Tomas Geffner

Latent generative search unlocks de novo design of untapped biomolecular interactions at scale

Kieran Didi, Danny Reidenbach, Matthew Penner, Supriya Ravichandran et autres

Abstract De novo protein design has advanced rapidly, yet designing binders to polar, solvent-exposed epitopes and small, flexible ligands remains challenging. Such hydrated surfaces and flexible molecules, including carbohydrates, provide few of the hydrophobic contacts favoured by current methods and have largely …

gb, us, cn, de, dk, kr (code pays fourni par la source)

DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling

Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis, Morteza Mardani et autres

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion language models with three components: (1) a continuous …

DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling

Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis, Morteza Mardani et autres

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion language models with three components: (1) a continuous …

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach et autres

Protein interaction modeling is central to protein design, which has been transformed by machine learning with applications in drug discovery and beyond. In this landscape, structure-based de novo binder design is cast as either conditional generative modeling or sequence optimization via structure …

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach et autres

Protein interaction modeling is central to protein design, which has been transformed by machine learning with applications in drug discovery and beyond. In this landscape, structure-based de novo binder design is cast as either conditional generative modeling or sequence optimization via structure …

Latent Target Score Matching, with an application to Simulation-Based Inference

Joohwan Ko, Tomas Geffner

Denoising score matching (DSM) for training diffusion models may suffer from high variance at low noise levels. Target Score Matching (TSM) mitigates this when clean data scores are available, providing a low-variance objective. In many applications clean scores are inaccessible due to …

Latent Target Score Matching, with an application to Simulation-Based Inference

Joohwan Ko, Tomas Geffner

Denoising score matching (DSM) for training diffusion models may suffer from high variance at low noise levels. Target Score Matching (TSM) mitigates this when clean data scores are available, providing a low-variance objective. In many applications clean scores are inaccessible due to …

Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design

Danny Reidenbach, Zhonglin Cao, Zuobai Zhang, Kieran Didi et autres

High-quality training datasets are crucial for the development of effective protein design models, but existing synthetic datasets often include unfavorable sequence-structure pairs, impairing generative model performance. We leverage ProteinMPNN, whose sequences are experimentally favorable as well as amenable to folding, together with …

La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

Tomas Geffner, Kieran Didi, Zhonglin Cao, Danny Reidenbach et autres

Recently, many generative models for de novo protein structure design have emerged. Yet, only few tackle the difficult task of directly generating fully atomistic structures jointly with the underlying amino acid sequence. This is challenging, for instance, because the model must reason …

Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow

Zhonglin Cao, Mario Geiger, Allan dos Santos Costa, Danny Reidenbach et autres

Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation require significant computational resources. In this work, we build upon flow-matching and propose …

Learning Straight Flows by Learning Curved Interpolants

Shiv Shankar, Tomas Geffner

Flow matching models typically use linear interpolants to define the forward/noise addition process. This, together with the independent coupling between noise and target distributions, yields a vector field which is often non-straight. Such curved fields lead to a slow inference/generation process. In …

Proteina: Scaling Flow-based Protein Structure Generative Models

Tomas Geffner, Kieran Didi, Zuobai Zhang, Danny Reidenbach et autres

Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop Proteina, a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on …