4/1/2026
Today, we’re announcing the Tamarind Bio Assay Portal.
We’ve partnered with A-Alpha Bio, Adaptyv, and Ginkgo Bioworks to bring protein and antibody assays directly into Tamarind, making it much easier for scientists to move from computational design to real experimental feedback.
This is an important step in how we think molecular design software should work. In practice, protein design is not bottlenecked by idea generation alone. It is bottlenecked by how quickly teams can validate those ideas, learn from the results, and run the next iteration. In other words, the real bottleneck is no longer just generating candidates. It is turning experimental results into a usable feedback loop.
The Tamarind Bio Assay Portal brings assay ordering and assay-driven iteration directly into Tamarind. We’re starting with a set of workhorse experiments that are central to protein and antibody engineering, including:
protein-protein binding affinity characterization
developability
expression
stability
The Assay Portal helps scientists:
Get fast, low-friction, cost-effective validation of designed proteins and antibodies, transparent pricing without needing separate MSAs
Specialize models on their own experimental data for affinity maturation, developability, and property optimization
Run lab-in-the-loop campaigns where each assay result improves the next design cycle
Turn wet lab data into model training infrastructure, including RL environments and large-scale datasets for pretraining
The process is simple, you generate new designs on Tamarind, rank them with the in silico scoring tools if needed, then simply press a button to validate your results for 100+ protein sequences.
Lab-in-the-loop protocols like NOS, MULTI-evolve, AlphaBind can take a relatively small amount of data for tasks like affinity maturation. Each of these publications show much stronger improvements over applying the base version of a given protocol. We believe the highest performing AI systems will be adapted to assay results, and the specific optimization criteria of the organizations deploying. Each round of optimization can now be done end to end on Tamarind.
We’ve selected our first set of partners due to the unique offerings of their platforms: A-Alpha for supporting massive throughput (up to millions of sequences) affordably, Adaptyv for diverse array of assays supporting both smaller and larger scales, Ginkgo for the breadth of developability and binding assays they offer.
Get in touch for access: info@tamarind.bio