Fulvio Ciriaco

QT interval prolongation is associated with an increased risk of torsades de pointes (TdP), a potentially life-threatening ventricular arrhythmia, making assessment of cardiac repolarization a critical component of drug development. This work demonstrates how integrated in silico methodologies can be used to predict and quantitatively characterize QT liability across the drug discovery and development continuum. A proof-of concept translational workflow combining molecular structure analysis, in vitro pharmacology, animal data, and clinical exposure-response modeling was evaluated using the retrospective case examples verapamil and dofetilide. Molecular structure- and pharmacology-based assessments predicted hERG channel interaction and potential QT risk for both compounds. While initial in silico analyses suggested a high QT liability for verapamil and dofetilide, mechanistic electrophysiological modeling differentiated their effects. For verapamil, concurrent calcium channel inhibition offset hERG-mediated effects, resulting in predicted reductions in action potential duration and no clinically relevant QT prolongation. In contrast, dofetilide produced concentration-dependent increases in action potential duration, consistent with its known proarrhythmic potential. Translation of nonclinical findings to humans accurately predicted the absence of clinically meaningful QT effects for verapamil and identified QT prolongation exceeding the regulatory 10 ms threshold for dofetilide at therapeutic concentrations. Drug exposure and pharmacokinetic properties could be anticipated based solely on molecular structure. This conceptual workflow demonstrates how integrated quantitative in silico approaches can support earlier identification, characterization, and communication of QT risk, enabling informed decision-making and improved development efficiency from bench to bedside.

The target‐engagement predictor, implemented within the InSilicoTrials cloud‐based, AI‐powered platform for model‐informed drug discovery and development, enables early exploration of time‐dependent pharmacological responses. Predictions can be generated using inputs ranging from molecular structure to in vitro, animal, and clinical data. Scaling and translation across species are supported, accounting for differences in body size and plasma protein binding. This tutorial demonstrates the application of the target‐engagement predictor for benchmarking and decision‐support in the evaluation of new drug candidates. Pharmacokinetic (PK) and pharmacodynamic (PD) data for carvedilol, ivabradine, and sunitinib were used as illustrative examples. The ANDROMEDA and PLATO software were used to predict human clinical PK and target affinity parameters, respectively, based on molecular SMILES representations of the drugs. These predictions were subsequently incorporated into longitudinal PKPD simulation models. User‐friendly input wizards and interactive results dashboards were developed to facilitate clinical trial simulation for broader project teams, without requiring programming expertise. Predictions derived from molecular structure were compared with data generated from in vitro, rat, and clinical experimental settings. The target‐engagement predictor enables integration of heterogenous data sources to support drug development decisions, including early benefit–risk assessment and dose selection for Phase 1 studies. Direct prediction based on molecular structure alone represents a promising approach for early‐stage screening and evaluation of new drug candidates.

Endocrine disruption remains a major concern in predictive toxicology, demanding accurate and interpretable models to assess molecular interactions with hormonal pathways. Here, we present a descriptor-free bidirectional long short-term memory (BiLSTM) framework designed to predict the toxicity of chemicals toward androgen (AR) and estrogen receptors (ER), two of the most complex and biologically relevant end points in toxicology. The model operates directly on SMILES strings, which are tokenized and converted into one-hot encoded sequences, enabling the automatic extraction of chemically meaningful representations without reliance on handcrafted molecular descriptors or fingerprints. To enhance interpretability, we introduce a novel explainable artificial intelligence (XAI) approach that aggregates character-level attribution scores into color-coded substructures, revealing features that drive or reduce toxicity and offering mechanistic insight into receptor-mediated effects. The models were trained on publicly available, high-quality data sets comprising 1664 and 1529 chemicals with experimental binary labels for AR and ER, respectively. Employing cross-validation analyses, based on 20% randomly stratified resampling iterated 10 times, the proposed workflow returned accuracy equal to 0.75 ± 0.08 and 0.81 ± 0.05, sensitivity equal to 0.66 ± 0.36 and 0.69 ± 0.17, and specificity equal to 0.76 ± 0.14 and 0.82 ± 0.06 for AR and ER end points, respectively. Our descriptor-free models ensure highly transparent results with a substructure level interpretability. These findings demonstrate the potential of deep learning directly on molecular textual representations to advance predictive toxicology and to support mechanistic understanding in chemical risk assessment.

This work introduces a fragment-based chemical language -- fragSMILES -- into reaction prediction with deep learning. FragSMILES encodes molecular substructures and chirality, enabling compact and expressive string representations. In a systematic comparison with well-established molecular notations — Simplified Molecular Input Line Entry System (SMILES), Self-Referencing Embedded Strings (SELFIES), and Sequential Attachment-based Fragment Embedding (SAFE) — fragSMILES achieved the highest performance across forward- and retro-synthesis prediction, with superior recognition of stereochemical reaction information. Moreover, fragSMILES enhances the capacity to capture stereochemical complexity -- a key challenge in synthesis planning. Our results demonstrate that chirality-aware and fragment-level representations can advance current computer-assisted synthesis planning efforts.

Developmental toxicity is key human health endpoint, especially relevant for safeguarding maternal and child well-being. It is an object of increasing attention from international regulatory bodies such as the US EPA (US Environmental Protection Agency) and ECHA (European CHemicals Agency). In this challenging scenario, non-test methods employing explainable artificial intelligence based techniques can provide a significant help to derive transparent predictive models whose results can be easily interpreted to assess the developmental toxicity of new chemicals at very early stages. To accomplish this task, we have developed web platforms such as TIRESIA and TISBE. Based on a benchmark dataset, TIRESIA employs an explainable artificial intelligence approach combined with SHAP analysis to unveil the molecular features responsible for calculating the developmental toxicity. Descending from TIRESIA, TISBE employs a larger dataset, an explainable artificial intelligence framework based on a fragment-based fingerprint encoding, a consensus classifier, and a new double top-down applicability domain. We report here some practical examples for getting started with TIRESIA and TISBE.

Generative models have revolutionized de novo drug design, allowing to produce molecules on-demand with desired physicochemical and pharmacological properties. String based molecular representations, such as SMILES (Simplified Molecular Input Line Entry System) strings and SELFIES (Self-Referencing Embedded Strings), have played a pivotal role in the success of generative approaches, thanks to their capacity to encode atom- and bond- information and ease-of-generation. However, such ‘atom-level’ string representations have certain limitations, in terms of capturing information on chirality, and synthetic accessibility of the corresponding designs. In this paper, we present fragSMILES, a novel fragment-based molecular representation in the form of string. fragSMILES encode fragments in a ‘chemically-meaningful’ way via a novel graph-reduction approach, allowing to obtain an efficient, interpretable, and expressive molecular representation, which also avoids fragment redundancy. fragSMILES advances the state-of-the-art of fragment-based representations, by reporting fragments and their ‘breaking’ bonds independently, without fragment redundancy. Moreover, fragSMILES also embeds information of molecular chirality, thereby overcoming known limitations of existing string notations. When compared with SMILES and SELFIES for de novo design, the fragSMILES notation showed its promise in generating molecules with desirable biochemical and scaffolds properties.

Chemical space modelling has great importance in unveiling and visualising latent information, which is critical in predictive toxicology related to drug discovery process. While the use of traditional molecular descriptors and fingerprints may suffer from the so-called curse of dimensionality, complex networks are devoid of the typical drawbacks of coordinate-based representations. Herein, we use chemical space networks (CSNs) to analyse the case of the developmental toxicity (Dev Tox), which remains a challenging endpoint for the difficulty of gathering enough reliable data despite very important for the protection of the maternal and child health. Our study proved that the Dev Tox CSN has a complex non-random organisation and can thus provide a wealth of meaningful information also for predictive purposes. At a phase transition, chemical similarities highlight well-established toxicophores, such as aryl derivatives, mostly neurotoxic hydantoins, barbiturates and amino alcohols, steroids, and volatile organic compounds ether-like chemicals, which are strongly suspected of the Dev Tox onset and can thus be employed as effective alerts for prioritising chemicals before testing.

Curcumin (Cur) is a hydrophobic polyphenol from the rhizome of Curcuma spp., while hydroxytyrosol (HT) is a water-soluble polyphenol from Olea europaea. Both show outstanding antioxidant properties but suffer from scarce bioavailability and low stability in biological fluids. In this work, the co-encapsulation of Cur and HT into liposomes was realized, and the liposomal formulation was improved using polymers to increase their survival in the gastrointestinal tract. Liposomes with different compositions were formulated: Type 1, composed of phospholipids and cholesterol; Type 2, also with a PEG coating; and Type 3 providing an additional shell of Eudragit^® S100, a gastro-resistant polymer. Samples were characterized in terms of size, morphology, ζ-potential, encapsulation efficiency, and loading capacity. All samples were subjected to a simulated in vitro digestion and their stability was investigated. The Eudragit^®S100 coating demonstrated prevention of early releases of HT in the mouth and gastric phases, while the PEG shell reduced bile salts and pancreatin effects during the intestinal digestion. In vitro antioxidant activity showed a cumulative effect for Cur and HT loaded in vesicles. Finally, liposomes with HT concentrations up to 40 μM and Cur up to 4.7 μM, alone or in combination, did not show cytotoxicity against Caco-2 cells.