Biology subjects

Chang, K. Y.

Publications and source records attributed to Chang, K. Y..

3 recordsLinked to original sources

bioRxiv2026

DualLoc: Full-parameter fine-tuning of cascaded dual transformers for protein subcellular localization prediction

Accurate protein subcellular localization is essential for biological function, and mislocalization is linked to numerous diseases. While current methods like DeepLoc 2.0 employ lightweight fine-tuning of protein language models (PLMs), their ability to predict multi-compartment localization remains limited. To address this, we introduce DualLoc, a multi-label localization predictor for ten compartments. DualLoc leverages full-parameter fine-tuning of a cascaded dual-transformer architecture, built upon foundational PLMs and augmented with attention and dropout layers. We evaluated this framework using three foundational PLMs--ProtBERT, ESM-2, and ProtT5--as backbones. Cross-validation on Swiss-Prot and independent validation on the Human Protein Atlas demonstrate consistent superiority over state-of-the-art baselines. The best-performing variant, DualLoc-ProtT5, achieves 0.5872 accuracy, 0.8271 micro-F1, and 0.7811 macro-F1, with substantial gains in the Matthews correlation coefficient for the nucleus (+0.13), cell membrane (+0.13), and extracellular space (+0.07). Pointwise mutual information analysis of model outputs reveals biologically relevant compartment couplings, notably between the Golgi apparatus and endoplasmic reticulum (PMI = 0.25, P < 10-6), accurately reflecting secretory pathway coordination. DualLoc provides both a highly accurate predictive tool and a robust framework for investigating protein multi-localization mechanisms. Author summaryWhere a protein resides within a cell determines what it does. When proteins end up in the wrong location, normal cellular function breaks down--a misplacement linked to diseases like cancer and Alzheimers. While computational tools exist to predict these locations, accurately tracking proteins that multitask across multiple cellular compartments simultaneously remains a major challenge. We developed DualLoc, a new approach that predicts protein locations across ten different cellular compartments, from the nucleus to the cell membrane. By training an advanced artificial intelligence model on large protein sequence databases, our method more accurately identifies where proteins go, especially in complex, multi-location scenarios. Importantly, our analysis revealed meaningful biological patterns. We found strong predictive links between compartments that work closely together, such as the Golgi apparatus and the endoplasmic reticulum--two organelles that coordinate protein processing and transport. This suggests our model captures genuine cellular logic rather than simply memorizing data. By improving how we predict protein localization, DualLoc helps researchers better understand normal cellular function and disease mechanisms. Our method is freely available to the biomedical community.

bioinformatics↗

bioRxiv2023

Oncogenic RAS drives rapid onset cellular plasticity and elicits a tumour-promoting neutrophil response at the inception of preneoplastic development

Oncogenic driver mutations are frequently found in normal tissues, suggesting that additional non-genetic factors are required for tumourigenesis. Phenotypic plasticity is an important gateway to malignancy and inflammation can fuel tumourigenesis, however, little is known about when and how these hallmarks first arise. Using single-cell transcriptomics and in vivo live imaging we have characterised the immediate cell intrinsic and innate immune responses during the first 24 hours following oncogenic Ras activation, in an inducible zebrafish model of HRASG12V-mediated skin tumour initiation. We found that only a subset of basal keratinocytes, but not superficial keratinocytes, are susceptible to RAS-driven phenotypic plasticity. These preneoplastic cells undergo dedifferentiation and partial EMT, resembling malignant cells observed in human squamous cell carcinoma (SCC). Strikingly, the same subset instigates the development of tumour-promoting neutrophils, which in turn enhance preneoplastic cell proliferation. Our findings demonstrate that the effects of oncogenic Ras are primarily determined by the cell of origin and reveal an association between the unlocking of phenotypic plasticity and the onset of tumour-promoting inflammation.

cancer biology↗

bioRxiv2020

Forecasting symptomatic influenza A infection based on pre-exposure gene expression using a Deep Learning approach

Background and ObjectiveNot everyone gets sick after an exposure to influenza A viruses (IAV). Although KLRD1 has been identified as a potential biomarker for influenza susceptibility, it remains unclear whether forecasting symptomatic flu infection based on pre-exposure host gene expression might be possible. MethodTo examine this hypothesis, we developed DeepFlu using the state-of-the-art deep learning approach on the human gene expression data infected with IAV subtype H1N1 or H3N2 viruses to forecast who would catch the flu prior to an exposure to IAV. ResultsThe results indicated that such forecast is possible and, in other words, gene expression could reflect the strength of host immunity. In the leave-one-person-out cross-validation, DeepFlu based on deep neural network outperformed the models using convolutional neural network, random forest, or support vector machine, achieving 70.0% accuracy, 0.787 AUROC, and 0.758 AUPR for H1N1 and 73.8% accuracy, 0.847 AUROC, and 0.901 AUPR for H3N2. In the external validation, DeepFlu also reached 71.4% accuracy, 0.700 AUROC, and 0.723 AUPR for H1N1 and 73.5% accuracy, 0.732 AUROC, and 0.749 AUPR for H3N2, surpassing the KLRD1 biomarker. In addition, DeepFlu which was trained only by pre-exposure data worked the best than by other time spans and mixed training data of H1N1 and H3N2 did not necessarily enhance prediction. DeepFlu is available at https://github.com/ntou-compbio/DeepFlu. ConclusionsDeepFlu is a prognostic tool that can moderately recognize individuals susceptible to the flu and may help prevent the spread of IAV.

bioinformatics↗