Fig. 1: The development of pGlycoQuant. | Nature Communications

Fig. 1: The development of pGlycoQuant.

From: pGlycoQuant with a deep residual network for quantitative glycoproteomics at intact glycopeptide level

Fig. 1

a Current glycopeptide quantitation software tools suffer from suboptimal reproducibility for lower-abundance signals, resulting in a high missing value rate. b pGlycoQuant supports both primary and tandem mass spectrometry quantitation for multiple quantitative strategies. c An embedded deep learning model of ResNet in pGlycoQuant for glycopeptide evidence matching and MBR analysis. d The FQR is estimated by fitting Gaussian mixture distribution with EM algorithm. e The MIR algorithm is proposed as an optional function in pGlycoQuant for increasing quantitative coverage of sialic acid-related glycopeptides.

Back to article page