Matched Molecular Pair Analysis in drug discovery

A new computational cross-structure-activity relationship (C-SAR) approach applies to a selective HDAC6 inhibitor dataset for accelerated structure development

Several structure-activity relationship (SAR) methodologies have been developed for the research community to improve the potential activity of prototype structures. To accomplish this, Topliss proposed the Topliss tree and the Topliss Batchwise scheme for structure development. Structure development necessitates tactics beyond traditional SAR procedures when handling issues, such as rapid structural inactivation during development. SAR data is vital for altering chemical structures and addressing compound problems. Obtaining unique SAR data that provides strategic options for structure transformation relevant to every chemotype and not limited to a specific parent structure, as the Topliss approach does, is challenging. In this context, we present the C-SAR strategy, which addresses these issues and accelerates structural development. The C-SAR method provides insights into converting an inactive compound into an active one. We used cheminformatics and molecular docking tools to study a chemical library of diverse chemotypes targeting HDAC6, arranging it in matched molecular pairs (MMPs) with high structural activity landscape index (SALI) values of 820880 and a diversity index of 0.5827 and identifying C-SAR highlights based on repetitive pharmacophoric substitution patterns across different MMP chemotypes that resulted in activity cliffs. C-SAR is beneficial for SAR expansion when high-quality structural data are available to study a dataset of various MMPs from a specific class of compounds and allows using the obtained C-SAR highlights to design compounds of novel chemotypes beyond the investigated dataset. Data imputation using deep-learning predictive models may address the issue of data availability for C-SAR.

Comparing Molecules Generated by MMPDB and REINVENT4 with Ideas from Drug Discovery Design Teams

This study compares molecules designed by drug discovery project teams from the Sanders Tri-Institutional Therapeutics Discovery Institute with molecules generated by two computational tools: MMPDB and REINVENT4. Seven different test cases with diverse chemotypes are studied in order to explore the potential of these computational tools in complementing human expertise in the early stages of drug discovery. By comparing the molecular structures and properties generated by MMPDB and REINVENT4 to those designed by project design teams, we aim to assess the value of such tools. The results indicate that MMPDB and REINVENT4 cover regions of chemical space larger than those covered by ideas from the drug discovery project teams. However, the chemical spaces covered by the two methods are quite different, and neither method completely covers the chemical space identified by the drug discovery project teams. Thus, the computational methods are complementary to one another and to drug discovery project team ideation. Effective application of generative molecule design tools has the potential to accelerate the identification of novel therapeutic candidates by expanding the chemical space explored during drug discovery and enabling optimal exploration.

Discovery of TNG462: A Highly Potent and Selective MTA-Cooperative PRMT5 Inhibitor to Target Cancers with MTAP Deletion

The gene encoding for MTAP is one of the most commonly deleted genes in cancer, occurring in approximately 10-15% of all human cancer. We have previously described the discovery of TNG908, a brain-penetrant clinical-stage compound that selectively targets MTAP-deleted cancer cells by binding to and inhibiting PRMT5 cooperatively with MTA, which is present in elevated concentrations in MTAP-deleted cells. Herein we describe the discovery of TNG462, a more potent and selective MTA-cooperative PRMT5 inhibitor with improved DMPK properties that is selective for MTAP-deleted cancers and is currently in Phase I/II clinical trials.

MTA-Cooperative PRMT5 Inhibitors: Mechanism Switching Through Structure-Based Design

Deletion of the MTAP gene leads to accumulation of the substrate of the MTAP protein, methylthioadenosine (MTA). MTA binds PRMT5 competitively with S-adenosyl-l-methionine (SAM), and selective inhibition of the PRMT5•MTA complex relative to the PRMT5•SAM complex can lead to selective killing of cancer cells with MTAP deletion. Herein, we describe the discovery of novel compounds using structure-based drug design to switch the mechanism of binding of known, SAM-cooperative PRMT5 inhibitors to an MTA-cooperative binding mechanism by occupying the portion of the SAM binding pocket in PRMT5 that is unoccupied when MTA is bound and hydrogen bonding to Arg368, thereby allowing them to selectively target MTAP-deleted cancer cells.

Macrocyclization as a Strategy for Kinetic Solubility Improvement: A Comparative Analysis of Matched Molecular Pairs

In recent years, rationally designed macrocycles have emerged as promising therapeutic modalities for challenging drug targets. Macrocycles can improve affinity, selectivity, and pharmacokinetic (PK) parameters, possibly via providing semirigid, preorganized scaffolds. Nevertheless, how macrocyclization affects PK-relevant properties is still poorly understood. To address this question, we systematically generated and compared 15 matched molecular pairs of macrocycles and structurally similar linear analogs. We found that macrocyclization substantially improves kinetic solubility while not impairing the other measured parameters. We hypothesize that this could arise from "chameleonicity," which was previously reported for large, natural-product-derived macrocycles. Our results show that the improvement of kinetic solubility is an underappreciated aspect of macrocycles that may facilitate formulation strategies compared to linear analogs to improve bioavailability.

Identification of bioactive compounds with popular single-atom modifications: Comprehensive analysis and implications for compound design

The extensive bioactivity data available in public databases, such as ChEMBL, has facilitated in-depth structure-activity relationship (SAR) analysis, which are essential for understanding the impact of molecular modifications on biological activity in a comprehensive manner. A central strategy in SAR analysis is the assessment of molecular similarity. Several approaches preferred by medicinal chemists have been developed to efficiently capture structurally related compounds on a large scale. Represented as a popular molecular editing strategy in hit-to-lead and lead optimization processes, we previously introduced four types of single-atom modifications (SAMs) as chemical similarity criterion and conducted a systematic analysis of their application in compound design. In this study, we expanded the analysis to cover 10 common SAMs, including carbon-nitrogen (N↔C), O↔C, N↔O, S↔O, as well as simpler modifications such as OH↔H, CH3↔H, and halogen-hydrogen (F, Cl, Br, I↔H) exchanges. Leveraging high-confidence bioactivity data from ChEMBL (version 34), we assembled a comprehensive dataset comprising 374,979 SAM pairs. Following an evaluation of the frequency of these SAM types in medicinal chemistry efforts, we focused on SAM-induced activity cliffs (ACs), yielding over 7400 ACs, substantially expanding the current knowledgebase of ACs associated with single-atom changes. Furthermore, structural analysis of these ACs, supported by experimental data, provides critical insights into the role of single-atom modifications in modulating compound activity, offering practical guidance for the structure-based optimization of molecular properties in drug development. As a result, we are providing open access to all identified ACs along with their associated structural information.

PepFuNN: Novo Nordisk Open-Source Toolkit to Enable Peptide in Silico Analysis

We present PepFuNN, a new open-source version of the PepFun package with functions to study the chemical space of peptide libraries and perform structure-activity relationship analyses. PepFuNN is a Python package comprising five modules to study peptides with natural amino acids and, in some cases, sequences with non-natural amino acids based on the availability of a public monomer dictionary. The modules allow calculating physicochemical properties, performing similarity analysis using different peptide representations, clustering peptides using molecular fingerprints or calculated descriptors, designing peptide libraries based on specific requirements, and a module dedicated to extracting matched pairs from experimental campaigns to guide the selection of the most relevant mutations in design new rounds. The code and tutorials are available at https://github.com/novonordisk-research/pepfunn.

ADMET evaluation in drug discovery: 21. Application and industrial validation of machine learning algorithms for Caco-2 permeability prediction

The Caco-2 cell model has been widely used to assess the intestinal permeability of drug candidates in vitro, owing to its morphological and functional similarity to human enterocytes. While Caco-2 cell assay is considered safe and cost-effective, it is also characterized by being time-consuming. Therefore, computational models that achieve high accuracies in predicting Caco-2 permeability are crucial for enhancing the efficiency of oral drug development. In this study, we conducted an in-depth analysis of the characteristics of an augmented Caco-2 permeability dataset, and evaluated a diverse range of machine learning algorithms in combination with different molecular representations. The results indicated that XGBoost generally provided better predictions than comparable models for the test sets. In addition, we investigated the transferability of machine learning models trained on publicly available data to internal pharmaceutical industry datasets. Our findings, based on the Shanghai Qilu's in-house dataset, showed that the boosting models retained a degree of predictive efficacy when applied to industry data. Furthermore, Y-randomization test and applicability domain analysis were employed to assess the robustness and generalizability of these models. Matched Molecular Pair Analysis (MMPA) was utilized to extract chemical transformation rules. We believe that the model developed in this study could represent a reliable tool for assessing Caco-2 permeability during early-stage drug discovery and the chemical transformation rules derived here could provide insights for optimizing Caco-2 permeability.Scientific contributionA comprehensive validation of various machine learning algorithms combined with diverse molecular representations on a large dataset for predicting Caco-2 permeability was reported. The transferability of machine learning models trained on publicly available data to internal pharmaceutical industry datasets was also investigated. Matched molecular pair analysis was carried out to provide reasonable suggestions for researchers to improve the Caco-2 permeability of compounds.

Discovery of BAY-405: An Azaindole-Based MAP4K1 Inhibitor for the Enhancement of T-Cell Immunity against Cancer

Mitogen-activated protein kinase kinase kinase kinase 1 (MAP4K1) is a serine/threonine kinase that acts as an immune checkpoint downstream of T-cell receptor stimulation. MAP4K1 activity is enhanced by prostaglandin E2 (PGE2) and transforming growth factor beta (TGFβ), immune modulators commonly present in the tumor microenvironment. Therefore, its pharmacological inhibition is an attractive immuno-oncology concept for inducing therapeutic T-cell responses in cancer patients. Here, we describe the systematic optimization of azaindole-based lead compound 1, resulting in the discovery of potent and selective MAP4K1 inhibitor 38 (BAY-405) that displays nanomolar potency in biochemical and cellular assays as well as in vivo exposure after oral dosing. BAY-405 enhances T-cell immunity and overcomes the suppressive effect of PGE2 and TGFβ. Treatment of tumor-bearing mice shows T-cell-dependent antitumor efficacy. MAP4K1 inhibition in conjunction with PD-L1 blockade results in a superior antitumor impact, illustrating the complementarity of the single agent treatments.

Identification of lysosomotropism using explainable machine learning and morphological profiling cell painting data

Lysosomotropism is a phenomenon of diverse pharmaceutical interests because it is a property of compounds with diverse chemical structures and primary targets. While it is primarily reported to be caused by compounds having suitable lipophilicity and basicity values, not all compounds that fulfill such criteria are in fact lysosomotropic. Here, we use morphological profiling by means of the cell painting assay (CPA) as a reliable surrogate to identify lysosomotropism. We noticed that only 35% of the compound subset with matching physicochemical properties show the lysosomotropic phenotype. Based on a matched molecular pair analysis (MMPA), no key substructures driving lysosomotropism could be identified. However, using explainable machine learning (XML), we were able to highlight that higher lipophilicity, basicity, molecular weight, and lower topological polar surface area are among the important properties that induce lysosomotropism in the compounds of this subset.

Improved QSAR models for PARP-1 inhibition using data balancing, interpretable machine learning, and matched molecular pair analysis

The poly (ADP-ribose) polymerase-1 (PARP-1) enzyme is an important target in the treatment of breast cancer. Currently, treatment options include the drugs Olaparib, Niraparib, Rucaparib, and Talazoparib; however, these drugs can cause severe side effects including hematological toxicity and cardiotoxicity. Although in silico models for the prediction of PARP-1 activity have been developed, the drawbacks of these models include low specificity, a narrow applicability domain, and a lack of interpretability. To address these issues, a comprehensive machine learning (ML)-based quantitative structure-activity relationship (QSAR) approach for the informed prediction of PARP-1 activity is presented. Classification models built using the Synthetic Minority Oversampling Technique (SMOTE) for data balancing gave robust and predictive models based on the K-nearest neighbor algorithm (accuracy 0.86, sensitivity 0.88, specificity 0.80). Regression models were built on structurally congeneric datasets, with the models for the phthalazinone class and fused cyclic compounds giving the best performance. In accordance with the Organization for Economic Cooperation and Development (OECD) guidelines, a mechanistic interpretation is proposed using the Shapley Additive Explanations (SHAP) to identify the important topological features to differentiate between PARP-1 actives and inactives. Moreover, an analysis of the PARP-1 dataset revealed the prevalence of activity cliffs, which possibly negatively impacts the model's predictive performance. Finally, a set of chemical transformation rules were extracted using the matched molecular pair analysis (MMPA) which provided mechanistic insights and can guide medicinal chemists in the design of novel PARP-1 inhibitors.

admetSAR3.0: a comprehensive platform for exploration, prediction and optimization of chemical ADMET properties

Absorption, distribution, metabolism, excretion and toxicity (ADMET) properties play a crucial role in drug discovery and chemical safety assessment. Built on the achievements of admetSAR and its successor, admetSAR2.0, this paper introduced the new version of the series, admetSAR3.0, as a comprehensive platform for chemical ADMET assessment, including search, prediction and optimization modules. In the search module, admetSAR3.0 hosted over 370 000 high-quality experimental ADMET data for 104 652 unique compounds, and supplemented chemical structure similarity search function to facilitate read-across. In the prediction module, we introduced comprehensive ADMET endpoints and two new sections for environmental and cosmetic risk assessments, empowering admetSAR3.0 to provide prediction for 119 endpoints, more than double numbers compared to the previous version. Furthermore, the advanced multi-task graph neural network framework offered robust and reliable support for ADMET prediction. In particular, a module named ADMETopt was added to automatically optimize the ADMET properties of query molecules through transformation rules or scaffold hopping. Finally, admetSAR3.0 provides user-friendly interfaces for multiple types of input data, such as SMILES string, chemical structure and batch molecule file, and supports various output types, including digital, chart displays and file downloads. In summary, admetSAR3.0 is anticipated to be a valuable and powerful tool in drug discovery and chemical safety assessment at http://lmmd.ecust.edu.cn/admetsar3/.

Deep simulated annealing for the discovery of novel dental anesthetics with local anesthesia and anti-inflammatory properties

Multifunctional therapeutics have emerged as a solution to the constraints imposed by drugs with singular or insufficient therapeutic effects. The primary challenge is to integrate diverse pharmacophores within a single-molecule framework. To address this, we introduced DeepSA, a novel edit-based generative framework that utilizes deep simulated annealing for the modification of articaine, a well-known local anesthetic. DeepSA integrates deep neural networks into metaheuristics, effectively constraining molecular space during compound generation. This framework employs a sophisticated objective function that accounts for scaffold preservation, anti-inflammatory properties, and covalent constraints. Through a sequence of local editing to navigate the molecular space, DeepSA successfully identified AT-17, a derivative exhibiting potent analgesic properties and significant anti-inflammatory activity in various animal models. Mechanistic insights into AT-17 revealed its dual mode of action: selective inhibition of NaV1.7 and 1.8 channels, contributing to its prolonged local anesthetic effects, and suppression of inflammatory mediators via modulation of the NLRP3 inflammasome pathway. These findings not only highlight the efficacy of AT-17 as a multifunctional drug candidate but also highlight the potential of DeepSA in facilitating AI-enhanced drug discovery, particularly within stringent chemical constraints.

Discovery of TNG908: A Selective, Brain Penetrant, MTA-Cooperative PRMT5 Inhibitor That Is Synthetically Lethal with MTAP-Deleted Cancers

It has been shown that PRMT5 inhibition by small molecules can selectively kill cancer cells with homozygous deletion of the MTAP gene if the inhibitors can leverage the consequence of MTAP deletion, namely, accumulation of the MTAP substrate MTA. Herein, we describe the discovery of TNG908, a potent inhibitor that binds the PRMT5·MTA complex, leading to 15-fold-selective killing of MTAP-deleted (MTAP-null) cells compared to MTAPintact (MTAP WT) cells. TNG908 shows selective antitumor activity when dosed orally in mouse xenograft models, and its physicochemical properties are amenable for crossing the blood-brain barrier (BBB), supporting clinical study for the treatment of both CNS and non-CNS tumors with MTAP loss.

A domain-label-guided translation model for molecular optimization

Molecular optimization, which aims to improve molecular properties by modifying complex molecular structures, is a crucial and challenging task in drug discovery. In recent years, translation models provide a promising way to transform low-property molecules to high-property molecules, which enables molecular optimization to achieve remarkable progress. However, most existing models require matched molecular pairs, which are prone to be limited by the datasets. Although some models do not require matched molecular pairs, their performance is usually sacrificed due to the lack of useful supervising information. To address this issue, a domain-label-guided translation model is proposed in this paper, namely DLTM. In the model, the domain label information of molecules is exploited as a control condition to obtain different embedding representations, enabling the model to generate diverse molecules. Besides, the model adopts a classifier network to identify the property categories of transformed molecules, guiding the model to generate molecules with desired properties. The performance of DLTM is verified on two optimization tasks, namely the quantitative estimation of drug-likeness and penalized logP. Experimental results show that the proposed DLTM is superior to the compared baseline models.

Multidrug efflux in Gram-negative bacteria: structural modifications in active compounds leading to efflux pump avoidance

Gram-negative bacteria cause the majority of critically drug-resistant infections, necessitating the rapid development of new drugs with Gram-negative activity. However, drug design is hampered by the low permeability of the Gram-negative cell envelope and the function of drug efflux pumps, which extrude foreign molecules from the cell. A better understanding of the molecular determinants of compound recognition by efflux pumps is, therefore, essential. Here, we quantitatively analysed the activity of 73,737 compounds, recorded in the publicly accessible database CO-ADD, across three strains of E. coli - the wild-type, the efflux-deficient tolC variant, and the hyper-permeable lpxC variant, to elucidate the molecular principles of evading efflux pumps. We computationally investigated molecular features within this dataset that promote, or reduce, the propensity of being recognised by the TolC-dependent efflux systems in E. coli. Our results show that, alongside a range of physicochemical features, the presence or absence of specific chemical groups in the compounds substantially increases the probability of avoiding efflux. A comparison of our findings with inward permeability data further underscores the primary role of efflux in determining drug bioactivity in Gram-negative bacteria.

Discovery of IRAK4 Inhibitors (Zabedosertib) and

Interleukin-1 receptor-associated kinase 4 (IRAK4) plays a critical role in innate inflammatory processes. Here, we describe the discovery of two clinical candidate IRAK4 inhibitors, BAY1834845 (zabedosertib) and BAY1830839, starting from a high-throughput screening hit derived from Bayer's compound library. By exploiting binding site features distinct to IRAK4 using an in-house docking model, liabilities of the original hit could surprisingly be overcome to confer both candidates with a unique combination of good potency and selectivity. Favorable DMPK profiles and activity in animal inflammation models led to the selection of these two compounds for clinical development in patients.

DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning

Established molecular machine learning models process individual molecules as inputs to predict their biological, chemical, or physical properties. However, such algorithms require large datasets and have not been optimized to predict property differences between molecules, limiting their ability to learn from smaller datasets and to directly compare the anticipated properties of two molecules. Many drug and material development tasks would benefit from an algorithm that can directly compare two molecules to guide molecular optimization and prioritization, especially for tasks with limited available data. Here, we develop DeepDelta, a pairwise deep learning approach that processes two molecules simultaneously and learns to predict property differences between two molecules from small datasets. On 10 ADMET benchmark tasks, our DeepDelta approach significantly outperforms two established molecular machine learning algorithms, the directed message passing neural network (D-MPNN) ChemProp and Random Forest using radial fingerprints, for 70% of benchmarks in terms of Pearson's r, 60% of benchmarks in terms of mean absolute error (MAE), and all external test sets for both Pearson's r and MAE. We further analyze our performance and find that DeepDelta is particularly outperforming established approaches at predicting large differences in molecular properties and can perform scaffold hopping. Furthermore, we derive mathematically fundamental computational tests of our models based on mathematical invariants and show that compliance to these tests correlates with overall model performance - providing an innovative, unsupervised, and easily computable measure of expected model performance and applicability. Taken together, DeepDelta provides an accurate approach to predict molecular property differences by directly training on molecular pairs and their property differences to further support fidelity and transparency in molecular optimization for drug development and the chemical sciences.

Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification

Siamese networks, representing a novel class of neural networks, consist of two identical subnetworks sharing weights but receiving different inputs. Here we present a similarity-based pairing method for generating compound pairs to train Siamese neural networks for regression tasks. In comparison with the conventional exhaustive pairing, it reduces the algorithm complexity from O(n2) to O(n). It also results in a better prediction performance consistently on the three physicochemical datasets, using a multilayer perceptron with the circular fingerprint as a proof of concept. We further include into a Siamese neural network the transformer-based Chemformer, which extracts task-specific features from the simplified molecular-input line-entry system representation of compounds. Additionally, we propose a means to measure the prediction uncertainty by utilizing the variance in predictions from a set of reference compounds. Our results demonstrate that the high prediction accuracy correlates with the high confidence. Finally, we investigate implications of the similarity property principle in machine learning.

Physicochemical Responsive Integrated Similarity Measure (PRISM) for a Comprehensive Quantitative Perspective of Sample Similarity Dynamically Assessed with NIR Spectra

Determining sample similarity underlies many foundational principles in analytical chemistry. For example, calibration models are unsuitable to predict outliers. Calibration transfer methods assume a moderate degree of sample and measurement dissimilarities between a calibration set and target prediction samples. Classification approaches link target sample similarities to groups of similar class samples. Although similarity is ubiquitous in analytical chemistry and everyday life, quantifying sample similarity is without a straightforward solution, especially when target domain samples are unlabeled and the only known features are measurable, such as spectra (the focus of this paper). The process proposed to assess sample similarity integrates spectral similarity information with contextual considerations among source analyte contents, model, and analyte predictions. This hybrid approach named the physicochemical responsive integrated similarity measure (PRISM) amplifies hidden-but-essential physicochemical properties encoded within respective spectra. PRISM is tested on four near-infrared (NIR) data sets for four diverse application areas to show efficacy. These applications are the assessment of prediction reliability and model updating for model generalizability, outlier detection, and basic matrix matching evaluation. Discussion is provided on adapting PRISM to classification problems. Results indicate that PRISM collects large amounts of similarity information and effectively integrates it to produce a quantitative similarity evaluation between the target sample and a source domain. The approach is also useful for biological samples with additional physiochemical variations. While PRISM is dynamically tested on NIR data, parts of PRISM were previously applied to other data types, and PRISM should be applicable to other measurement systems perturbed by matrix effects.

Fast prediction of antibiotic permeability through membrane channels using Brownian dynamics

The efficient permeation across the Gram-negative bacterial membrane is an important step in the overall process of antibacterial action of a molecule and the one that has posed a significant hurdle on the way toward approved antibiotics. Predicting the permeability for a large library of molecules and assessing the effect of different molecular transformations on permeation rates of a given molecule is critical to the development of effective antibiotics. We present a computational approach for obtaining estimates of molecular permeability through a porin channel in a matter of hours using a Brownian dynamics approach. The fast sampling using a temperature acceleration scheme enables the approximate estimation of permeability using the inhomogeneous solubility diffusion model. Although the method is a significant approximation to similar all-atom approaches tested previously, we show that the present approach predicts permeabilities that correlate fairly well with the respective experimental permeation rates from liposome swelling experiments and accumulation rates from antibiotic accumulation assays, and is significantly, i.e., about 14 times, faster compared with a previously reported approach. The possible applications of the scheme in high-throughput screening for fast permeators are discussed.

Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization

Molecular optimization, which transforms a given input molecule X into another Y with desired properties, is essential in molecular drug discovery. The traditional approaches either suffer from sample-inefficient learning or ignore information that can be captured with the supervised learning of optimized molecule pairs. In this study, we present a novel molecular optimization paradigm, Graph Polish. In this paradigm, with the guidance of the source and target molecule pairs of the desired properties, a heuristic optimization solution can be derived: given an input molecule, we first predict which atom can be viewed as the optimization center, and then the nearby regions are optimized around this center. We then propose an effective and efficient learning framework, Teacher and Student polish, to capture the dependencies in the optimization steps. A teacher component automatically identifies and annotates the optimization centers and the preservation, removal, and addition of some parts of the molecules; a student component learns these knowledges and applies them to a new molecule. The proposed paradigm can offer an intuitive interpretation for the molecular optimization result. Experiments with multiple optimization tasks are conducted on several benchmark datasets. The proposed approach achieves a significant advantage over the six state-of-the-art baseline methods. Also, extensive studies are conducted to validate the effectiveness, explainability, and time savings of the novel optimization paradigm.

An overview of compound properties, multiparameter optimization, and computational drug design methods for PARP-1 inhibitor drugs

Breast cancer treatment with PARP-1 inhibitors remains challenging due to emerging toxicities, drug resistance, and unaffordable costs of treatment options. How do we invent strategies to design better anti-cancer drugs? A part of the answer is in optimized compound properties, desirability functions, and modern computational drug design methods that drive selectivity and toxicity and have not been reviewed for PARP-1 inhibitors. Nonetheless, comparisons of these compound properties for PARP-1 inhibitors are not available in the literature. In this review, we analyze the physchem, PKPD space to identify inherent desirability functions characteristic of approved drugs that can be valuable for the design of better candidates. Recent literature utilizing ligand, structure-based drug design strategies and matched molecular pair analysis (MMPA) for the discovery of novel PARP-1 inhibitors are also reviewed. Thus, this perspective provides valuable insights into the medchem and multiparameter optimization of PARP-1 inhibitors that might be useful to other medicinal chemists.

Chemical rules for optimization of chemical mutagenicity via matched molecular pairs analysis and machine learning methods

Chemical mutagenicity is a serious issue that needs to be addressed in early drug discovery. Over a long period of time, medicinal chemists have manually summarized a series of empirical rules for the optimization of chemical mutagenicity. However, given the rising amount of data, it is getting more difficult for medicinal chemists to identify more comprehensive chemical rules behind the biochemical data. Herein, we integrated a large Ames mutagenicity data set with 8576 compounds to derive mutagenicity transformation rules for reversing Ames mutagenicity via matched molecular pairs analysis. A well-trained consensus model with a reasonable applicability domain was constructed, which showed favorable performance in the external validation set with an accuracy of 0.815. The model was used to assess the generalizability and validity of these mutagenicity transformation rules. The results demonstrated that these rules were of great value and could provide inspiration for the structural modifications of compounds with potential mutagenic effects. We also found that the local chemical environment of the attachment points of rules was critical for successful transformation. To facilitate the use of these mutagenicity transformation rules, we integrated them into ADMETopt2 ( http://lmmd.ecust.edu.cn/admetsar2/admetopt2/ ), a free web server for optimization of chemical ADMET properties. The above-mentioned approach would be extended to the optimization of other toxicity endpoints.

BAY-069, a Novel (Trifluoromethyl)pyrimidinedione-Based BCAT1/2 Inhibitor and Chemical Probe

The branched-chain amino acid transaminases (BCATs) are enzymes that catalyze the first reaction of catabolism of the essential branched-chain amino acids to branched-chain keto acids to form glutamate. They are known to play a key role in different cancer types. Here, we report a new structural class of BCAT1/2 inhibitors, (trifluoromethyl)pyrimidinediones, identified by a high-throughput screening campaign and subsequent optimization guided by a series of X-ray crystal structures. Our potent dual BCAT1/2 inhibitor BAY-069 displays high cellular activity and very good selectivity. Along with a negative control (BAY-771), BAY-069 was donated as a chemical probe to the Structural Genomics Consortium.

Enhanced-Sampling Simulations for the Estimation of Ligand Binding Kinetics: Current Status and Perspective

The dissociation rate (k off) associated with ligand unbinding events from proteins is a parameter of fundamental importance in drug design. Here we review recent major advancements in molecular simulation methodologies for the prediction of k off. Next, we discuss the impact of the potential energy function models on the accuracy of calculated k off values. Finally, we provide a perspective from high-performance computing and machine learning which might help improve such predictions.

IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method

The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.

The N,N,O-Trisubstituted Hydroxylamine Isostere and Its Influence on Lipophilicity and Related Parameters

The influence of substitution of an N,N,O-trisubstituted hydroxylamine (-NR-OR'-) unit for a hydrocarbon (-CHR-CH2-), ether (-CHR-OR'-), or amine (-NR-CHR'-) moiety on lipophilicity and other ADME parameters is described. A matched molecular pair analysis was conducted across five series of compounds, which showed that the replacement of carbon-carbon bonds by N,N,O-trisubstituted hydroxylamines typically leads to a reduction in logP comparable to that achieved with a tertiary amine group. In contrast, the weakly basic N,N,O-trisubstituted hydroxylamines have greater logD 7.4 values than tertiary amines. It is also demonstrated that the N,N,O-trisubstituted hydroxylamine moiety can improve metabolic stability and reduce human plasma protein binding relative to the corresponding hydrocarbon and ether units. Coupled with recent synthetic methods for hydroxylamine assembly by N-O bond formation, these results provide support for the re-evaluation of the N,N,O-trisubstituted hydroxylamine moiety in small-molecule optimization schemes in medicinal chemistry.

Data-Driven Derivation of Molecular Substructures That Enhance Drug Activity in Gram-Negative Bacteria

The complex cell envelope of Gram-negative bacteria creates a formidable barrier to antibiotic influx. Reduced drug uptake impedes drug development and contributes to a wide range of drug-resistant bacterial infections, including those caused by extremely resistant species prioritized by the World Health Organization. To develop new and efficient treatments, a better understanding of the molecular features governing Gram-negative permeability is essential. Here, we present a data-driven approach, using matched molecular pair analysis and machine learning on minimal inhibitory concentration data from Gram-positive and Gram-negative bacteria to uncover chemical features that influence Gram-negative bioactivity. We find recurring chemical moieties, of a wider range than previously known, that consistently improve activity and suggest that this insight can be used to optimize compounds for increased Gram-negative uptake. Our findings may help to expand the chemical space of broad-spectrum antibiotics and aid the search for new antibiotic compound classes.

Controlled Molecule Generator for Optimizing Multiple Chemical Properties

Generating a novel and optimized molecule with desired chemical properties is an essential part of the drug discovery process. Failure to meet one of the required properties can frequently lead to failure in a clinical test which is costly. In addition, optimizing these multiple properties is a challenging task because the optimization of one property is prone to changing other properties. In this paper, we pose this multi-property optimization problem as a sequence translation process and propose a new optimized molecule generator model based on the Transformer with two constraint networks: property prediction and similarity prediction. We further improve the model by incorporating score predictions from these constraint networks in a modified beam search algorithm. The experiments demonstrate that our proposed model, Controlled Molecule Generator (CMG), outperforms state-of-the-art models by a significant margin for optimizing multiple properties simultaneously.

Semi-automated workflow for molecular pair analysis and QSAR-assisted transformation space expansion

In the process of drug discovery, the optimization of lead compounds has always been a challenge faced by pharmaceutical chemists. Matched molecular pair analysis (MMPA), a promising tool to efficiently extract and summarize the relationship between structural transformation and property change, is suitable for local structural optimization tasks. Especially, the integration of MMPA with QSAR modeling can further strengthen the utility of MMPA in molecular optimization navigation. In this study, a new semi-automated procedure based on KNIME was developed to support MMPA on both large- and small-scale datasets, including molecular preparation, QSAR model construction, applicability domain evaluation, and MMP calculation and application. Two examples covering regression and classification tasks were provided to gain a better understanding of the importance of MMPA, which has also shown the reliability and utility of this MMPA-by-QSAR pipeline.

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

Pairwise Difference Regression: A Machine Learning Meta-algorithm for Improved Prediction and Uncertainty Quantification in Chemical Search

Machine learning (ML) plays a growing role in the design and discovery of chemicals, aiming to reduce the need to perform expensive experiments and simulations. ML for such applications is promising but difficult, as models must generalize to vast chemical spaces from small training sets and must have reliable uncertainty quantification metrics to identify and prioritize unexplored regions. Ab initio computational chemistry and chemical intuition alike often take advantage of differences between chemical conditions, rather than their absolute structure or state, to generate more reliable results. We have developed an analogous comparison-based approach for ML regression, called pairwise difference regression (PADRE), which is applicable to arbitrary underlying learning models and operates on pairs of input data points. During training, the model learns to predict differences between all possible pairs of input points. During prediction, the test points are paired with all training set points, giving rise to a set of predictions that can be treated as a distribution of which the mean is treated as a final prediction and the dispersion is treated as an uncertainty measure. Pairwise difference regression was shown to reliably improve the performance of the random forest algorithm across five chemical ML tasks. Additionally, the pair-derived dispersion is both well correlated with model error and performs well in active learning. We also show that this method is competitive with state-of-the-art neural network techniques. Thus, pairwise difference regression is a promising tool for candidate selection algorithms used in chemical discovery.

MolOpt: A Web Server for Drug Design using Bioisosteric Transformation

BACKGROUND

Bioisosteric replacement is widely used in drug design for lead optimization. However, the identification of a suitable bioisosteric group is not an easy task.

METHODS

In this work, we present MolOpt, a web server for in silico drug design using bioisosteric transformation. Potential bioisosteric transformation rules were derived from data mining, deep generative machine learning and similarity comparison. MolOpt tries to assist the medicinal chemist in his/her search for what to make next.

RESULTS AND DISCUSSION

By replacing molecular substructures with similar chemical groups, MolOpt automatically generates lists of analogues. MolOpt also evaluates forty important pharmacokinetic and toxic properties for each newly designed molecule. The transformed analogues can be assessed for possible future study.

CONCLUSION

MolOpt is useful for the identification of suitable lead optimization ideas. The MolOpt Server is freely available for use on the web at http://xundrug.cn/molopt.

Effects of Replacing Oxygenated Functionality with Fluorine on Lipophilicity

The replacement of oxygenated functionality (hydroxy and alkoxy) with a fluorine atom is a commonly used bioisosteric replacement in medicinal chemistry. In this paper, we use molecular matched-pair analysis to better understand the effects of this replacement on lipophilicity. It seems that the reduced log P of the oxygenated compound is normally dominant in determining the size of this difference. We observe that the presence of additional electron-donating groups on an aromatic ring generally increases the difference in lipophilicity between an oxygenated compound and its fluorinated analogue, while electron-withdrawing groups lead to smaller differences. Ortho-substituted compounds generally display a reduced difference in log P compared to para- and meta-substituted compounds, particularly if an ortho-substituent can form an intramolecular hydrogen bond. Hydrogen-bond acceptors remote to an aromatic ring containing fluorine/oxygen can also reduce the difference in log P between oxygen- and fluorine-substituted compounds.

QSAR-assisted-MMPA to expand chemical transformation space for lead optimization

Matched molecular pairs analysis (MMPA) has become a powerful tool for automatically and systematically identifying medicinal chemistry transformations from compound/property datasets. However, accurate determination of matched molecular pair (MMP) transformations largely depend on the size and quality of existing experimental data. Lack of high-quality experimental data heavily hampers the extraction of more effective medicinal chemistry knowledge. Here, we developed a new strategy called quantitative structure-activity relationship (QSAR)-assisted-MMPA to expand the number of chemical transformations and took the logD7.4 property endpoint as an example to demonstrate the reliability of the new method. A reliable logD7.4 consensus prediction model was firstly established, and its applicability domain was strictly assessed. By applying the reliable logD7.4 prediction model to screen two chemical databases, we obtained more high-quality logD7.4 data by defining a strict applicability domain threshold. Then, MMPA was performed on the predicted data and experimental data to derive more chemical rules. To validate the reliability of the chemical rules, we compared the magnitude and directionality of the property changes of the predicted rules with those of the measured rules. Then, we compared the novel chemical rules generated by our proposed approach with the published chemical rules, and found that the magnitude and directionality of the property changes were consistent, indicating that the proposed QSAR-assisted-MMPA approach has the potential to enrich the collection of rule types or even identify completely novel rules. Finally, we found that the number of the MMP rules derived from the experimental data could be amplified by the predicted data, which is helpful for us to analyze the medicinal chemical rules in local chemical environment. In summary, the proposed QSAR-assisted-MMPA approach could be regarded as a very promising strategy to expand the chemical transformation space for lead optimization, especially when no enough experimental data can support MMPA.

The Derivation of a Matched Molecular Pairs Based ADME/Tox Knowledge Base for Compound Optimization

Matched Molecular Pairs (MMP) analysis is a well-established technique for Structure Activity and Property Analysis (SAR and SPR). Summarizing multiple MMPs that describe the same structural change into a single chemical transform can be a powerful tool for prediction (termed Transform from here on). This is particularly useful in the area of Absorption, Distribution, Metabolism, and Elimination (ADME) analysis that is less influenced by 3D structural binding effects. The creation of a knowledge database containing many of these Transforms across typical ADME assays promises to be a powerful approach to aid multidimensional optimization. We present a detailed workflow for the derivation of such a database. We include details of an MMP fragmentation algorithm with associated statistical summarization methods for the derivation of Transforms. This is made freely available as part of the LillyMol software package. We describe the application of this method to several ADME/Tox (Toxicity) assay data sets and highlight multiple cases where the impact of traditional medicinal chemistry Transforms is contradicted by MMP data. We also describe the internal software interface used by medicinal chemists to aid the design of new compounds via automated suggestion. This approach utilizes the matched pairs database to "suggest" improved compounds in an automated design scenario. A nonvisual script-based version of the automated suggestions code with an associated set of described chemical Transforms is also made freely available along with this paper and as part of the LillyMol software package. Finally, we contrast this knowledge database against a larger database of all MMPs derived from a 2 million compound diversity set and a subset of MMPs seen in historical discovery projects. The comparison against all transforms in the diversity collection highlights the very low coverage of the transform database as compared to all possible transforms involving 15 atom fragments. The comparison against a smaller subset of Transforms seen on internal Medicinal Chemistry projects shows better coverage of the transform database for a small set of common medicinal chemistry strategies. Within the context of all possible transforms available to a medicinal chemistry project team, the challenge remains to move beyond mere idea generation from past projects toward high quality prediction for novel ADME/Tox modulating Transforms.

Tautomer Standardization in Chemical Databases: Deriving Business Rules from Quantum Chemistry

Databases of small, potentially bioactive molecules are ubiquitous across the industry and academia. Designed such that each unique compound should appear only once, the multiplicity of ways in which many compounds can be represented means that these databases require methods for standardizing the representation of chemistry. This is commonly achieved through the use of "Chemistry Business Rules", sets of predefined rules that describe the "house style" of the database in question. At Syngenta, the historical approach to the design of chemistry business rules has been to focus on consistency of representation, with chemical relevance given secondary consideration. In this work, we overturn that convention. Through the use of quantum chemistry calculations, we define a set of chemistry business rules for tautomer standardization that reproduces gas-phase energetic preferences. We go on to show that, compared to our historic approach, this method yields tautomers that are in better agreement with those observed experimentally in condensed phases and that are better suited for use in predictive models.

Predicting liver cytosol stability of small molecules

Over the last few decades, chemists have become skilled at designing compounds that avoid cytochrome P (CYP) 450 mediated metabolism. Typical screening assays are performed in liver microsomal fractions and it is possible to overlook the contribution of cytosolic enzymes until much later in the drug discovery process. Few data exist on cytosolic enzyme-mediated metabolism and no reliable tools are available to chemists to help design away from such liabilities. In this study, we screened 1450 compounds for liver cytosol-mediated metabolic stability and extracted transformation rules that might help medicinal chemists in optimizing compounds with these liabilities. In vitro half-life data were collected by performing in-house experiments in mouse (CD-1 male) and human (mixed gender) cytosol fractions. Matched molecular pairs analysis was performed in conjunction with qualitative-structure activity relationship modeling to identify chemical structure transformations affecting cytosolic stability. The transformation rules were prospectively validated on the test set. In addition, selected rules were validated on a diverse chemical library and the resulting pairs were experimentally tested to confirm whether the identified transformations could be generalized. The validation results, comprising nearly 250 library compounds and corresponding half-life data, are made publicly available. The datasets were also used to generate in silico classification models, based on different molecular descriptors and machine learning methods, to predict cytosol-mediated liabilities. To the best of our knowledge, this is the first systematic in silico effort to address cytosolic enzyme-mediated liabilities.

hERG toxicity assessment: Useful guidelines for drug design

All along the drug development process, one of the most frequent adverse side effects, leading to the failure of drugs, is the cardiac arrhythmias. Such failure is mostly related to the capacity of the drug to inhibit the human ether-à-go-go-related gene (hERG) cardiac potassium channel. The early identification of hERG inhibition properties of biological active compounds has focused most of attention over the years. In order to prevent the cardiac side effects, a great number of in silico, in vitro and in vivo assays have been performed. The main goal of these studies is to understand the reasons of these effects, and then to give information or instructions to scientists involved in drug development to avoid the cardiac side effects. To evaluate anticipated cardiovascular effects, early evaluation of hERG toxicity has been strongly recommended for instance by the regulatory agencies such as U.S. Food and Drug Administration (FDA) and European Medicines Agency (EMA). Thus, following an initial screening of a collection of compounds to find hits, a great number of pharmacomodulation studies on the novel identified chemical series need to be performed including activity evaluation towards hERG. We provide in this concise review clear guidelines, based on described examples, illustrating successful optimization process to avoid hERG interactions as cases studies and to spur scientists to develop safe drugs.

LogD Contributions of Substituents Commonly Used in Medicinal Chemistry

The importance of physicochemical property calculation and measurement is well-established in drug discovery. In particular, lipophilicity predictions play a central role in target design and prioritization. While significant progress has been made in our ability to calculate both logP and logD, the quality of these predictions is limited by the size and diversity of the underlying data set. Access to diverse data sets and advanced models is often limited to large organizations or consortia, and they are not available to many students and practitioners of medicinal chemistry. A molecular matched pair analysis of median ΔlogD _7.4 contributions for substituents commonly used in drug discovery programs at Genentech is reported. The results of this ΔlogD analysis are compiled into a single table, which we anticipate will be of use to practicing medicinal chemists.

Bioisosteric Replacement of Amide Group with 1,2,3-Triazoles in Acetaminophen Addresses Reactive Oxygen Species-Mediated Hepatotoxic Insult in Wistar Albino Rats

Acetaminophen (AP) is a popularly recommended over-the-counter analgesic-antipyretic in clinical use. However, the drug is handicapped by the occurrence of hepatotoxic insult following acute ingestion. Consequently, AP-induced hepatotoxicity is often implicated in accidental or suicidal overdose. In the current study, we investigated the potential of bioisosteric replacement of amide in AP with 1,2,3-triazoles in curbing AP-induced hepatotoxicity. The therapeutic utility of synthesized bioisosteres was established by careful tailoring and optimization of the synthetic methodology along with detailed toxicological testing of pharmacologically potent acetaminophen-triazole derivatives (APTDs). Along the same lines, we herein report a series of 17 novel APTDs synthesized via aromatic substitution using sodium azide, l-proline, and copper iodide followed by click reaction with substituted alkynes using copper sulfate and sodium ascorbate. Pharmacological evaluation of synthesized APTDs revealed that, out of the series of 17 compounds, 5a and 5e were found to be most efficacious in exerting anti-inflammatory, analgesic, and antipyretic activity in an animal model. Further toxicity studies documented that, in both acute and sub-acute toxicology, AP administration caused significant hepatotoxicity, which was found to be a consequence of ROS-mediated oxidative stress. Potent APTDs (5a and 5e), on the other hand, revealed no adverse event in both acute and sub-toxicological analyses. Median lethal dose (LD₅₀) and no observed adverse effect level (NOAEL) values for 5a and 5e were found to be >1000 mg/kg and 2000 mg/kg, respectively. The human equivalent dose, defining the maximum safe concentration of a compound in a human's physiology, was found to be 27.68 mg/kg for the most potent APTDs (5a and 5e). Thus, it can be concluded that triazole incorporation into AP nucleus produced conjugates devoid of hepatotoxic manifestations, having the added advantage of anti-inflammatory efficacy along with analgesic and antipyretic potency.

Advances in covalent kinase inhibitors

This comprehensive review details recent advances, challenges and innovations in covalent kinase inhibition within a 10 year period (2007–2018).

Nonadditivity Analysis

We introduce the statistics behind a novel type of SAR analysis named "nonadditivity analysis". On the basis of all pairs of matched pairs within a given data set, the approach analyzes whether the same transformations between related molecules have the same effect, i.e., whether they are additive. Assuming that the experimental uncertainty is normally distributed, the additivities can be analyzed with statistical rigor and sets of compounds can be found that show significant nonadditivity. Nonadditivity analysis can not only detect nonadditivity, potential SAR outliers, and sets of key compounds but also allow estimating an upper limit of the experimental uncertainty in the data set. We demonstrate how complex SAR features that inform medicinal chemistry can be found in large SAR data sets. Finally, we show how the upper limit of experimental uncertainty for a given biochemical assay can be estimated without the need for repeated measurements of the same protein-ligand system.

Capturing and applying knowledge to guide compound optimisation

Successful drug discovery requires knowledge and experience across many disciplines, and no current 'artificial intelligence' (AI) method can replace expert scientists. However, computers can recall more information than any individual or team and facilitate the transfer of knowledge across disciplines. Here, we discuss how knowledge relating to chemistry and the biological and physicochemical properties required for a successful compound can be captured. Furthermore, we illustrate how, by combining and applying this knowledge computationally, a broader range of optimisation strategies can be rigorously explored, and the results presented in an intuitive way for consideration by the experts.

Lowering Lipophilicity by Adding Carbon: One-Carbon Bridges of Morpholines and Piperazines

In this article, we report our investigation of a phenomenon by which bridging morpholines across the ring with one-carbon tethers leads to a counterintuitive reduction in lipophilicity. This effect was also found to occur in piperazines and piperidines and lowered the measured log D_7.4 of the bridged molecules by as much as -0.8 relative to their unbridged counterparts. As lowering lipophilicity without introducing additional heteroatoms can be desirable, we believe this potentially provides a useful tactic to improve the drug-like properties of molecules containing morpholine-, piperazine-, and piperidine-like motifs.