Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xueting Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cell-free DNA screening for sex chromosome aneuploidy in 67,099 pregnancies: A retrospective analysis

    by Yiqing Yu, Yan Lü, Xiya Zhou, Yulin Jiang, Na Hao, Mengmeng Li, Xueting Yang, Juntao Liu, Qingwei Qi

    Objectives: To evaluate the efficacy of non-invasive prenatal testing in detecting sex chromosome aneuploidies. Methods: A total of 67,099 pregnant women were recruited in this retrospective observational study at Peking Union Medical College Hospital; 300 cases at high risk of sex chromosome aneuploidies were screened and 36 cases refused invasive prenatal diagnosis after detailed prenatal genetic counselling. The clinical data and prenatal diagnosis results were collected. Results: 101 cases were in accordance with non-invasive prenatal testing results after invasive prenatal diagnosis: 95 cases had follow-up confirmation with abnormal sex aneuploidies (14 for monosomy X; 36 for 47, XXY; 22 for trisomy X and 23 for 47, XYY). The total positive predictive value was 38.26% (101/264). The accuracy of different Z scores was calculated, respectively, with positive predictive value ranging from 33.96% to 41.38% and a decreased sensitivity with rise of the Z score. Conclusions: Non-invasive prenatal testing is an effective screening method for sex chromosome trisomy, rather than monosomy X, with relatively high accuracy. Z score = 3 is an optimum risk threshold in sex chromosome aneuploidies.

  • Open Access

    Double Linear Transformer for Background Music Generation from Videos

    by Xueting Yang, Ying Yu, Xiaoyu Wu

    Many music generation research works have achieved effective performance, while rarely combining music with given videos. We propose a model with two linear Transformers to generate background music according to a given video. To enhance the melodic quality of the generated music, we firstly input note-related and rhythm-related music features separately into each Transformer network. In particular, we pay attention to the connection and the independence of music features. Then, in order to generate the music that matches the given video, the current state-of-the-art cross-modal inference method is set up to establish the relationship between visual mode and sound mode. Subjective and objective experiment indicate that the generated background music matches the video well and is also melodious.