Lachlan Stuart

METASPACE-ML improves metabolite annotation in imaging mass spectrometry by using machine learning, achieving higher precision and throughput than a rule-based method.

The paper evaluates spatial metabolomics protocols and technologies, showing extensive metabolite coverage and comparable results across imaging MS methods.

ColocAI quantifies co-localization between mass spectrometry images using AI, outperforming existing methods and providing insights into 10,273 molecules from public datasets.

An open-source cloud engine annotates imaging mass spectrometry data at controlled false discovery rate; publicly shared results reached over 3200 datasets and 6 million metabolite images by January 2019.

The paper develops machine and deep learning methods to identify off-sample ions in mass spectrometry images, achieving high F1 scores.