ポスター発表
- 第3日 5月21日(金) P2会場(Zoom)
-
3P-44 PDF
臨床検体のハイスループット分析におけるイオンモビリティマススペクトルの機械学習
LCMS analysis using an ion mobility mass spectrometer allows component separation by mobility in addition to mass and chromatographic retention time, so that more component information can be obtained. In high-throughput, large sample set analysis for disease biomarker discovery and/or diagnostic model development, rapid LC separation and flow injection methods are often used, which compromise separation along the time axis. Ion mobility analysis is suitable for large-scale study as it can be obtained without compromising analysis throughput. Here, we report a preliminary study on the construction of a machine-learning model that can discriminate patient attributes, using two-dimensional (mobility–m/z) spectral data.