Matthes, F. | bioRxiv Science

bioRxiv2020

Simvastatin Therapy Attenuates Memory Deficits that Associate to Brain Monocyte Infiltration in Chronic Hypercholesterolemic ApoE-/- Mice

Evidence associates cardiovascular risk factors with unfavorable systemic and neuro-inflammation and cognitive decline in the elderly. Cardiovascular therapeutics (e.g., statins and anti-hypertensives) possess immune-modulatory functions in parallel to their cholesterol- or blood pressure (BP)-lowering properties. How their ability to modify immune responses affects cognitive function is unknown. Here, we examined the effect of chronic hypercholesterolemia on inflammation and memory function in Apolipoprotein E (ApoE) knockout mice and normocholesterolemic wild-type mice. Chronic hypercholesterolemia that was accompanied by moderate blood pressure elevations associated with apparent immune system activation characterized by increases in circulating pro-inflammatory Ly6Chi monocytes in ApoE-/- mice. The persistent low-grade immune activation that is associated with chronic hypercholesterolemia facilitates the infiltration of pro-inflammatory Ly6Chi monocytes into the brain of aged ApoE-/- but not wild-type mice, and links to memory dysfunction. Therapeutic cholesterol-lowering through simvastatin reduced systemic and neuro-inflammation, and the occurrence of memory deficits in aged ApoE-/- mice with chronic hypercholesterolemia. BP-lowering therapy alone (i.e., hydralazine) attenuated some neuro-inflammatory signatures but not the occurrence of memory deficits. Our study suggests a link between chronic hypercholesterolemia, myeloid cell activation and neuro-inflammation with memory impairment and encourages cholesterol-lowering therapy as safe strategy to control hypercholesterolemia-associated memory decline during ageing.

physiology↗

bioRxiv2019

Modeling the Language of Life - Deep Learning Protein Sequences

BackgroundOne common task in Computational Biology is the prediction of aspects of protein function and structure from their amino acid sequence. For 26 years, most state-of-the-art approaches toward this end have been marrying machine learning and evolutionary information. The retrieval of related proteins from ever growing sequence databases is becoming so time-consuming that the analysis of entire proteomes becomes challenging. On top, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome.\n\nResultsWe introduce a novel way to represent protein sequences as continuous vectors (embeddings) by using the deep bi-directional model ELMo taken from natural language processing (NLP). The model has effectively captured the biophysical properties of protein sequences from unlabeled big data (UniRef50). After training, this knowledge is transferred to single protein sequences by predicting relevant sequence features. We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple convolutional neural networks on existing data sets for two completely different prediction tasks. At the per-residue level, we significantly improved secondary structure (for NetSurfP-2.0 data set: Q3=79%{+/-}1, Q8=68%{+/-}1) and disorder predictions (MCC=0.59{+/-}0.03) over methods not using evolutionary information. At the per-protein level, we predicted subcellular localization in ten classes (for DeepLoc data set: Q10=68%{+/-}1) and distinguished membrane-bound from water-soluble proteins (Q2= 87%{+/-}1). All results built upon the embeddings gained from the new tool SeqVec neither explicitly nor implicitly using evolutionary information. Nevertheless, it improved over some methods using such information. Where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created the vector representation on average in 0.03 seconds.\n\nConclusionWe have shown that transfer learning can be used to capture biochemical or biophysical properties of protein sequences from large unlabeled sequence databases. The effectiveness of the proposed approach was showcased for different prediction tasks using only single protein sequences. SeqVec embeddings enable predictions that outperform even some methods using evolutionary information. Thus, they prove to condense the underlying principles of protein sequences. This might be the first step towards competitive predictions based only on single protein sequences.\n\nAvailabilitySeqVec: https://github.com/mheinzinger/SeqVec Prediction server: https://embed.protein.properties

bioinformatics↗