Chemistry and materials discovery reframed as a constrained search: the Matflow Optimizer Core navigates the parameter space of compositions and conditions to propose novel, lab-ready candidates ranked by the objectives you choose.
Search strategies
Matflow Adaptive Search — surrogate-guided search that learns a response surface and exploits it iteratively.
Matflow Evolutionary Search — a genuine multi-objective genetic algorithm (population-evolution style) that maintains a diverse population of candidates.
Objectives and ranking
Set one or more objectives with weights (e.g. maximize conversion, minimize cost). Candidates are ranked by TOPSIS against your weights, and Pareto dominance is computed directly — the result is an actual trade-off front, not a single "best" answer.
Constraints
Compositional constraints — a set of columns that must sum to 100% (essential for mixture formulations).
Per-feature bounds — min/max allowed values for any input column.
Both are enforced during candidate generation, not filtered out afterward.
The output
A downloadable portfolio of ranked candidates with their input parameters and predicted performance. Load it into TEA or the lab — the report is designed to prioritize your next set of real experiments.