A framework for conditional diffusion modelling with applications in motif scaffolding for protein design

• URL: http://arxiv.org/abs/2312.09236v4
• Date: Wed, 13 Mar 2024 22:49:33 GMT
• Title: A framework for conditional diffusion modelling with applications in motif scaffolding for protein design
• Abstract summary: Many protein design applications, such as binder or enzyme design, require scaffolding a structural motif with high precision. Generative modelling paradigms based on denoising diffusion processes emerged as a leading candidate to address this motif scaffolding problem. We propose a new variation on existing conditional training protocols based on the mathematically well-understood Doob's h-transform.
• Score: 11.346153061528504
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many protein design applications, such as binder or enzyme design, require scaffolding a structural motif with high precision. Generative modelling paradigms based on denoising diffusion processes emerged as a leading candidate to address this motif scaffolding problem and have shown early experimental success in some cases. In the diffusion paradigm, motif scaffolding is treated as a conditional generation task, and several conditional generation protocols were proposed or imported from the Computer Vision literature. However, most of these protocols are motivated heuristically, e.g. via analogies to Langevin dynamics, and lack a unifying framework, obscuring connections between the different approaches. In this work, we unify conditional training and conditional sampling procedures under one common framework based on the mathematically well-understood Doob's h-transform. This new perspective allows us to draw connections between existing methods and propose a new variation on existing conditional training protocols. We illustrate the effectiveness of this new protocol in both, image outpainting and motif scaffolding and find that it outperforms standard methods.

Related papers

• Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling [19.701450236748254]
  We introduce Chamaileon, which unifies multi-target and multi-state binder design by formulating the problem as cross-context binding landscape modeling.<n>The framework is underpinned by a training paradigm termed In-Context Complex Co-Design (I3CD) for context-aware sequence-structure co-modeling.
  arXiv  Detail & Related papers  (2026-07-26T07:35:10Z)
• Unifying Deep Stochastic Processes for Image Enhancement [2.2649197740853677]
  We introduce a unified perspective on image enhancement by classifying recent methods into three families of continuous-time processes.<n>We show that all of these approaches arise from a common differential equation (SDE) formulation.<n>We conduct a controlled empirical study across multiple image enhancement tasks using identical architectures and training protocols.
  arXiv  Detail & Related papers  (2026-05-02T18:40:03Z)
• Demystifing Video Reasoning [71.53763299316041]
  We show that reasoning in video models instead primarily emerges along the diffusion denoising steps.<n>We identify several emergent reasoning behaviors critical to model performance.<n>Motivated by these insights, we present a training-free strategy as a proof-of-concept.
  arXiv  Detail & Related papers  (2026-03-17T17:59:55Z)
• OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design [0.2578364360202627]
  We propose a unified approach in OMTRA, which flexibly performs many tasks relevant to drug design (SBDD)<n>We curate a dataset of 500M 3D molecular conformers, complementing protein-ligand data and expanding the chemical diversity available for training.<n>OMTRA obtains state of the art performance on pocket-conditioned de novo design and docking; however, the effects of large-scale pretraining and multi-task training are modest.
  arXiv  Detail & Related papers  (2025-12-04T18:46:35Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem [38.84662767814454]
  Key challenge to address under the condition of limited training data is how to fine-tune pre-trained vision-language models in a parameter-efficient manner. This paper proposes a unified computational framework to integrate existing methods together, identify their nature and support in-depth comparison. As a demonstration, we extend existing methods by modeling inter-class correlation between representers in reproducing kernel Hilbert space (RKHS)
  arXiv  Detail & Related papers  (2024-10-15T15:22:30Z)
• A Simple Approach to Unifying Diffusion-based Conditional Generation [63.389616350290595]
  We introduce a simple, unified framework to handle diverse conditional generation tasks. Our approach enables versatile capabilities via different inference-time sampling schemes. Our model supports additional capabilities like non-spatially aligned and coarse conditioning.
  arXiv  Detail & Related papers  (2024-10-15T09:41:43Z)
• Structure Preserving Diffusion Models [19.374406313635966]
  This paper focuses on structure-preserving diffusion models (SPDM) We propose a new framework that considers the geometric structures affecting the diffusion process. We implement an equivariant denoising diffusion bridge model, which achieves reliable equivariant image noise reduction and style transfer.
  arXiv  Detail & Related papers  (2024-02-29T17:16:20Z)
• Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis [62.07413805483241]
  Steered Diffusion is a framework for zero-shot conditional image generation using a diffusion model trained for unconditional generation. We present experiments using steered diffusion on several tasks including inpainting, colorization, text-guided semantic editing, and image super-resolution.
  arXiv  Detail & Related papers  (2023-09-30T02:03:22Z)
• Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation [6.7311791228366]
  This paper introduces LyCORIS, an open-source library that offers a wide selection of fine-tuning methodologies for Stable Diffusion. We also present a framework for the systematic assessment of varied fine-tuning techniques. Our work provides essential insights into the nuanced effects of fine-tuning parameters, bridging the gap between state-of-the-art research and practical application.
  arXiv  Detail & Related papers  (2023-09-26T11:36:26Z)
• Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption [73.98706049140098]
  We propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss. Specifically, we design a phasic training strategy with phasic content fusion to help our model learn content and style information when t is large. Finally, we propose a cross-domain structure guidance strategy that enhances structure consistency during domain adaptation.
  arXiv  Detail & Related papers  (2023-09-07T14:14:11Z)
• Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement [53.2171981279647]
  We present a framework that encapsulates both the VP- and variance-exploding (VE)-based diffusion methods. To improve performance and ease model training, we analyze the common difficulties encountered in diffusion models. We evaluate our model against several methods using a public benchmark to showcase the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-14T14:22:22Z)
• Protein Design with Guided Discrete Diffusion [67.06148688398677]
  A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling. We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models. NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
  arXiv  Detail & Related papers  (2023-05-31T16:31:24Z)
• Diffusion Models for Constrained Domains [11.488860260925504]
  We present two distinct noising processes based on (i) the logarithmic barrier metric and (ii) the reflected Brownian motion induced by the constraints. We then demonstrate the practical utility of our methods on a number of synthetic and real-world tasks, including applications from robotics and protein design.
  arXiv  Detail & Related papers  (2023-04-11T17:19:45Z)
• Diffusion Action Segmentation [63.061058214427085]
  We propose a novel framework via denoising diffusion models, which shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions.
  arXiv  Detail & Related papers  (2023-03-31T10:53:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.