Martin Steinegger

The paper predicts quaternary structures of viral proteins using AlphaFold2 and AlphaFold-Multimer, identifying new insights into vaccinology and protease targets.

Reward-guided inference-time search over the Proteína-Complexa sequence-structure codesign model yields validated binders across 127 targets, kinases and a free carbohydrate, with codesigned sequences outperforming ProteinMPNN redesign.

5,776,417 ColabFold-AlphaFold2 structures cover 98.9% of viral UniProt 2025_03 sequences, 16.4-fold more than earlier versions, with 75.3% high-confidence and 72.6% of viral reference proteomes fully covered.

Foldseek-Interface clusters protein interaction interfaces from PDB data, revealing 77,167 interface clusters and novel interface types.

Riboseek is a fast and sensitive sequence alignment tool for RNA and DNA that uses di-mers for alignment, outperforming BLASTN and nhmmer in speed and sensitivity.

This paper organizes a community challenge to develop automated virus taxonomy classification tools and evaluates their performance on a combined dataset of expert-curated and metagenomic sequences.

The paper expands the AlphaFold Protein Structure Database to include proteome-scale quaternary structures, predicting 1.81M high-confidence protein complexes and revealing conserved structural clusters across domains of life.

Accelign accelerates pairwise sequence alignment using GPUs, achieving significant speedups over existing CPU and GPU implementations for DNA, RNA, and protein sequences.

Folddisco efficiently searches for similar protein structural motifs in large databases using a geometric feature index and rarity-based scoring, achieving faster query times and better storage efficiency than existing methods.

The paper introduces a method to select Reference Proteomes for UniProt, increasing coverage and reducing redundancy in the knowledgebase.

The paper improves metagenomic classification by using spaced metamers, reduced alphabets, and syncmers, enhancing precision and recall while reducing database size and increasing speed.

evedesign provides a unified framework for conditional biosequence design, enabling multiobjective workflows and experimental integration across various applications.

StrucTTY provides real-time, interactive visualization of protein structures in text-only terminals using ASCII graphics and supports multi-structure comparison and Foldseek alignments.

The paper accelerates protein structure prediction using OpenFold with TensorRT and MMseqs2-GPU, achieving 131x faster inference than AlphaFold2 on specific hardware.

FoldMason uses Foldseek's 3Di+AA alphabet for progressive multiple structure alignment, beating structure aligners' LDDT on AlphaFold DB clusters at near sequence-aligner speed, scaling to 100,000 structures.

This paper introduces ProtProfileMD, a model that predicts protein dynamics from sequences, improving homology detection by capturing conformational changes through 3Di tokens.

IFUM is a deep learning model that improves folding stability prediction by jointly estimating free energy and unfolded state ensembles, showing better accuracy than previous methods.

Phold pairs ProstT5-predicted 3Di tokens with Foldseek searches against 1,363,704 curated phage structures, annotating 49.4% of CDS in 1,419 INPHARED genomes versus 34.7% for Pharokka MMseqs2.

This paper introduces a new 20-letter alphabet, TEA, derived from protein language models, enabling efficient homology searches comparable to structure-based methods without structural data.

LoL-align improves protein structure alignment by maximizing a local log-odds score, outperforming TMalign and DALI in sensitivity and speed.

This study identifies ancient immune convergence between prokaryotes and primates through SAMD9/9L proteins and reveals recent adaptations in bonobos and chimps enhancing HIV resistance.

The paper introduces SaprotHub, a platform that simplifies training and sharing of protein language models, enabling non-experts to build and collaborate on customized models.

The paper introduces a structure-informed phylogenetic framework to study the evolutionary diversification of RRNPPA quorum sensing receptors in gram-positive bacteria and their viruses.

The paper introduces Metabuli App, a desktop tool for metagenomic taxonomic profiling, offering user-friendly interfaces and local execution without requiring command-line skills or high-performance computing.

The paper introduces GPU-accelerated homology search with MMseqs2, achieving faster sequence similarity detection than CPU methods and improving structure prediction speeds.

This paper introduces MSA Pairformer, a memory-efficient protein language model that outperforms existing methods in contact prediction and variant effect prediction.

The paper presents an nf-core framework for comparing multiple sequence aligners, aiming to streamline deployment and evaluation of MSA tools in HPC environments.

This paper determines the structure of Escherichia coli PatZ, revealing its homotetrameric architecture and the role of the regulatory domain in catalytic activity and substrate specificity.

Unicore identifies structural core genes for phylogenetic analysis using protein language models and structural strings, achieving faster runtime and broader taxonomic applicability than existing methods.

SoftAlign is an end-to-end protein structure alignment method that improves accuracy over existing tools while being compatible with other alignment strategies.