Johansen, A. R. | bioRxiv Science

bioRxiv2020

Language modelling for biological sequences - curated datasets and baselines

MotivationLanguage modelling (LM) on biological sequences is an emergent topic in the field of bioinformatics. Current research has shown that language modelling of proteins can create context-dependent representations that can be applied to improve performance on different protein prediction tasks. However, little effort has been directed towards analyzing the properties of the datasets used to train language models. Additionally, only the performance of cherry-picked downstream tasks are used to assess the capacity of LMs. ResultsWe analyze the entire UniProt database and investigate the different properties that can bias or hinder the performance of LMs such as homology, domain of origin, quality of the data, and completeness of the sequence. We evaluate n-gram and Recurrent Neural Network (RNN) LMs to assess the impact of these properties on performance. To our knowledge, this is the first protein dataset with an emphasis on language modelling. Our inclusion of properties specific to proteins gives a detailed analysis of how well natural language processing methods work on biological sequences. We find that organism domain and quality of data have an impact on the performance, while the completeness of the proteins has little influence. The RNN based LM can learn to model Bacteria, Eukarya, and Archaea; but struggles with Viruses. By using the LM we can also generate novel proteins that are shown to be similar to real proteins. Availability and implementationhttps://github.com/alrojo/UniLanguage

bioinformatics↗

bioRxiv2019

Prediction of GPI-Anchored proteins with pointer neural networks

GPI-anchors constitute a very important post-translational modification, linking many proteins to the outer face of the plasma membrane in eukaryotic cells. Since experimental validation of GPI-anchoring signals is slow and costly, computational approaches for predicting them from amino acid sequences are needed. However, the most recent GPI predictor is more than a decade old and considerable progress has been made in machine learning since then. We present a new dataset and a novel method, NetGPI, for GPI signal prediction. NetGPI is based on recurrent neural networks, incorporating an attention mechanism that simultaneously detects GPI-anchoring signals and points out the location of their{omega} -sites. The performance of NetGPI is superior to existing methods with regards to discrimination between GPI-anchored proteins and other secretory proteins and approximate ({+/-}1 position) placement of the{omega} -site. NetGPI is available at: https://services.healthtech.dtu.dk/service.php?NetGPI The code repository is available at: https://github.com/mhgislason/netgpi-1.1

bioinformatics↗