Principal Odor Map

POM (Principal Odor Map)

Predicts the relationship between molecular structure and human odor descriptors with ~85% accuracy.

This is an attempt to address the

Structure–Odor Relationship problem, but fully reproducing real-world scents—where hundreds of compounds interact and produce emergent properties—remains a major unsolved challenge.

The new AI tool that represents the future of fragrance formulations | Givaudan

Givaudan is transforming the way perfumers create with a trailblazing new tool. Reflecting our commitment to digital innovation and learning, ‘Carto’ uses artificial intelligence (AI) to help perfumers achieve better results than ever before.

https://www.givaudan.com/fragrance-beauty/perfumery-school/carto-the-future-of-fragrance-formulations

Scent, In Silico

Once a primal instinct, olfaction is now being mapped, measured, and modeled by machines.

https://www.asimov.press/p/scent

Osmo

Home - Osmo

Create custom fragrances faster with Osmo. AI-powered fragrance development and end-to-end manufacturing built for brands to launch fine fragrance with speed, precision, and creativity.

https://www.osmo.ai/

Benchmark

Dream Olfaction Challenge

Home

DREAM Challenges use crowd-sourcing to solve complex biomedical research questions Crowd-sourced DREAM Challenges have benchmarked informatic algorithms in biomedicine Cross-disciplinary participants from around the world have volunteered as solvers. Academic journal publications have resulted from DREAM Challenges covering a range of disease areas

https://dreamchallenges.org/

Principal Odor Map

POM (Principal Odor Map)

Benchmark

Recommendations