English

New machine learning algorithm accurately decodes molecular optical 'fingerprints'

1512
2025-05-09 10:57:00
See translation

Recently, a research team from Rice University in the United States developed a new machine learning algorithm - Peak Sensitive Elastic Network Logistic Regression (PSE-LR). This algorithm is adept at interpreting the unique optical characteristics of molecules, materials, and disease biomarkers, which can help achieve faster and more accurate medical diagnosis and sample analysis. The relevant paper was published in the latest issue of the journal Nano.

The research team stated that the core breakthrough of this technology lies in teaching computers to recognize unique "fingerprints" generated by the interaction between molecules or materials and light. With the help of this technology, in the future, doctors may be able to capture early signals of Alzheimer's disease by simply shining light on a drop of liquid or tissue sample.

PSE-LR not only has the ability to distinguish autumn hair, but also has the interpretability of being open and honest. Unlike other "black box" machine learning models, it can generate clear "feature importance maps" that accurately highlight key spectral segments, making diagnostic results reliable, interpretable, traceable, and easy to verify.

Compared with other machine learning models, PSE-LR shows superior performance, especially in identifying subtle or overlapping spectral features. In addition, in the subsequent series of validation experiments, the performance of the algorithm was also commendable, including the successful detection of the trace presence of COVID-19 spike protein in the liquid, the accurate identification of neuroprotective components in mouse brain tissue, the effective differentiation of microscopic spectral differences in Alzheimer's disease samples, and the identification of the unique optical characteristics of two-dimensional semiconductor materials.

Source: Opticsky

Related Recommendations
  • ABB will add optical sensors to four greenhouse gas monitoring satellites

    ABB has signed a third contract with the global leader in high-resolution space greenhouse gas monitoring, GHGSat, to manufacture optical sensors for its C12, C13, C14, and C15 satellites. It is reported that C12, C13, C14, and C15 satellites are scheduled to be launched into orbit in 2024.These new satellites will join GHGSat's expanding constellation for detecting and quantifying industrial gas ...

    2023-12-06
    See translation
  • Progress made in the research and development of high-performance electrically pumped topology lasers by the Institute of Semiconductors, Chinese Academy of Sciences

    Topological laser (TL) is a laser device designed and manufactured using the principles of topological optics, which can produce a robust single-mode laser and is an ideal light source for future new optoelectronic integrated chips. Electrically pumped topology lasers have become a research hotspot due to their small size and ease of integration, but topology lasers based on electrical injection a...

    2024-06-06
    See translation
  • Particles have "fuzzy memory" in solid-state batteries

    When you shoot a laser at a solid-state battery, you find that the particles inside are not thrown into the chaos. This surprised a team of researchers from the United States and the United Kingdom.The team discovered the persistence of memory in ions that help move electricity around solid-state batteries.This discovery has improved the understanding of solid-state batteries, which are candidate...

    2024-02-18
    See translation
  • This perovskite solar cell laser equipment company has received another round of financing

    Recently, Lecheng Intelligent Technology (Suzhou) Co., Ltd. (hereinafter referred to as "Lecheng Intelligent") completed a strategic financing round of tens of millions of yuan, which is exclusively invested by Dongfang Fenghai Capital. The financing funds will mainly be used for technology research and development, laboratory construction, and talent recruitment.This is the second round of financ...

    2023-10-10
    See translation
  • Changguang Huaxin's revenue in the first half of the year was 142 million yuan, and its net profit decreased by 117.97% year-on-year

    On August 30th, Changguang Huaxin released its results for the first half of 2023. In the first half of this year, the company achieved a revenue of 142 million yuan, a year-on-year decrease of 43.23%; Net profit attributable to shareholders of the listed company -10.6374 million yuan, a year-on-year decrease of 117.97%.Due to macroeconomic factors such as a slowdown in economic growth, market con...

    2023-08-31
    See translation