DeepFRI

Open weights Flatiron Institute,University of California San Diego,Jagiellonian University,New York University (NYU),Broad Institute,University of Auckland,Massachusettes General Hospital,Harvard Medical School,Massachusetts Institute of Technology (MIT) May 2021

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
Flatiron Institute,University of California San Diego,Jagiellonian University,New York University (NYU),Broad Institute,University of Auckland,Massachusettes General Hospital,Harvard Medical School,Massachusetts Institute of Technology (MIT)
Organisation type
Academia,Academia,Academia,Research collective,Academia,Academia,Academia
Country
United States of America, Poland, New Zealand
Published
26 May 2021
Authors
Vladimir Gligorijević, P. Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C. Taylor, Ian M. Fisk, Hera Vlamakis, Ramnik J. Xavier, Rob Knight, Kyunghyun Cho & Richard Bonneau

What it does

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

Domain
Biology
Task
Protein function 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

30k PDB + 220k SWISS-MODEL = 250k 250k * 0.8 = 200k

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
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Open source

The source code for training the DeepFRI model, together with neural network weights are available for research and non-commercial use at https://github.com/flatironinstitute/DeepFRI (BSD-3-Clause license) and it can be cited by using https://doi.org/10.5281/zenodo.4650027. A web service of our method is available at https://beta.deepfri.flatironinstitute.org/

How it is classified

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

Record confidence
Confident
Citations
786

Sources

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

Reference
Structure-based protein function prediction using graph convolutional networks
Last updated
1 January 2026

What the numbers mean

Where it came from

DeepFRI was published by Flatiron Institute,University of California San Diego,Jagiellonian University,New York University (NYU),Broad Institute,University of Auckland,Massachusettes General Hospital,Harvard Medical School,Massachusetts Institute of Technology (MIT), in United States of America, in May 2021. academia,Academia,Academia,Research collective,Academia,Academia,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein function prediction.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Answers

DeepFRI — common questions

01

What is DeepFRI used for?

DeepFRI works in Biology, and is recorded as handling protein function prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

Where can I download DeepFRI?

The weights for DeepFRI are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

03

What GPU do I need to run DeepFRI?

We cannot say. DeepFRI has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

04

Is DeepFRI open source?

Its weights are published, so DeepFRI can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

05

How many parameters does DeepFRI have?

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

06

Who created DeepFRI?

DeepFRI was published by Flatiron Institute,University of California San Diego,Jagiellonian University,New York University (NYU),Broad Institute,University of Auckland,Massachusettes General Hospital,Harvard Medical School,Massachusetts Institute of Technology (MIT), based in United States of America, categorised as academia,Academia,Academia,Research collective,Academia,Academia,Academia.

07

When was DeepFRI released?

DeepFRI was published in May 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 1 January 2026

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.