Publications

GraphPart: homology partitioning for biological sequence analysis

Published in NAR Genomics and Bioinformatics, 2023

We introduce GraphPart, an algorithm for homology partitioning of biological sequence datasets for machine learning. Python package

Recommended citation: Felix Teufel, Magnús Halldór Gíslason, José Juan Almagro Armenteros, Alexander Rosenberg Johansen, Ole Winther, Henrik Nielsen, GraphPart: homology partitioning for biological sequence analysis, NAR Genomics and Bioinformatics, Volume 5, Issue 4, December 2023, lqad088, https://doi.org/10.1093/nargab/lqad088 https://academic.oup.com/nargab/article/5/4/lqad088/7318077

DeepPeptide predicts cleaved peptides in proteins using conditional random fields

Published in Bioinformatics, 2023

DeepPeptide, a CRF-based model that predicts cleaved peptides and propeptides directly from the precursor protein sequence. Online predictor Code

Recommended citation: Felix Teufel, Jan Christian Refsgaard, Christian Toft Madsen, Carsten Stahlhut, Mads Grønborg, Ole Winther, Dennis Madsen, DeepPeptide predicts cleaved peptides in proteins using conditional random fields, Bioinformatics, 2023;, btad616, https://doi.org/10.1093/bioinformatics/btad616 https://doi.org/10.1093/bioinformatics/btad616

Deorphanizing Peptides Using Structure Prediction

Published in Journal of Chemical Information and Modeling, also accepted at MLSB Workshop at NeurIPS, 2022

We combined AlphaFold-Multimer with DeepTMHMM as a peptide receptor deorphanization method. Code

Recommended citation: Felix Teufel, Jan C. Refsgaard, Marina A. Kasimova, Kristine Deibler, Christian T. Madsen, Carsten Stahlhut, Mads Grønborg, Ole Winther, and Dennis Madsen Journal of Chemical Information and Modeling 2023 63 (9), 2651-2655 DOI: 10.1021/acs.jcim.3c00378 https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00378

Combining mass spectrometry and machine learning to discover bioactive peptides

Published in Nature Communications, 2022

Discovering bioactive peptides in large-scale peptidomics studies directly from the MS signal. Code

Recommended citation: Madsen, C.T., Refsgaard, J.C., Teufel, F.G. et al. Combining mass spectrometry and machine learning to discover bioactive peptides. Nat Commun 13, 6235 (2022). https://www.nature.com/articles/s41467-022-34031-z

SignalP 6.0 predicts all five types of signal peptides using protein language models

Published in Nature Biotechnology, 2022

SignalP 6.0, the first signal peptide prediction model capable of predicting all known types of signal peptides. Online predictor Code

Recommended citation: Teufel, F., Almagro Armenteros, J.J., Johansen, A.R. et al. SignalP 6.0 predicts all five types of signal peptides using protein language models. Nat Biotechnol (2022). https://www.nature.com/articles/s41587-021-01156-3