Frequently Asked Questions
How CompKitchen scores pairings.
CompKitchen ranks ingredient pairings by shared volatile flavor compounds. Shared chemistry is a reason to try a pair, not a promise that it works. Here's how it works.
How does molecular flavor pairing actually work?
Every ingredient contains dozens to hundreds of volatile aroma compounds — molecules that evaporate and hit your nose when you eat. Two ingredients that share many of the same compounds can taste coherent together, but shared compounds only weakly predict which pairs cooks actually use, so treat overlap as a reason to try a pair, not a promise. CompKitchen ranks 861 ingredients across 5,133 compounds and scores pairs by how much molecular overlap they share and how often recipes use them together. High overlap + low recipe co-occurrence = a pairing worth testing that few people are cooking yet.
Where does the compound data come from?
We merge FlavorDB 2.0 (IIITD's public molecular flavor database), FooDB, PubChem, ChemTastesDB, Dr. Duke's USDA phytochemical database, and extractions from a library of 44,648 papers indexed via PubMed (not all of them are GC-MS studies, and not all yielded data). Recipe co-occurrence data comes from a curated corpus of 628,352 recipes combining OpenRecipes (CC BY), Fandom Recipes Wiki (CC BY-SA), and public-domain cookbook scans from Project Gutenberg and the Internet Archive. Each compound-food link comes from a public database or a published paper; about a quarter of links so far record which one. See the methodology page for the full data pipeline.
What's a 'novel' pairing?
A pairing is flagged novel when two ingredients share a high fraction of compounds (compound_score ≥ 0.40) but almost never appear together in recipes (recipe_score ≤ 0.10). The shared chemistry makes them worth testing, not a sure thing. Current examples, with live counts, are on Flavor Surprises.
How is the pairing score calculated?
Two layered scores. Compound score is the IDF-weighted Jaccard similarity of the two ingredients' volatile compound sets — shared compounds divided by total unique compounds, weighted so rare distinctive compounds count more than ubiquitous ones. Recipe score is the Normalized Pointwise Mutual Information (NPMI) of how often the two co-occur in real recipes. The final score blends them 50/50 compound-to-recipe with a synergy bonus when both are strong.
What does CompKitchen publish about its scores?
Every data source, every scoring formula, and every ingredient profile. You can see why two ingredients score high together — which compounds they share, and, where measured, at what concentrations and how perceptually impactful each one is.
Why do my favorite classic pairings score low sometimes?
Two reasons. (1) Classic pairings often work on contrast (heat × cream, acid × fat) rather than compound similarity — those fall outside the compound-overlap framework but still work because balance matters. (2) Our category-diversity filter prevents the top results from all being herbs or all being berries, which can push true soul-mate pairings down the list if they're in the same family. The comparison tool at /compare shows raw compound overlap without diversity filtering.
What's a 'flavor cluster'?
Each ingredient is tagged with its dominant flavor family — fruity, green & herbal, roasted & savory, sulfury & pungent, sweet & caramel, spicy & warm, floral, woody & earthy, dairy & creamy, or sour & tangy. These labels come from analyzing each ingredient's compounds, weighted by IDF (rarity) and odor threshold (perceptual impact). You'll see the cluster tags at the top of every ingredient profile page.
Is CompKitchen vegan / allergen-aware?
Partly, and every flag is auto-detected from names, so it can miss things. Each ingredient has dietary flags (vegan, vegetarian, kosher, halal, gluten-free, dairy-free, nut-free, egg-free, alcohol-free) and Big-9 allergen tags (milk, eggs, fish, shellfish, tree nuts, peanuts, wheat, soy, sesame); an ingredient page shows them in its “Is it vegan, gluten-free…” answer. The pairing tools can filter by them under Diet. Recipe pages show a “Contains” line read from the recipe’s ingredients and method. We never mark a recipe as free of an allergen. Check labels if you manage allergies or strict observance.
Can I use CompKitchen for my cooking right now?
Yes. Start with the flavor tools — type an ingredient and see its top pairings, or find a molecular substitute when you're out of something, or describe a mood ("smoky", "citrusy") and get matching ingredients. Every result links to a full compound profile so you can see why it's suggested.
Is CompKitchen free for academic use?
Not free, but discounted. Sign in with an academic email (.edu, .ac.uk, .edu.au and most academic domains) and you're verified instantly for the Educator plan ($49/yr) or the Classroom plan ($199/yr, up to 30 seats, includes API key access). No academic email? Apply at /education. We ask (but don't require) that you cite the methodology paper if CompKitchen contributes to published research.
What's included in CompKitchen Pro?
Pro ($12/mo or $99/yr) unlocks the full ranked pairing list (free shows top 5), full chemistry on every result (OAV where measured, odor threshold, aroma class, chemical class, CAS, key-aroma flag, volatility, odor description), the full inverted compound index at /compound/{name} (free pages show the first 8 ingredients), the full molecule lists on /compare pages (the comparison summary is free), and CSV export on every pairing run. Also includes saved pantries with notes, opt-in search history, and priority email support (24hr weekday reply). Free use, with or without an account, gets the top 5 results in every tool, compare summaries, compound pages, Recipe Remix, all ingredient profiles, and the full recipe browser.
Do you have an API?
Yes — see the Enterprise page. The JSON API exposes every engine method (pair, novel, substitute, bridge, mood, pantry) plus batch endpoints for up to 50 ingredients per request. Used internally for the site and available to recipe platforms, product developers, and research teams.
Can I submit data or corrections?
Yes — if you see an ingredient missing or a compound profile that looks off, email [email protected] with the citation and we'll review. Every added compound-food link needs a published source.
Try it
Flavor Tools
Run a pairing query →
Go deeper MethodologyScoring formulas & sources →
Explore Flavor MapUMAP of 450 ingredients →
Question not answered here?
Email [email protected] — a person replies, and the good questions end up on this page.