Skip to content

Lucid

Commercial protein synthesis has become significantly more accessible and affordable in recent years, expanding the number of providers and lowering the cost of custom protein orders.

Core trick

Each order passes BLAST similarity, InterProScan motif, and Foldseek structure checks, so sequences that diverged from known threats can still be flagged.

Tags

Description

Commercial protein synthesis has become significantly more accessible and affordable in recent years, expanding the number of providers and lowering the cost of custom protein orders. This accessibility has prompted regulatory attention: a 2024 executive order requires federally funded researchers to purchase synthetic nucleic acids and proteins only from providers adhering to established screening frameworks, and additional legislation is currently moving through the Senate to broaden these requirements. Current screening infrastructure predominantly relies on sequence similarity search (BLAST) against databases of known pathogens and select agents. This approach has documented limitations. Sequences that have been redesigned to preserve function while reducing similarity to known threats can fall below detection thresholds. Split-order attacks, in which individually innocuous fragments are ordered separately and assembled post-delivery, are not addressed by per-order screening in isolation. Lucid is a screening tool that applies multiple analysis layers to incoming synthesis orders. Given a protein sequence, it performs sequence similarity search against pathogen and toxin databases, functional domain annotation via InterProScan to identify threat-associated motifs independent of overall sequence identity, and structural homology search via Foldseek to detect conserved folds in sequences that have diverged beyond recognition by the other two methods. Each layer's output informs whether the next layer is invoked, following an escalation model where computationally cheaper checks run first and more intensive analysis is triggered only when earlier results are ambiguous. In addition to whole-sequence analysis, Lucid decomposes each order into its constituent protein domains, screens them individually, and evaluates the combination for synergistic risk. This addresses the split-order problem by assessing whether components that pass screening in isolation could constitute a threat when assembled. The output is a structured risk assessment that includes per-layer findings, an overall risk classification, reasoning traces, and recommended actions. Lucid is deployed as a single API endpoint, accepting a sequence and returning a report, intended to integrate into existing order intake systems at synthesis providers with minimal implementation overhead.
Aarjav0210/lucid★ 11 forksTypeScriptCreated Mar 21, 2026 · last push Apr 27, 2026

README excerpt

# Lucid

**Automated biosecurity screening for the protein synthesis industry.**

---

## The Problem

The commercial protein synthesis industry is facing a new era of regulatory scrutiny. The 2024 Executive Order on Safe, Secure, and Trustworthy AI directed federal agencies to establish standards for nucleic acid synthesis screening — and the practical burden of compliance falls on synthesis providers who must verify that every incoming order is safe before it ships.

Today, most providers rely on BLAST-based sequence homology screening: compare the order against a database of known threats and flag anything that looks too similar. This worked when the threat landscape was limited to naturally occurring pathogens. It no longer does.

Modern AI protein design tools — ProteinMPNN, RFdiffusion, EvoDiff — can generate sequences that preserve the three-dimensional fold and biological function of a dangerous protein while reducing sequence identity far below BLAST detection thresholds. A redesigned toxin catalytic domain at 25% sequence identity passes BLAST without a second glance, but it folds into the same lethal structure.

Worse, chimeric sequences can split a dangerous function across individually benign domains. A cell-binding lectin domain fused to a ribosome-inactivating enzyme domain produces a functional toxin delivery system — but each domain in isolation is unremarkable. Full-sequence BLAST dilutes the signal from any single dangerous component because the benign doma

Team