Peptide AI / 2026

PepDDG.

Peptide–protein binding ΔΔG prediction via information channel decomposition.

NeurIPS 2026

01 / The problem

Predict how a peptide–protein change affects binding free energy (ΔΔG).

02 / The core idea

Information channel decomposition for peptide–protein binding ΔΔG prediction.

How the idea flows

FIGURE 01 / ORIGINAL CONCEPT SKETCH

Peptide–protein binding comparison
Predict binding free-energy change (ΔΔG)

Task-level concept only; detailed architecture awaits a public source.

03 / What the public evidence shows

Richard reports NeurIPS 2026 acceptance. A public paper, author list, detailed architecture and quantitative result table have not been verified for this site.

04 / Where the claim stops

This sketch does not invent channel names, training losses, datasets, benchmark numbers or a code URL.

An editorial scope note, not an unverified quotation of author limitations.