# AI Formulation Search for Chemical R&D | QQuantum.ai

> AI formulation development on your own lab history: find the nearest past recipes, see their results and get next experiments, chemists choosing what to run.

Source: https://qquantum.ai/solutions/chemicals-and-materials/formulation-search

[Home](https://qquantum.ai) [solutions](https://qquantum.ai/solutions) [chemicals-and-materials](https://qquantum.ai/solutions/chemicals-and-materials) formulation-search

Chemicals & Materials

# Formulation search. Start from what worked.

Most new formulations are variations on old ones. The fastest experiment is the one you find in the archive instead of running again.

All Chemicals & Materials →

## What it is

AI formulation search lets a chemist describe a target, such as a coating with a given gloss, cure time and VOC limit, and see the closest formulations your company has ever made, what they achieved in testing and why they were dropped. It then suggests the next experiments most likely to close the gap, ranked with their uncertainty. The chemist chooses what to run, and every result goes back into the record.

It works for coatings, adhesives, polymers, lubricants, personal care and agrochemical formulations alike, because the method is the same: join recipes, raw-material data and test results into one record, then search and model over it. Suggestion methods range from similarity search and property models to Bayesian optimisation, chosen to fit how much data you have.

## What it handles

01

### Archive search

Natural-language and similarity search across recipes, test results and notes, including old notebooks digitised from scans, with links back to the original record.

02

### Next-experiment suggestions

Candidate formulations ranked by expected performance and by how much each would teach the model, so a small budget of experiments is spent well.

03

### Constraint checks

Suggestions filtered against your rules: restricted substances, REACH candidate-list entries, cost ceilings, approved suppliers and raw-material availability.

04

### Not: a safety or regulatory verdict

A suggested formulation is a hypothesis. Its hazard classification, safety data and market approvals are determined by your regulatory team after it exists.

## How a suggestion is made

FORMULATION LOOP

1. 01 Target properties, limits, cost
2. 02 Search the archive nearest past formulations and results
3. 03 Model and rank expected performance with uncertainty
4. 04 Constraint filter restricted substances, suppliers, cost
5. 05 Chemist chooses what to make and test
6. 06 · Branch / escalation Results back every test improves the next round

Solid: one roundDashed: bench results feeding the next

Uncertainty is shown with every suggestion, so a chemist can tell a confident prediction from an informed guess.

Questions

## Questions about Formulation Search.

### What is AI formulation development?

It is the use of machine learning on formulation records and test results to find relevant past work, predict how a new recipe will perform and suggest which experiments to run next. It shortens the path to a target by making each experiment more informative. It does not remove the need to make and test the formulation.

### How much data does AI formulation need?

Less than people expect for search, and more for prediction. Searching the archive is useful from day one. Property models and optimisation need a few dozen well-recorded experiments in a given family to beat a chemist’s intuition, and they improve with each round. We check your data on a sample before promising anything.

### Can AI formulate cosmetics or personal care products?

The same method applies to cosmetic formulation, with extra constraints: ingredient restrictions under EU Cosmetics Regulation 1223/2009, stability and preservation requirements and claims substantiation. The system can filter and suggest within those rules. The safety assessment and product information file remain the responsible person’s.

Keep reading

- [Industry AI for Chemicals](https://qquantum.ai/solutions/chemicals-and-materials)
- [Use case Materials Discovery](https://qquantum.ai/solutions/chemicals-and-materials/materials-discovery)
- [Service Predictive Analytics](https://qquantum.ai/algorithmic-marketing/predictive-analytics)
- [Technology Choosing a Vector Database](https://qquantum.ai/technology/vector-databases)
