👤 X Orozco-Ruiz

An increased number of low-density lipoprotein particles (LDL-P) is a common feature of patients with Metabolic syndrome (MetS). Increasing the size of these particles is one of the primary therapeutic and dietary interventions goals. However, genetic variability, like single nucleotide polymorphisms (SNPs), modulate the response to dietary strategies. Therefore, we hypothesise that the presence of SNPs in genes associated with MetS may modulate the effect of a dietary intervention on the size of LDL-P. This was a before-and-after clinical study conducted with 146 participants with MetS. The participants underwent a lifestyle intervention for 10 weeks. At baseline the presence of SNPs associated with MetS were determined. Anthropometric, biochemical, hormonal parameters, and lipoprotein analysis were taken before and after the intervention. Results revealed that the common homozygous ATP-binding cassette transporter A1 (ABCA1) genotype was associated with a decreased LDL-C concentration. However, after adjusting for sex, age and baseline weight, polymorphisms in the fat mass and obesity-associated (FTO) gene, the peroxisome proliferator-activated receptor (PPARγ), and the apolipoprotein E (APOE) gene were associated with a better response to the intervention in terms of increasing LDL-P size. Our results revealed changes in LDL-P size associated with polymorphisms in the APOE, FTO and PPARγ genes in response to the dietary intervention. These results highlight the importance of genetic factors in personalized nutritional strategies aimed at improving cardiovascular risk in patients with MetS. NCT03611140, www. gov. Show less

Chemical descriptors encode the physicochemical and structural properties of small molecules, and they are at the core of chemoinformatics. The broad release of bioactivity data has prompted enriched representations of compounds, reaching beyond chemical structures and capturing their known biological properties. Unfortunately, bioactivity descriptors are not available for most small molecules, which limits their applicability to a few thousand well characterized compounds. Here we present a collection of deep neural networks able to infer bioactivity signatures for any compound of interest, even when little or no experimental information is available for them. Our signaturizers relate to bioactivities of 25 different types (including target profiles, cellular response and clinical outcomes) and can be used as drop-in replacements for chemical descriptors in day-to-day chemoinformatics tasks. Indeed, we illustrate how inferred bioactivity signatures are useful to navigate the chemical space in a biologically relevant manner, unveiling higher-order organization in natural product collections, and to enrich mostly uncharacterized chemical libraries for activity against the drug-orphan target Snail1. Moreover, we implement a battery of signature-activity relationship (SigAR) models and show a substantial improvement in performance, with respect to chemistry-based classifiers, across a series of biophysics and physiology activity prediction benchmarks. Show less