Christoph Feinauer

Foundation Models Improve Perturbation Response Prediction

This study evaluates foundation models for predicting cellular responses to perturbations, finding that some pretrained embeddings improve predictions while others do not.

Uncertainty-Aware Discrete Diffusion Improves Protein Design

This paper introduces an uncertainty-aware discrete diffusion model for protein design, improving sequence generation from 3D structures by incorporating position-specific uncertainty and pretrained models.

TULIP - a Transformer based Unsupervised Language model for Interacting Peptides and T-cell receptors that generalizes to unseen epitopes

TULIP is an unsupervised transformer model for predicting TCR epitope binding, outperforming existing methods on unseen epitopes by addressing data limitations and bias.

Generating Interacting Protein Sequences using Domain-to-Domain Translation

The paper develops a method to generate protein domain sequences that interact with another domain, outperforming existing approaches and exploring fine-tuning and structure prediction.

Mean Dimension of Generative Models for Protein Sequences

This paper introduces the mean dimension metric to evaluate generative models for protein sequences, showing that high performance does not require high complexity.

Interpretable Pairwise Distillations for Generative Protein Sequence Models

The paper evaluates three neural network models for protein sequences, showing that pairwise models can replicate their performance in mutational effect prediction.

Natural representation of composite data with replicated autoencoders

This paper introduces a method using replicated autoencoders optimized for local entropy to infer compositional features from noisy data, showing improved performance on synthetic and protein sequence data.

Context-Aware Prediction of Pathogenicity of Missense Mutations Involved in Human Disease

This work improves pathogenicity prediction of missense mutations by incorporating sequence context, achieving accuracy comparable to state-of-the-art methods.

Inferring protein-protein interaction networks from inter-protein sequence co-evolution

This paper introduces a method to infer protein-protein interaction networks from sequence co-evolution, achieving high true-positive rates in test cases.