User profiles for Ole Winther

Ole Winther

Biology, Univ of Copenhagen, Genomic Medicine, Rigshospitalet and Technical University …
Verified email at bio.ku.dk
Cited by 23764

SignalP 5.0 improves signal peptide predictions using deep neural networks

…, CK Sønderby, TN Petersen, O Winther… - Nature …, 2019 - nature.com
Signal peptides (SPs) are short amino acid sequences in the amino terminus of many newly
synthesized proteins that target proteins into, or across, membranes. Bioinformatic tools can …

Ladder variational autoencoders

…, L Maaløe, SK Sønderby, O Winther - Advances in neural …, 2016 - proceedings.neurips.cc
Variational autoencoders are powerful models for unsupervised learning. However deep
models with several layers of dependent stochastic variables are difficult to train which limits …

NetSurfP‐2.0: Improved prediction of protein structural features by integrated deep learning

…, MOA Sommer, O Winther… - Proteins: Structure …, 2019 - Wiley Online Library
The ability to predict local structural features of a protein from the primary sequence is of
paramount importance for unraveling its function in absence of experimental structural …

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

…, MH Gíslason, SI Pihl, KD Tsirigos, O Winther… - Nature …, 2022 - nature.com
Signal peptides (SPs) are short amino acid sequences that control protein secretion and
translocation in all living organisms. SPs can be predicted from sequence data, but existing …

Autoencoding beyond pixels using a learned similarity metric

…, H Larochelle, O Winther - … on machine learning, 2016 - proceedings.mlr.press
We present an autoencoder that leverages learned representations to better measure
similarities in data space. By combining a variational autoencoder (VAE) with a generative …

JASPAR, the open access database of transcription factor-binding profiles: new content and tools in the 2008 update

…, MHE Tang, T Marstrand, O Winther… - Nucleic acids …, 2007 - academic.oup.com
JASPAR is a popular open-access database for matrix models describing DNA-binding
preferences for transcription factors and other DNA patterns. With its third major release, …

DeepLoc: prediction of protein subcellular localization using deep learning

…, SK Sønderby, H Nielsen, O Winther - …, 2017 - academic.oup.com
Motivation The prediction of eukaryotic protein subcellular localization is a well-studied
topic in bioinformatics due to its relevance in proteomics research. Many machine learning …

DeepTMHMM predicts alpha and beta transmembrane proteins using deep neural networks

…, P Marcatili, H Nielsen, A Krogh, O Winther - BioRxiv, 2022 - biorxiv.org
Transmembrane proteins span the lipid bilayer and are divided into two major structural
classes, namely alpha helical and beta barrels. We introduce DeepTMHMM, a deep learning …

DeepLoc 2.0: multi-label subcellular localization prediction using protein language models

…, AR Johansen, H Nielsen, O Winther - Nucleic Acids …, 2022 - academic.oup.com
The prediction of protein subcellular localization is of great relevance for proteomics research.
Here, we propose an update to the popular tool DeepLoc with multi-localization prediction …

Detecting sequence signals in targeting peptides using deep learning

…, M Salvatore, O Emanuelsson, O Winther… - Life science …, 2019 - life-science-alliance.org
In bioinformatics, machine learning methods have been used to predict features embedded
in the sequences. In contrast to what is generally assumed, machine learning approaches …