LifeTracer

Published:

Discriminating Abiotic and Biotic Organics in Meteorite and Terrestrial Samples Using Machine Learning on Mass Spectrometry Data

Astrobiology · Mass Spectrometry · Machine Learning · Meteorites — PNAS Nexus 2025

Project website Paper (PNAS Nexus)

One of my favorite projects. In collaboration with two NASA scientists — Denise Buckner and José Carlos Aponte — we collected 18 meteorite and soil samples from Antarctica and pre-processed 750 GB of two-dimensional gas chromatography–mass spectrometry data.

LifeTracer uses machine learning on this data to discriminate biotic from abiotic organics, helping distinguish the chemical signatures of life from those of abiotic astrochemistry — a central problem in astrobiology.

LifeTracer Analysis Peak explorer Feature explorer