ASMS 2023: A Look at the Wednesday Morning Oral Session on Artificial Intelligence in MS Instrumentation and Applications

Published on: 

On June 7th from 8:30–10:30 am at ASMS, an oral session on artificial intelligence and mass spectrometry will take place. We preview this session here.

From 8:30–10:30 am, Grand Ballroom C will be home to an oral session titled “Artificial Intelligence in MS Instrumentation and Applications”. Session Chair Heather Desaire of the University of Kansas will preside the event, which will discuss the potential artificial intelligence could have in how mass spectrometry is conducted.

The premiere talk, starting at 8:30 am, will be led by Shivani Patel of Bristol Myers Squibb in Princeton, New Jersey. The focus will be on how Patel and her team developed a predictive multiple reaction monitoring (MRM) model for high-throughput ADME analyses using learning-to-rank (LTR) techniques.

Next, at 8:50 am, Philip M. Remes of Thermo Fisher Scientific in San Jose, California, will lead a talk titled “‘HODLING’ When Ions Go ‘to the Moon’” that will focus on how this tool can be useful beyond being solely used in mass spectrometry.

At 9:10 am, Melih Yilmaz of the University of Washington in Seattle, Washington, will talk about how her team used a transformer model to induce sequence-to-sequence translation from mass spectra to peptides.


Following this, the 9:30 am talk will be led by Johra Muhammad Moosa of the University of Waterloo in Waterloo, Ontario, Canada, with a focus on improving peptide identification rate by machine learning with second-ranked peptide spectrum matches.

Subsequently, Damien B. Wilburn of Ohio State University in Columbus, Ohio, will lead the 9:50 am talk, which will discuss probabilistic modeling of peptide chromatography with Chronologer-NF provides novel insights into reverse phase chemistry.

Finally, the 10:10 talk will be led by Heinrich Ruser of the Institute for Applied Physics and Metrology in the University of Bundeswehr Munich, located in Neubiberg, Germany. This will focus on real-time analysis and classification of aerosol particles using single-particle mass spectrometry and machine learning.