May 4, 2026

BioWatch Brief: Rapid Pathogen Risk Assessment via Staged LLM Triage

David Nai, Kevin Fickert, Jessica Anderson

Biosecurity analysts face a growing asymmetry: outbreak reporting volume has expanded substantially while the number of trained personnel able to synthesise that information in real time has not. BioWatch Brief compresses the analyst intake stage from hours to minutes via a three-stage LLM pipeline (structured extraction, retrieval against a curated corpus of historical outbreaks and biosecurity policy frameworks, and grounded analysis), producing a structured risk card from arbitrary input reports. The architecture deliberately separates fact extraction from retrieval and synthesis, constraining LLM outputs at each stage and surfacing uncertainty rather than masking it. Built on gpt-4.1-mini with a curated 21-entry open corpus (16 historical outbreaks, 5 policy/framework documents) normalised across pathogen, location, transmission, response history, lessons learned, and source URLs. React frontend, FastAPI backend, single /analyze_report endpoint. Built at the Apart AIxBio Hackathon, April 2026 (University of Pennsylvania).

Review Project

View Related Sprint

Reviewer's Comments

The problem framing in your introduction is strong, the asymmetry between outbreak reports and analyst capacity is a real chokepoint. The architectural argument in your discussion, that structural fidelity has to be enforced rather than prompted for, is a good contribution worth exploring and developing further. I could see a lot of value in a tool like this existing.

The idea is sound, but the current implementation does have limitations. To your credit you identify and flag many of them in the limitations section. The RAG search is tied to key words, and the current corpus is small, so it limits the usefulness but does work for a demonstration for a hackathon. However, the full results are not provided anywhere and only one example is given.

Tying one of the categories to geography could be limiting as well. While some viral and bacterial families which can cause a PHEIC are geographically limited, others are not, influenza immediately springs to mind. Geographic anchoring also somewhat limits the effectiveness for bioweapons or engineered pandemics which could cause GCBRs and could, by design, be first unleashed anywhere. One could consider keeping the fields but weighing them differently in the scoring in some manner.

The scenario library described in the reports is author and crafted to match exactly what the tool needs, was used during development, and had no held-out set. Section 4 then reflects expected behavior on constructed examples, rather than evidence the system works on inputs it hasn't seen or might be messier. The line that uncertainty flags "correlated with the cases where ground-truth assessment was itself ambiguous to the human authors" is somewhat confusing, and essentially the authors agreeing with themselves.

The planning notes /doc on GitHub suggested running 10–15 archived ProMED alerts with documented outcomes as an eval. That would have been great and would have given you real evidence for the report. Even a smaller number, like five archived alerts with retrospective WHO classifications, would substantially strengthen this section and serve as stronger proof BioWatch Brief is behaving and functioning as intended.

The linked codebase is somewhat hard to follow compared to the submitted final write up. It looks like there are two distinct pipelines in it? Pipeline.py and main.py?

The first has the FastAPI backend using OpenAI's gpt-4.1-mini and seemss to match the staged pipeline described in your Methods section. It also has the keyword-scored retrieval over the fixed corpus and the grounded synthesis. The two LLM round trips. It is also named "main." I judged only on this one, as it seems to be the submission.

The second is using the Anthropic SDK and Claude Opus 4.5 with tool use and the output is quite different, but has no RAG/keyword based corpus retrieval. I am not scoring on this pipeline, as the paper seems to indicate the first, but the outputs here seem richer and more informative. So just a flag it could be good to build towards this more in-depth and informative outputs in the submitted, RAG + corpus grounded tool.

You also have code for a live signal assessment in the first / main pipeline but that does not seem to be implemented in any way with a way to get live signal, though the planning document has some ideas in it. Not judging on that, just flagging this is a good area to expand and work on if you continue with this tool.

A minor quibble but the write-up likely used some resources that are not cited. The mention of BlueDot and Metabiota sent me googling as I was curious if said BlueDot was related to BlueDot impact at all, and the first result in this paper https://pmc.ncbi.nlm.nih.gov/articles/PMC7378493/. Feel like this should have been cited in the report, which then makes me wonder if there are other missing citations. I am not saying there are, just it raises the spectre of it. You do also disclose the use of of LLMs for brainstorming, but the planning MD appears to be generated by Claude / Claude Code and I am sure it was after a lot of back and forth with user(s) but it is more a design spec than just a brainstorming doc. Which I think is fine, that's the way things work now, but maybe could have been disclosed differently. This is such a new area it is hard to say, so not scoring against this at all, just mentioning it.

Cite this work

@misc {

title={

(HckPrj) BioWatch Brief: Rapid Pathogen Risk Assessment via Staged LLM Triage

author={

David Nai, Kevin Fickert, Jessica Anderson

date={

5/4/26

organization={Apart Research},

note={Research submission to the research sprint hosted by Apart.},

howpublished={https://apartresearch.com}

}

Recent Projects

View All

Apr 27, 2026

OliGraph: graph-based screening of large oligopools

Existing synthesis screening tools cannot evaluate short oligonucleotide pools, whose overlapping fragments can be reassembled into regulated sequences via polymerase cycling assembly (PCA) yet fall below gene-length detection thresholds. We present OliGraph, an open-source tool that constructs a bi-directed overlap graph from an oligonucleotide pool and extracts contigs for downstream gene-length screening. An optional PCA mode retains only cross-strand overlaps consistent with PCA chemistry. We validated OliGraph in a blinded study across ten simulated pools (70–9,184 oligonucleotides, 30–300 bp) spanning four risk categories. BLAST screening of individual oligonucleotides failed to identify sequences of concern in most pools: three returned zero hits, and vector noise obscured true positives in the remainder. After OliGraph assembly, contig-level BLAST matched the longest assembled sequences (up to 1,905 bp) to sequences of concern at 97–100% identity. In one pool, assembly collapsed 1,634 individual BLAST results into 10 hits from a single contig, all assigned to the same source organism. PCA mode correctly distinguished assemblable from non-assemblable fragments within the same pool. Two pools with no assemblable structure yielded no contigs. OliGraph processed all pools in under 0.2 seconds, fast enough for real-time order screening and consistent with proposals to bring oligonucleotide orders within the scope of synthesis screening regulation.

Apr 27, 2026

BioRT-Bench: A Multi-Attack Red-Teaming Benchmark for Bio-Misuse Safeguards in Frontier LLMs

Frontier AI laboratories are expected to maintain safeguards against biological misuse, but whether deployed models actually refuse bio-misuse queries under adversarial pressure is largely unmeasured in the public literature. We introduce BioRT-Bench, a benchmark that runs four attack methods (direct request, PAIR, Crescendo, and base64 encoding) against four frontier models (Claude Sonnet 4.6, GPT-5.4, DeepSeek V4-flash, Kimi K2.5) across 40 prompts spanning five biosecurity-relevant categories. Responses are scored by a calibrated judge extending StrongREJECT with two bio-specific dimensions: specificity and actionability. We measure Attack Success Rate (ASR), where 0 means the model fully refused and 1 means it provided specific, actionable bio-misuse content. Our results reveal a sharp robustness divide: Chinese frontier models (DeepSeek, Kimi) have under 5% refusal rates even under direct request (ASR 0.88 and 0.79), while Western models (Claude, GPT) maintain substantially stronger safeguards (ASR 0.15 and 0.16). Crescendo is the most effective attack across all models, both in bypassing refusal and in eliciting actionable content. Claude Sonnet 4.6 is the most robust model tested, achieving 100% refusal against base64-encoded prompts.

Apr 27, 2026

PROTEUS (PROTein Evaluation for Unusual Sequences): Structure-Informed Safety Screening for de novo and Evasion-Prone Protein-Coding Sequences

AI protein design tools like RFdiffusion, ProteinMPNN, and Bindcraft make it trivial to produce low-homology sequences that fold into active, potentially hazardous architectures. However, sequence homology-based biosafety screening tools cannot detect proteins that pose functional risk through structurally novel mechanisms with no sequence precedent. We present a tiered computational pipeline that addresses this gap by combining MMseqs2 sequence alignment with structure-based comparison via FoldSeek and DALI against curated toxin databases totaling ~34,000 entries. AlphaFold2-predicted structures are screened for both global fold similarity (FoldSeek) and local active/allosteric site geometry (DALI), capturing convergent functional hazards that sequence screening misses. The pipeline was validated against a panel of toxins, benign proteins, structural mimics, and de novo-designed Munc13 binders, as well as modified ricin variants with residue substitutions. We additionally tested robustness to partial-synthesis evasion, where a bad actor submits multiple shorter coding sequences intended for downstream reassembly into a full toxin-coding gene. We found that while sequence-based screening did not identify any de novo ricin analogues with high certainty, the combined pipeline with FoldSeek and DALI identified all 24 tested de novo ricins as toxic.

Apr 27, 2026