Rapid quantitative analysis of soybean protein isolates secondary structure by two-dimensional correlation infrared spectroscopy through pH perturbation

The infrared spectroscopy (IR) signal of protein is prone to being covered by impurity signals, and the accuracy of the secondary structure content calculated using spectral data is poor. To tackle this challenge, a rapid high-precision quantitative model for protein secondary structure was proposed. Firstly, a two-dimensional correlation calculation was performed based on 60 groups of soybean protein isolates (SPI) infrared spectroscopy data, resulting in a two-dimensional correlation infrared spectroscopy (2DCOS-IR). Subsequently, the optimal characteristic bands of the four secondary structures were extracted from the 2DCOS-IR. Ultimately, partial least squares (PLS), long short-term memory (LSTM), and bidirectional long short-term memory (BILSTM) algorithms were used to model the extracted characteristic bands and predict the content of SPI secondary structure. The findings suggested that BILSTM combined with 2DCOS-IR model (2DCOS-BILSTM) exhibited superior predictive performance. The prediction sets for α-helix, β-sheet, β-turn, and random coil were designated as 0.9257, 0.9077, 0.9476, and 0.8443, respectively, and their corresponding RMSEP values were 0.26, 0.48, 0.20, and 0.15. This strategy enhances the precision of IR and facilitates the rapid identification of secondary structure components within SPI, which is vital for the advancement of protein industrial production.