Curated peptide knowledgebase

Pep2Net-DB

174,825 peptide records · 422,021 assay records · public database cross-references and literature · functional annotations · structure prediction & dataset export.

Scroll to browse

Statistics snapshot: · Version 20261118T130

Unique sequences
174,825
Assay records
422,021
Access
Search + Browse
Output
Predict + Export

Core database modules

Grouped entry points for search, browsing, analysis, and export.

Read documentation
Assay-level peptide evidence model

Missing image: static/svg/one to more2.svg
Assay-level evidence

One peptide record can connect to many observations.

The database separates stable peptide attributes from experimental context, so records stay easier to filter, compare, and export.

Peptide layer Sequence, identifiers, properties, structures, and modifications.
Evidence layer Activity, target, method, source organism, condition, and reference.
Research output Filtered subsets for prediction, statistics, and downstream analysis.
Data pipeline

From heterogeneous sources to a unified knowledgebase.

Public databases, patents and literature are cleaned, normalised, functionally mapped and cross-validated before serving through the web platform.

Historical workflow illustration: numbers within the diagram describe an earlier release. Current totals are shown in the statistics snapshot above.

ESM-2 + GATv2 Model Architecture

All function prediction models share a unified backbone: ESM-2 protein language model produces per-residue embeddings, which are processed by GATv2 graph attention layers to capture long-range residue interactions. Bundle models (Toxicity / Antiviral) output multiple labels simultaneously; single-label models are optimised per functional category.

ESM-2 + GATv2 model architecture
Open full-size SVG
How to Cite
Citation information will be available upon publication. Please check back later.