Botanical ingredients from TCM, Ayurveda, and traditional food systems carry centuries of empirical use. We produce the molecular science that explains why they work.
Traditional medicine systems have documented the effects of botanical ingredients for thousands of years. Computational food science is how we begin to understand why, at the level of molecular interaction.
Luminae Research is a boutique computational food science consultancy. We screen botanical ingredients from TCM, Ayurveda, and other traditional health systems across a 7-receptor female hormone panel, producing structured binding intelligence and quantified evidence for wellness brands, ingredient developers, and R&D teams. All findings, regardless of signal strength, are reported and published. The dataset grows with every engagement.
Early access to our ingredient screens as we produce them, input into which ingredients we prioritize next, and first-look on findings before they enter the public dataset. Suited to teams who want ongoing visibility into emerging botanical evidence.
A full computational screen of a specific ingredient or ingredient panel across all 7 receptors, with confidence intervals, Monte Carlo coverage simulation, sensitivity analysis, and a formulation shortlist. All findings reported, regardless of signal direction.
Bring a biological question rather than a named ingredient. We identify which botanicals in our growing dataset most plausibly address your target receptor profile, and screen novel candidates if needed. Suited to early-stage formulation decisions.
We ask a precise question for each ingredient: do its bioactive compounds physically fit the relevant hormone receptor in a way that predicts meaningful interaction, and with what probability? The pipeline is four steps, fully quantified at each stage.
| Compound | Receptor | ΔG | Signal |
|---|---|---|---|
| Quercetin | ERβ | −8.4 | Strong |
| Rutin | ERβ | −7.9 | Strong |
| Betulinic acid | ERα | −7.4 | Moderate |
| Oleanolic acid | ERβ | −6.8 | Moderate |
| Coclaurine | ERα | −6.5 | Moderate |
| Spinosin | ERβ | −6.1 | Moderate |
| Compound | Receptor | ΔG | Confidence |
|---|---|---|---|
| Quercetin | ERβ | −8.4 | 0.89 |
| Coclaurine | ERα | −6.5 | 0.92 |
| Rutin | ERβ | −7.9 | 0.84 |
Binding energy (ΔG) quantifies how favorably a botanical compound fits a hormone receptor's active site. The more negative the value, the more thermodynamically favorable the interaction.
A compound at ΔG of -9 kcal/mol binds roughly an order of magnitude more tightly than one at -7. Paired with a structural confidence score, it distinguishes predictions with strong geometric support from those requiring further investigation.
For most botanical ingredients, no binding data of any kind exists across the female hormone receptor panel. A weak score is still the first quantified number in a previously empty field. That is what makes the dataset novel, and what makes every result reportable regardless of direction.
Developing hormone-health or adaptogenic formulations and wanting structured molecular research on botanical ingredients, grounded in both traditional use and quantified computational evidence across the full receptor panel.
Working with botanicals from TCM or Ayurveda and wanting a rigorous mechanistic picture of how their bioactive compounds may interact with female hormone receptors, reported fully regardless of what the data shows.
Starting from a biological problem rather than a named ingredient, and wanting to query a growing dataset of screened botanicals to identify which candidates have the most plausible mechanistic profile for your target.
A boutique computational food science consultancy at the intersection of quantitative methods, pharma-grade molecular modeling, and female hormone biology.
Luminae Research applies the predictive modeling techniques of pharmaceutical drug discovery to botanical and food ingredients with deep roots in traditional medicine. Where TCM, Ayurveda, and other systems have documented effects empirically over centuries, computational food science offers a molecular lens for understanding why.
Our methodology draws from quantitative finance and pharmaceutical research, applying probabilistic risk frameworks to ingredient decisions. Every engagement is built around transparent methodology and explicitly quantified uncertainty so your team knows exactly what the data supports.
Tell us your ingredient focus or biological question and we will send a sample showing the depth and format of what you would receive. We will also indicate which service tier fits your situation best.
