# Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement

arXiv: https://arxiv.org/abs/2305.15151 · HTML: https://mlsanity.com/paper/2305.15151/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 67 references that are in the map.
- First posted on arXiv 20 May 2023.

## Builds on (most cited first, 28 of 28)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data](https://mlsanity.com/paper/1807.02547/) (2018)
- [Learning from Protein Structure with Geometric Vector Perceptrons](https://mlsanity.com/paper/2009.01411/) (2020)
- [SimVP: Simpler yet Better Video Prediction](https://mlsanity.com/paper/2206.05099/) (2022)
- [Protein Representation Learning by Geometric Structure Pretraining](https://mlsanity.com/paper/2203.06125/) (2022)
- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [PiFold: Toward effective and efficient protein inverse folding](https://mlsanity.com/paper/2209.12643/) (2022)
- [OntoProtein: Protein Pretraining With Gene Ontology Embedding](https://mlsanity.com/paper/2201.11147/) (2022)
- [Structure-informed Language Models Are Protein Designers](https://mlsanity.com/paper/2302.01649/) (2023)
- [AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB](https://mlsanity.com/paper/2202.01079/) (2022)
- [Protein sequence design with deep generative models](https://mlsanity.com/paper/2104.04457/) (2021)
- [Deep Learning in Protein Structural Modeling and Design](https://mlsanity.com/paper/2007.08383/) (2020)
- [Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design](https://mlsanity.com/paper/2106.13058/) (2021)
- [OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning](https://mlsanity.com/paper/2209.04851/) (2022)
- [Target-aware Molecular Graph Generation](https://mlsanity.com/paper/2202.04829/) (2022)
- [Deep Generative Modeling for Protein Design](https://mlsanity.com/paper/2109.13754/) (2021)
- [SemiRetro: Semi-template framework boosts deep retrosynthesis prediction](https://mlsanity.com/paper/2202.08205/) (2022)
- [CoSP: Co-supervised pretraining of pocket and ligand](https://mlsanity.com/paper/2206.12241/) (2022)
- [HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle](https://mlsanity.com/paper/2207.05477/) (2022)
- [DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints](https://mlsanity.com/paper/2301.09642/) (2023)
- [PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding](https://mlsanity.com/paper/2302.07120/) (2023)
- [TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifs](https://mlsanity.com/paper/2204.13048/) (2022)

## Built on by (most cited first, 12 of 12)

- [DPLM-2: A Multimodal Diffusion Protein Language Model](https://mlsanity.com/paper/2410.13782/) (2024)
- [Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design](https://mlsanity.com/paper/2310.05764/) (2023)
- [FoldToken: Learning Protein Language via Vector Quantization and Beyond](https://mlsanity.com/paper/2403.09673/) (2024)
- [De novo protein design using geometric vector field networks](https://mlsanity.com/paper/2310.11802/) (2023)
- [Generative AI for Controllable Protein Sequence Design: A Survey](https://mlsanity.com/paper/2402.10516/) (2024)
- [PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design](https://mlsanity.com/paper/2312.00080/) (2023)
- [Generative artificial intelligence for de novo protein design](https://mlsanity.com/paper/2310.09685/) (2023)
- [Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization](https://mlsanity.com/paper/2410.19471/) (2024)
- [Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models](https://mlsanity.com/paper/2312.04019/) (2023)
- [EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization](https://mlsanity.com/paper/2506.09496/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [SymFold: Synergizing Evolutionary and Structural Priors for Accurate Protein Inverse Folding](https://mlsanity.com/paper/2609.01353/) (2026)

## Abstract (arXiv)

Recent studies have shown competitive performance in protein design that aims to find the amino acid sequence folding into the desired structure. However, most of them disregard the importance of predictive confidence, fail to cover the vast protein space, and do not incorporate common protein knowledge. After witnessing the great success of pretrained models on diverse protein-related tasks and the fact that recovery is highly correlated with confidence, we wonder whether this knowledge can push the limits of protein design further. As a solution, we propose a knowledge-aware module that refines low-quality residues. We also introduce a memory-retrieval mechanism to save more than 50% of the training time. We extensively evaluate our proposed method on the CATH, TS50, and TS500 datasets and our results show that our Knowledge-Design method outperforms the previous PiFold method by approximately 9% on the CATH dataset. Specifically, Knowledge-Design is the first method that achieves 60+% recovery on CATH, TS50 and TS500 benchmarks. We also provide additional analysis to demonstrate the effectiveness of our proposed method. The code will be publicly available.