15 April 2021 in The EMBO Journal
22 October 2021 in Medical & Biological Engineering & Computing
Computerized interpretation of electrocardiogram plays an important role in daily cardiovascular healthcare. However, inaccurate interpretations lead to misdiagnoses and delay proper treatments. In this work, we built a high-quality Chinese 12-lead resting electrocardiogram dataset with 15,357 records, and called for a community effort to improve the performances of CIE through the China ECG AI Contest 2019. This dataset covers most types of ECG interpretations, including the normal type, 8 common abnormal types, and the other type which includes both uncommon abnormal and noise signals. Based on the Contest, we systematically assessed and analyzed a set of top-performing methods, most of which are deep neural networks, with both their commonalities and characteristics. This study establishes the benchmarks for computerized interpretation of 12-lead resting electrocardiogram and provides insights for the development of new methods. A community effort to assess and improve computerized interpretation of 12-lead resting electrocardiogram
14 August 2026 in Science Advances
Amylose content is widely regarded as one of the decisive parameters determining rice grain quality. However, the regulatory mechanisms underlying amylose synthesis across different rice subspecies remain poorly understood. Here, we report that FLO6 (Floury Endosperm 6) undergoes phase separation to form condensates that adhere to the surface of starch granules, and these condensates are capable of recruiting GBSS1 (Granule-Bound Starch Synthase 1). A single-nucleotide polymorphism (SNP 3194 ) within the FLO6 gene endows the FLO6 alleles from japonica and indica subspecies with distinct condensate properties. This divergence results in varying GBSS1 activities within the FLO6 condensates, ultimately contributing to differences in grain amylose content. While the well-known allelic variation of GBSS1 establishes the baseline enzyme abundance, the evolutionary adaptation of the FLO6-GBSS1 module serves as an essential superimposed regulatory layer that fine-tunes amylose synthesis across different rice subspecies. Our findings offer potential biotechnological avenues for directionally altering grain amylose content.