Blog covering our recent research: Anupam Jain, Rakhi N K, Ganesh Bagler*, "Analysis of food pairing in regional cuisines of India", PLoS ONE 10(10): e0139539. doi:10.1371/journal.pone.0139539
"Culinary Fingerprints" of regional cuisines of India
Any national cuisine is a sum total of its variety of regional cuisines, which are the cultural and historical identifiers of their respective regions. India is home to a number of regional cuisines, from diverse climates, geographies and cultures, that showcase its culinary diversity. We investigated the phenomenon of food pairing which examines compatibility of two ingredients in a recipe in terms of their shared flavor compounds. Our study highlighted "negative (contrasting) food pairing" as an invariant feature of Indian regional cuisines. Through an intensive data analytical study at the level of cuisine, recipes as well as ingredient pairs, we present unique culinary fingerprints that could be used to design algorithms for generating novel recipes and recipe recommender systems.
Data of regional cuisines of India
We compiled a large set of recipes representing eight different regional and cultural cuisines of India: Bengali, Gujarati, Jain, Maharashtrian, Mughlai, Punjabi, Rajasthani and South Indian. The data includes a total of 2543 recipes across all the regional cuisines.
Computing the food pairing
Starting with the data of ingredients in a recipe and flavor molecules responsible for olfactory and gustatory sensations, we computed the average food pairing in a recipe, and that for the whole regional cuisine.
Negative (contrasting) food pairing and "Culinary Fingerprints"
We find that contrary to what is reported in various national cuisines, negative (contrasting) food pairing is a quintessential feature of all the regional cuisines. Further, we propose that the pattern of contribution of individual food categories as a "culinary fingerprint" of regional cuisines. This reflects the contribution of individual food categories towards food pairing in the cuisine. While spice is the key contributor contrasting food pairing, variations across categories provides a unique culinary imprint of the cuisine at the molecular level.
Application of culinary fingerprints
Our study provides an opportunity to explore possible causal connection between diet and health (food as medicine) as well as prospection of therapeutic molecules from food ingredients. Given typical size of a recipe (8 ingredients) and the number of ingredients available (~200), the repertoire of possible recipes is astronomically large. Flavor pairing could thus be used as a basic principle in algorithm design for both recipe recommendation and novel recipe generation, thereby enabling computational systems to enter the creative domain of cooking and suggesting recipes. In such algorithms, candidate recipes could be generated based on existing domain knowledge and flavor pairing plays a crucial role while selecting the best among these candidates.
Ganesh Bagler
"Culinary Fingerprints" of regional cuisines of India
Any national cuisine is a sum total of its variety of regional cuisines, which are the cultural and historical identifiers of their respective regions. India is home to a number of regional cuisines, from diverse climates, geographies and cultures, that showcase its culinary diversity. We investigated the phenomenon of food pairing which examines compatibility of two ingredients in a recipe in terms of their shared flavor compounds. Our study highlighted "negative (contrasting) food pairing" as an invariant feature of Indian regional cuisines. Through an intensive data analytical study at the level of cuisine, recipes as well as ingredient pairs, we present unique culinary fingerprints that could be used to design algorithms for generating novel recipes and recipe recommender systems.
Data of regional cuisines of India
We compiled a large set of recipes representing eight different regional and cultural cuisines of India: Bengali, Gujarati, Jain, Maharashtrian, Mughlai, Punjabi, Rajasthani and South Indian. The data includes a total of 2543 recipes across all the regional cuisines.
 |
| (From http://www.indianfoodsco.com/Classes/map_de.gif) |
Computing the food pairing
Starting with the data of ingredients in a recipe and flavor molecules responsible for olfactory and gustatory sensations, we computed the average food pairing in a recipe, and that for the whole regional cuisine.
 |
| Computation of food pairing pattern in a cuisine |
Negative (contrasting) food pairing and "Culinary Fingerprints"
We find that contrary to what is reported in various national cuisines, negative (contrasting) food pairing is a quintessential feature of all the regional cuisines. Further, we propose that the pattern of contribution of individual food categories as a "culinary fingerprint" of regional cuisines. This reflects the contribution of individual food categories towards food pairing in the cuisine. While spice is the key contributor contrasting food pairing, variations across categories provides a unique culinary imprint of the cuisine at the molecular level.
The pattern of variations in contribution towards negative (contrasting) food pairing across food categories provides an unique culinary imprint of each regional cuisine at the molecular level.
 |
| Culinary Fingerprints of regional cuisines of India at the molecular level |
Application of culinary fingerprints
Our study provides an opportunity to explore possible causal connection between diet and health (food as medicine) as well as prospection of therapeutic molecules from food ingredients. Given typical size of a recipe (8 ingredients) and the number of ingredients available (~200), the repertoire of possible recipes is astronomically large. Flavor pairing could thus be used as a basic principle in algorithm design for both recipe recommendation and novel recipe generation, thereby enabling computational systems to enter the creative domain of cooking and suggesting recipes. In such algorithms, candidate recipes could be generated based on existing domain knowledge and flavor pairing plays a crucial role while selecting the best among these candidates.
(By 'Symphony of Love' on Flickr, No changes made in the original image)
Ganesh Bagler
No comments:
Post a Comment