Andreas Keller

The paper presents an ensemble model that improves predictions of perceptual similarity between odor mixtures using a curated dataset and collaborative challenge results.

This study identifies genetic associations between olfactory receptors and odor perception in humans, revealing novel links and supporting the hypothesis of olfactory gene degradation.

The paper investigates how genetic variation in olfactory receptors affects odor perception by analyzing sequencing data and phenotypes from 332 individuals.

The paper predicts perceptual ratings for odorants using natural language semantics and chemoinformatic features, achieving higher accuracy for more descriptors than previous methods.

The paper introduces SMELL-S and SMELL-R, olfactory tests that reduce bias from odor-specific insensitivity and prior experience by using unfamiliar odorant mixtures, showing high reliability across populations.

The paper demonstrates that machine learning can accurately predict odor perception from molecular features, enabling reverse-engineering of smell.

The paper estimates human olfactory discriminative capacity exceeds one trillion stimuli, acknowledging sensitivity to assumptions about significance thresholds and olfactory space dimensionality.