Education
- B.E. in Bioengineering The University of Sheffield 2023
We build usable bioinformatics methods to annotate life at scale.
Milot Mirdita is an Assistant Professor at the Department of Precision Medicine SKKU School of Medicine. His research focuses on scalable, open bioinformatics infrastructure for metagenomic analysis, high-throughput homology search, clustering, taxonomy, and structure prediction.
He previously worked with Prof. Dr. Martin Steinegger (SNU) and Dr. Johannes Söding (MPI-NAT) to create widely used methods for sequence alignment and annotation. Milot trained at the University of Göttingen and Max-Planck Institute for Multidisciplinary Sciences (Dr. rer. nat.), LMU Munich (M.Sc. Computer Science), and LMU/TUM (B.Sc. Bioinformatics).
We are hiring at all levels (interns, graduate students, postdocs, and research software engineers) excited for large-scale data processing, HPC/GPU programming, machine learning or open-source scientific software. Send a short introduction and CV to milot@mirdita.org.
Choonghwan Lee
Intern
Dohyun Lim
Intern
Hongju Lee
Intern
Jaewon Kim
Intern
Milot Mirdita
Assistant Professor at SKKU
Seda Nur Kabadayi
Intern
Yul Kim
Intern
Easy and accurate AlphaFold2 inference in the browser, maintained together with the Steinegger Lab (SNU), Solab (MIT) and open-source contributors.
Open ColabFold Protocol GitHub
Structure search that lets researchers query massive protein databases for homologous folds in seconds.
Visit Foldseek Server Paper GitHub
GPU-accelerated sequence search for high throughput and low latency.
MMseqs2-GPU Paper GitHubFull list available on ORCID or Google Scholar.
Multiple protein structure alignment at scale with FoldMason
Protein structure-informed bacteriophage genome annotation with Phold
De novo discovery of conserved gene clusters in microbial genomes with Spacedust
AlphaFold Protein Structure Database and 3D-Beacons: new data and capabilities
Rapid and sensitive protein complex alignment with Foldseek-Multimer
Easy and accurate protein structure prediction using ColabFold
BFVD—a large repository of predicted viral protein structures
Metagenomic-scale analysis of the predicted protein structure universe
Structural motif search across the protein-universe with Folddisco
The OMG dataset: an open MetaGenomic corpus for mixed-modality genomic language modeling
Clustering predicted structures at the scale of the known protein universe
Cross-phyla protein annotation by structural prediction and alignment
Foldcomp: a library and format for compressing and indexing large protein structure sets
LambdaPP: fast and accessible protein‐specific phenotype predictions
SpacePHARER: sensitive identification of phages from CRISPR spacers in prokaryotic hosts
Fast and sensitive taxonomic assignment to metagenomic contigs
PredictProtein - predicting protein structure and function for 29 years
Going to extremes – a metagenomic journey into the dark matter of life
DescribePROT: database of amino acid-level protein structure and function predictions
Protein sequence analysis using the MPI bioinformatics toolkit
HH-suite3 for fast remote homology detection and deep protein annotation
MMseqs2 desktop and local web server app for fast, interactive sequence searches
Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold
Uniclust databases of clustered and deeply annotated protein sequences and alignments
Cloud prediction of protein structure and function with PredictProtein for Debian
Feel free to reach out for collaborations, talks, or student opportunities.