{"id":128639,"title":"Orikata Bio + Megure Labs, learning from evolution and mastering the art of folding proteins","tagline":"A multiplayer discovery workspace for human and agentic scientists","body":"<https://www.youtube.com/watch?v=UvAccQQgqMg>\n\n**TL;DR:** We're building a world model for biology and the tools that both human and agentic scientists need to use it: biological data, SOTA sequence and structure search, clustering, and alignment, optimized AI4Science model inference, and a shared discovery workbench. Today we're launching Umi and Sora, the Orikata web toolkit, and hosted model inference with Noto, alongside the open-source release of Hikoboshi and Orihime. The full Noto discovery workbench follows in mid-November.\n\nFor Umi and Sora access, email [info@orikata.ai](mailto:info@orikata.ai). The public search demo currently covers TEDBench.\n\nHey everyone! I'm Casey, founder of Orikata Bio PBC, the company behind Orikata Bio and Megure Labs. At Orikata, we're building Ibuki, a world model for biology that learns from evolution itself to help scientists understand and engineer biology. Our first focus is mastering the art of folding proteins.\n\nAt Megure, we're building the scientific software to train and run those models, and Noto, a shared multiplayer discovery workbench for human and agentic scientists.\n\nI'm a former MD/PhD student at UPenn. As an undergraduate at Berkeley, I was jointly advised by Matt Francis and Jennifer Doudna, one of the 2020 Nobel Prize in Chemistry laureates; that work led to a first-author JACS paper, two additional publications, and a co-invented patent underlying Catena Bio (YC S21). I later pursued a fully supported MPhil at the University of Cambridge, where I initiated a collaboration between my Cambridge supervisors and David Baker, 2024 Nobel Laureate also in Chemistry. That collaboration later became part of Archon Bio. I'm also first author of an ICML 2026 paper, and a coauthor of a 2026 Nature Biotechnology paper on AI-guided in-silico evolution. My work has taken me from wet-lab biochemistry to machine learning and the systems needed to run it efficiently.\n\nBuilding those models meant solving many problems underneath them first.\n\nWe needed data to learn from, tools to find, organize, and compare the relevant biology, and software that could run the whole thing efficiently. And scientists, both agentic and human, need somewhere to work with those results. These are the pieces we're bringing together across Orikata Bio and Megure Labs.\n\n**What has evolution already tried?** Evolution has spent billions of years exploring ways to build living systems. The sequences, structures, and other forms of biological data we collect are a record of that exploration. If we can learn how they relate, we can use that context to understand what exists and design what comes next.\n\nWe started by assembling Umi, with **over 100 billion unique protein sequences**, and Sora, with **nearly 2 billion predicted and experimental protein structures**. Umi brings together more than 340 billion raw sequence records before deduplication. That's larger than the datasets used to train leading protein models, and on par with today's largest assembled sequence collections.\n\nWe built these collections by bringing together biological data scattered across public repositories, legacy tape archives and old servers. Recovering the files was only the beginning. We converted, normalized, deduplicated, and stored those records in an efficient format so many scientists and agents can work with the same collection at once.\n\nHaving all that data raises the next question: **how do you search through it?**\n\nThe tools scientists use to discover and compare genes and proteins were built for much smaller databases. Search, clustering, and alignment supply the biological context for structure-prediction models, generative-design models, and, increasingly, agentic discovery pipelines. Those steps matter during training and inference, and they are becoming the bottleneck.\n\nLooking at how those tools compare proteins, we realized that the fixed substitution matrices used by classical sequence-alignment tools are secretly just the simplest possible example of a neural network. They assign a fixed score to each pair of amino acids, scoring how similar the two amino acid tokens are, wherever those amino acids appear in a sequence.\n\n**What if we replaced that fixed matrix with a contextual substitution operator: a neural network that learns how to compare positions using their sequence, structure, or both?**\n\nClassical alignment can also be understood as **structured cross-attention**. It finds and highlights corresponding positions across related sequences. Across many proteins, those correspondences form multiple sequence alignments, or MSAs, the evolutionary context used by AlphaFold and other similar biological ML models.\n\nThat gives us a different learning objective: **predict which positions correspond**. We can train on known alignments, learn directly from structure through geometric self-supervision, or combine the two depending on what's available. We can also learn from alignment examples from proteins that have no structures.\n\nTo train through those calculations, we built Orihime, our GPU-backed structured-attention and differentiable-alignment library at Megure Labs. Orihime lets us train the models through the alignment calculation itself, with CPU, CUDA, and HIP implementations. The research behind it is described in our first-author ICML 2026 paper.\n\nAt Orikata, we used those learned comparisons to build Hikoboshi, our neural-network bioinformatics suite. We're releasing tools for:\n\n* Pairwise, all-versus-all, and multiple alignment of sequences and structures.\n* Clustering proteins by sequence or learned similarity.\n* Natively multimodal protein sequence and structure search.\n* Building evolutionary trees.\n* Reconstructing ancestral states.\n* Estimating evolutionary rates.\n\nThe alignment tools accept sequences, structures, or both, and run locally on CPU. With sequence input, our models recover structural relationships without requiring an input structure. With structure input, our alignments reach TMalign-level full-protein geometric quality.\n\nLDDT measures structural agreement, and F1 measures how well we recover corresponding positions. Both range from 0 to 1, with 1 the maximum.\n\nOn the SABmark twilight benchmark, sequence-only Hikoboshi delivers **62% higher full-protein LDDT than MAFFT and 48% higher than MUSCLE5** for pairwise alignment. For multiple sequence alignment on the same benchmark, the gains are **57% and 50%, respectively**.\n\nWith structures on BaliFam1000, our self-supervised geometric-consistency model reaches **full-protein LDDT 0.785 versus the recently released LoL-Align's 0.777**, and **F1 0.95 versus 0.94**. On AFDBv4, our structure-assisted multiple sequence alignments reach **full-protein LDDT 0.62 against FoldMason's 0.54**.\n\nEmail [info@orikata.ai](mailto:info@orikata.ai) for the full benchmark results.\n\nThe Orikata web toolkit brings these workflows into your browser. Run analyses on your own data, compare our methods with established tools, and inspect the sequences, structures, and results together in one workspace.\n\nTo find relevant biology in these collections, we're extending Hikoboshi with vector search. We retain one learned vector per residue for alignment and project those representations into compact protein vectors for candidate search. That lets us use approximate nearest-neighbor (ANN) vector search to retrieve candidates before comparing them in detail.\n\nUsing precomputed representations for 462K proteins, ANN candidate search on a single CPU core was **500 times faster than Foldseek's prefilter**, with an index **over an order of magnitude smaller**. The compact vectors retain biological similarity for protein search. You can try out the search function over the TEDBench dataset today, with larger datasets coming soon.\n\nThose search and alignment models are part of the foundation we're building for **Ibuki**, the 'breath of life,' our world-model family for biology. We want it to learn across the breadth of life: how sequence, structure, and function relate, and how to use those relationships to understand and engineer biology. **That connects folding, inverse folding, and generative design with multimodal search, clustering, alignment, ancestral sequence and structure reconstruction, evolutionary rate prediction, conservation, and phylogenetic tree building.** The tools find evolutionary context, the models use it to predict and design, and better representations improve the tools in turn.\n\nWe're pre-training then fine-tuning our own models to use alongside the ESM- and ProteinMPNN-based models in today's Hikoboshi release. Ibuki-based workflow models are trained but not part of this initial release. Our goal is to connect what the family learns about sequence, structure, and evolution with the workflows scientists use to understand and engineer biology.\n\nAt Megure Labs, we're building Hataya around a simple idea: **AI models should ship as software**. Hataya is an inference engine that compiles models and their dependencies into optimized standalone programs for CPUs and GPUs. We're building it to run Hikoboshi and Ibuki alongside public scientific ML models.\n\nThe code that runs, the exact weights, and the evidence comparing its outputs with the original model ship together in a .hya model package. Scientists can inspect what ran, check the results, and run the model on their own hardware or through a hosted service.\n\n**AI should be reproducible. AI should be verifiable. AI should be yours.**\n\nScientists and their agents also need a place to run the models and work with their results. We're launching Noto with hosted model inference, so you can run biological AI models without setting up the models and compute yourself.\n\nThe full **Noto** discovery workbench follows in **mid-November**, bringing **human and agentic scientists** into the same **multiplayer workspace**. Plan an experiment, work with its generated data, run an analysis or model, maybe even train a new model, and keep all the results in the notebook. The inputs, methods, and results stay connected across local and hosted compute, so both human and agentic scientists can see how a result was produced and build on it.\n\nWe call it a discovery workbench because we're building it for human and agentic scientists to work together as peers. Both can plan experiments, run analyses and models, and build on each other's work in the same shared notebook. We're starting with biology and building toward other areas of research.\n\n**Here's what we're launching today:**\n\n* **Umi and Sora**, our curated sequence and structure databases.\n* **The Orikata toolkit** for sequence, structure, and evolutionary analysis on the web.\n* **Noto inference** for running biological AI models.\n* **Hikoboshi**, our neural-network bioinformatics toolkit, and **Orihime**, our differentiable-alignment library, as open source.\n\n**Hosted inference and agentic workflows are online now in Noto, with 45+ models and tools in addition to the Hikoboshi toolkit. The agentic Noto discovery workbench launches in mid-November, with new features added daily. You can use Noto on the web now. A desktop app is coming soon, with native iOS and Android support planned for early 2027.**\n\nOur curated corpora, precomputed representations, indexes, and hosted infrastructure are paid-access offerings. We offer individual and team plans and metered API usage. We're expanding web, API, and MCP access for scientists and their agents.\n\nIf you're doing protein engineering, biological ML, or agentic discovery, try the Orikata toolkit, run a model with Noto, or build with the open-source tools. We'd love to hear what you're working on. If you know a research group or biotech team that would find this useful, I'd love an introduction. For Umi and Sora access or the full Noto workbench, **reply here or email [info@orikata.ai](mailto:info@orikata.ai)**.\n\nWe're strong believers in open science, and we hope you'll build the future of biology with us.\n\nOrikata Bio: [https://orikata.ai](https://orikata.ai/)\\\nMegure Labs: [https://megure.ai](https://megure.ai/)\\\nUmi: [https://orikata.ai/umi](https://orikata.ai/umi/) \\\nSora: [https://orikata.ai/sora](https://orikata.ai/sora/) \\\nOrikata toolkit: [https://orikata.ai/tools](https://orikata.ai/tools/) \\\nHikoboshi: <https://github.com/orikata-bio/hikoboshi> \\\nOrihime: <https://github.com/megure-labs/orihime> \\\nIbuki: [https://orikata.ai/ibuki](https://orikata.ai/ibuki/)\\\nNoto: [https://megure.ai/noto](https://megure.ai/noto/)","slug":"XSp-orikata-bio-megure-labs-learning-from-evolution-and-mastering-the-art-of-folding-proteins","created_at":"2026-11-12T22:51:19.219Z","updated_at":"2026-11-18T10:15:26.222Z","total_vote_count":4,"url":"https://www.ycombinator.com/launches/XSp-orikata-bio-megure-labs-learning-from-evolution-and-mastering-the-art-of-folding-proteins","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":32126,"name":"Orikata Bio PBC","slug":"orikata-bio-pbc","url":"https://orikata.ai","logo":"https://bookface-images.s3.amazonaws.com/small_logos/9bb8600184285ab1a6b407bed29e46c143375796.png","batch":"Fall 2026","industry":"B2B","tags":["Machine Learning","SaaS","Enterprise Software","AI"],"search_path":"https://bookface.ycombinator.com/company/32126"}}