bio.rodeo
ModelsOrganizationsProvidersLeaderboardAboutSign in
bio.rodeo

The authoritative source for evaluating biological foundation models. No hype, just honest analysis.

Categories
  • DNA & Gene
  • RNA
  • Protein
  • Small molecule
  • Single-cell
  • Spatial omics
  • Pathology
  • Imaging
  • Metabolomics
  • Biosignals
  • Language model
bio.rodeoModelsOrganizationsProvidersLeaderboardAboutFAQSubmit a modelContact
© 2026 Pulsatance. All rights reserved. ~
Built by Pulsatance
models / protein / idp-rg-mlp
Protein
University of Central FloridaReleased July 2024

IDP Gyration-Radius MLP

Predicts the radius of gyration of intrinsically disordered proteins from 23 physics-derived sequence features, screening missense mutants in bulk.

The short version

  • —Screens every possible missense mutation in a disordered protein for large size changes
  • —Returns a full residue-by-substitution heat map of chain size in minutes
  • —Takes 23 interpretable physics features rather than a learned sequence embedding
  • —SHAP traces predictions to chain length, charge decoration, and hydropathy decoration
  • —Outputs land on the same scale as the simulations, so flagged mutants re-simulate directly
5Citations

Where to run it

No providers recorded yet. Browse all providers

For a disordered protein of length L there are roughly 20L possible missense mutations. Most are benign; a few reshape the conformational ensemble enough to matter for disease, and intrinsically disordered proteins (IDPs) are implicated in Alzheimer's and Parkinson's disease, type II diabetes, and — through p53 — a large share of human cancer. Identifying that small pathogenic subset is the problem, and the standard computational route is too expensive to enumerate: coarse-grained Brownian dynamics on a single-bead-per-residue hydropathy model gives an accurate mean radius of gyration, but running it per mutant across a proteome is out of reach.

This model replaces the simulation with a regression. Swarnadeep Seth and Aniket Bhattacharya, in the Department of Physics at the University of Central Florida, ran Brownian dynamics on roughly 6,500 IDP sequences drawn from MobiDB and used the resulting gyration radii as supervised labels for a multilayer perceptron that reads 23 physics-derived features computed from the FASTA sequence alone. The work was posted as a preprint in July 2024 and published in Biomacromolecules in 2025.

It is deliberately narrow. Where generative approaches such as AI-IDP and IDPForge produce full conformational ensembles, this network predicts one global observable — chain size — cheaply enough that every point mutation in a sequence can be evaluated exhaustively and the handful of large-effect substitutions handed back to simulation.

#Key Features

  • Interpretable physics features, not learned embeddings: The 23 inputs are computed directly from sequence — chain length, mass, charge and hydropathy distribution moments and their RMS fluctuations, all-residue and charge-only Shannon entropies, charge fractions, the charge asymmetry parameter, sequence charge decoration (SCD), sequence hydropathy decoration (SHD), and a sequence-based charge-patch metric introduced in the paper.
  • Generalizes to unseen sequences: On 33 well-characterized IDPs held entirely out of training, predictions reach 97% accuracy with a mean squared error of 0.03 and R² of 0.95 against Brownian dynamics, with error under about 5% for all but four.
  • Exhaustive mutational scanning: One trained checkpoint predicts the gyration radius of every single-substitution mutant of a given IDP, rendered as a residue-by-substitution heat map of percentage change from wild type.
  • Explained predictions: SHAP attribution ranks chain length as the dominant predictor, followed by SCD, SHD, and the new charge-patch parameter — an ordering consistent with polymer-physics expectations for a heteropolymer's size.
  • Simulation-checkable output: Predictions share the scale of the simulation that trained the network, so flagged mutants can be re-simulated directly; for the 24-residue histatin-5, the prediction map overlaps the Brownian dynamics map at about 80%.

#Technical Details

The network has eight fully connected hidden layers tapering from 128 units down to 4, alternating ReLU and hyperbolic-tangent activations, with four dropout layers at 30%, 30%, 20% and 20%, and a single linear output neuron returning the radius of gyration in nanometres. Training ran for 1,200 epochs at batch size 50 using Adam with a learning rate of 0.0021 and decay rate of 0.0005, minimizing a combined mean squared logarithmic error and Huber loss with early stopping; training and test accuracy stayed within a 90-97% band across repeated runs.

Labels come from Brownian dynamics on the HPS2 coarse-grained model: each amino acid is a single bead carrying a CALVADOS-derived hydropathy value at interaction strength ε = 0.2 kcal/mol, consecutive beads joined by harmonic bonds at 0.38 nm, with charged residues interacting through a Debye-screened Coulomb potential. Source sequences were selected from MobiDB at lengths of 20-300 residues with disorder scores of 99% or above. Inference is four to six orders of magnitude faster than rerunning the simulation.

#Applications

The intended use is triage. A researcher studying a disease-associated disordered protein can score every possible missense substitution in minutes, isolate the positions where the predicted chain dimension shifts sharply, and commit simulation or experimental effort only to those. Scanning a whole sequence at once localizes mutation-prone regions, which helps in interpreting variants of uncertain significance in disordered regions that structure-based predictors cannot reach. Sequence-to-size prediction also supports the design of disordered linkers with target compaction.

#Impact

The contribution is a demonstration that a small, fully interpretable network trained on simulation output can stand in for that simulation across a combinatorial search space, and that explainable-AI attribution over physics features recovers the polymer-physics reasoning a practitioner would apply by hand. The caveats are equally clear. Ground truth is simulated rather than measured, so accuracy is bounded by the fidelity of the HPS2 model; the single output is a global size observable, and the authors note explicitly that a large change in the radius of gyration does not by itself imply a pathogenic variant; four of the 33 validation proteins fall outside the 5% error band. No code or trained weights accompany the publication, so the network must be reproduced from the described architecture and training protocol.

At a glance

Released
July 2024
Category
Protein
Organization
University of Central Florida

Related models

  • AI-IDP

    German Center for Neurodegenerative Diseases (DZNE)

  • Conditioned pLM for Generative IDP Design

    LAAS-CNRS / Centre de Biochimie Structurale

  • IDPForge

    Chinese Academy of Sciences

  • IDPFunNet

    Shandong University

  • Disobind

    National Centre for Biological Sciences

Links

Research Paper

Tags

intrinsically_disordered_proteinsmultilayer_perceptronproperty_predictionvariant_effect_prediction

Something wrong?

Much of this page is generated or calculated automatically. Flag anything that looks off and we will re-run it.