Chen, T.-M. | bioRxiv Science

bioRxiv2022

EZH2/ hSULF1 axis mediates receptor tyrosine kinase signaling to shape cartilage tumor progression

BackgroundChondrosarcomas are primary cancers of cartilaginous tissue and capable of alteration to highly aggressive, metastatic, and treatment-refractory states, leading to a poor prognosis with a five-year survival rate at 11 months for the dedifferentiated subtype. At present, the surgical resection of chondrosarcoma is the only effective treatment, and no other treatment options including targeted therapies, conventional chemotherapies, or immunotherapies are available for these patients. MethodsA non-biased ChIP sequence, cDNA microarray analysis, and validation of chondrosarcoma cell lines identified sulfatase 1(SULF1) as the top EZH2-targeted gene to regulate chondrosarcoma progression. Receptor tyrosine kinase (RTK) array of chondrosarcoma cells with vector control or ectopically expressed SULF1 revealed that cMET was the downstream signal. The regulation of the EZH2/SULF1/cMET axis was further validated in mice and patient samples with mice models and chondrosarcoma tissue array, respectively. ResultsThe EZH2/SULF1/cMET axis is identified, which contributes to the malignancy of chondrosarcoma and provides a potential therapeutic option for the disease. Ectopically expressed SULF1 or pharmaceutical inhibition of the cMET pathway significantly retards the chondrosarcoma growth and extends mice survival. ConclusionsThe results not only established a signal pathway promoting the malignancy of chondrosarcoma but also provided a therapeutic potential for further development of effective target therapy to treat chondrosarcoma.

cancer biology↗

bioRxiv2019

Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model

BackgroundElectrocardiogram (ECG) is widely used to detect cardiac arrhythmia (CA) and heart diseases. The development of deep learning modeling tools and publicly available large ECG data in recent years has made accurate machine diagnosis of CA an attractive task to showcase the power of artificial intelligence (AI) in clinical applications.\n\nMethods and FindingsWe have developed a convolution neural network (CNN)-based model to detect and classify nine types of heart rhythms using a large 12-lead ECG dataset (6877 recordings) provided by the China Physiological Signal Challenge (CPSC) 2018. Our model achieved a median overall F1-score of 0.84 for the 9-type classification on CPSC2018s hidden test set (2954 ECG recordings), which ranked first in this latest AI competition of ECG-based CA diagnosis challenge. Further analysis showed that concurrent CAs observed in the same patient were adequately predicted for the 476 patients diagnosed with multiple CA types in the dataset. Analysis also showed that the performances of using only single lead data were only slightly worse than using the full 12 lead data, with leads aVR and V1 being the most prominent. These results are extensively discussed in the context of their agreement with and relevance to clinical observations.\n\nConclusionsAn AI model for automatic CA diagnosis achieving state-of-the-art accuracy was developed as the result of a community-based AI challenge advocating open-source research. In- depth analysis further reveals the models ability for concurrent CA diagnosis and potential use of certain single leads such as aVR in clinical applications.\n\nAbbreviationsCA, cardiac arrhythmia; AF, Atrial fibrillation; I-AVB, first-degree atrioventricular block; LBBB, left bundle branch block; RBBB, right bundle branch block; PAC, premature atrial contraction; PVC, premature ventricular contraction; STD, ST-segment depression; STE, ST-segment elevation.

bioinformatics↗