LLM-bioseq-probe
LLM-bioseq-probe is a datasets & benchmarks tool whose code is published by XinmingTu on GitHub, first public in 2026. API-based probe for protein and DNA sequences in LLM training data: next-amino-acid accuracy on 668 little-studied DUF-family proteins versus residue-shuffled controls, with test sets, all replies and a CLI.
| Category | Datasets & benchmarks |
|---|---|
| Developer (GitHub) | XinmingTu |
| Website | xinmingtu.cn/blog/2026/claude-opus-5-5-protein-sequences |
| GitHub | XinmingTu/LLM-bioseq-probe |
| Released | 2026-11-17 (source) |
| Code license | MIT |
| Weights license | no model weights involved |
| What this allows | Permissive (commercial OK) Use, modify and ship it inside closed-source commercial products; keep the license text and copyright notices. What do these mean? |
| License source | raw.githubusercontent.com/XinmingTu/LLM-bioseq-probe/main/LICENSE · checked 2026-11-18 |
| Pricing | Open source |
| Tags | #benchmark#protein-language-models#llm-evaluation#training-data#dna |
| Last checked | · links verified |
Can I use LLM-bioseq-probe commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: MIT
- Weights: no model weights involved
- Source: raw.githubusercontent.com/XinmingTu/LLM-bioseq-probe/main/LICENSE · license checked 2026-11-18
What the license types mean · not legal advice.
Specs
| Size | 668 proteins from 167 DUF Pfam families (5 cuts each, 6,680 questions with shuffled controls); 257 families in the extended family-size set |
|---|---|
| Modality | — |
| Access | GitHub repo (TSV test sets, gzipped JSONL replies); probe-model CLI for Anthropic, OpenAI, Gemini, Fireworks APIs |
| GitHub stars | 9 |
| Interface | — |
Compare with…
Pick 1–3 other Datasets & benchmarks tools to compare side by side with LLM-bioseq-probe.
Related
Meta FAIR's open dataset of DFT calculations on diverse molecules, with evaluations and baseline models.
ML-ready datasets and benchmarks for therapeutics.
Benchmarks for protein fitness and mutation effect prediction.