Explore the vast range of titles available.

The support vector machine (SVM) algorithm is one of the most widely used machine learning (ML) methods for predicting active compounds and molecular properties. In chemoinformatics and drug discovery, SVM has been a state-of-the-art ML approach for more than a decade. A unique attribute of SVM is that it operates in feature spaces of increasing dimensionality. Hence, SVM conceptually departs from the paradigm of low dimensionality that applies to many other methods for chemical space navigation. The SVM approach is applicable to compound classification, and ranking, multi-class predictions, and –in algorithmically modified form– regression modeling. In the emerging era of deep learning (DL), SVM retains its relevance as one of the premier ML methods in chemoinformatics, for reasons discussed herein. We describe the SVM methodology including strengths and weaknesses and discuss selected applications that have contributed to the evolution of SVM as a premier approach for compound classification, property predictions, and virtual compound screening.

Difficulties in interpreting machine learning (ML) models and their predictions limit the practical applicability of and confidence in ML in pharmaceutical research. There is a need for agnostic approaches aiding in the interpretation of ML models regardless of their complexity that is also applicable to deep neural network (DNN) architectures and model ensembles. To these ends, the SHapley Additive exPlanations (SHAP) methodology has recently been introduced. The SHAP approach enables the identification and prioritization of features that determine compound classification and activity prediction using any ML model. Herein, we further extend the evaluation of the SHAP methodology by investigating a variant for exact calculation of Shapley values for decision tree methods and systematically compare this variant in compound activity and potency value predictions with the model-independent SHAP method. Moreover, new applications of the SHAP analysis approach are presented including interpretation of DNN models for the generation of multi-target activity profiles and ensemble regression models for potency prediction.

Machine learning (ML) systems can model quantitative structure-property relationships (QSPR) using existing experimental data and make property predictions for new molecules. With the advent of modalities such as targeted protein degraders (TPD), the applicability of QSPR models is questioned and ML usage in TPD-centric projects remains limited. Herein, ML models are developed and evaluated for TPDs’ property predictions, including passive permeability, metabolic clearance, cytochrome P450 inhibition, plasma protein binding, and lipophilicity. Interestingly, performance on TPDs is comparable to that of other modalities. Predictions for glues and heterobifunctionals often yield lower and higher errors, respectively. For permeability, CYP3A4 inhibition, and human and rat microsomal clearance, misclassification errors into high and low risk categories are lower than 4% for glues and 15% for heterobifunctionals. For all modalities, misclassification errors range from 0.8% to 8.1%. Investigated transfer learning strategies improve predictions for heterobifunctionals. This is the first comprehensive evaluation of ML for the prediction of absorption, distribution, metabolism, and excretion (ADME) and physicochemical properties of TPD molecules, including heterobifunctional and molecular glue sub-modalities. Taken together, our investigations show that ML-based QSPR models are applicable to TPDs and support ML usage for TPDs’ design, to potentially accelerate drug discovery. Targeted protein degraders are a recently developed drug modality for which it is unclear whether traditional QSAR can be applied. Here the authors show that classical ML can be used to predict properties of these drugs.

Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions to uncover relationships between target proteins. On the basis of a large-scale analysis generating and comparing machine learning models for more than 200 proteins, feature importance correlation analysis is shown to detect similar compound binding characteristics. Furthermore, rather unexpectedly, the analysis also reveals functional relationships between proteins that are independent of active compounds and binding characteristics. Feature importance correlation analysis does not depend on specific representations, algorithms, or metrics and is generally applicable as long as predictive models can be derived. Moreover, the approach does not require or involve explainable or interpretable machine learning, but only access to feature weights or importance values. On the basis of our findings, the approach represents a new facet of machine learning in drug discovery with potential for practical applications.

The use of copper (Cu 2+ ) and cobalt (Co 2+ ) has been described to stimulate blood vessel formation, a key process for the success of tissue regeneration. However, understanding how different concentrations of these ions affect cellular response is important to design scaffolds for their delivery to better fine tune the angiogenic response. On the one hand, gene expression analysis and the assessment of tubular formation structures with human umbilical vein endothelial cells (HUVEC) revealed that high concentrations (10μM) of Cu 2+ in early times and lower concentrations (0.1 and 1μM) at later times (day 7) enhanced angiogenic response. On the other hand, higher concentrations (25μM) of Co 2+ during all time course increased the angiogenic gene expression and 0.5, 5 and 25μM enhanced the ability to form tubular structures. To further explore synergistic effects combining both ions, the non-toxic concentrations were used simultaneously, although results showed an increased cell toxicity and no improvement of angiogenic response. These results provide useful information for the design of Cu 2+ or Co 2+ delivery scaffolds in order to release the appropriate concentration during time course for blood vessel stimulation.

The present study aimed at evaluating the effectiveness of different natural deep eutectic solvents (NADES) on the extraction of phenolic compounds from Lavandula pedunculata subsp. lusitanica (Chaytor) Franco, on the antioxidant activity, and acetylcholinesterase (AChE), butyrylcholinesterase (BChE) and tyrosinase (Tyr) inhibitory capacities. Ten different NADES were used in this research and compared with conventional solvents. Ultrasound-assisted extraction (UAE) for 60 min proved to be the best extraction condition, and proline:lactic acid (1:1) and choline chloride:urea (1:2) extracts showed the highest total phenolic contents (56.00 ± 0.77 mgGAE/gdw) and antioxidant activity [64.35 ± 1.74 mgTE/gdw and 72.13 ± 0.97 mgTE/gdw in 2.2-diphenyl-1-picrylhydrazyl (DPPH) and 2.2′-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS) methods, respectively]. These extracts also exhibited enzymes inhibitory capacity particularly against Tyr and AChE. Even so, organic acid-based NADES showed to be the best extractants producing extracts with considerable ability to inhibit enzymes. Twenty-four phenolic compounds were identified by HPLC-HRMS, being rosmarinic acid, ferulic acid and salvianolic acid B the major compounds. The results confirmed that the combination of UAE and NADES provide an excellent alternative to organic solvents for sustainable and green extraction, and have huge potential for use in industrial applications involving the extraction of bioactive compounds from plants.

Since their discovery, miRNAs have emerged as a promising therapeutical approach in the treatment of several diseases, as demonstrated by miR-212 and its relation to addiction. Here we prove that the miR-212/132 cluster can be regulated by morphine, through the activation of mu opioid receptor (Oprm1). The molecular pathways triggered after morphine administration also induce changes in the levels of expression of oprm1. In addition, miR-212/132 cluster is actively repressing the expression of mu opioid receptor by targeting a sequence in the 3' UTR of its mRNA. These findings suggest that this cluster is closely related to opioid signaling, and function as a post-transcriptional regulator, modulating morphine response in a dose dependent manner. The regulation of miR-212/132 cluster expression is mediated by MAP kinase pathway, CaMKII-CaMKIV and PKA, through the phosphorylation of CREB. Moreover, the regulation of both oprm1 and of the cluster promoter is mediated by MeCP2, acting as a transcriptional repressor on methylated DNA after prolonged morphine administration. This mechanism explains the molecular signaling triggered by morphine as well as the regulation of the expression of the mu opioid receptor mediated by morphine and the implication of miR-212/132 in these processes.

Hollow fibre renewal liquid membranes (HFRLMs) are susceptible to third-phase formation during rare earth element (REE) extraction using D2EHPA (bis(2-ethylhexyl phosphoric acid)), potentially leading to membrane fouling and decreased mass transfer efficiency. This study investigated the effects of various parameters, such as the composition of the aqueous feed and organic phases, on the third-phase formation and limiting organic concentration (LOC) of REE(III) in D2EHPA. Higher concentrations of REEs and a higher pH in the feed phase correlated with decreased mass transfer, while yttrium showed a greater propensity to induce third-phase formation compared to other REEs. Conditions favouring the use of linear aliphatic diluents, low extractant concentrations (5–10 v/v% D2EHPA) and the absence of modifiers also contributed to third-phase formation. The addition of tri-n-butyl phosphate (TBP) mitigated third-phase formation without evidence of synergy with D2EHPA. These findings provide key insights into formulating extraction systems that prevent third-phase formation in HFRLM processes.

Alterations of balance are a growing public health problem as they affect one in three adults over the age of 65, and one in two over the age of 80. Identifying the factors that affect postural stability is essential in designing specific interventions to maintain the independence and mobility of older people. The aim of this review was to understand the use of accelerometers in order to assess the balance in older people. Analyzing the most appropriate evaluation methodology and protocolizing it will optimize the processes of early identification of balance alterations. However, quantitative assessment methods of balance are usually limited to a laboratory environment, a factor that can be overcome by accelerometers. A systematic search was carried out across eight databases where accelerometers were employed to assess balance in older people. Articles were excluded if they focused on sensor design and did not measure balance or apply the technology on targeted participants. A total of 19 articles were included for full-text analysis, where participants took part in the balance evaluation monitored by accelerometers. The analysis of spatio-temporal parameters and the magnitude of the accelerations recorded by the devices were the most common study variables. Accelerometer usage has potential to positively influence interventions based on physical exercise to improve balance and prevent falls in older people.

Health-promoting foods are attracting growing interest as complements to pharmacological interventions, particularly when incorporated into bioactive-enriched functional foods. The date palm (Phoenix dactylifera L.) plays a key socio-economic role in arid and semi-arid regions, and is widely recognized for its high nutritional value, functional attributes, and therapeutic potential. Date fruits and their processing by-products, particularly the seeds, are a rich source of essential nutrients, dietary fiber, and diverse phytochemicals with documented antioxidant, anti-inflammatory, antidiabetic, and antimicrobial properties. This narrative review summarizes the latest evidence from experimental, preclinical, and emerging clinical studies on the nutritional composition, phytochemical profile, and biofunctional properties of dates and their derivatives, with particular emphasis on seeds as a significant processing by-product. Recent advances in their valorization for food applications, including bakery products, dairy products, beverages, meat products, confectionery, and active packaging, are critically discussed, as are their emerging uses in the pharmaceutical and related industries. Particular attention is given to their potential to improve the nutritional quality, functional performance, sensory attributes, and shelf life of food products. Overall, date fruits and their by-products are cost-effective, natural, and sustainable ingredients for developing value-added functional foods. Their efficient valorization offers promising strategies for reducing waste, implementing circular economy principles, and meeting the increasing consumer demand for healthier products. This review highlights the need for multidisciplinary research and innovation to advance sustainable by-product utilization, improve agro-industrial waste management, and expand the range of high-value applications for date fruits and seeds, thereby contributing to global food security, economic development, and improved public health.