Task-Similarity is a Crucial Factor for Few-Shot Meta-Learning of Structure-Activity Relationships.

Machine learning models support computer-aided molecular design and compound optimization. However, the initial phases of drug discovery often face a scarcity of training data for these models. Meta-learning has emerged as a potentially promising strategy, harnessing the wealth of structure-activity data available for known targets to facilitate efficient few-shot model training for the specific target of interest. In this study, we assessed the effectiveness of two different meta-learning methods, namely model-agnostic meta-learning (MAML) and adaptive deep kernel fitting (ADKF), specifically in the regression setting. We investigated how factors such as dataset size and the similarity of training tasks impact predictability. The results indicate that ADKF significantly outperformed both MAML and a single-task baseline model on the inhibition data. However, the performance of ADKF varied across different test tasks. Our findings suggest that considerable enhancements in performance can be anticipated primarily when the task of interest is similar to the tasks incorporated in the meta-learning process.

Integrating Reaction Schemes, Reagent Databases, and Virtual Libraries into Fragment-Based Design by Reinforcement Learning.

Lead optimization supported by artificial intelligence (AI)-based generative models has become increasingly important in drug design. Success factors are reagent availability, novelty, and the optimization of multiple properties. Directed fragment-replacement is particularly attractive, as it mimics medicinal chemistry tactics. Here, we present variations of fragment-based reinforcement learning using an actor-critic model. Novel features include freezing fragments and using reagents as the fragment source. Splitting molecules according to reaction schemes improves synthesizability, while tuning network output probabilities allows us to balance novelty versus diversity. Combining fragment-based optimization with virtual library encodings allows the exploration of large chemical spaces with synthesizable ideas. Collectively, these enhancements influence design toward high-quality molecules with favorable profiles. A validation study using 15 pharmaceutically relevant targets reveals that novel structures are obtained for most cases, which are identical or related to independent validation sets for each target. Hence, these modifications significantly increase the value of fragment-based reinforcement learning for drug design. The code is available on GitHub: https://github.com/Sanofi-Public/IDD-papers-fragrl.

Interpretation of Structure-Activity Relationships in Real-World Drug Design Data Sets Using Explainable Artificial Intelligence.

In silico models based on Deep Neural Networks (DNNs) are promising for predicting activities and properties of new molecules. Unfortunately, their inherent black-box character hinders our understanding, as to which structural features are important for activity. However, this information is crucial for capturing the underlying structure-activity relationships (SARs) to guide further optimization. To address this interpretation gap, "Explainable Artificial Intelligence" (XAI) methods recently became popular. Herein, we apply and compare multiple XAI methods to projects of lead optimization data sets with well-established SARs and available X-ray crystal structures. As we can show, easily understandable and comprehensive interpretations are obtained by combining DNN models with some powerful interpretation methods. In particular, SHAP-based methods are promising for this task. A novel visualization scheme using atom-based heatmaps provides useful insights into the underlying SAR. It is important to note that all interpretations are only meaningful in the context of the underlying models and associated data.

Using Graph Databases to Investigate Trends in Structure-Activity Relationship Networks.

Mining the steadily increasing amount of chemical and biological data is a key challenge in drug discovery. Graph databases offer viable alternatives for capturing interrelationships between molecules and for generating novel insights for design. In a graph database, molecules and their properties are mapped to nodes, while relationships are described by edges. Here, we introduce a graph database for navigation in chemical space, analogue searching, and structure-activity relationship (SAR) analysis. We illustrate this concept using hERG channel inhibitors from ChEMBL to extract SAR knowledge. This graph database is built using different relationships, namely 2D-fingerprint similarity, matched molecular pairs, topomer distances, and structure-activity landscape indices (SALI). Typical applications include retrieving analogues linked by single or multiple edge paths to the query compound as well as detection of nonadditive SAR features. Finally, we identify triplets of linked molecules for clustering. The speed of searching and analysis allows the user to interactively navigate the database and to address complex questions in real-time.

Impact of Different Automated Binding Pose Generation Approaches on Relative Binding Free Energy Simulations.

Relative binding free energy (RBFE) prediction methods such as free energy perturbation (FEP) are important today for estimating protein-ligand binding affinities. Significant hardware and algorithmic improvements now allow for simulating congeneric series within days. Therefore, RBFE calculations have an enormous potential for structure-based drug discovery. As typically only a few representative crystal structures for a series are available, other ligands and design proposals must be reliably superimposed for meaningful results. An observed significant effect of the alignment on FEP led us to develop an alignment approach combining docking with maximum common substructure (MCS) derived core constraints from the most similar reference pose, named MCS-docking workflow. We then studied the effect of binding pose generation on the accuracy of RBFE predictions using six ligand series from five pharmaceutically relevant protein targets. Overall, the MCS-docking workflow generated consistent poses for most of the ligands in the investigated series. While multiple alignment methods often resulted in comparable FEP predictions, for most of the cases herein, the MCS-docking workflow produced the best accuracy in predictions. Furthermore, the FEP analysis data strongly support the hypothesis that the accuracy of RBFE predictions depends on input poses to construct the perturbation map. Therefore, an automated workflow without manual intervention minimizes potential errors and obtains the most useful predictions with significant impact for structure-based design.

Predictive Multitask Deep Neural Network Models for ADME-Tox Properties: Learning from Large Data Sets.

Successful drug discovery projects require control and optimization of compound properties related to pharmacokinetics, pharmacodynamics, and safety. While volume and chemotype coverage of public and corporate ADME-Tox (absorption, distribution, excretion, metabolism, and toxicity) databases are constantly growing, deep neural nets (DNN) emerged as transformative artificial intelligence technology to analyze those challenging data. Relevant features are automatically identified, while appropriate data can also be combined to multitask networks to evaluate hidden trends among multiple ADME-Tox parameters for implicitly correlated data sets. Here we describe a novel, fully industrialized approach to parametrize and optimize the setup, training, application, and visual interpretation of DNNs to model ADME-Tox data. Investigated properties include microsomal lability in different species, passive permeability in Caco-2/TC7 cells, and logD. Statistical models are developed using up to 50 000 compounds from public or corporate databases. Both the choice of DNN hyperparameters and the type and quantity of molecular descriptors were found to be important for successful DNN modeling. Alternate learning of multiple ADME-Tox properties, resulting in a multitask approach, performs statistically superior on most studied data sets in comparison to DNN single-task models and also provides a scalable method to predict ADME-Tox properties from heterogeneous data. For example, predictive quality using external validation sets was improved from R2 of 0.6 to 0.7 comparing single-task and multitask DNN networks from human metabolic lability data. Besides statistical evaluation, a new visualization approach is introduced to interpret DNN models termed "response map", which is useful to detect local property gradients based on structure fragmentation and derivatization. This method is successfully applied to visualize fragmental contributions to guide further design in drug discovery programs, as illustrated by CRCX3 antagonists and renin inhibitors, respectively.

Characterizing hydration sites in protein-ligand complexes towards the design of novel ligands.

Water is an essential part of protein binding sites and mediates interactions to ligands. Its displacement by ligand parts affects the free binding energy of resulting protein-ligand complexes. Therefore the characterization of solvation properties is important for design. Of particular interest is the propensity of localized water to be favorably displaced by a ligand. This review discusses two popular computational approaches addressing these questions, namely WaterMap based on statistical mechanics analysis of MD simulations and 3D RISM based on integral equation theory of liquids. The theoretical background and recent applications in structure-based design will be presented.

Identification and Characterization of a Single High-Affinity Fatty Acid Binding Site in Human Serum Albumin.

A single high-affinity fatty acid binding site in the important human transport protein serum albumin (HSA) is identified and characterized using an NBD (7-nitrobenz-2-oxa-1,3-diazol-4-yl)-C12 fatty acid. This ligand exhibits a 1:1 binding stoichiometry in its HSA complex with high site-specificity. The complex dissociation constant is determined by titration experiments as well as radioactive equilibrium dialysis. Competition experiments with the known HSA-binding drugs warfarin and ibuprofen confirm the new binding site to be different from Sudlow-sites I and II. These binding studies are extended to other albumin binders and fatty acid derivatives. Furthermore an X-ray crystal structure allows locating the binding site in HSA subdomain IIA. The knowledge about this novel HSA site will be important for drug depot development and for understanding drug-protein interaction, which are important prerequisites for modulation of drug pharmacokinetics.

Thermodynamic Characterization of Hydration Sites from Integral Equation-Derived Free Energy Densities: Application to Protein Binding Sites and Ligand Series.

Water molecules play an essential role for mediating interactions between ligands and protein binding sites. Displacement of specific water molecules can favorably modulate the free energy of binding of protein-ligand complexes. Here, the nature of water interactions in protein binding sites is investigated by 3D RISM (three-dimensional reference interaction site model) integral equation theory to understand and exploit local thermodynamic features of water molecules by ranking their possible displacement in structure-based design. Unlike molecular dynamics-based approaches, 3D RISM theory allows for fast and noise-free calculations using the same detailed level of solute-solvent interaction description. Here we correlate molecular water entities instead of mere site density maxima with local contributions to the solvation free energy using novel algorithms. Distinct water molecules and hydration sites are investigated in multiple protein-ligand X-ray structures, namely streptavidin, factor Xa, and factor VIIa, based on 3D RISM-derived free energy density fields. Our approach allows the semiquantitative assessment of whether a given structural water molecule can potentially be targeted for replacement in structure-based design. Finally, PLS-based regression models from free energy density fields used within a 3D-QSAR approach (CARMa - comparative analysis of 3D RISM Maps) are shown to be able to extract relevant information for the interpretation of structure-activity relationship (SAR) trends, as demonstrated for a series of serine protease inhibitors.

Influence of thermodisinfection and duration of cryopreservation at different temperatures on pull out strength of cancellous bone.

Thermodisinfection of human femoral heads from living donors harvested during hip joint replacement is an established processing procedure. This study was designed to examine the influence of heat sterilization on pull out strength of cancellous bone and storage at different temperatures up to 2 years since we had previously studied the storage of unprocessed cancellous bone. Porcine cancellous bone resembling human bone structure was obtained from 140 proximal humerus of 6-8 months old piglets. Pull out strength of screws after thermodisinfection was compared with unprocessed cancellous bone and tested immediately and after 6, 12 and 24 months of storage at -20 and -80 °C. A three-way ANOVA was performed and significance level was 5 %. The thermodisinfected bone showed a pull out force of 2729 N (1657-3568 N). The reduction of pull out strength compared with unprocessed bone over all periods of storage was 276 N on average with 95 % confidence interval ranging from 166 N to 389 N (p < 0.0001). Different freezing temperatures did not influence this mechanic property within 24 months storage and showed no difference compared with fresh frozen bone. Thermodisinfection of cancellous bone preserves tensile strength necessary for clinical purposes. The storage at -20 °C for at least 2 years did not show relevant decrease of pull out strength compared with -80 °C without difference between thermodisinfected and fresh frozen bone. The increase of the storage temperature to -20 °C for at least 2 years should be considered.

Discovery, Structure Elucidation, and Biological Characterization of Nannocystin†A, a Macrocyclic Myxobacterial Metabolite with Potent Antiproliferative Properties.

Microbial natural products are a rich source of bioactive molecules to serve as drug leads and/or biological tools. We investigated a little-explored myxobacterial genus, Nannocystis sp., and discovered a novel 21-membered macrocyclic scaffold that is composed of a tripeptide and a polyketide part with an epoxyamide moiety. The relative and absolute configurations of the nine stereocenters was determined by NMR spectroscopy, molecular dynamics calculations, chemical degradation, and X-ray crystallography. The compound, named nannocystin A (1), was found to inhibit cell proliferation at low nanomolar concentrations through the early induction of apoptosis. The mode of action of 1 could not be matched to that of standard drugs by transcriptional profiling and biochemical experiments. An initial investigation of the structure-activity relationship based on seven analogues demonstrated the importance of the epoxide moiety for high activity.

Benzimidazole-carboxamides as potent and bioavailable stearoyl-CoA desaturase (SCD1) inhibitors from ligand-based virtual screening and chemical optimization.

The discovery of potent benzimidazole stearoyl-CoA desaturase (SCD1) inhibitors by ligand-based virtual screening is described. ROCS 3D-searching gave a favorable chemical motif that was subsequently optimized to arrive at a chemical series of potent and promising SCD1 inhibitors. In particular, compound SAR224 was selected for further pharmacological profiling based on favorable in vitro data. After oral administration to male ZDF rats, this compound significantly decreased the serum fatty acid desaturation index, thus providing conclusive evidence for SCD1 inhibition in vivo by SAR224.

Quantum mechanics-based properties for 3D-QSAR.

We have used a set of four local properties based on semiempirical molecular orbital calculations (electron density (ρ), hydrogen bond donor field (HDF), hydrogen bond acceptor field (HAF), and molecular lipophilicity potential (MLP)) for 3D-QSAR studies to overcome the limitations of the current force field-based molecular interaction fields (MIFs). These properties can be calculated rapidly and are thus amenable to high-throughput industrial applications. Their statistical performance was compared with that of conventional 3D-QSAR approaches using nine data sets (angiotensin converting enzyme inhibitors (ACE), acetylcholinesterase inhibitors (AchE), benzodiazepine receptor ligands (BZR), cyclooxygenase-2 inhibitors (COX2), dihydrofolate reductase inhibitors (DHFR), glycogen phosphorylase b inhibitors (GPB), thermolysin inhibitors (THER), thrombin inhibitors (THR), and serine protease factor Xa inhibitors (fXa)). The 3D-QSAR models generated were tested thoroughly for robustness and predictive ability. The average performance of the quantum mechanical molecular interaction field (QM-MIF) models for the nine data sets is better than that of the conventional force field-based MIFs. In the individual data sets, the QM-MIF models always perform better than, or as well as, the conventional approaches. It is particularly encouraging that the relative performance of the QM-MIF models improves in the external validation. In addition, the models generated showed statistical stability with respect to model building procedure variations such as grid spacing size and grid orientation. QM-MIF contour maps reproduce the features important for ligand binding for the example data set (factor Xa inhibitors), demonstrating the intuitive chemical interpretability of QM-MIFs.

Impact of Applicability Domains to Generative Artificial Intelligence.

Molecular generative artificial intelligence is drawing significant attention in the drug design community, with several experimentally validated proof of concepts already published. Nevertheless, generative models are known for sometimes generating unrealistic, unstable, unsynthesizable, or uninteresting structures. This calls for methods to constrain those algorithms to generate structures in drug-like portions of the chemical space. While the concept of applicability domains for predictive models is well studied, its counterpart for generative models is not yet well-defined. In this work, we empirically examine various possibilities and propose applicability domains suited for generative models. Using both public and internal data sets, we use generative methods to generate novel structures that are predicted to be actives by a corresponding quantitative structure-activity relationships model while constraining the generative model to stay within a given applicability domain. Our work looks at several applicability domain definitions, combining various criteria, such as structural similarity to the training set, similarity of physicochemical properties, unwanted substructures, and quantitative estimate of drug-likeness. We assess the structures generated from both qualitative and quantitative points of view and find that the applicability domain definitions have a strong influence on the drug-likeness of generated molecules. An extensive analysis of our results allows us to identify applicability domain definitions that are best suited for generating drug-like molecules with generative models. We anticipate that this work will help foster the adoption of generative models in an industrial context.

3D-QSAR based on quantum-chemical molecular fields: toward an improved description of halogen interactions.

Current 3D-QSAR methods such as CoMFA or CoMSIA make use of classical force-field approaches for calculating molecular fields. Thus, they can not adequately account for noncovalent interactions involving halogen atoms like halogen bonds or halogen-π interactions. These deficiencies in the underlying force fields result from the lack of treatment of the anisotropy of the electron density distribution of those atoms, known as the "σ-hole", although recent developments have begun to take specific interactions such as halogen bonding into account. We have now replaced classical force field derived molecular fields by local properties such as the local ionization energy, local electron affinity, or local polarizability, calculated using quantum-mechanical (QM) techniques that do not suffer from the above limitation for 3D-QSAR. We first investigate the characteristics of QM-based local property fields to show that they are suitable for statistical analyses after suitable pretreatment. We then analyze these property fields with partial least-squares (PLS) regression to predict biological affinities of two data sets comprising factor Xa and GABA-A/benzodiazepine receptor ligands. While the resulting models perform equally well or even slightly better in terms of consistency and predictivity than the classical CoMFA fields, the most important aspect of these augmented field-types is that the chemical interpretation of resulting QM-based property field models reveals unique SAR trends driven by electrostatic and polarizability effects, which cannot be extracted directly from CoMFA electrostatic maps. Within the factor Xa set, the interaction of chlorine and bromine atoms with a tyrosine side chain in the protease S1 pocket are correctly predicted. Within the GABA-A/benzodiazepine ligand data set, PLS models of high predictivity resulted for our QM-based property fields, providing novel insights into key features of the SAR for two receptor subtypes and cross-receptor selectivity of the ligands. The detailed interpretation of regression models derived using improved QM-derived property fields thus provides a significant advantage by revealing chemically meaningful correlations with biological activity and helps in understanding novel structure-activity relationship features. This will allow such knowledge to be used to design novel molecules on the basis of interactions additional to steric and hydrogen-bonding features.

Development of in silico filters to predict activation of the pregnane X receptor (PXR) by structurally diverse drug-like molecules.

The pregnane X receptor (PXR), a member of the nuclear hormone superfamily, regulates the expression of several enzymes and transporters involved in metabolically relevant processes. The significant induction of CYP450 enzymes by PXR, in particular CYP3A4, might significantly alter the metabolism of prescribed drugs. In order to early identify molecules in drug discovery with a potential to activate PXR as antitarget, we developed fast and reliable in silico filters by ligand-based QSAR techniques. Two classification models were established on a diverse dataset of 434 drug-like molecules. A second augmented set allowed focusing on interesting regions in chemical space. These classifiers are based on decision trees combined with a genetic algorithm based variable selection to arrive at predictive models. The classifier for the first dataset on 29 descriptors showed good performance on a test set with a correct classification of both 100% for PXR activators and non-activators plus 87% for activators and 83% for non-activators in an external dataset. The second classifier then correctly predicts 97% activators and 91% non-activators in a test set and 94% for activators and 64% non-activators in an external set of 50 molecules, which still qualifies for application as a filter focusing on PXR activators. Finally a quantitative model for PXR activation for a subset of these molecules was derived using a regression-tree approach combined with GA variable selection. This final model shows a predictive r(2) of 0.774 for the test set and 0.452 for an external set of 33 molecules. Thus, the combination of these filters consistently provide guidelines for lowering PXR activation in novel candidate molecules.

Effect of Storage Temperature on Allograft Bone.

BACKGROUND: The recommendations for storage temperature of allogeneic bone are varying between -20 °C and -70 °C and down to -80 °C. The necessary temperature of storage is not exactly defined by scientific data, and the effect of different storage temperatures onto the biomechanical and the biological behavior is discussed controversially. METHODS: The historical development of storage temperature of bone banks is described. A survey on literature concerning the biomechanical and biological properties of allograft bone depending on the procurement and storage temperature is given as well as on national and international regulations on storage conditions of bone banks (European Council, American Association of Tissue Banks (AATB), European Association of Tissue Banks (EATB)). RESULTS: Short-term storage up to 6 months is recommended with -20 °C and -40 °C for a longer period (AATB), and EATB recommends storage at -40 °C and even -80 °C while the regulations of the German German Medical Association (Bundesärztekammer) from 2001 recommend storage at -70 °C. Duration of storage at -20 °C can be maintained at least for 2 years. The potential risk of proteolysis with higher storage temperatures remains, but a definite impairment of bone ingrowth due to a storage at -20 °C was not shown in clinical use, and no adverse biomechanical effects of storage at -20 °C could be proven. CONCLUSION: Biomechanical studies showed no clinically relevant impairment of biomechanical properties of cancellous bone due to different storage temperatures. Sterilization procedures bear the advantage of inactivating enzymatic activity though reducing the risk of proteolysis. In those cases a storage temperature of -20 °C can be recommended for at least a period of 2 years, and the risk of undesired effects seems to be low for native unprocessed bone.

Optimizing interactions to protein binding sites by integrating docking-scoring strategies into generative AI methods.

The identification and optimization of promising lead molecules is essential for drug discovery. Recently, artificial intelligence (AI) based generative methods provided complementary approaches for generating molecules under specific design constraints of relevance in drug design. The goal of our study is to incorporate protein 3D information directly into generative design by flexible docking plus an adapted protein-ligand scoring function, thereby moving towards automated structure-based design. First, the protein-ligand scoring function RFXscore integrating individual scoring terms, ligand descriptors, and combined terms was derived using the PDBbind database and internal data. Next, design results for different workflows are compared to solely ligand-based reward schemes. Our newly proposed, optimal workflow for structure-based generative design is shown to produce promising results, especially for those exploration scenarios, where diverse structures fitting to a protein binding site are requested. Best results are obtained using docking followed by RFXscore, while, depending on the exact application scenario, it was also found useful to combine this approach with other metrics that bias structure generation into "drug-like" chemical space, such as target-activity machine learning models, respectively.

Artificial Intelligence in Compound Design.

Artificial intelligence has seen an incredibly fast development in recent years. Many novel technologies for property prediction of drug molecules as well as for the design of novel molecules were introduced by different research groups. These artificial intelligence-based design methods can be applied for suggesting novel chemical motifs in lead generation or scaffold hopping as well as for optimization of desired property profiles during lead optimization. In lead generation, broad sampling of the chemical space for identification of novel motifs is required, while in the lead optimization phase, a detailed exploration of the chemical neighborhood of a current lead series is advantageous. These different requirements for successful design outcomes render different combinations of artificial intelligence technologies useful. Overall, we observe that a combination of different approaches with tailored scoring and evaluation schemes appears beneficial for efficient artificial intelligence-based compound design.

Molecular basis for inhibiting human glucose transporters by exofacial inhibitors.

Human glucose transporters (GLUTs) are responsible for cellular uptake of hexoses. Elevated expression of GLUTs, particularly GLUT1 and GLUT3, is required to fuel the hyperproliferation of cancer cells, making GLUT inhibitors potential anticancer therapeutics. Meanwhile, GLUT inhibitor-conjugated insulin is being explored to mitigate the hypoglycemia side effect of insulin therapy in type 1 diabetes. Reasoning that exofacial inhibitors of GLUT1/3 may be favored for therapeutic applications, we report here the engineering of a GLUT3 variant, designated GLUT3exo, that can be probed for screening and validating exofacial inhibitors. We identify an exofacial GLUT3 inhibitor SA47 and elucidate its mode of action by a 2.3 Å resolution crystal structure of SA47-bound GLUT3. Our studies serve as a framework for the discovery of GLUTs exofacial inhibitors for therapeutic development.