Lipids makes more than 40% of the human brain in dry weight, and have broad information carrying roles in the CNS. In-vivo quantitative MRI (qMRI) aims at characterizing the biological properties of brain tissue. However, it lacks specificity to the molecular environment. Here, we present a novel biophysical framework that allows to decode the lipid composition of brain tissue from the MRI signal. First, we tested our approach on lipid samples of known composition. Next, by comparing the our molecular-specific measures to postmortem histological data, we were able to predict in-vivo lipidomic profiles in the human brain.