Non-targeted analysis and machine learning methods for HRMS feature importance and identification

Grossman, Jarod

Permalink

https://hdl.handle.net/2142/109863 Copy

Description

Title

Non-targeted analysis and machine learning methods for HRMS feature importance and identification

Author(s)

Grossman, Jarod

Issue Date

2021-04-27

Keyword(s)

• machine learning
• emerging contaminants

Abstract

Presented by: Jarod Grossman – Senior Scientist at Agilent Technologies, jarod.grossman@agilent.com Abstract: Non-Targeted Analysis (NTA) is an important and booming field of Mass Spectrometry currently, however, there exists a void in data analysis and conclusions on sample findings due to the sheer informatics and data analysis effort NTA often demands. There can be hundreds to tens of thousands of features that must be sorted through in order to determine which features should then be more confidently ID’d through targeted methods or even what features of which to attempt to determine experimental importance. This presentation will touch on methods and software that can be used to assign importance to features in an NTA experiment and how to then identify these features and bring about important and meaningful conclusions in a high-throughput and efficient manner. Biography: Jarod Grossman is a Scientist at Agilent Technologies. He has previously worked at the US EPA, where he developed workflows for non-targeted analysis and suspect screening to map the chemical space of common media and environments. Jarod has become a leader in the field of Exposomics, consulting with researchers and scientists around the world as one of the foremost experts, as well as organizing national conferences on the topic.

Series/Report Name or Number

2021 Emerging Contaminants in the Environment Conference (ECEC21)

Type of Resource

• text
• still image

Language

en

Permalink

• http://hdl.handle.net/2142/109863
• https://youtu.be/LXM3i-atSKo

Owning Collections