Related papers: FoldToken2: Learning compact, invariant and genera…
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…
Have you ever been troubled by the complexity and computational cost of SE(3) protein structure modeling and been amazed by the simplicity and power of language modeling? Recent work has shown promise in simplifying protein structures as…
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…
To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or…
Recent advances in Text-to-3D (T23D) generative models have enabled the synthesis of diverse, high-fidelity 3D assets from textual prompts. However, existing challenges restrict the development of reliable T23D quality assessment (T23DQA).…
Structure determination is key to understanding protein function at a molecular level. Whilst significant advances have been made in predicting structure and function from amino acid sequence, researchers must still rely on expensive,…
Proteins are the most important biomolecules for living organisms. The understanding of protein structure, function, dynamics and transport is one of most challenging tasks in biological science. In the present work, persistent homology is,…
A protein's function depends critically on its conformational ensemble, a collection of energy weighted structures whose balance depends on temperature and environment. Though recent deep learning (DL) methods have substantially advanced…
In recent years, deep learning techniques have made significant strides in molecular generation for specific targets, driving advancements in drug discovery. However, existing molecular generation methods present significant limitations:…
Protein inverse folding-that is, predicting an amino acid sequence that will fold into the desired 3D structure-is an important problem for structure-based protein design. Machine learning based methods for inverse folding typically use…
Protein representation learning is critical for numerous biological tasks. Recently, large transformer-based protein language models (pLMs) pretrained on large scale protein sequences have demonstrated significant success in sequence-based…
Protein structure is central to biological function, and enabling multimodal protein models requires joint reasoning over sequence, structure, and function. A key barrier is the lack of principled protein structure tokenizers (PSTs):…
The protein backbone is described as a smooth curved and twisted line in three-dimensional (3D) space and characterized by its curvature $\kappa(s)$ and torsion $\tau(s)$ both expressed as a function of arc length s. It is shown that the…
Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…
Extensively exploring protein conformational landscapes remains a major challenge in computational biology due to the high computational cost involved in dynamic physics-based simulations. In this work, we propose a novel pipeline, MoDyGAN,…
Protein design is a fundamental challenge in biotechnology, aiming to design novel sequences with specific functions within the vast space of possible proteins. Recent advances in deep generative models have enabled function-based protein…
While all the information required for the folding of a protein is contained in its amino acid sequence, one has not yet learnt how to extract this information so as to predict the detailed, biological active, three-dimensional structure of…
De novo protein structure prediction from amino acid sequence is one of the most challenging problems in computational biology. As one of the extensively explored mathematical models for protein folding, Hydrophobic-Polar (HP) model enables…
Proteins must fold quickly to acquire their biologically functional three-dimensional native structures. Hence, these are mainly stabilized by local contacts, while intricate topologies such as knots are rare. Here, we reveal the existence…
Inverse protein folding, the process of designing sequences that fold into a specific 3D structure, is crucial in bio-engineering and drug discovery. Traditional methods rely on experimentally resolved structures, but these cover only a…