BioBank variants, which improves gene expression prediction and enables eQTL identification when combined with sequence-to-function models.

DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery

DrugPlayGround benchmarks large language models for drug discovery tasks like drug characteristics and interactions, assessing their performance against traditional methods.

Non-planar perylene diimides dual-targeting mitochondrial membrane potential and mitochondrial DNA transcription for an-titumor Therapy

This paper develops a non-planar perylene diimide compound that targets both mitochondrial membrane potential and mtDNA transcription, showing antitumor effects in breast cancer models.

SpatialAgent: An Autonomous AI Agent for Spatial Biology

SpatialAgent integrates large language models with dynamic tool retrieval, multimodal interpretation, and claim verification to automate end-to-end spatial biology workflows from gene-panel design to tissue annotation and hypothesis generation.

Beyond Integration: SuperGLUE Facilitates Explainable Training Framework for Multi-modal Data Analysis

This paper introduces a scalable probabilistic deep learning framework for multi-modal data integration, demonstrating improved preservation of local and global structures in complex biological systems.

Tumour purity as a prognostic factor in colon cancer

This study investigates tumour purity in colon cancer, finding it correlates with prognosis, mutation burden, and immune microenvironment, with low purity linked to worse survival and less chemotherapy benefit.