High-density lipoprotein (HDL) nanoparticles promote endothelial cell (EC) function and suppress inflammation, but their utility in treating EC dysfunction has not been fully explored.  Here, we describe a fusion protein named ApoA1-ApoM (A1M) consisting of apolipoprotein A1 (ApoA1), the principal structural protein of HDL that forms lipid nanoparticles, and ApoM, a chaperone for the bioactive lipid sphingosine 1-phosphate (S1P). A1M forms HDL-like particles, binds S1P, and is signaling competent. Molecular dynamic simulations showed that the S1P-bound ApoM moiety in A1M efficiently activated the EC surface receptors. Treatment of human umbilical vein endothelial cells (HUVECs) with A1M-S1P stimulated barrier function either alone or cooperatively with other barrier-enhancing molecules, including the stable prostacyclin analog iloprost, and suppressed cytokine-induced inflammation. A1M-S1P injection into mice during sterile inflammation suppressed neutrophil influx and inflammatory mediator secretion. Moreover, systemic A1M administration led to a sustained increase in circulating HDL-bound S1P and suppressed inflammation in a murine model of LPS-induced endotoxemia. We propose that A1M administration may enhance vascular endothelial barrier function, suppress cytokine storm, and promote resilience of the vascular endothelium.

In cancer research, high-throughput screening technologies produce large amounts of multiomics data from different populations and cell types. However, analysis of such data encounters difficulties due to disease heterogeneity, further exacerbated by human biological complexity and genomic variability. The specific profile of cancer as a disease (or, more realistically, a set of diseases) urges the development of approaches that maximize the effect while minimizing the dosage of drugs. Now is the time to redefine the approach to drug discovery, bringing an Artificial Intelligence (AI)-powered informational view that integrates the relevant scientific fields and explores new territories.
Here, we show SYNPRED, an interdisciplinary approach that leverages specifically designed ensembles of AI algorithms, links omics and biophysical traits to predict anticancer drug synergy. It uses four reference models (Bliss, Highest Single Agent, Loewe, and Zero Interaction Potency), which, coupled with AI algorithms, allowed us to attain the ones with the best predictive performance and pinpoint the most appropriate reference model for synergy prediction, often overlooked in similar studies. By using an independent test set, SYNPRED exhibits state-of-the-art performance metrics either in the classification (accuracy 0.80, precision 0.81, recall 0.81, AUROC 0.80, and F1-score - 0.81) or in the regression models, mainly when using the Zero Interaction Potency synergy reference model (RMSE 7.10, MSE 50.46, Pearson 0.80, R2 0.43, MAE 4.61, Spearman 0.73). Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches. A simple web-based application was constructed, allowing easy access by non-expert researchers.
The performance of SYNPRED rivals that of the existing methods that tackle the same problem, yielding unbiased results trained with one of the most comprehensive datasets available (NCI-ALMANAC). The leveraging of different reference models allowed deeper insights into which of them is the most appropriate one to use for synergy prediction. The Zero Interaction Potency clearly stood out with improved performance among the full scope of surveyed approaches and synergy reference models. Furthermore, SYNPRED takes a particular focus on data interpretability, which has been in the spotlight lately when using the most advanced AI techniques.

MEmbrane protein dimer Novel Structure Analyser database (MENSAdb) contains essential evolutionary and physico-chemical properties of membrane complexes to understand the basic principles underlying their formation.

MEmbrane protein dimer Novel Structure Analyser database (MENSAdb) contains essential evolutionary and physico-chemical properties of membrane complexes to understand the basic principles underlying their formation.

MEmbrane protein dimer Novel Structure Analyser database (MENSAdb) contains essential evolutionary and physico-chemical properties of membrane complexes to understand the basic principles underlying their formation.

MEmbrane protein dimer Novel Structure Analyser database (MENSAdb) contains essential evolutionary and physico-chemical properties of membrane complexes to understand the basic principles underlying their formation.