Milot Mirdita

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

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.

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.

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.

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 simple and efficient method for detecting related genetic sequences with position-varying substitution, insertion, and deletion probabilities, and demonstrates its application to identify relics of LF-SINE in the human genome.

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

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.

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.

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

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 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.

Spacedust identifies conserved gene clusters in microbial genomes using structure comparison and statistical methods, recovering most known antiviral defense systems.

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

The paper combines AlphaFold and ESMfold predictions to create a large structural dataset, identifies novel protein folds and domain combinations, and highlights the value of metagenomic data for structural diversity.

Foldseek-Multimer rapidly aligns protein complexes by clustering superposition vectors, outperforming the gold standard in speed while maintaining alignment quality.

BFVD provides a large repository of predicted viral protein structures, enhancing annotation of bacteriophage proteins compared to sequence-based methods.

ProstT5, a ProtT5 fine-tuned to translate between amino acids and Foldseek 3Di tokens, predicts structure strings for remote homology search and performs inverse folding.

The Open MetaGenomic (OMG) corpus combines 3.1T base pairs and 3.3B protein coding sequences in mixed amino-acid and nucleotide format to pretrain the genomic language model gLM2.

A Foldseek-based linear-time structural clustering groups 52 million AlphaFold DB representatives into 2.27 million non-singleton clusters; 31% lack known structural or domain annotation.

The paper uses petabase-scale homology searches from SRA data to improve protein structure prediction accuracy using ColabFold, achieving better results than default methods.

Foldseek's 3Di tertiary-interaction alphabet enables structure search four to five orders of magnitude faster than Dali and TM-align at 86% and 88% of their respective sensitivities.

Foldcomp compresses and indexes large protein structure sets with high efficiency and accuracy, offering faster compression and comparable reconstruction quality.

LambdaPP provides fast, accessible protein feature predictions including structure and function, using AI models and embeddings from protein Language Models.

ColabFold couples 40–60-fold faster MMseqs2 homology search to AlphaFold2, matching it on CASP14 and AlphaFold-multimer on ClusPro complexes, yielding close to 1,000 structures daily per GPU.

SpacePHARER identifies phage-host relationships by matching CRISPR spacers to phage genomes in genomic or metagenomic data, improving sensitivity through protein-level comparisons and multiple match evidence.

MMseqs2 taxonomy assigns taxonomic labels to metagenomic contigs using fragment extraction and weighted voting, achieving 2-18x speed improvements over existing tools.