Introduction

Intrinsically disordered regions (IDRs) drive essential cellular functions but resist conventional structural-function annotation due to their dynamic conformations. Current computational methods struggle with cross-dataset generalization and functional subtype discrimination. We present IDPFunNet, a hybrid deep learning model combining convolutional neural network, bidirectional LSTM, residual MLP, and the protein language model ProtT5 to predict six IDR functional classes: five binding subtypes and disorded flexible linkers (DFLs).

Download IDPFunNet

IDPFunNet (github)

IDPFunNet(93.1MB)

The benchmark datasets

Dataset_result

Reference

Liang et al, Hybrid Deep Learning with Protein Language Models and Dual-Path Architecture for Predicting IDP Functions, submitted, 2025.

---