AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering

Tianxiao Li, Hongyu Guo, Filippo Grazioli, Mark Gerstein, Martin Renqiang Min

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative protein structure design · 1 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
remove Wasserstein loss (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)fraction positive valid: 0.23±0.02 -> 0.21±0.02Improved
remove Wasserstein loss (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)MMD zf positive vs negative: 0.163±0.015 -> 0.040±0.026Improved
remove auxiliary classifier (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)fraction positive valid: 0.23±0.02 -> 0.13±0.04Improved
remove auxiliary classifier (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)MMD zf positive vs negative: 0.163±0.015 -> 0.087±0.067Improved
add decoder using only zs (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)fraction positive valid: 0.23±0.02 -> 0.18±0.01No clear effect
add decoder using only zs (ablation)TCR-dWAE · TCR engineering ablation (VDJDB)MMD zf positive vs negative: 0.163±0.015 -> 0.238±0.029Mixed
use disentangled WAE instead of VAETCR-dWAE · VDJDB TCR engineeringfraction positive valid: 0.16±0.01 -> 0.23±0.02Improved
use TCR-dWAE instead of greedy / genetic / MCTS mutation baselinesTCR-dWAE · VDJDB TCR engineeringfraction positive valid: 0.02±0.0 -> 0.23±0.02Improved
replace zf with random embedding (ablation)TCR-dWAE · VDJDB reconstructionreconstruction accuracy: 0.9044 ± 0.0020 -> 0.7535 ± 0.0085Hurt
replace both embeddings with random (ablation)TCR-dWAE · VDJDB reconstructionreconstruction accuracy: 0.9044 ± 0.0020 -> 0.6016 ± 0.0030Hurt
use transformer decoder instead of LSTM decoder (ablation)TCR-dWAE · VDJDBfraction positive validNo clear effect
model hypervariable region only (trimmed) (ablation)TCR-dWAE · VDJDBfraction positive validHurt

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