Part B: SLICE-MSI-A Machine Learning Interface for System Suitability Testing of Mass Spectrometry Imaging Platforms

Area of Science:

• Analytical Chemistry
• Computational Biology

Background:

• Mass spectrometry imaging (MSI) lacks standardized protocols for system suitability testing.
• Implementing machine learning (ML) for MSI quality control (QC) faces technical barriers.

Purpose of the Study:

• To develop a user-friendly graphical user interface (GUI) for ML-based QC of MSI platforms.
• To enable community-wide adoption of standardized MSI instrument evaluation.

Main Methods:

• Developed SLICE-MSI software using Python with PySimpleGUI, Pandas, Numpy, and Scikit-Learn.
• Utilized ML algorithms trained on data from instruments under clean and compromised conditions.
• Provided clear instructions for file formatting and implementation across different MSI platforms.

Main Results:

• SLICE-MSI offers a streamlined approach for evaluating MSI instrument performance.
• The software facilitates easy implementation for diverse laboratories and MSI configurations.
• Detailed guidance ensures effective use of ML for classifying MSI platform conditions.

Conclusions:

• SLICE-MSI provides an efficient and accessible GUI for ML-driven QC of mass spectrometry imaging platforms.
• This tool standardizes instrument classification, enhancing data quality and reproducibility in MSI studies.