Tokyo Tech Talks #6: AI in the Lab
Join us on July 28, 2026 at Build+ in Ebisu for an evening on AI in the lab — from scattered evidence to better experiments.
We’re excited to announce Tokyo Tech Talks #6.
Last time, we asked where the human belongs when software can act on its own. This time, we are moving into the lab: a domain where AI has to connect back to experiments, evidence, protocols, instruments, and physical work. The theme for this event is AI in the Lab.
The specific focus is agentic AI for wet-lab work: from scattered evidence to better experiments.
Event Details
- Date: Tuesday, July 28, 2026
- Time: 7:00 PM - 9:00 PM JST
- Location: Build+, 6F, MARIX Ebisu Bldg., 4-4-6 Ebisu, Shibuya, Tokyo
- View on Google Maps
Schedule
- 7:00 PM - 8:00 PM: Talks — Short presentations on AI systems for lab discovery, automation, scripting, and documentation
- 8:00 PM - 9:00 PM: Drinks & Networking
The Theme: AI in the Lab
In biology, important discoveries are rarely isolated facts. They often emerge from connections between genes, proteins, pathways, experiments, and prior observations. Interaction maps help researchers organize those connections, but the evidence needed to build them is often scattered across papers, databases, and underused sources such as non-English theses that conventional search can miss.
The future lab will need more than better search. As software and hardware become more connected, labs will need systems that turn scattered evidence into action: candidate prioritization, assay suggestions, validation plans, plate layouts, labels, user scripting in Python and KS, and rich documentation that captures work as it happens.
Using influenza research as a case study, we will introduce LabNexus, a prototype platform for AI-assisted wet-lab work built around modular LNApps. One example is Discovery, an LNApp that helps retrieve, translate, parse, and connect fragmented scientific evidence into traceable interaction maps and ranked candidate cards for downstream experiments.
The goal is practical: help researchers understand what is already known, decide what is worth testing next, and turn scattered knowledge into better wet-lab experiments.
What We’ll Explore
This event brings together people thinking about agentic systems that do not stop at answering questions. They help prepare the next experiment.
From Scattered Evidence to Traceable Maps
Scientific evidence is distributed across languages, formats, databases, papers, and local knowledge. We’ll look at how retrieval, translation, parsing, and citation tracking can work together so interaction maps remain useful, inspectable, and grounded.
Agents That Move Toward Experiments
The interesting step is not only finding a paper. It is deciding what should happen next. We’ll explore how agentic tools can help rank candidates, suggest assays, draft validation plans, and make downstream wet-lab work easier to reason about.
Automation, Scripting, and Documentation in One Loop
Wet-lab work produces protocols, plate layouts, labels, instrument settings, notes, and decisions. We’ll discuss what changes when those pieces are connected in a system that can script actions, assist documentation, and preserve context as work unfolds.
KS for Scientific Scripting
KS is a new STEM-oriented language designed for scripting apps such as LabNexus LNApps. It combines optional typing with type inference, language blocks for domain-specific languages, built-in units of measure, runtime parameter constraints, and readable syntax inspired by Kotlin, Swift, Python, C#, and F#.
Who Should Attend
- Researchers and lab scientists interested in AI-assisted discovery and experimental planning
- Computational biologists and bioinformaticians working with fragmented evidence, interaction maps, or candidate prioritization
- Engineers and developers building agents, lab automation tools, scientific scripting systems, or research software
- Anyone curious about what happens when agentic AI meets physical scientific work
Join Us
If you’re interested in attending, register here.
Come spend an evening with people thinking seriously about how AI systems can help labs move from scattered evidence to better experiments. The talks will be short, the demos concrete, and the conversation open-ended.