Where developmental toxicity meets explainable artificial intelligence: state-of-the-art and perspectives.

INTRODUCTION: The application of Artificial Intelligence (AI) to predictive toxicology is rapidly increasing, particularly aiming to develop non-testing methods that effectively address ethical concerns and reduce economic costs. In this context, Developmental Toxicity (Dev Tox) stands as a key human health endpoint, especially significant for safeguarding maternal and child well-being. AREAS COVERED: This review outlines the existing methods employed in Dev Tox predictions and underscores the benefits of utilizing New Approach Methodologies (NAMs), specifically focusing on eXplainable Artificial Intelligence (XAI), which proves highly efficient in constructing reliable and transparent models aligned with recommendations from international regulatory bodies. EXPERT OPINION: The limited availability of high-quality data and the absence of dependable Dev Tox methodologies render XAI an appealing avenue for systematically developing interpretable and transparent models, which hold immense potential for both scientific evaluations and regulatory decision-making.

Investigation on Novel E/Z 2-Benzylideneindan-1-One-Based Photoswitches with AChE and MAO-B Dual Inhibitory Activity.

The multitarget therapeutic strategy, as opposed to the more traditional 'one disease-one target-one drug', may hold promise in treating multifactorial neurodegenerative syndromes, such as Alzheimer's disease (AD) and related dementias. Recently, combining a photopharmacology approach with the multitarget-directed ligand (MTDL) design strategy, we disclosed a novel donepezil-like compound, namely 2-(4-((diethylamino)methyl)benzylidene)-5-methoxy-2,3-dihydro-1H-inden-1-one (1a), which in the E isomeric form (and about tenfold less in the UV-B photo-induced isomer Z) showed the best activity as dual inhibitor of the AD-related targets acetylcholinesterase (AChE) and monoamine oxidase B (MAO-B). Herein, we investigated further photoisomerizable 2-benzylideneindan-1-one analogs 1b-h with the unconjugated tertiary amino moiety bearing alkyls of different bulkiness and lipophilicity. For each compound, the thermal stable E geometric isomer, along with the E/Z mixture as produced by UV-B light irradiation in the photostationary state (PSS, 75% Z), was investigated for the inhibition of human ChEs and MAOs. The pure E-isomer of the N-benzyl(ethyl)amino analog 1h achieved low nanomolar AChE and high nanomolar MAO-B inhibition potencies (IC50s 39 and 355 nM, respectively), whereas photoisomerization to the Z isomer (75% Z in the PSS mixture) resulted in a decrease (about 30%) of AChE inhibitory potency, and not in the MAO-B one. Molecular docking studies were performed to rationalize the different E/Z selectivity of 1h toward the two target enzymes.

TIRESIA: An eXplainable Artificial Intelligence Platform for Predicting Developmental Toxicity.

Herein, a robust and reproducible eXplainable Artificial Intelligence (XAI) approach is presented, which allows prediction of developmental toxicity, a challenging human-health endpoint in toxicology. The application of XAI as an alternative method is of the utmost importance with developmental toxicity being one of the most animal-intensive areas of regulatory toxicology. In this work, the established CAESAR (Computer Assisted Evaluation of industrial chemical Substances According to Regulations) training set made of 234 chemicals for model learning is employed. Two test sets, including as a whole 585 chemicals, were instead used for validation and generalization purposes. The proposed framework favorably compares with the state-of-the-art approaches in terms of accuracy, sensitivity, and specificity, thus resulting in a reliable support system for developmental toxicity ensuring informativeness, uncertainty estimation, generalization, and transparency. Based on the eXtreme Gradient Boosting (XGB) algorithm, our predictive model provides easy interpretative keys based on specific molecular descriptors and structural alerts enabling one to distinguish toxic and nontoxic chemicals. Inspired by the Organisation for Economic Co-operation and Development (OECD) principles for the validation of Quantitative Structure-Activity Relationships (QSARs) for regulatory purposes, the results are summarized in a standard report in portable document format, enclosing also details concerned with a density-based model applicability domain and SHAP (SHapley Additive exPlanations) explainability, the latter particularly useful to better understand the effective roles played by molecular features. Notably, our model has been implemented in TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), a free of charge web platform available at http://tiresia.uniba.it.

Novel Class of Chalcone Oxime Ethers as Potent Monoamine Oxidase-B and Acetylcholinesterase Inhibitors.

Previously synthesized novel chalcone oxime ethers (COEs) were evaluated for inhibitory activities against monoamine oxidases (MAOs) and acetylcholinesterase (AChE). Twenty-two of the 24 COEs synthesized, except COE-17 and COE-24, had potent and/or significant selective inhibitory effects on MAO-B. COE-6 potently inhibited MAO-B with an IC50 value of 0.018 µM, which was 105, 2.3, and 1.1 times more potent than clorgyline, lazabemide, and pargyline (reference drugs), respectively. COE-7, and COE-22 were also active against MAO-B, both had an IC50 value of 0.028 µM, which was 67 and 1.5 times lower than those of clorgyline and lazabemide, respectively. Most of the COEs exhibited weak inhibitory effects on MAO-A and AChE. COE-13 most potently inhibited MAO-A (IC50 = 0.88 µM) and also significantly inhibited MAO-B (IC50 = 0.13 µM), and it could be considered as a potential nonselective MAO inhibitor. COE-19 and COE-22 inhibited AChE with IC50 values of 5.35 and 4.39 µM, respectively. The selectivity index (SI) of COE-22 for MAO-B was higher than that of COE-6 (SI = 778.6 vs. 222.2), but the IC50 value (0.028 µM) was slightly lower than that of COE-6 (0.018 µM). In reversibility experiments, inhibitions of MAO-B by COE-6 and COE-22 were recovered to the levels of reference reversible inhibitors and both competitively inhibited MAO-B, with Ki values of 0.0075 and 0.010 µM, respectively. Our results show that COE-6 and COE-22 are potent, selective MAO-B inhibitors, and COE-22 is a candidate of dual-targeting molecule for MAO-B and AChE.

Design of enamides as new selective monoamine oxidase-B inhibitors.

OBJECTIVES: To develop of new class of selective and reversible MAO-B inhibitors from enamides. METHODS: Syntheses of the titled derivatives (AD1-AD11) were achieved by reacting cinnamoyl chloride and various primary and secondary amines in basic medium. All eleven compounds were investigated for in vitro inhibitory activities against recombinant human MAO-A and MAO-B. The reversibilities of lead compound inhibitions were analysed by dialysis. MTT assays of lead compounds were performed using normal VERO cell lines. KEY FINDINGS: Compounds AD3 and AD9 exhibited the greatest inhibitory activity against MAO-B with IC50 values of 0.11 and 0.10 µm, respectively, and were followed by AD2 and AD1 (0.51 and 0.71 µm, respectively). Most of the compounds weakly inhibited MAO-A, with the exceptions AD9 and AD7, which had IC50 values of 4.21 and 5.95 µm, respectively. AD3 had the highest selectivity index (SI) value for MAO-B (>363.6) and was followed by AD9 (SI 42.1). AD3 and AD9 were found to be competitive inhibitors of MAO-B with Ki values of 0.044 ± 0.0036 and 0.039 ± 0.0047 µm, respectively. Reversibility experiments showed AD3 and AD9 were reversible inhibitors of MAO-B; dialysis restored the activity of MAO-B to the reference level. MTT assays revealed AD3 and AD9 were non-toxic to normal VERO cell lines with IC50 values of 153.96 and 194.04 µg/ml, respectively. Computational studies provided hypothetical binding modes for AD3 and AD9 in the binding cavities of MAO-A and MAO-B. CONCLUSIONS: These results encourage further studies on the enamide scaffold as potential drug candidates for the treatment of Alzheimer's and Parkinson's diseases.

Structure-Based Identification and Design of Angiotensin Converting Enzyme-Inhibitory Peptides from Whey Proteins.

Besides their nutritional value, whey protein (WP) peptides are food components retaining important pharmacological properties for controlling hypertension. We herein report how the use of complementary experimental and theoretical investigations allowed the identification of novel angiotensin converting enzyme inhibitory (ACEI) peptides obtained from a WP hydrolysate and addressed the rational design of even shorter sequences based on molecular pruning. Thus, after bromelain digestion followed by a 5 kDa cutoff ultrafiltration, WP hydrolysate with ACEI activity was fractioned by RP-HPLC; 2 out of 23 collected fractions retained ACEI activity and were analyzed by liquid chromatography-tandem mass spectrometry (LC-MS/MS). In the face of 128 identified peptides, molecular docking was carried out to prioritize peptides and to rationally guide the design of novel shorter and bioactive sequences. Therefore, 11 peptides, consisting of 3-6 amino acids and with molecular weights in the range from 399 to 674 Da, were rationally designed and then purchased to determine the IC50 value. This approach allowed the identification of two novel peptides: MHI and IAEK with IC50 ACEI values equal to 11.59 and 25.08 µM, respectively. Interestingly, we also confirmed the well-known ACEI IPAVF with an IC50 equal to 9.09 µM. In light of these results, this integrated approach could pave the way for high-throughput screening and identification of new peptides in dairy products. In addition, the herein proposed ACEI peptides could be exploited for novel applications both for food production and pharmaceuticals.

Design, synthesis and biological evaluation of oxygenated chalcones as potent and selective MAO-B inhibitors.

The present study documents the synthesis of oxygenated chalcone (O1-O26) derivatives and their abilities to inhibit monoamine oxidases. All 26 derivatives examined showed potent inhibitory activity against MAO-B. Compound O23 showed the greatest inhibitory activity against MAO-B with an IC50 value of 0.0021 µM, followed by compounds O10 and O17 (IC50 = 0.0030 and 0.0034 µM, respectively). In addition, most of the derivatives potently inhibited MAO-A and O6 was the most potent inhibitor with an IC50 value of 0.029 µM, followed by O3, O4, O9, and O2 (IC50 = 0.035, 0.053, 0.072, and 0.082 µM, respectively). O23 had a high selectivity index (SI) value for MAO-B of 138.1, and O20 (IC50 value for MAO-B = 0.010 µM) had an extremely high SI of >4000. In dialysis experiments, inhibitions of MAO-A and MAO-B by O6 and O23, respectively, were recovered to their respective reversible reference levels, demonstrating both are reversible inhibitors. Kinetic studies revealed that O6 and O23 competitively inhibited MAO-A and MAO-B, respectively, with respective Ki values of 0.016 ±â€¯0.0007 and 0.00050 ±â€¯0.00003 µM. Lead compound are also non-toxic at 200 µg/mL in normal rat spleen cells. Molecular docking simulations and subsequent Molecular Mechanics/Generalized Born Surface Area calculations provided a rationale that explained experimental data.

Accelerating Drug Discovery by Early Protein Drug Target Prediction Based on a Multi-Fingerprint Similarity Search.

In this continuing work, we have updated our recently proposed Multi-fingerprint Similarity Search algorithm (MuSSel) by enabling the generation of dominant ionized species at a physiological pH and the exploration of a larger data domain, which included more than half a million high-quality small molecules extracted from the latest release of ChEMBL (version 24.1, at the time of writing). Provided with a high biological assay confidence score, these selected compounds explored up to 2822 protein drug targets. To improve the data accuracy, samples marked as prodrugs or with equivocal biological annotations were not considered. Notably, MuSSel performances were overall improved by using an object-relational database management system based on PostgreSQL. In order to challenge the real effectiveness of MuSSel in predicting relevant therapeutic drug targets, we analyzed a pool of 36 external bioactive compounds published in the Journal of Medicinal Chemistry from October to December 2018. This study demonstrates that the use of highly curated chemical and biological experimental data on one side, and a powerful multi-fingerprint search algorithm on the other, can be of the utmost importance in addressing the fate of newly conceived small molecules, by strongly reducing the attrition of early phases of drug discovery programs.