SI-Ready Data for Engineering Biology: Technical Standards and Quality for Accelerating Discovery and Innovation
October 2026 - January 2027 | Virtual & In-person
EBRC aims to accelerate applications of super/artificial intelligence (SI/AI) and machine learning (ML) methods towards engineering biology challenges by convening stakeholder workshops focused on developing standards for SI-ready biodata. Initial workshops will focus specifically on standards for protein sequence-function data to advance fields like precision medicine, biomanufacturing, and drug development.
About
Recent innovation in engineering biology has been driven by advances in biological SI/AI models that synthesize large amounts of data to identify emergent trends and enable novel discoveries. Beyond simply increasing the volume of biological data (biodata) available to train new SI/AI models, the crucial next step is the creation of SI-ready datasets that are standardized, well-annotated, and optimally formatted for advanced model training. However, the definition of SI-ready biodata, the parameters that define it, and the best practices for constructing such datasets are not yet established and vary across stakeholders and experts. Resolving these challenges will require building community consensus through structured stakeholder engagement, providing the critical foundation for future coordination, data standardization, and best practices development.
EBRC, in collaboration with members of NIST’s Cellular Engineering Group, are organizing a two-day in-person workshop on January 28–29th, 2027 at the Johns Hopkins Bloomberg Center in Washington, D.C. that will be focused on building a diverse community of stakeholders that will be organized to produce best practices and frameworks for protein sequence-function data standardization for improving SI-readiness. Leading up to the in-person event, three virtual meetings will be held to identify priority topic areas, opportunities, and challenges for meeting our goals. Over the course of several weeks, these meetings will ensure that a strong foundational framework for SI-ready data standards and critical challenge areas are identified. Building off of this initial work, EBRC and our NIST co-hosts will facilitate effective exchange of ideas and perspectives at the in-person meeting through a mixture of expert presentations, panels, and breakout sessions. EBRC staff and collaborators will develop freely-accessible published reports and engage with data generators, curators, and policymakers to disseminate our findings.
Registration for the in-person meeting is now open (link below). Please also use the form to express your interest in the virtual meetings or email sebastian@ebrc.org.
Upcoming Events
Virtual Meeting 1: Oct. 15, 2026 10 am – 12 pm PDT | 1 – 3 pm EDT
This first virtual meeting in the “SI-Ready Data for Engineering Biology: Technical Standards and Quality for Accelerating Discovery and Innovation” workshop series aims to establish the background needs and goals for this series and begin to identify priority discussion areas for subsequent virtual meetings and ultimately the final in-person workshop. Please RSVP below for the Zoom link and calendar invitation.
RSVP here
Virtual Meeting 2: TBA
Description coming soon!
Virtual Meeting 3: TBA
Description coming soon!
In-person Meeting: Jan. 28th–29th, 2027 at Johns Hopkins Bloomberg Center in Washington, D.C.
Drawing on findings and insights from the previous virtual meetings, this two day, in-person workshop will focus on the key topics and challenges surrounding SI-readiness. Sessions will likely address: data management, curation, provenance, quality and uncertainty metrics, and feature selection, for their downstream usefulness in training SI/AI models, as well as considerations for implementation and standardization. The meeting will feature talks and panels from invited experts, as well as opportunities for small group collaboration and dialogues.
Register here