Qing Shao

The paper benchmarks ESM-2 model precision configurations for variant-effect prediction, finding that average performance metrics hide critical failures and that asymmetric activation quantization improves accuracy.

The paper identifies PLK1-mediated phosphorylation of PHGDH as a mechanism driving serine metabolism reprogramming in advanced prostate cancer, increasing reliance on exogenous serine uptake.

This paper introduces DPLM, a dynamics-aware protein language model that integrates molecular dynamics simulations with sequence data to improve predictions of protein properties.

This study introduces ProtLoc-GRPO, a reinforcement learning method that improves subcellular localization prediction by optimizing PPI networks, achieving a 7% macro-F1 score improvement.

This study shows that PLK1-mediated PDHA1 phosphorylation impairs mitochondrial function and promotes Cr(VI)-induced lung cancer progression by disrupting energy metabolism and apoptosis.

This paper introduces S-PLM, a 3D structure-aware protein language model that improves prediction tasks by integrating structural information through efficient fine-tuning.

S-PLM improves protein language models by integrating 3D structure information through contrastive learning, outperforming sequence-only models in clustering and classification tasks.

The paper evaluates AlphaFold2's fairness in predicting protein 3D structures by analyzing PLDDT score variability across amino acid types, secondary structures, and sequence lengths, revealing systematic biases.