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.

Quantitative Polypharmacology Profiling Based on a Multifingerprint Similarity Predictive Approach.

We present a new quantitative ligand-based bioactivity prediction approach employing a multifingerprint similarity search algorithm, enabling the polypharmacological profiling of small molecules. Quantitative bioactivity predictions are made on the basis of the statistical distributions of multiple Tanimoto similarity θ values, calculated through 13 different molecular fingerprints, and of the variation of the measured biological activity, reported as ΔpIC50, for all of the ligands sharing a given protein drug target. The application data set comprises as much as 4241 protein drug targets as well as 418 485 ligands selected from ChEMBL (release 25) by employing a set of well-defined filtering rules. Several large internal and external validation studies were carried out to demonstrate the robustness and the predictive potential of the herein proposed method. Additional comparative studies, carried out on two freely available and well-known ligand-target prediction platforms, demonstrated the reliability of our proposed approach for accurate ligand-target matching. Moreover, two applicative cases were also discussed to practically describe how to use our predictive algorithm, which is freely available as a user-friendly web platform. The user can screen single or multiple queries at a time and retrieve the output as a terse html table or as a json file including all of the information concerning the explored similarities to obtain a deeper understanding of the results. High-throughput virtual reverse screening campaigns, allowing for a given query compound the quick detection of the potential drug target from a large collection of them, can be carried out in batch on demand.

Theoretical insights on acceptor-donor dyads for organic photovoltaics.

The field of organic photovoltaics has witnessed a steady growth in the last few decades and a recent renewal with the blossoming of single-material organic solar cells (SMOSCs). However, due to the intrinsic complexity of these devices (both in terms of their size and of the condensed phases involved), computational approaches to accurately predict their geometrical and electronic structure and to link their microscopic properties to the observed macroscopic behaviour are still lacking. In this work, we have focused on the rationalization of transport dynamics and we have set up a computational approach that makes a combined use of classical simulations and Density Functional Theory with the aim of disclosing the most relevant electronic and structural features of dyads used for SMOSC applications. As a prototype dyad, we have considered a molecule that consists in a dithiafulvalene-functionalized diketopyrrolopyrrole (DPP), acting as an electron donor, covalently linked to a fulleropyrrolidine (Ful), the electron acceptor. Our results, beside a quantitative agreement with experiments, show that the overall observed mobilities result from the competing packing mechanisms of the constituting units within the dyad both in the case of crystalline and amorphous phases. As a consequence, not all stable polymorphs have the same efficiency in transporting holes or electrons which often results in a highly directional carrier transport that is not, in general, a desirable feature for polycrystalline thin-films. The present work, linking microscopic packing to observed transport, thus opens the route for the in silico design of new dyads with enhanced and controlled structural and electronic features.

A New Approach for Drug Target and Bioactivity Prediction: The Multifingerprint Similarity Search Algorithm (MuSSeL).

We present MuSSeL, a multifingerprint similarity search algorithm, able to predict putative drug targets for a given query small molecule as well as to return a quantitative assessment of its bioactivity in terms of Ki or IC50 values. Predictions are automatically made exploiting a large collection of high quality experimental bioactivity data available from ChEMBL (version 22.1) combining, in a consensus-like approach, predictions resulting from a similarity search performed using 13 different fingerprint definitions. Importantly, the herein proposed algorithm is also effective in detecting and handling activity cliffs. A calibration set including small molecules present in the last updated version of ChEMBL (version 23) was employed to properly tune the algorithm parameters. Three randomly built external sets were instead challenged for model performances. The potential use of MuSSeL was also challenged by a prospective exercise for the prediction of five bioactive compounds taken from articles published in the Journal of Medicinal Chemistry just few months ago. The paper emphasizes the importance of implementing multifingerprint consensus strategies to increase the confidence in prediction of similarity search algorithms and provides a fast and easy-to-run tool for drug target and bioactivity prediction.

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.

Comparative molecular dynamics study of neuromyelitis optica-immunoglobulin G binding to aquaporin-4 extracellular domains.

Neuromyelitis optica (NMO) is an inflammatory demyelinating disease of the central nervous system in which most patients have serum autoantibodies (called NMO-IgG) that bind to astrocyte water channel aquaporin-4 (AQP4). A potential therapeutic strategy in NMO is to block the interaction of NMO-IgG with AQP4. Building on recent observation that some single-point and compound mutations of the AQP4 extracellular loop C prevent NMO-IgG binding, we carried out comparative Molecular Dynamics (MD) investigations on three AQP4 mutants, TP137-138AA, N153Q and V150G, whose 295-ns long trajectories were compared to that of wild type human AQP4. A robust conclusion of our modeling is that loop C mutations affect the conformation of neighboring extracellular loop A, thereby interfering with NMO-IgG binding. Analysis of individual mutations suggested specific hydrogen bonding and other molecular interactions involved in AQP4-IgG binding to AQP4.

Multidisciplinary study of a new ClC-1 mutation causing myotonia congenita: a paradigm to understand and treat ion channelopathies.

Myotonia congenita is an inherited disease that is characterized by impaired muscle relaxation after contraction caused by loss-of-function mutations in the skeletal muscle ClC-1 channel. We report a novel ClC-1 mutation, T335N, that is associated with a mild phenotype in 1 patient, located in the extracellular I-J loop. The purpose of this study was to provide a solid correlation between T335N dysfunction and clinical symptoms in the affected patient as well as to offer hints for drug development. Our multidisciplinary approach includes patch-clamp electrophysiology on T335N and ClC-1 wild-type channels expressed in tsA201 cells, Western blot and quantitative PCR analyses on muscle biopsies from patient and unaffected individuals, and molecular dynamics simulations using a homology model of the ClC-1 dimer. T335N channels display reduced chloride currents as a result of gating alterations rather than altered surface expression. Molecular dynamics simulations suggest that the I-J loop might be involved in conformational changes that occur at the dimer interface, thus affecting gating. Finally, the gene expression profile of T335N carrier showed a diverse expression of K+ channel genes, compared with control individuals, as potentially contributing to the phenotype. This experimental paradigm satisfactorily explained myotonia in the patient. Furthermore, it could be relevant to the study and therapy of any channelopathy.-Imbrici, P., Altamura, C., Camerino, G. M., Mangiatordi, G. F., Conte, E., Maggi, L., Brugnoni, R., Musaraj, K., Caloiero, R., Alberga, D., Marsano, R. M., Ricci, G., Siciliano, G., Nicolotti, O., Mora, M., Bernasconi, P., Desaphy, J.-F., Mantegazza, R., Camerino, D. C. Multidisciplinary study of a new ClC-1 mutation causing myotonia congenita: a paradigm to understand and treat ion channelopathies.

Predictive Structure-Based Toxicology Approaches To Assess the Androgenic Potential of Chemicals.

We present a practical and easy-to-run in silico workflow exploiting a structure-based strategy making use of docking simulations to derive highly predictive classification models of the androgenic potential of chemicals. Models were trained on a high-quality chemical collection comprising 1689 curated compounds made available within the CoMPARA consortium from the US Environmental Protection Agency and were integrated with a two-step applicability domain whose implementation had the effect of improving both the confidence in prediction and statistics by reducing the number of false negatives. Among the nine androgen receptor X-ray solved structures, the crystal 2PNU (entry code from the Protein Data Bank) was associated with the best performing structure-based classification model. Three validation sets comprising each 2590 compounds extracted by the DUD-E collection were used to challenge model performance and the effectiveness of Applicability Domain implementation. Next, the 2PNU model was applied to screen and prioritize two collections of chemicals. The first is a small pool of 12 representative androgenic compounds that were accurately classified based on outstanding rationale at the molecular level. The second is a large external blind set of 55450 chemicals with potential for human exposure. We show how the use of molecular docking provides highly interpretable models and can represent a real-life option as an alternative nontesting method for predictive toxicology.

Challenging AQP4 druggability for NMO-IgG antibody binding using molecular dynamics and molecular interaction fields.

Neuromyelitis optica (NMO) is a multiple sclerosis-like immunopathology disease affecting optic nerves and the spinal cord. Its pathological hallmark is the deposition of a typical immunoglobulin, called NMO-IgG, against the water channel Aquaporin-4 (AQP4). Preventing NMO-IgG binding would represent a valuable molecular strategy for a focused NMO therapy. The recent observation that aspartate in position 69 (D69) is determinant for the formation of NMO-IgG epitopes prompted us to carry out intensive Molecular Dynamics (MD) studies on a number of single-point AQP4 mutants. Here, we report a domino effect originating from the point mutation at position 69: we find that the side chain of T62 is reoriented far from its expected position leaning on the lumen of the pore. More importantly, the strength of the H-bond interaction between L53 and T56, at the basis of the loop A, is substantially weakened. These events represent important pieces of a clear-cut mechanistic rationale behind the failure of the NMO-IgG binding, while the water channel function as well as the propensity to aggregate into OAPs remains unaltered. The molecular interaction fields (MIF)-based analysis of cavities complemented MD findings indicating a putative binding site comprising the same residues determining epitope reorganization. In this respect, docking studies unveiled an intriguing perspective to address the future design of small drug-like compounds against NMO. In agreement with recent experimental observations, the present study is the first computational attempt to elucidate NMO-IgG binding at the molecular level, as well as a first effort toward a less elusive AQP4 druggability.

Human Aquaporin-4 and Molecular Modeling: Historical Perspective and View to the Future.

Among the different aquaporins (AQPs), human aquaporin-4 (hAQP4) has attracted the greatest interest in recent years as a new promising therapeutic target. Such a membrane protein is, in fact, involved in a multiple sclerosis-like immunopathology called Neuromyelitis Optica (NMO) and in several disorders resulting from imbalanced water homeostasis such as deafness and cerebral edema. The gap of knowledge in its functioning and dynamics at the atomistic level of detail has hindered the development of rational strategies for designing hAQP4 modulators. The application, lately, of molecular modeling has proved able to fill this gap providing a breeding ground to rationally address compounds targeting hAQP4. In this review, we give an overview of the important advances obtained in this field through the application of Molecular Dynamics (MD) and other complementary modeling techniques. The case studies presented herein are discussed with the aim of providing important clues for computational chemists and biophysicists interested in this field and looking for new challenges.

Identification of a point mutation impairing the binding between aquaporin-4 and neuromyelitis optica autoantibodies.

Neuromyelitis optica (NMO) is characterized by the presence of pathogenic autoantibodies (NMO-IgGs) against supra-molecular assemblies of aquaporin-4 (AQP4), known as orthogonal array of particles (OAPs). NMO-IgGs have a polyclonal origin and recognize different conformational epitopes involving extracellular AQP4 loops A, C, and E. Here we hypothesize a pivotal role for AQP4 transmembrane regions (TMs) in epitope assembly. On the basis of multialignment analysis, mutagenesis, NMO-IgG binding, and cytotoxicity assay, we have disclosed the key role of aspartate 69 (Asp(69)) of TM2 for NMO-IgG epitope assembly. Mutation of Asp(69) to histidine severely impairs NMO-IgG binding for 85.7% of the NMO patient sera analyzed here. Although Blue Native-PAGE, total internal reflection fluorescence microscopy, and water transport assays indicate that the OAP Asp(69) mutant is similar in structure and function to the wild type, molecular dynamic simulations have revealed that the D(69)H mutation has the effect of altering the structural rearrangements of extracellular loop A. In conclusion, Asp(69) is crucial for the spatial control of loop A, the particular molecular conformation of which enables the assembly of NMO-IgG epitopes. These findings provide additional clues for new strategies for NMO treatment and a wealth of information to better approach NMO pathogenesis.

A new gating site in human aquaporin-4: Insights from molecular dynamics simulations.

Aquaporin-4 (AQP4) is the predominant water channel in different organs and tissues. An alteration of its physiological functioning is responsible for several disorders of water regulation and, thus, is considered an attractive target with a promising therapeutic and diagnostic potential. Molecular dynamics (MD) simulations performed on the AQP4 tetramer embedded in a bilayer of lipid molecules allowed us to analyze the role of spontaneous fluctuations occurring inside the pore. Following the approach by Hashido et al. [Hashido M, Kidera A, Ikeguchi M (2007) Biophys J 93: 373-385], our analysis on 200ns trajectory discloses three domains inside the pore as key elements for water permeation. Herein, we describe the gating mechanism associated with the well-known selectivity filter on the extracellular side of the pore and the crucial regulation ensured by the NPA motifs (asparagine, proline, alanine). Notably, on the cytoplasmic side, we find a putative gate formed by two residues, namely, a cysteine belonging to the loop D (C178) and a histidine from loop B (H95). We observed that the spontaneous reorientation of the imidazole ring of H95 acts as a molecular switch enabling H-bond interaction with C178. The occurrence of such local interaction seems to be responsible for the narrowing of the pore and thus of a remarkable decrease in water flux rate. Our results are in agreement with recent experimental observations and may represent a promising starting point to pave the way for the discovery of chemical modulators of AQP4 water permeability.

Effects of different self-assembled monolayers on thin-film morphology: a combined DFT/MD simulation protocol.

Organic thin film transistors (OTFTs) are multilayer field-effect transistors that employ an organic conjugated material as semiconductor. Several experimental groups have recently demonstrated that the insertion of an organic self-assembled monolayer (SAM) between the dielectric and the semiconductive layer is responsible for a sensible improvement of the OTFT performances in terms of an increased charge carrier mobility caused by a higher degree of order in the organic semiconductor layer. Here, we describe a combined periodic density functional theory (DFT) and classical molecular dynamics (MD) protocol applied to four different SAMs and a pentacene monolayer deposited onto their surfaces. In particular, we investigate the morphology and the surface of the four SAMs and the translational, orientational, and nematic order of the monolayer through the calculation of several distribution functions and order parameters pointing out the differences among the systems and relating them to known experimental results. Our calculations also suggest that small differences in the SAM molecular design will produce remarkable differences in the SAM surface and monolayer order. In particular, our simulations explain how a SAM with a bulky terminal group results in an irregular and rough surface that determines the deposition of a disordered semiconductive monolayer. On the contrary, SAMs with a small terminal group generate smooth surfaces with uninterrupted periodicity, thus favoring the formation of an ordered pentacene monolayer that increases the mobility of charge carriers and improves the overall performances of the OTFT devices. Our results clearly point out that the in silico procedure presented here might be of help in tuning the design of SAMs in order to improve the quality of OTFT devices.

Morphological and charge transport properties of amorphous and crystalline P3HT and PBTTT: insights from theory.

We explore the relation between the morphological and the charge transport properties of poly(3-hexylthiophene) (P3HT) and poly(2,5-bis(3-alkylthiophen-2-yl)thieno[3,2-b]thiophene) (PBTTT) semiconductor polymers in both amorphous and crystalline phases. Using molecular dynamics to simulate bulk supercells and the Marcus theory to analyze the transport properties we found that amorphous systems display a reduced hole mobility due to the loss of nematic order and π-π stacking leading to a reduction in the electronic coupling between two chains. In the crystal phase, PBTTT displays a larger charge mobility than P3HT due to the interdigitation of the side chains enhancing the stability of the conjugated rings on the backbones. This more stable π-π stacking reduces the energetic disorder with respect to P3HT and increases the electronic coupling. In contrast, in the amorphous phase, PBTTT displays a reduced charge mobility with respect to P3HT due to the absence of side chains attached to the thienothiophenes, which increases their fluctuations and the energetic disorder. In addition, we show that it is possible to calculate the reorganization energy neglecting the side chains of the polymers and thus saving computational time. Within this approximation, we obtained mobility values matching the experimental measurements, thus confirming that the side chains are crucial to shape the morphology of the polymeric systems but are not involved in the charge transport process.

Molecular interactions between a diphenyl scaffold and PED/PEA15: Implications for type II diabetes therapeutics targeting PED/PEA15 - Phospholipase D1 interaction.

In a recent study, we have identified BPH03 as a promising scaffold for the development of compounds aimed at modulating the interaction between PED/PEA15 (Phosphoprotein Enriched in Diabetes/Phosphoprotein Enriched in Astrocytes 15) and PLD1 (phospholipase D1), with potential applications in type II diabetes therapy. PED/PEA15 is known to be overexpressed in certain forms of diabetes, where it binds to PLD1, thereby reducing insulin-stimulated glucose transport. The inhibition of this interaction reestablishes basal glucose transport, indicating PED as a potential target of ligands capable to recover glucose tolerance and insulin sensitivity. In this study, we employ computational methods to provide a detailed description of BPH03 interaction with PED, evidencing the presence of a hidden druggable pocket within its PLD1 binding surface. We also elucidate the conformational changes that occur during PED interaction with BPH03. Moreover, we report new NMR data supporting the in-silico findings and indicating that BPH03 disrupts the PED/PLD1 interface displacing PLD1 from its interaction with PED. Our study represents a significant advancement toward the development of potential therapeutics for the treatment of type II diabetes.

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.

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.

Structural Characterization of the Full-Length Anti-CD20 Antibody Rituximab.

Rituximab, a murine-human chimera, is the first monoclonal antibody (mAb) developed as a therapeutic agent to target CD20 protein. Its Fab domain and its interaction with CD20 have been extensively studied and high-resolution atomic models obtained by X-ray diffraction or cryo-electron microscopy are available. However, the structure of the full-length antibody is still missing as the inherent protein flexibility hampers the formation of well-diffracting crystals and the reconstruction of 3D microscope images. The global structure of rituximab from its dilute solution is here elucidated by small-angle X-ray scattering (SAXS). The limited data resolution achievable by this technique has been compensated by intensive computational modelling that led to develop a new and effective procedure to characterize the average mAb conformation as well as that of the single domains. SAXS data indicated that rituximab adopts an asymmetric average conformation in solution, with a radius of gyration and a maximum linear dimension of 52 Å and 197 Å, respectively. The asymmetry is mainly due to an uneven arrangement of the two Fab units with respect to the central stem (the Fc domain) and reflects in a different conformation of the individual units. As a result, the Fab elbow angle, which is a crucial determinant for antigen recognition and binding, was found to be larger (169°) in the more distant Fab unit than that in the less distant one (143°). The whole flexibility of the antibody has been found to strongly depend on the relative inter-domain orientations, with one of the Fab arms playing a major role. The average structure and the amount of flexibility has been studied in the presence of different buffers and additives, and monitored at increasing temperature, up to the complete unfolding of the antibody. Overall, the structural characterization of rituximab can help in designing next-generation anti-CD20 antibodies and finding more efficient routes for rituximab production at industrial level.

CATMoS: Collaborative Acute Toxicity Modeling Suite.

BACKGROUND: Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals. OBJECTIVES: The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (LD50 value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [LD50 (LD50≤50mg/kg)], and nontoxic chemicals (LD50>2,000mg/kg). METHODS: An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches. RESULTS: The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results. DISCUSSION: CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.