Recently, Professors Wang Yanfeng and Huang Chun, along with their colleagues from the Biological Information Processing Team at the College of Electrical and Information Engineering, published a research paper titled "Breast Tumor Diagnosis Based on Molecular Learning Vector Quantization Neural Networks" in Advanced Science, one of the top journals in the fields of materials science and chemistry.

DNA nanotechnology plays a vital role inprecision cancer medicine. Currently, molecular circuits have been used to detect tumor-specific biomarkers and control the release of therapeutic drugs. However, these systems lack self-learning capabilities for the intelligent diagnosis of biological samples and have limited data processing power. In this study, a molecular learning vector quantization neural network model based on DNA strand displacement technology was developed. By using the gene expression levels of cancer-specific miRNA biomarkers as input to the neural network, the model diagnoses two types of breast cancer from different data sources, achieving accuracy rates of 94% and 97.5%, respectively. This technology enables real-time and accurate cancer diagnosis in biological environments, and provides a theoretical foundation for early cancer detection and personalized medicine.

In this paper, Zhengzhou University of Light Industry is listed as the first affiliation, with Huang Chun as the first author, graduate student Shao Jiaying as the second author, and Wang Yanfeng as the corresponding author.This research was funded and supported by the National Natural Science Foundation of China and the Key Research Projects of Higher Education Institutions in Henan Province.

As part of the Wiley Advanced product portfolio, Advanced Science is an interdisciplinary sciencejournal that primarilypublishes cutting-edge basic and applied research in the fields of materials science, physics, chemistry, medicine, life sciences, and engineering. It is recognizedas a topjournal in the Q1of the CAS Journal Ranking, with an impact factor of 14.3 in 2024.

Journal article link:https://doi.org/10.1002/advs.202409150