CPAC

Closed weights Texas A&M September 2022

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
Texas A&M
Organisation type
Academia
Country
United States of America
Published
18 September 2022
Authors
Yuning You, Yang Shen

What it does

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

Domain
Biology
Task
Protein-ligand binding affinity prediction, Protein-ligand contact 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
589,944,195 tokens

Calculations: 60,137 × 1,000 = 6.0137 × 10⁷ 12,798,671 × 1,000 = 1.2798671 × 10¹⁰ 6.0137 × 10⁷ + 1.2798671 × 10¹⁰ = 1.3400678 × 10¹⁰ Final estimate: 1.34 × 10¹⁰ datapoints assumes 1000 datapoints per sequence?

How it is classified

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

Record confidence
Speculative
Citations
25

Sources

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

Reference
Cross-modality and self-supervised protein embedding for compound–protein affinity and contact prediction
Last updated
1 January 2026

What the numbers mean

What this model is

CPAC was published by Texas A&M, in United States of America, in September 2022. academia is the category the publisher falls under.

It works in Biology, and is recorded as doing protein-ligand binding affinity prediction, Protein-ligand contact prediction.

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

Training and provenance

The training set ran to roughly 589,944,195 tokens.

Answers

CPAC — common questions

01

Is CPAC open source?

The licensing for CPAC was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

How many parameters does CPAC have?

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

03

Who created CPAC?

CPAC was published by Texas A&M, based in United States of America, categorised as academia.

04

When was CPAC released?

CPAC was published in September 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is CPAC used for?

CPAC works in Biology, and is recorded as handling protein-ligand binding affinity prediction, Protein-ligand contact prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run CPAC?

None. CPAC 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.

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.