English

New machine learning algorithm accurately decodes molecular optical 'fingerprints'

1448
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
  • Ultra fast laser tracking the "ballistic" motion of electrons in graphene

    Figure 1. The setup of Hui Zhao and his team at the University of Kansas Ultra Fast Laser Laboratory.A team of researchers from the University of Kansas's ultrafast laser laboratory recently managed to capture real-time ballistic transmission of electrons in graphene, which could lead to faster, more powerful, and more energy-efficient electronic devices in the future.The motion of electrons is of...

    2024-01-09
    See translation
  • Zeiss Medical Technology nominated for the 2025 German Future Award

    Germany’s Office of the Federal President has announced the nominations for the German Future Prize 2025 (“Deutscher Zukunftspreis”). This year’s nominees include Dr. Mark Bischoff, Dr. Gregor Stobrawa and Dirk Mühlhoff from Zeiss Medical Technology (ZMT), for their project for minimally-invasive lenticule extraction to correct refractive errors. Nominated: Dirk Mühlhoff, Mark Bischoff, and Gr...

    09-22
    See translation
  • Nat. Commun.: Two color orthogonal polarized organic light-emitting diode

    In recent years, linearly polarized organic light-emitting diodes have greatly enriched the application scenarios of polarization optics and optoelectronics industries. The low-cost and large-area preparation of linearly polarized organic light-emitting diodes with high polarization, strong directional emission, narrow bandwidth, and multi-color adjustability is an important challenge in the curre...

    2024-02-29
    See translation
  • Top management changes at Laser Photonics Corp., a US laser equipment manufacturer

    Recently, Laser Photonics Corp. (LPC), a Nasdaq listed equipment developer, announced that it has appointed John T. Armstrong as its new Executive Vice President. Before assuming his position at LPC, Armstrong served as Vice President of Astronics Test Systems, a subsidiary of Astronics Corporation, a global leader in advanced technology and products in critical mission areas such as aerospace a...

    2024-11-20
    See translation
  • Scientists use glass to create femtosecond lasers

    Image source: Federal Institute of Technology in Lausanne, SwitzerlandScience and Technology Daily, Beijing, September 27th (Reporter Zhang Jiaxin) Commercial femtosecond lasers are manufactured by placing optical components and their mounting bases on a substrate, which requires strict alignment of optical components. So, is it possible to manufacture femtosecond lasers entirely from glas...

    2023-09-28
    See translation