Research into how carvacrol and metformin affect several human proteins in a hyperglycemic condition: A comparative study in silico and in vitro.

Carvacrol (CV) is an organic compound found in the essential oils of many aromatic herbs. It is nearly unfeasible to analyze all the current human proteins for a query ligand using in vitro and in vivo methods. This study aimed to clarify whether CV possesses an anti-diabetic feature via Docking-based inverse docking and molecular dynamic (MD) simulation and in vitro characterization against a set of novel human protein targets. Herein, the best poses of CV docking simulations according to binding energy ranged from -7.9 to -3.5 (kcal/mol). After pathway analysis of the protein list through GeneMANIA and WebGestalt, eight interacting proteins (DPP4, FBP1, GCK, HSD11ß1, INSR, PYGL, PPARA, and PPARG) with CV were determined, and these proteins exhibited stable structures during the MD process with CV. In vitro application, statistically significant results were achieved only in combined doses with CV or metformin. Considering all these findings, PPARG and INSR, among these target proteins of CV, are FDA-approved targets for treating diabetes. Therefore, CV may be on its way to becoming a promising therapeutic compound for treating Diabetes Mellitus (DM). Our outcomes expose formerly unexplored potential target human proteins, whose association with diabetic disorders might guide new potential treatments for DM.

ESSENCE-Dock: A Consensus-Based Approach to Enhance Virtual Screening Enrichment in Drug Discovery.

Drug development is a complex, costly, and time-consuming endeavor. While high-throughput screening (HTS) plays a critical role in the discovery stage, it is one of many factors contributing to these challenges. In certain contexts, virtual screening can complement the HTS, potentially offering a more streamlined approach in the initial stages of drug discovery. Molecular docking is an example of a popular virtual screening technique that is often used for this purpose; however, its effectiveness can vary greatly. This has led to the use of consensus docking approaches that combine results from different docking methods to improve the identification of active compounds and reduce the occurrence of false positives. However, many of these methods do not fully leverage the latest advancements in molecular docking. In response, we present ESSENCE-Dock (Effective Structural Screening ENrichment ConsEnsus Dock), a new consensus docking workflow aimed at decreasing false positives and increasing the discovery of active compounds. By utilizing a combination of novel docking algorithms, we improve the selection process for potential active compounds. ESSENCE-Dock has been made to be user-friendly, requiring only a few simple commands to perform a complete screening while also being designed for use in high-performance computing (HPC) environments.

Comparative assessment of different anti-CD147/Basigin 2 antibodies as a potential therapeutic anticancer target by molecular modeling and dynamic simulation.

Cluster of differentiation 147 (CD147) is an attractive target for anticancer therapy since it is pivotal in developing and progressing several of malignant tumors in the context of its high expression levels. Although anti-CD147 antibodies by different laboratories are designed for the Ig-like domains of CD147, there is a demand to provide priority among these anti-CD147 antibodies for developing of therapeutic anti-CD147 antibody before experimental validations. This study uses molecular docking and dynamic simulation techniques to compare the binding modes and affinities of nine antibody models against the Ig-like domains of CD147. After obtaining the model antibodies by homology modeling via Robetta, we predicted the CDRs of nine antibodies and the epitopes of CD147 to reach more accurate results for antigen affinity in molecular docking. Next, from HADDOCK 2.4., we meticulously handpicked the most superior model clusters (Z-Score: - 2.5 to - 1.2) and identified that meplazumab had higher affinities according to the success rate as the percentage of a scoring scale. We achieved stable simulations of CD147-antibody interaction. Our outcomes hold hypothetical importance for further experimental cancer research on the design and development of the relevant model antibodies.

Accelerating Big Data Analysis through LASSO-Random Forest Algorithm in QSAR Studies.

MOTIVATION: The aim of quantitative structure-activity prediction (QSAR) studies is to identify novel drug-like molecules that can be suggested as lead compounds by means of two approaches, which are discussed in this article. First, to identify appropriate molecular descriptors by focusing on one feature-selection algorithms; and second to predict the biological activities of designed compounds. Recent studies have shown increased interest in the prediction of a huge number of molecules, known as Big Data, using deep learning models. However, despite all these efforts to solve critical challenges in QSAR models, such as over-fitting, massive processing procedures, is major shortcomings of deep learning models. Hence, finding the most effective molecular descriptors in the shortest possible time is an ongoing task. One of the successful methods to speed up the extraction of the best features from big datasets is the use of least absolute shrinkage and selection operator (LASSO). This algorithm is a regression model that selects a subset of molecular descriptors with the aim of enhancing prediction accuracy and interpretability because of removing inappropriate and irrelevant features. RESULTS: To implement and test our proposed model, a random forest was built to predict the molecular activities of Kaggle competition compounds. Finally, the prediction results and computation time of the suggested model were compared with the other well-known algorithms, i.e. Boruta-random forest, deep random forest and deep belief network model. The results revealed that improving output correlation through LASSO-random forest leads to appreciably reduced implementation time and model complexity, while maintaining accuracy of the predictions. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Addendum: MCC950 closes the active conformation of NLRP3 to an inactive state.

An Addendum to this paper has been published: https://doi.org/10.1038/s41589-021-00741-6.

Piperazine-derived small molecules as potential Flaviviridae NS3 protease inhibitors. In vitro antiviral activity evaluation against Zika and Dengue viruses.

Since 2011 Direct Acting antivirals (DAAs) drugs targeting different non-structural (NS) viral proteins (NS3, NS5A or NS5B inhibitors) have been approved for clinical use in HCV therapies. However, currently there are not licensed therapeutics to treat Flavivirus infections and the only licensed DENV vaccine, Dengvaxia, is restricted to patients with preexisting DENV immunity. Similarly to NS5 polymerase, the NS3 catalytic region is evolutionarily conserved among the Flaviviridae family sharing strong structural similarity with other proteases belonging to this family and therefore is an attractive target for the development of pan-flavivirus therapeutics. In this work we present a library of 34 piperazine-derived small molecules as potential Flaviviridae NS3 protease inhibitors. The library was developed through a privileged structures-based design and then biologically screened using a live virus phenotypic assay to determine the half-maximal inhibitor concentration (IC50) of each compound against ZIKV and DENV. Two lead compounds, 42 and 44, with promising broad-spectrum activity against ZIKV (IC50 6.6 µM and 1.9 µM respectively) and DENV (IC50 6.7 µM and 1.4 µM respectively) and a good security profile were identified. Besides, molecular docking calculations were performed to provide insights about key interactions with residues in NS3 proteases' active sites.

Fishing the Targets of Bioactive Compounds from Psidium guajava L. Leaves in the Context of Diabetes.

Psidium guajava L. (guava) leaves have demonstrated their in vitro and in vivo effect against diabetes mellitus (DM). However, there is a lack of literature concerning the effect of the individual phenolic compounds present in the leaves in DM disease. The aim of the present work was to identify the individual compounds in Spanish guava leaves and their potential contribution to the observed anti-diabetic effect. Seventy-three phenolic compounds were identified from an 80% ethanol extract of guava leaves by high performance liquid chromatography coupled to electrospray ionization and quadrupole time-of-flight mass spectrometry. The potential anti-diabetic activity of each compound was evaluated with the DIA-DB web server that uses a docking and molecular shape similarity approach. The DIA-DB web server revealed that aldose reductase was the target protein with heterogeneous affinity for compounds naringenin, avicularin, guaijaverin, quercetin, ellagic acid, morin, catechin and guavinoside C. Naringenin exhibited the highest number of interactions with target proteins dipeptidyl peptidase-4, hydroxysteroid 11-beta dehydrogenase 1, aldose reductase and peroxisome proliferator-activated receptor. Compounds catechin, quercetin and naringenin displayed similarities with the known antidiabetic drug tolrestat. In conclusion, the computational workflow showed that guava leaves contain several compounds acting in the DM mechanism by interacting with specific DM protein targets.

A Phytoprostane from Gracilaria longissima Increases Platelet Activation, Platelet Adhesion to Leukocytes and Endothelial Cell Migration by Potential Binding to EP3 Prostaglandin Receptor.

Plant phytoprostanes (PhytoPs) are lipid oxidative stress mediators that share structural similarities with mammal prostaglandins (PGs). They have been demonstrated to modulate inflammatory processes mediated by prostaglandins. The present study aims to test the effects of the most abundant oxylipin from Gracilaria longissima, ent-9-D1t-Phytoprostane (9-D1t-PhytoP), on platelet activation and vascular cells as well as clarify possible interactions with platelets and the endothelial EP3 receptor Platelet and monocyte activation was assessed by flow cytometry in the presence of purified 9-D1t-PhytoP. Cell migration was studied using the human Ea.hy926 cell line by performing a scratch wound healing assay. The RNA expression of inflammatory markers was evaluated by RT-PCR under inflammatory conditions. Blind docking consensus was applied to the study of the interactions of selected ligands against the EP3 receptor protein. The 9D1t-PhytoP exerts several pharmacological effects; these include prothrombotic and wound-healing properties. In endothelial cells, 9D1t-PhytP mimics the migration stimulus of PGE2. Computational analysis revealed that 9D1t-PhytP forms a stable complex with the hydrophobic pocket of the EP3 receptor by interaction with the same residues as misoprostol and prostaglandin E2 (PGE2), thus supporting its potential as an EP3 agonist. The potential to form procoagulant platelets and the higher endothelial migration rate of the 9-D1t-PhytoP, together with its capability to interact with PGE2 main target receptor in platelets suggest herein that this oxylipin could be a strong candidate for pharmaceutical research from a multitarget perspective.

Effects of In Vitro Digestion of Polyphenols from Coffee on Binding Parameters to Human Topoisomerase II α.

Type II topoisomerase (TOPII) is an enzyme that influences the topology of DNA. DNA breaks generated by TOPII may result in mutagenic or cytotoxic changes in cancer cells. In this study, we characterized interactions of TOPIIα with coffee extracts and individual chlorogenic acids (CHAs) from the extracts by performing isothermal titration calorimetry (ITC) and molecular docking (MD) simulations. The study showed that the highest affinity to TOPIIα was found in green coffee (ΔG = -38.23 kJ/mol) and monochlorogenic acids fraction of coffee extracts (ΔG = -35.80 kJ/mol), resulting from the high content of polyphenols, such as CHAs, which can bind to the enzyme in the active site. Coffee extracts and their fractions maintained a high affinity for TOPIIα after simulated digestion in the presence of probiotic bacteria. It can be concluded that coffee may be a potential TOPIIα inhibitor considered as a functional food for cancer prevention.

Flavonoids improve the stability and function of P23H rhodopsin slowing down the progression of retinitis pigmentosa in mice.

The balanced homeostasis of the G protein-coupled receptor (GPCR), rhodopsin (Rho), is required for vision. Misfolding mutations in Rho cause photoreceptor death, leading to retinitis pigmentosa (RP) and consequently blindness. With no cure currently available, the development of efficient therapy for RP is an urgent need. Pharmacological supplementation with molecular chaperones, including flavonoids, improves stability, folding, and membrane targeting of the RP Rho mutants in vitro. Thus, we hypothesized that flavonoids by binding to P23H Rho and enhancing its conformational stability could mitigate detrimental effects of this mutation on retinal health. In this work, we evaluated the pharmacological potential of two model flavonoids, quercetin and myricetin, by using in silico, in vitro, and in vivo models of P23H Rho. Our computational analysis showed that quercetin could interact within the orthosteric binding pocket of P23H Rho and shift the conformation of its N-terminal loop toward the wild type (WT)-like state. Quercetin added to the NIH-3T3 cells stably expressing P23H Rho increased the stability of this receptor and improved its function. Systemic administration of quercetin to P23H Rho knock-in mice substantially improved retinal morphology and function, which was associated with an increase in levels of Rho and cone opsins. In addition, treatment with quercetin resulted in downregulation of the UPR signaling and oxidative stress-related markers. This study unravels the pharmacological potential of quercetin to slow down the progression of photoreceptor death in Rho-related RP and highlights its prospective as a lead compound to develop a novel therapeutic remedy to counter RP pathology.

METADOCK 2: a high-throughput parallel metaheuristic scheme for molecular docking.

MOTIVATION: Molecular docking methods are extensively used to predict the interaction between protein-ligand systems in terms of structure and binding affinity, through the optimization of a physics-based scoring function. However, the computational requirements of these simulations grow exponentially with: (i) the global optimization procedure, (ii) the number and degrees of freedom of molecular conformations generated and (iii) the mathematical complexity of the scoring function. RESULTS: In this work, we introduce a novel molecular docking method named METADOCK 2, which incorporates several novel features, such as (i) a ligand-dependent blind docking approach that exhaustively scans the whole protein surface to detect novel allosteric sites, (ii) an optimization method to enable the use of a wide branch of metaheuristics and (iii) a heterogeneous implementation based on multicore CPUs and multiple graphics processing units. Two representative scoring functions implemented in METADOCK 2 are extensively evaluated in terms of computational performance and accuracy using several benchmarks (such as the well-known DUD) against AutoDock 4.2 and AutoDock Vina. Results place METADOCK 2 as an efficient and accurate docking methodology able to deal with complex systems where computational demands are staggering and which outperforms both AutoDock Vina and AutoDock 4. AVAILABILITY AND IMPLEMENTATION: https://Baldoimbernon@bitbucket.org/Baldoimbernon/metadock_2.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Studying noncovalent or covalent bond problem between smoothened and cholesterol by molecular dynamics simulation and Markov state model.

Smoothened (SMO) is an attractive therapeutic target for the treatment and prevention of several malignant tumors of the nervous system. The crystal structure of SMO shows cholesterol interacts with residue Asp95 via the noncovalent bond. However, some studies indicate that cholesterol covalently binds to residue Asp95 of SMO. To study these contradictory results, we performed molecular dynamics (MD) simulations and Markov state model (MSM) on SMO in complex with noncovalent-bound and covalent-bound cholesterol. The MD simulated results showed that the noncovalent-bound cholesterol was extremely unstable around the position of residue Asp95 of SMO, while the covalent-bound cholesterol could keep the stable connection with residue Asp95 of SMO. The free energy landscape showed that noncovalent-bound cholesterol had more deep energy wells than covalent-bound cholesterol when it dynamically interacted with the extracellular domain of SMO crystal structure. The MSM results showed the noncovalent-bound cholesterol had more dynamic configuration transformation pathways than the covalent-bound cholesterol. These results theoretically revealed cholesterol should have a covalent bond with residue Asp95 if cholesterol could be stable in the near position of residue Asp95 of SMO. Our studies not only elucidate the covalent binding contradictory issue between cholesterol and residue Asp95 of SMO, but also supply helpful information for antagonists design of SMO.

Ligand-based virtual screening, molecular docking, and molecular dynamics of eugenol analogs as potential acetylcholinesterase inhibitors with biological activity against Spodoptera frugiperda.

The development of new, more selective, environmental-friendly insecticide alternatives is in high demand for the control of Spodoptera frugiperda (S. frugiperda). The major objective of this work was to search for new potential S. frugiperda acetylcholinesterase (AChE) inhibitors. A ligand-based virtual screening was initially carried out considering six scaffolds derived from eugenol and the ZINC15, PubChem, and MolPort databases. Subsequently, molecular docking analysis of the selected compounds on the active site and a second region (determined by blind molecular docking) of the AChE of S. frugiperda was performed. Molecular dynamics and Molecular Mechanics Poisson-Boltzmann Surface Area analyses were also applied to improve the docking results. Finally, three new eugenol analogs were evaluated in vitro against S. frugiperda larvae. The virtual screening identified 1609 compounds from the chemical libraries. Control compounds were selected from the interaction fingerprint by molecular docking. Only three new eugenol analogs (1, 3, and 4) were stable at 50 ns by molecular dynamics. Compounds 1 and 4 had the best biological activity by diet (LC50 = 0.042 mg/mL) and by topical route (LC50 = 0.027 mg/mL), respectively. At least three new eugenol derivatives possessed good-to-excellent insecticidal activity against S. frugiperda.

African derived phytocompounds may interfere with SARS-CoV-2 RNA capping machinery via inhibition of 2'-O-ribose methyltransferase: An in silico perspective.

Despite the ongoing vaccination against the life-threatening COVID-19, there is need for viable therapeutic interventions. The S-adenosyl-l-Methionine (SAM) dependent 2-O'-ribose methyltransferase (2'-O-MTase) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) presents a therapeutic target against COVID-19 infection. In a bid to profile bioactive principles from natural sources, a custom-made library of 226 phytochemicals from African medicinal plants with especially anti-malarial activity was screened for direct interactions with SARS-CoV-2 2'-O-MTase (S2RMT) using molecular docking and molecular dynamics (MD) simulations as well as binding free energies methods. Based on minimal binding energy lower than sinefungin (a reference methyl-transferase inhibitor) and binding mode analysis at the catalytic site of S2RMT, a list of 26 hit phytocompounds was defined. The interaction of these phytocompounds was compared with the 2'-O-MTase of SARS-CoV and MERS-CoV. Among these compounds, the lead phytocompounds (LPs) viz: mulberrofuran F, 24-methylene cycloartenol, ferulate, 3-benzoylhosloppone and 10-hydroxyusambarensine interacted strongly with the conserved KDKE tetrad within the substrate binding pocket of the 2'-O-MTase of the coronavirus strains which is critical for substrate binding. The thermodynamic parameters analyzed from the MD simulation trajectories of the LPs-S2RMT complexes presented an eminent structural stability and compactness. These LPs demonstrated favorable druggability and in silico ADMET properties over a diverse array of molecular computing descriptors. The LPs show promising prospects in the disruption of S2RMT capping machinery in silico. However, these LPs should be validated via in vitro and in vivo experimental models.

Identification of Kukoamine A, Zeaxanthin, and Clexane as New Furin Inhibitors.

The endogenous protease furin is a key protein in many different diseases, such as cancer and infections. For this reason, a wide range of studies has focused on targeting furin from a therapeutic point of view. Our main objective consisted of identifying new compounds that could enlarge the furin inhibitor arsenal; secondarily, we assayed their adjuvant effect in combination with a known furin inhibitor, CMK, which avoids the SARS-CoV-2 S protein cleavage by means of that inhibition. Virtual screening was carried out to identify potential furin inhibitors. The inhibition of physiological and purified recombinant furin by screening selected compounds, Clexane, and these drugs in combination with CMK was assayed in fluorogenic tests by using a specific furin substrate. The effects of the selected inhibitors from virtual screening on cell viability (293T HEK cell line) were assayed by means of flow cytometry. Through virtual screening, Zeaxanthin and Kukoamine A were selected as the main potential furin inhibitors. In fluorogenic assays, these two compounds and Clexane inhibited both physiological and recombinant furin in a dose-dependent way. In addition, these compounds increased physiological furin inhibition by CMK, showing an adjuvant effect. In conclusion, we identified Kukoamine A, Zeaxanthin, and Clexane as new furin inhibitors. In addition, these drugs were able to increase furin inhibition by CMK, so they could also increase its efficiency when avoiding S protein proteolysis, which is essential for SARS-CoV-2 cell infection.

Senescence-Independent Anti-Inflammatory Activity of the Senolytic Drugs Dasatinib, Navitoclax, and Venetoclax in Zebrafish Models of Chronic Inflammation.

Telomere shortening is the main molecular mechanism of aging, but not the only one. The adaptive immune system also ages, and older organisms tend to develop a chronic pro-inflammatory status with low-grade inflammation characterized by chronic activation of the innate immune system, called inflammaging. One of the main stimuli that fuels inflammaging is a high nutrient intake, triggering a metabolic inflammation process called metainflammation. In this study, we report the anti-inflammatory activity of several senolytic drugs in the context of chronic inflammation, by using two different zebrafish models: (i) a chronic skin inflammation model with a hypomorphic mutation in spint1a, the gene encoding the serine protease inhibitor, kunitz-type, 1a (also known as hai1a) and (ii) a non-alcoholic fatty liver disease/non-alcoholic steatohepatitis (NAFLD/NASH) model with inflammation induced by a high-fat diet. Our results show that, although these models do not manifest premature aging, the senolytic drugs dasatinib, navitoclax, and venetoclax have an anti-inflammatory effect that results in the amelioration of chronic inflammation.

Computational Study of Asian Propolis Compounds as Potential Anti-Type 2 Diabetes Mellitus Agents by Using Inverse Virtual Screening with the DIA-DB Web Server, Tanimoto Similarity Analysis, and Molecular Dynamic Simulation.

Propolis contains a wide range of pharmacological activities because of their various bioactive compounds. The beneficial effect of propolis is interesting for treating type-2 diabetes mellitus (T2DM) owing to dysregulation of multiple metabolic processes. In this study, 275 of 658 Asian propolis compounds were evaluated as potential anti-T2DM agents using the DIA-DB web server towards 18 known anti-diabetes protein targets. More than 20% of all compounds could bind to more than five diabetes targets with high binding affinity (<−9.0 kcal/mol). Filtering with physicochemical and pharmacokinetic properties, including ADMET parameters, 12 compounds were identified as potential anti-T2DM with favorable ADMET properties. Six of those compounds, (2R)-7,4'-dihydroxy-5-methoxy-8-methylflavone; (RR)-(+)-3'-senecioylkhellactone; 2',4',6'-trihydroxy chalcone; alpinetin; pinobanksin-3-O-butyrate; and pinocembrin-5-methyl ether were first reported as anti-T2DM agents. We identified the significant T2DM targets of Asian propolis, namely retinol-binding protein-4 (RBP4) and aldose reductase (AKR1B1) that have important roles in insulin sensitivity and diabetes complication, respectively. Molecular dynamic simulations showed stable interaction of selected propolis compounds in the active site of RBP4 and AKR1B1. These findings suggest that Asian propolis compound may be effective for treatment of T2DM by targeting RBP4 and AKR1B1.

MCC950 closes the active conformation of NLRP3 to an inactive state.

NLRP3 (NOD-like receptor pyrin domain-containing protein 3) is an innate immune sensor that contributes to the development of different diseases, including monogenic autoinflammatory syndromes, gout, atherosclerosis, and Alzheimer's disease. The molecule sulfonylurea MCC950 is a NLRP3 inflammasome inhibitor with potential clinical utility. However, the mechanism of action of MCC950 remains unknown. Here, we characterize the mechanism of action of MCC950 in both wild-type and autoinflammatory-related NLRP3 mutants, and demonstrate that MCC950 closes the 'open' conformation of active NLRP3.

Combined Structure and Ligand-Based Design of Selective Acetylcholinesterase Inhibitors.

Acetylcholinesterase is a prime target for therapeutic intervention in Alzheimer's disease. Acetylcholinesterase inhibitors (AChEIs) are used to improve cognitive abilities, playing therefore an important role in disease management. Drug repurposing screening has been performed on a corporate chemical library containing 11 353 compounds using a target fishing approach comprising three-dimensional (3D) shape similarity and pharmacophore modeling against an approved drug database, Drugbank. This initial screening identified 108 hits. Among them, eight molecules showed structural similarity to the known AChEI drug, pyridostigmine. Further structure-based screening using a pharmacophore-guided rescoring method identifies one more potential hit. Experimental evaluations of the identified hits sieve out a highly selective AChEI scaffold. Further lead optimization using a substructure search approach identifies 24 new potential hits. Three of the 24 compounds (compounds 10b, 10h, and 10i) based on a 6-(2-(pyrrolidin-1-yl)pyrimidin-4-yl)-thiazolo[3,2-a]pyrimidine scaffold showed highly promising AChE inhibition ability with IC50 values of 13.10 ± 0.53, 16.02 ± 0.46, and 6.22 ± 0.54 µM, respectively. Moreover, these compounds are highly selective toward AChE. Compound 10i shows AChE inhibitory activity similar to a known Food and Drug Administration (FDA)-approved drug, galantamine, but with even better selectivity. Interaction analysis reveals that hydrophobic and hydrogen-bonding interactions are the primary driving forces responsible for the observed high affinity of the compound with AChE.

Towards the Interpretability of Machine Learning Predictions for Medical Applications Targeting Personalised Therapies: A Cancer Case Survey.

Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements. In this sense, learning tools are becoming a commodity but, to be able to assist doctors on a daily basis, it is essential to fully understand how models can be interpreted. In this survey, we analyse current machine learning models and other in-silico tools as applied to medicine-specifically, to cancer research-and we discuss their interpretability, performance and the input data they are fed with. Artificial neural networks (ANN), logistic regression (LR) and support vector machines (SVM) have been observed to be the preferred models. In addition, convolutional neural networks (CNNs), supported by the rapid development of graphic processing units (GPUs) and high-performance computing (HPC) infrastructures, are gaining importance when image processing is feasible. However, the interpretability of machine learning predictions so that doctors can understand them, trust them and gain useful insights for the clinical practice is still rarely considered, which is a factor that needs to be improved to enhance doctors' predictive capacity and achieve individualised therapies in the near future.