Bota Biosciences Releases BPL, a Compiler-Verified Protocol Language for AI-Driven Biomanufacturing
SAN FRANCISCO and HANGZHOU, China, June 23, 2026 /PRNewswire/ -- Bota Biosciences ("Bota"), a Physical AI biomanufacturing company, announced the release of the Biology Protocol Language (BPL) and its generation pipeline, BPL-COGEN, on bioRxiv. The announcement coincides with Bota's selection for the World Economic Forum's MINDS program 2026, which recognizes the company for its work in Physical AI-driven biomanufacturing on the WEF's global roster of validated industrial AI deployments.
Biological protocols today still rely on natural language — instructions like "resuspend in an appropriate volume" leave concentration, duration, and technique unstated. A 2016 survey of 1,576 researchers found more than 70% had failed to reproduce another scientist's experiments. Semiconductor design resolved an analogous problem through Verilog and VHDL; software engineering through typed, compiler-verified languages. Biology has lacked an equivalent — and that absence is now the rate-limiting step between AI-driven experimental design and reproducible physical execution.
BPL introduces a biology-native type system in which every quantity carries physical units, every reagent declares its physical form, and every container maintains compiler-tracked state — rejecting physically impossible operations before any experiment begins. BPL-COGEN automates the translation from natural-language SOPs to verified BPL code via a generate–validate–repair loop, coupling a fine-tuned 30-billion-parameter language model with a deterministic compiler. Evaluated against 300 published Nature Protocols papers, the system achieved 95.1% first-pass consistency, advancing to 98.6% after two rounds of compiler-simulation feedback. Cross-platform validation confirmed reproducible execution across manual and automated contexts. Source code is available on GitLab under the MIT License.
As the execution layer of Bota's world-leading Physical AI-driven biofoundry platform SAION AI, BPL translates AI-generated experimental intent into precise, verifiable machine instructions. With the global biomanufacturing market projected to reach $6 trillion by 2035, formal protocol standards may prove as foundational to this industry as compiler infrastructure was to semiconductors and software. BPL represents a step toward a different vision of AI for science: not AI assisting scientists, but AI closing the loop between discovery and production, between experiment and market.
SOURCE Bota Biosciences
Share this article