Fluorescence spectral shape analysis for nucleotide identification

Abstract

We report a conjugated polyelectrolyte fluorescence-based biosensor P-C-3 and a general methodology to evaluate spectral shape recognition to identify biomolecules using artificial intelligence. By using well-defined analytes, we demonstrate that the fluorescence spectral shape of P-C-3 is sensitive to minor structural changes and exhibits distinct signature patterns for different analytes. A method was also developed to select useful features to reduce computational complexity and prevent overfitting of the data. It was found that the normalized intensity of 3 to 5 selected wavelengths was sufficient for the fluorescence biosensor to classify 13 distinct nucleotides and distinguish as little as single base substitutions at distinct positions in the primary sequence of oligonucleotides rapidly with nearly 100% classification accuracy. Photophysical studies led to a model to explain the mechanism of these fluorescence spectral shape changes, which provides theoretical support for applying this method in complicated biological systems. Using the feature selection algorithm to measure the relative intensity of a few selected wavelengths significantly reduces measurement time, demonstrating the potential for fluorescence spectrum shape analysis in high-throughput and high-content screening.

Fusarium head blight monitoring in wheat ears using machine learning and multimodal data from asymptomatic to symptomatic periods

“…Many researchers have found that the amount of input variables or spectral features affect ML algorithms’ performance ( Fallahpour et al., 2017 ; Bhardwaj and Patra, 2018 ). ML classifiers were used with feature selection techniques to improve fluorescence spectroscopic nucleotide identification ( Huang et al., 2019b ). Their machine learning and sequential floating forward selection (ML-SFFS) approach has not been applied to reflectance spectroscopy in combination with chlorophyll fluorescence of plants for disease diagnosis.…”

Hyperspectral Monitoring of Powdery Mildew Disease Severity in Wheat Based on Machine Learning

“…The sensitive band for wheat powdery mildew is mainly located at 580–720 nm ( Graeff et al, 2006 ). Based on the spectral characteristics of the canopy, a new vegetation index for wheat powdery mildew, NDVI 1 ( Huang et al, 2019b ), was constructed, and a good estimate effect was obtained. Recently, He et al (2020) analyzed the appropriate monitoring angles of wheat powdery mildew from different observation angles and established a new vegetation index, RPMI, which has expanded the application scope of the monitoring model.…”

Phone Camera Nano-Biosensor Using Mighty Sensitive Transparent Reusable Upconversion Paper

“…19−22 Recent developments in fluorescence-assisted detection use machine learning to analyze the curve pattern and identify the nucleotide. 23 The ubiquitous access to smartphones gives the convenience of sensor integration like the piezo etc., for on-the-spot analysis. 24 Similarly, the use of smartphone camera sensors has been developed for the quantification of metal, glucose, antibiotics, covid virus, etc.…”

“…The cutting-edge technology to control the optical properties in nanoparticles led to the development of optical sensors for metal ions and the quantification of organic molecules. − Such detection is based on fluorescence and absorbance energy transfer (ET), static/dynamic quenching mechanism, and fluorescence resonance energy transfer (FRET)/inner filter effect . Other mechanisms like electron/hole annealing, aggregation-induced quenching/emission, and chroma response have been explored for fluorescence change and colorimetric detection. − Recent developments in fluorescence-assisted detection use machine learning to analyze the curve pattern and identify the nucleotide . The ubiquitous access to smartphones gives the convenience of sensor integration like the piezo etc., for on-the-spot analysis .…”