GGNN

Closed weights Westlake University,Tsinghua University,Toyota Technological Institute at Chicago August 2023

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
Westlake University,Tsinghua University,Toyota Technological Institute at Chicago
Organisation type
Academia,Academia,Academia
Country
China, United States of America
Published
5 August 2023
Authors
Fang Wu, Lirong Wu, Dragomir Radev, Jinbo Xu and Stan Z. Li

What it does

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

Domain
Biology
Task
Proteins, Protein interaction prediction, Protein protein binding affinity prediction, Protein representation learning
Base model
ESM2-650M

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

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
7.6 × 10²¹ FLOP

ESM-2 650M is very likely the majority of FLOPs, since they only used 2 A100s (ESM-2 650M used 512 V100s for 8 days). As such I'm reporting the compute from ESM-2 650M here only.

How it was established
Other

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100 SXM4 80 GB
Chips used
2
Power draw
1.6 kW

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
Unreleased
Training code
Open source

MIT license https://github.com/smiles724/GNN-Bottleneck

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

"In this work, we integrate the knowledge learned by well-trained protein language models into several state-of-the-art geometric networks and evaluate a variety of protein representation learning benchmarks, including protein-protein interface prediction, model quality assessment, protein-protein rigid-body docking, and binding affinity prediction. Our findings show an overall improvement of 20% over baselines."

Record confidence
Confident
Citations
43

Sources

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

Reference
Integration of pre-trained protein language models into geometric deep learning networks
Last updated
1 January 2026

What the numbers mean

Background

GGNN was published by Westlake University,Tsinghua University,Toyota Technological Institute at Chicago, in China, in August 2023. It comes out of academia,Academia,Academia.

It works in Biology, and is recorded as doing proteins, Protein interaction prediction, Protein protein binding affinity prediction, Protein representation learning.

It is derived from ESM2-650M rather than trained from scratch, which is the usual way a specialised model is produced.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Training it took roughly 7.6 × 10²¹ FLOP of computation, on NVIDIA A100 SXM4 80 GB — a measure of what producing the model cost, not of how fast it answers.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

GGNN — common questions

01

What is GGNN used for?

GGNN works in Biology, and is recorded as handling proteins, Protein interaction prediction, Protein protein binding affinity prediction, Protein representation learning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

How much compute was used to train GGNN?

Around 7.6 × 10²¹ FLOP, on NVIDIA A100 SXM4 80 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

03

What GPU do I need to run GGNN?

None. GGNN 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

Is GGNN open source?

No. GGNN has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does GGNN have?

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

06

Who created GGNN?

GGNN was published by Westlake University,Tsinghua University,Toyota Technological Institute at Chicago, based in China, categorised as academia,Academia,Academia.

07

When was GGNN released?

GGNN was published in August 2023. 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.