Edit · Readme ← View page Saving needs a token. Log in or register to get one. Edits are public and licensed CC-BY-SA-4.0. # SignalP 6.0 — Research Notes Research notes on **SignalP 6.0**, the DTU Health Tech tool that predicts signal peptides and their cleavage sites across all domains of life using a protein language model. Compiled 2026-07-14 from the DTU service page, the *Nature Biotechnology* paper, the PMC full text, and the `fteufel/signalp-6.0` repository. **Source clip in this vault:** [[2026-07-15_182916_serviceshealthtechdtudk_SignalP-6.0]] **Downloaded assets:** `papers/…SignalP-6.0_*.pdf`, `raw/…SignalP-6.0/` ## One-line summary SignalP 6.0 is the first tool that predicts **all five known signal-peptide types** in one model. It couples a 30-layer BERT protein language model (ProtBERT, pretrained on UniRef100) to a conditional random field (CRF) decoder that labels every residue, so it also returns the **cleavage site** and the **n-/h-/c-region** structure of the signal peptide. ## Contents | File | What's in it | |------|--------------| | [01-overview.md](01-overview.md) | What signal peptides are, the five types, why v6.0 matters | | [02-architecture.md](02-architecture.md) | Model architecture, training data, cross-validation | | [03-usage.md](03-usage.md) | Web server + standalone CLI: install, arguments, outputs | | [04-benchmarks-and-context.md](04-benchmarks-and-context.md) | Performance vs SignalP 5.0, limitations, related tools, references | | [05-build-notes.md](05-build-notes.md) | Result of cloning + building the GitHub repo (2026-07-14) | | [06-retraining-cost.md](06-retraining-cost.md) | What it would cost to remake the weights ourselves (fine-tune, not pretrain) | ## Fast facts - **Developers:** Teufel, Almagro Armenteros, Nielsen et al. — DTU Health Tech / Univ. of Copenhagen / Stockholm Univ. - **Paper:** *Nature Biotechnology* **40**(7):1023–1025 (2022). DOI [10.1038/s41587-021-01156-3](https://doi.org/10.1038/s41587-021-01156-3). Preprint: bioRxiv 2021.06.09.447770. - **Web server:** https://services.healthtech.dtu.dk/services/SignalP-6.0/ (free; ≤1000 proteins/job) - **Code:** https://github.com/fteufel/signalp-6.0 · **Mirror:** https://dtu.biolib.com/SignalP-6 - **License:** free for academic use; commercial use requires a license. - **Correspondence:** Henrik Nielsen (DTU Health Tech). Save Cancel Preview · live