[2P01-53] Poster Presentation

[2P48] Development of peptide and lipid SIMS spectrum prediction system using Random Forest and evaluation of RF importance of each label

*Mine Iwahori¹, Daisuke Hayashi¹, Satoka Aoyagi¹ (1. Seikei University)

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is a powerful surface analysis technique that can provide 3D molecular imaging and chemical structural information. However, the identification of the peaks is often difficult because of peak overlapping and matrix effects. Therefore, we developed a system to predict ToF-SIMS spectra of unknown organic materials such as peptides. For general organic molecule prediction, the labels for supervised learning have been improved by applying chemical structures. In this study, ToF-SIMS spectral of peptides, lipids, and their mixture were analyzed using Random Forest (RF), a supervised learning method based on decision trees. The chemical structures of sample molecules denoted in SMILES strings were divided into smaller strings to create modified labels. RF was used to predict the spectral dataset with the modified labels. In addition, the feature importance of RF for each label was obtained to evaluate the effectiveness of the labels.