How to use DeepSig Signal Peptide Prediction Online

Use DeepSig to predict signal peptides and their cleavage sites from protein sequences.

DeepSig uses organism-specific ensembles to detect N-terminal signal peptides and predict cleavage sites. It classifies each sequence as Signal Peptide, Transmembrane, or Other and reports class probabilities, cleavage coordinates, and predicted mature sequences. Use it to investigate secretion signals and compare protein constructs. Transmembrane classification is an N-terminal classification; it is not a whole-protein topology map.

How DeepSig Signal Peptide Prediction Works

Submit Input Sequences and select Organism. Supply the native N terminus; fragments missing it cannot recover the original secretion signal. All inputs must belong to the selected organism group. DeepSig analyzes the first 96 residues and pads shorter inputs. U is encoded as C; X contributes an unknown-residue vector.

The signal-peptide call uses the published group-specific thresholds: 0.725 for eukaryotes, 0.72 for Gram-positive bacteria, and 0.7575 for Gram-negative bacteria. If the signal threshold is not reached, Transmembrane is selected when its ensemble probability is at least the Other probability; otherwise Other is selected. Prediction Confidence equals the signal probability for signal-positive inputs and the selected class probability renormalized over Transmembrane and Other for signal-negative inputs. Raw three-class probabilities are also exported.

Cleavage After Position is one-based and identifies the final residue of the signal peptide. Cleavage decoding runs only for signal-positive inputs. The residue plot reports the fraction of 20 cleavage models assigning a residue to the signal peptide; this is an ensemble vote fraction, not a calibrated cleavage probability. A residue is included when at least 10 models vote for it. Predicted mature sequences begin at the next residue. A cleavage outside a short input is reported as unresolved, with no mature sequence exported.

Download predictions.csv, cleavage_votes.csv, and mature_sequences.fasta. The FASTA contains only resolved signal-positive mature sequences and can be empty. No predicted signal peptides yields a header-only cleavage-vote CSV. Predictions support experimental prioritization and do not establish secretion efficiency or experimental cleavage.

What is Neurosnap?

Neurosnap is the leading platform for bioinformatics and computational science focused on expanding access to powerful modeling and simulation tools. Because many state-of-the-art machine learning systems remain complex to install, configure, and scale, Neurosnap offers a clean, browser-based workspace that removes the burden of infrastructure management, dependency conflicts, and command-line tooling.

Built for biologists, chemists, and cross-disciplinary scientists, the platform enables advanced computational workflows without requiring expertise in software engineering or cloud architecture. Researchers can launch analyses through an intuitive interface, connect programmatically through a comprehensive API, and rely on automated resource management to scale workloads efficiently. By taking care of the underlying compute and operational complexity, Neurosnap allows teams to devote their energy to scientific progress and faster iteration. Security and data protection remain foundational principles, with clear safeguards outlined in our Terms of Use and Privacy Policy to ensure your work stays protected.

Advancing Discovery with DeepSig Signal Peptide Prediction on Neurosnap

Using DeepSig Signal Peptide Prediction on Neurosnap could drastically accelerate organism-specific secretion-signal screening from protein sequences.

Compare up to 100 named protein sequences per job.
Distinguish signal-peptide predictions from N-terminal transmembrane features.
Inspect cleavage ensemble votes and download predicted mature sequences.

How to Use DeepSig Signal Peptide Prediction on Neurosnap

To harness the capabilities of DeepSig Signal Peptide Prediction, researchers can follow this streamlined workflow within Neurosnap:

Access Neurosnap: Start by logging in to the Neurosnap website.
Select Tool: From the list of available tools, choose DeepSig Signal Peptide Prediction.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the DeepSig Signal Peptide Prediction job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
Review Output: Explore your results through rich visualizations, including figures, plots, and interactive views designed to help you analyze findings with clarity and confidence.

Citations

Please cite the original work when using DeepSig Signal Peptide Prediction in publications or research outputs.

Savojardo C, Martelli PL, Fariselli P, Casadio R. DeepSig: deep learning improves signal peptide detection in proteins. Bioinformatics 34(10), 1690–1696 (2018). https://doi.org/10.1093/bioinformatics/btx818.

Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/

Similar Services

Explore related tools that support similar research workflows:

TSignal Signal Peptide Prediction

USPNet Signal Peptide Prediction

USPNet-fast Signal Peptide Prediction

In Silico Digestion | Pyteomics

Proudly supporting 50,000+ scientists worldwide, including 7,000+ leading biotech and global biopharma organizations.