AMALPHI: A Machine Learning Platform for Predicting Drug-Induced PhospholIpidosis.

Drug-induced phospholipidosis (PLD) involves the accumulation of phospholipids in cells of multiple tissues, particularly within lysosomes, and it is associated with prolonged exposure to druglike compounds, predominantly cationic amphiphilic drugs (CADs). PLD affects a significant portion of drugs currently in development and has recently been proven to be responsible for confounding antiviral data during drug repurposing for SARS-CoV-2. In these scenarios, it has become crucial to identify potential safe drug candidates in advance and distinguish them from those that may lead to false in vitro antiviral activity. In this work, we developed a series of machine learning classifiers with the aim of predicting the PLD-inducing potential of drug candidates. The models were built on a high-quality chemical collection comprising 545 curated small molecules extracted from ChEMBL v30. The most effective model, obtained using the balanced random forest algorithm, achieved high performance, including an AUC value computed in validation as high as 0.90. The model was made freely available through a user-friendly web platform named AMALPHI (https://www.ba.ic.cnr.it/softwareic/amalphiportal/), which can represent a valuable tool for medicinal chemists interested in conducting an early evaluation of PLD inducer potential.

DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues.

In this paper, we present a deep learning algorithm for automated design of druglike analogues (DeLA-Drug), a recurrent neural network (RNN) model composed of two long short-term memory (LSTM) layers and conceived for data-driven generation of similar-to-bioactive compounds. DeLA-Drug captures the syntax of SMILES strings of more than 1 million compounds belonging to the ChEMBL28 database and, by employing a new strategy called sampling with substitutions (SWS), generates molecules starting from a single user-defined query compound. Remarkably, the algorithm preserves druglikeness and synthetic accessibility of the known bioactive compounds present in the ChEMBL28 repository. The absence of any time-demanding fine-tuning procedure enables DeLA-Drug to perform a fast generation of focused libraries for further high-throughput screening and makes it a suitable tool for performing de novo design even in low-data regimes. To provide a concrete idea of its applicability, DeLA-Drug was applied to the cannabinoid receptor subtype 2 (CB2R), a known target involved in different pathological conditions such as cancer and neurodegeneration. DeLA-Drug, available as a free web platform (http://www.ba.ic.cnr.it/softwareic/deladrugportal/), can help medicinal chemists interested in generating analogues of compounds already available in their laboratories and, for this reason, good candidates for an easy and low-cost synthesis.

Magnetoelectric Coupling Springing Up in Molecular Ferroelectric: [N(C2H5)3CH3][FeCl4].

A molecule-based ferroelectric triethylmethylammonium tetrachloroferrate(III) ([N(C2H5)3CH3][FeCl4]) powder was designed as a multifunctional material exhibiting excellent multiple bistability. Prepared by the slow evaporation method at room temperature, the compound crystallizes in the non-centrosymmetric assembly of hexagonal symmetry (P63mc space group) which undergoes a reversible temperature-triggered phase transition pinpointed at 363 K to the centrosymmetric packing within the P63/mmc space group. Aside from the inseparable role of the symmetry-breaking process smoothly unveiled from the X-ray powder diffraction data, a striking change in the dielectric permittivity observed during the paraelectric-to-ferroelectric phase transition directly discloses the bistable dielectric behavior-an exceptionally high increase in the dielectric permittivity of about 360% at 100 kHz across the heating and cooling cycles is direct proof showing the highly desirable stimuli-responsive electric ordering in this improper ferroelectric architecture. Due to the magnetically modulated physical properties resulting in the coupling of magnetic and electric orderings, the flexible assembly of [N(C2H5)3CH3][FeCl4] could be used to boost the design and development of novel magnetoelectric devices.

Azetidine-Borane Complexes: Synthesis, Reactivity, and Stereoselective Functionalization.

The present study reports, for the first time, the synthesis and structural features of azetidine-borane complexes, as well as their reactivity in lithiation reactions. A temperature-dependent stereoselectivity has been disclosed in the reaction of borane with N-alkyl-2-arylazetidines, allowing for a stereoselective preparation of azetidine-borane complexes 2 and 3. A regioselective hydrogen/lithium permutation, at the benzylic position, was observed in lithiation reactions of complexes possessing a syn relationship, between the ring proton and the BH3 group. In contrast, scarce or no reactivity was noticed in complexes lacking such a stereochemical requirement. The configurational stability of the lithiated intermediates has also been investigated, in order to shed some light on the stereoselectivity of the lithiation/electrophile trapping sequence. Calculations helped in supporting experimental observations, concerning structure and reactivity of these azetidine-borane complexes. Data suggest that the BH3 group could promote the lithiation reaction likely by an electrostatic complex induced proximity effect. Interestingly, a new synthetic strategy for the synthesis of N-alkyl-2,2-disubstituted azetidines has been developed.

DeLA-DrugSelf: Empowering multi-objective de novo design through SELFIES molecular representation.

In this paper, we introduce DeLA-DrugSelf, an upgraded version of DeLA-Drug [J. Chem. Inf. Model. 62 (2022) 1411-1424], which incorporates essential advancements for automated multi-objective de novo design. Unlike its predecessor, which relies on SMILES notation for molecular representation, DeLA-DrugSelf employs a novel and robust molecular representation string named SELFIES (SELF-referencing Embedded String). The generation process in DeLA-DrugSelf not only involves substitutions to the initial string representing the starting query molecule but also incorporates insertions and deletions. This enhancement makes DeLA-DrugSelf significantly more adept at executing data-driven scaffold decoration and lead optimization strategies. Remarkably, DeLA-DrugSelf explicitly addresses the SELFIES-related collapse issue, considering only collapse-free compounds during generation. These compounds undergo a rigorous quality metrics evaluation, highlighting substantial advancements in terms of drug-likeness, uniqueness, and novelty compared to the molecules generated by the previous version of the algorithm. To evaluate the potential of DeLA-DrugSelf as a mutational operator within a genetic algorithm framework for multi-objective optimization, we employed a fitness function based on Pareto dominance. Our objectives focused on target-oriented properties aimed at optimizing known cannabinoid receptor 2 (CB2R) ligands. The results obtained indicate that DeLA-DrugSelf, available as a user-friendly web platform (https://www.ba.ic.cnr.it/softwareic/delaself/), can effectively contribute to the data-driven optimization of starting bioactive molecules based on user-defined parameters.

CrystalMELA: a new crystallographic machine learning platform for crystal system determination.

Determination of the crystal system and space group is the first step of crystal structure analysis. Often this turns out to be a bottleneck in the material characterization workflow for polycrystalline compounds, thus requiring manual interventions. This work proposes a new machine-learning (ML)-based web platform, CrystalMELA (Crystallography MachinE LeArning), for crystal systems classification. Two different ML models, random forest and convolutional neural network, are available through the platform, as well as the extremely randomized trees algorithm, available from the literature. The ML models learned from simulated powder X-ray diffraction patterns of more than 280 000 published crystal structures from organic, inorganic and metal-organic compounds and minerals which were collected from the POW_COD database. A crystal system classification accuracy of 70%, which improved to more than 90% when considering the Top-2 classification accuracy, was obtained in tenfold cross-validation. The validity of the trained models has also been tested against independent experimental data of published compounds. The classification options in the CrystalMELA platform are powerful, easy to use and supported by a user-friendly graphic interface. They can be extended over time with contributions from the community. The tool is freely available at https://www.ba.ic.cnr.it/softwareic/crystalmela/ following registration.

Chitosan/snail slime films as multifunctional platforms for potential biomedical and cosmetic applications: physical and chemical characterization.

Due to the pollution problem, the use of more sustainable materials with a reduced environmental impact, spanning across biocompatible and biodegradable polymers, is growing worldwide in many different fields, particularly when referring to applications in Life Sciences. Accordingly, with the aim of developing multifunctional materials for potential cosmetic/biomedical purposes, this work reports the physical and chemical characterization of chitosan-based films blended with snail slime, exhibiting antioxidant and sunscreen features. A suitable formulation for preparing free-standing chitosan platforms, mixing low molecular weight chitosan, lactic acid, glycerol, and snail slime into an appropriate ratio, is thus described. The results obtained by morphological analysis and ATR-FTIR spectroscopy, XRD, swelling analysis (also when varying pH, ionic strength, and temperature), and WVTR measurements evidence a uniform distribution of snail slime inside the chitosan network, forming more compacted structures. At first, the UV-Vis analysis is used to investigate the theoretical Sun Protection Factor, finding that these innovative platforms can be used for preventing sunburn. Then, the antioxidant features are investigated using the ABTS assay, displaying a snail slime-mediated and dose-dependent boosted activity.

ALPACA: A machine Learning Platform for Affinity and selectivity profiling of CAnnabinoids receptors modulators.

The development of small molecules that selectively target the cannabinoid receptor subtype 2 (CB2R) is emerging as an intriguing therapeutic strategy to treat neurodegeneration, as well as to contrast the onset and progression of cancer. In this context, in-silico tools able to predict CB2R affinity and selectivity with respect to the subtype 1 (CB1R), whose modulation is responsible for undesired psychotropic effects, are highly desirable. In this work, we developed a series of machine learning classifiers trained on high-quality bioactivity data of small molecules acting on CB2R and/or CB1R extracted from ChEMBL v30. Our classifiers showed strong predictive power in accurately determining CB2R affinity, CB1R affinity, and CB2R/CB1R selectivity. Among the built models, those obtained using random forest as algorithm proved to be the top-performing ones (AUC in validation ≥0.96) and were made freely accessible through a user-friendly web platform developed ad hoc and called ALPACA (https://www.ba.ic.cnr.it/softwareic/alpaca/). Due to its user-friendly interface and robust predictive power, ALPACA can be a valuable tool in saving both time and resources involved in the design of selective CB2R modulators.

Crystal structure determination of a lifelong biopersistent asbestos fibre using single-crystal synchrotron X-ray micro-diffraction.

The six natural silicates known as asbestos may induce fatal lung diseases via inhalation, with a latency period of decades. The five amphibole asbestos species are assumed to be biopersistent in the lungs, and for this reason they are considered much more toxic than serpentine asbestos (chrysotile). Here, we refined the atomic structure of an amosite amphibole asbestos fibre that had remained in a human lung for ∼40 years, in order to verify the stability in vivo. The subject was originally exposed to a blend of chrysotile, amosite and crocidolite, which remained in his parietal pleura for ∼40 years. We found a few relicts of chrysotile fibres that were amorphous and magnesium depleted. Amphibole fibres that were recovered were undamaged and suitable for synchrotron X-ray micro-diffraction experiments. Our crystal structure refinement from a recovered amosite fibre demonstrates that the original atomic distribution in the crystal is intact and, consequently, that the atomic structure of amphibole asbestos fibres remains stable in the lungs for a lifetime; during which time they can cause chronic inflammation and other adverse effects that are responsible for carcinogenesis. The amosite fibres are not iron depleted proving that the iron pool for the formation of the asbestos bodies is biological (haemoglobin/plasma derived) and that it does not come from the asbestos fibres themselves.