NetSurfP-2.0

Closed weights Technical University of Denmark,University of Copenhagen,Universidad Nacional de San Martín,AIMST University September 2018

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Technical University of Denmark,University of Copenhagen,Universidad Nacional de San Martín,AIMST University
Organisation type
Academia,Academia,Academia,Academia
Country
Denmark, Argentina, Malaysia
Published
10 September 2018
Authors
Michael Schantz Klausen, Martin Closter Jespersen, Henrik Nielsen, Kamilla Kjærgaard Jensen, Vanessa Isabell Jurtz, Casper Kaae Sønderby, Morten Otto Alexander Sommer, Ole Winther, Morten Nielsen, Bent Petersen, View ORCID ProfilePaolo Marcatili

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Biology
Task
Protein folding prediction, Protein property prediction

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

"A structural dataset consisting of 12,185 crystal structures was obtained from the Protein Data Bank (PDB) (23), culled and selected by the PISCES server (24) with 25% sequence similarity clustering threshold and a resolution of 2.5 Å or better. To avoid overfitting, any sequence that had more than 25% identity to any sequences in the test datasets (see “Evaluation” section for details) was removed, as well as peptide chains with less than 20 residues, leaving 10,837 sequences. Finally, we rand…

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Hosted access (no API)
Training code
Unreleased

NetSurfP-2.0 is available both as a web-server, and as an independent software (http://www.cbs.dtu.dk/services/NetSurfP-2.0/). The web-server version accepts up to 4,000 sequences or 4,000,000 residues per job.

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

"We assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features."

Record confidence
Unknown

Sources

Where this record came from and when it was last checked.

Reference
NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning
Last updated
28 November 2025

What the numbers mean

Where it came from

NetSurfP-2.0 was published by Technical University of Denmark,University of Copenhagen,Universidad Nacional de San Martín,AIMST University, in the country recorded as Denmark, during September 2018. The category the publisher falls under is academia,Academia,Academia,Academia.

It works in the domain of Biology, and is recorded as performing the task of protein folding prediction, Protein property prediction.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

The reason it appears in this catalogue at all: sOTA improvement.

Answers

NetSurfP-2.0 — common questions

01

NetSurfP-2.0— when was it released?

It was published in September 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

NetSurfP-2.0— what is it used for?

It works in the domain of Biology, and is recorded as handling the task of protein folding prediction, Protein property prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

03

NetSurfP-2.0— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

04

NetSurfP-2.0— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

05

NetSurfP-2.0— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

06

NetSurfP-2.0— who created it?

It was published by Technical University of Denmark,University of Copenhagen,Universidad Nacional de San Martín,AIMST University, based in Denmark, an organisation categorised as academia,Academia,Academia,Academia.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.