# De novo protein design using geometric vector field networks arXiv: https://arxiv.org/abs/2310.11802 ยท HTML: https://mlsanity.com/paper/2310.11802/ ## Key facts - Cited by 14 papers in the map (data through 14 Oct 2026). - Builds on 21 of its 52 references that are in the map. - First posted on arXiv 18 Oct 2023. ## Builds on (most cited first, 21 of 21) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017) - [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020) - [Learning from Protein Structure with Geometric Vector Perceptrons](https://mlsanity.com/paper/2009.01411/) (2020) - [SE(3) diffusion model with application to protein backbone generation](https://mlsanity.com/paper/2302.02277/) (2023) - [Protein Representation Learning by Geometric Structure Pretraining](https://mlsanity.com/paper/2203.06125/) (2022) - [PiFold: Toward effective and efficient protein inverse folding](https://mlsanity.com/paper/2209.12643/) (2022) - [ATOM3D: Tasks On Molecules in Three Dimensions](https://mlsanity.com/paper/2012.04035/) (2020) - [ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs](https://mlsanity.com/paper/2206.08515/) (2022) - [Structure-informed Language Models Are Protein Designers](https://mlsanity.com/paper/2302.01649/) (2023) - [Learning Hierarchical Protein Representations via Complete 3D Graph Networks](https://mlsanity.com/paper/2207.12600/) (2022) - [DeepSF: deep convolutional neural network for mapping protein sequences to folds](https://mlsanity.com/paper/1706.01010/) (2017) - [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) - [Contrastive Representation Learning for 3D Protein Structures](https://mlsanity.com/paper/2205.15675/) (2022) - [A Latent Diffusion Model for Protein Structure Generation](https://mlsanity.com/paper/2305.04120/) (2023) - [Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design](https://mlsanity.com/paper/2106.13058/) (2021) - [Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement](https://mlsanity.com/paper/2207.06616/) (2022) - [Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement](https://mlsanity.com/paper/2305.15151/) (2023) - [DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints](https://mlsanity.com/paper/2301.09642/) (2023) - [Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning](https://mlsanity.com/paper/2201.13299/) (2022) ## Built on by (most cited first, 14 of 14) - [DPLM-2: A Multimodal Diffusion Protein Language Model](https://mlsanity.com/paper/2410.13782/) (2024) - [UniIF: Unified Molecule Inverse Folding](https://mlsanity.com/paper/2405.18968/) (2024) - [Bridge-IF: Learning Inverse Protein Folding with Markov Bridges](https://mlsanity.com/paper/2411.02120/) (2024) - [Generative AI for Controllable Protein Sequence Design: A Survey](https://mlsanity.com/paper/2402.10516/) (2024) - [ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search](https://mlsanity.com/paper/2506.00925/) (2025) - [PRISM: Enhancing Protein Inverse Folding through Fine-Grained Retrieval on Structure-Sequence Multimodal Representations](https://mlsanity.com/paper/2510.11750/) (2025) - [PDFBench: A Benchmark for De novo Protein Design from Function](https://mlsanity.com/paper/2505.20346/) (2025) - [Floating Anchor Diffusion Model for Multi-motif Scaffolding](https://mlsanity.com/paper/2406.03141/) (2024) - [AlphaFolding: 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance](https://mlsanity.com/paper/2408.12419/) (2024) - [Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling](https://mlsanity.com/paper/2505.21452/) (2025) - [Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration](https://mlsanity.com/paper/2401.02141/) (2024) - [AlphaFold Database Debiasing for Robust Inverse Folding](https://mlsanity.com/paper/2506.08365/) (2025) - [Demystify Protein Generation with Hierarchical Conditional Diffusion Models](https://mlsanity.com/paper/2507.18603/) (2025) - [RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness](https://mlsanity.com/paper/2602.04637/) (2026) ## Abstract (arXiv) Innovations like protein diffusion have enabled significant progress in de novo protein design, which is a vital topic in life science. These methods typically depend on protein structure encoders to model residue backbone frames, where atoms do not exist. Most prior encoders rely on atom-wise features, such as angles and distances between atoms, which are not available in this context. Thus far, only several simple encoders, such as IPA, have been proposed for this scenario, exposing the frame modeling as a bottleneck. In this work, we proffer the Vector Field Network (VFN), which enables network layers to perform learnable vector computations between coordinates of frame-anchored virtual atoms, thus achieving a higher capability for modeling frames. The vector computation operates in a manner similar to a linear layer, with each input channel receiving 3D virtual atom coordinates instead of scalar values. The multiple feature vectors output by the vector computation are then used to update the residue representations and virtual atom coordinates via attention aggregation. Remarkably, VFN also excels in modeling both frames and atoms, as the real atoms can be treated as the virtual atoms for modeling, positioning VFN as a potential universal encoder. In protein diffusion (frame modeling), VFN exhibits an impressive performance advantage over IPA, excelling in terms of both designability (67.04% vs. 53.58%) and diversity (66.54% vs. 51.98%). In inverse folding (frame and atom modeling), VFN outperforms the previous SoTA model, PiFold (54.7% vs. 51.66%), on sequence recovery rate. We also propose a method of equipping VFN with the ESM model, which significantly surpasses the previous ESM-based SoTA (62.67% vs. 55.65%), LM-Design, by a substantial margin.