AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design

Ziyi Yang, Zitong Tian, Yinjun Jia, Tianyi Zhang, Jiqing Zheng, Hao Wang, Yubu Su, Juncai He, Lei Liu, Yanyan Lan

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Diffusion for protein and antibody design · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add axial feature injection (cross) to UniMoMoUniMoMo (pep.) · LNR D-peptide designright chirality % (minimized): 23.95 -> 99.81Improved
add axial feature injection (cross) to UniMoMo, L taskUniMoMo (pep.) · LNR L-peptide designright chirality % (minimized): 76.98 -> 99.83Improved
add axial feature injection (triple) to UniMoMoUniMoMo (pep.) · LNR D-peptide designright chirality % (minimized): 23.95 -> 99.75Improved
add axial feature injection (commu.) to UniMoMoUniMoMo (pep.) · LNR D-peptide designright chirality % (minimized): 23.95 -> 99.88Improved
choice of axial vector type (cross vs triple vs commutator) (ablation)PepMirror · LNR D-peptide designaverage Vina score: -4.15, -4.20, -4.25No clear effect
add all three axial vector types concatenated (ablation)PepMirror · LNR D-peptide designIMP % (Vina): 72.04 -> 75.00Mixed
use pseudo-scalar triple_scalar instead of axial vector channels (ablation)PepMirror (triple) · LNR D-peptide designright chirality % (minimized): 99.75 -> 99.19Hurt
inject pseudo-scalar once instead of every layer (ablation)PepMirror (triple_scalar) · LNR D-peptide designright chirality % (minimized): 99.19 -> 96.98Hurt
add axial feature injection to the encoder (latent L-D discrepancy) (ablation)UniMoMo encoder · LNR pocket latentsinversion-induced latent distance: 10^-2 scale median, more than four orders of magnitude larger than without AFIImproved
switch from L to D design taskRFDiffusion · LNR Vinaaverage Vina score: -3.30 -> -1.77Hurt
switch from L to D design taskRFDiffusion · LNR VinaIMP %: 44.09% -> 16.13%Hurt
reflect test pockets across different planes instead of inversion (ablation)PepMirror (cross) · LNR D-peptide designIMP % (Vina): 63.44, 65.59, 69.89, 66.67No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy