From mundane to surprising nonadditivity: drivers and impact on ML models.

Nonadditivity (NA) in Structure-Activity and Structure-Property Relationship (SAR) data is a rare but very information rich phenomenon. It can indicate conformational flexibility, structural rearrangements, and errors in assay results and structural assignment. While purely ligand-based conformational causes of NA are rather well understood and mundane, other factors are less so and cause surprising NA that has a huge influence on SAR analysis and ML model performance. We here report a systematic analysis across a wide range of properties (20 on-target biological activities and 4 physicochemical ADME-related properties) to understand the frequency of various different phenomena that may lead to NA. A set of novel descriptors were developed to characterize double transformation cycles and identify trends in NA. Double transformation cycles were classified into "surprising" and "mundane" categories, with the majority being classed as mundane. We also examined commonalities among surprising cycles, finding LogP differences to have the most significant impact on NA. A distinct behavior of NA for on-target sets compared to ADME sets was observed. Finally, we show that machine learning models struggle with highly nonadditive data, indicating that a better understanding of NA is an important future research direction.

Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry.

Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon-carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an F 1-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.

Novel Indane-Containing NBTIs with Potent Anti-Gram-Negative Activity and Minimal hERG Inhibition.

Novel bacterial topoisomerase inhibitors (NBTIs) make up a promising new class of antibiotics with the potential to combat the growing threat of antimicrobial resistance. Two key challenges in the development of NBTIs have been to obtain broad spectrum activity against multidrug-resistant Gram-negative bacteria and to diminish inhibition of the hERG cardiac ion channel. Here we report the optimization of a series of NBTIs bearing a novel indane DNA intercalating moiety. The addition of a basic, polar side chain connected to the indane by an ether or an N-linked secondary amide linkage together with a lipophilicity-lowering modification of the enzyme binding moiety led to compounds such as 2a and 2g which showed excellent broad spectrum potency and minimal hERG inhibition. Compound 2a demonstrated robust bactericidal in vivo activity in a mouse lung infection model with the strain P. aeruginosa ATCC 27853 which is resistant to several clinically relevant antibiotics. Rodent pharmacokinetic studies with 2a revealed an unusual profile characterized by rapid tissue distribution and a prolonged, flat terminal phase. This profile precluded further development of these compounds as potential new antibiotics.

Discovery of a Series of Indane-Containing NBTIs with Activity against Multidrug-Resistant Gram-Negative Pathogens.

The rise of multidrug-resistant (MDR) Gram-negative bacteria is a major global health problem necessitating the discovery of new classes of antibiotics. Novel bacterial topoisomerase inhibitors (NBTIs) target the clinically validated bacterial type II topoisomerases with a distinct binding site and mechanism of action to fluoroquinolone antibiotics, thus avoiding cross-resistance to this drug class. Here we report the discovery of a series of NBTIs incorporating a novel indane DNA binding moiety. X-ray cocrystal structures of compounds 2 and 17a bound to Staphylococcus aureus DNA gyrase-DNA were determined, revealing specific interactions with the enzyme binding pocket at the GyrA dimer interface and a long-range electrostatic interaction between the basic amine in the linker and the carboxylate of Asp83. Exploration of the structure-activity relationship within the series led to the identification of lead compound 18c, which showed potent broad-spectrum activity against a panel of MDR Gram-negative bacteria.

Optimal force control of a permanent magnet linear synchronous motor with multiple shuttles.

Using permanent magnet linear synchronous machines for transportation tasks offers a higher flexibility in production plants compared to conventional conveyor solutions. In this context, passive transportation devices (shuttles) with permanent magnets are commonly used. When multiple shuttles are operated in close vicinity, disturbances due to magnetic interaction can occur. To allow for high-speed operation of the motor with high position control accuracy, these coupling effects must be considered. This paper presents a model-based control strategy that is based on a magnetic equivalent circuit model which is able to describe the nonlinear magnetic behavior at low computational costs. A framework is derived for the model calibration based on measurements. An optimal control scheme for the multi-shuttle operation is derived that allows to accurately track the desired tractive forces of the shuttles while minimizing the ohmic losses at the same time. The control concept is experimentally validated on a test bench and compared to a state-of-the-art field-oriented control concept typically used in industry.

A high quality, industrial data set for binding affinity prediction: performance comparison in different early drug discovery scenarios.

We release a new, high quality data set of 1162 PDE10A inhibitors with experimentally determined binding affinities together with 77 PDE10A X-ray co-crystal structures from a Roche legacy project. This data set is used to compare the performance of different 2D- and 3D-machine learning (ML) as well as empirical scoring functions for predicting binding affinities with high throughput. We simulate use cases that are relevant in the lead optimization phase of early drug discovery. ML methods perform well at interpolation, but poorly in extrapolation scenarios-which are most relevant to a real-world application. Moreover, we find that investing into the docking workflow for binding pose generation using multi-template docking is rewarded with an improved scoring performance. A combination of 2D-ML and 3D scoring using a modified piecewise linear potential shows best overall performance, combining information on the protein environment with learning from existing SAR data.

Selecting the Reaction Path in On-Surface Synthesis through the Electron Chemical Potential in Graphene.

The organometallic on-surface synthesis of the eight-membered sp2 carbon-based ring cyclooctatetraene (C8H8, Cot) with the neighboring rare-earth elements ytterbium and thulium yields fundamentally different products for the two lanthanides, when conducted on graphene (Gr) close to the charge neutrality point. Sandwich-molecular YbCot wires of more than 500 Å length being composed of an alternating sequence of Yb atoms and upright-standing Cot molecules result from the on-surface synthesis with Yb. In contrast, repulsively interacting TmCot dots consisting of a single Cot molecule and a single Tm atom result from the on-surface synthesis with Tm. While the YbCot wires are bound through van der Waals interactions to the substrate, the dots are chemisorbed to Gr via the Tm atoms being more electropositive compared to Yb atoms. When the electron chemical potential in Gr is substantially raised (n-doping) through backside doping from an intercalation layer, the reaction product in the synthesis with Tm can be tuned to TmCot sandwich-molecular wires rather than TmCot dots. By use of density functional theory, it is found that the reduced electronegativity of Gr upon n-doping weakens the binding as well as the charge transfer between the reaction intermediate TmCot dot and Gr. Thus, the assembly of the TmCot dots to long TmCot sandwich-molecular wires becomes energetically favorable. It is thereby demonstrated that the electron chemical potential in Gr can be used as a control parameter in an organometallic on-surface synthesis to tune the outcome of a reaction.

What We Learned in 25 Years of Interactive Molecular Design Sessions.

We retrace Prof. François Diederich's consultancy work for Roche and its impact over the years he worked with us. François Diederich uniquely shaped our approach to molecular design, and interactions with him and his research group at ETH Zurich have created deep insights into molecular recognition. Herein we share how his style and approach continue to inspire us.

The Playbooks of Medicinal Chemistry Design Moves.

Large databases of biologically relevant molecules, such as ChEMBL, SureChEMBL, or compound collections of pharmaceutical or agrochemical companies, are invaluable sources of medicinal chemistry information, albeit implicit. We developed a modified matched molecular pair approach to systematically and exhaustively extract the transformations in these databases and distill them into snippets of explicit design knowledge that are easily interpretable and directly applicable. The resulting "playbooks of medicinal chemistry design moves" capture the collective pharmaceutical and agrochemical research expertise across multiple chemists, companies, targets, and projects. They can be queried in an automated fashion for systematic prospective design and compound generation. The ChEMBL playbook and an application to exploit it are available at https://github.com/mahendra-awale/medchem_moves.

Matched Molecular Series Analysis for ADME Property Prediction.

Generation and prioritization of new molecules are the most central part of the drug design process. Matched molecular series analysis (MMSA) has recently been proposed as a formal approach that captures both of these key elements of design. In order to better understand the power of MMSA and its specific limitations, we here evaluate its performance as an ADME property prediction tool. We use four large and diverse inhouse data sets, logD, microsomal clearance, CYP2C9, and CYP3A4 inhibition. MMSA follows the concept of parallel structure-activity relationship (SAR), where if two identical substituent series on different scaffolds show similarity in their property profiles, SAR from one series can be transferred to the other series. We test four different similarity metrics to identify pairs of molecular series where information can be transferred. We find that the best prediction performance is achieved by a combination of centered root-mean-square deviation (cRMSD) and a network score approach previously published by Keefer et al. However, cRMSD alone strikes the best balance between accuracy and the number of predictions that can be made. We identify statistical metrics that allow estimating when MMSA predictions will work, similar to the well-known applicability domain concept in machine learning. MMSA achieves a prediction accuracy that is comparable to a standard machine-learning model and matched molecular pair analysis. In contrast to machine learning, however, it is very easy to understand where MMSA predictions are coming from. Finally, to prospectively test the power of MMSA, we retested compounds that were strong outliers in the initial predictions and show how the MMSA model can help to identify erroneous data points.

Multiscale modelling of drug mechanism and safety.

Here, we introduce models at three levels-molecular level, cellular and omics level, and organ and system level-that study drug mechanism and safety in preclinical drug discovery. The models differ in both their scope of study and technical details, but are all rooted in mathematical descriptions of complex biological systems, and all require informatics tools that handle large-volume, heterogeneous, and noisy data. We present principles and recent developments with examples at each level and highlight the synergy by a case study. We proffer a multiscale modelling view of drug discovery, call for a seamless flow of information in the form of models, and examine potential impacts.

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.

Safety screening in early drug discovery: An optimized assay panel.

BACKGROUND: Several factors contribute to the development failure of novel pharmaceuticals, one of the most important being adverse effects in pre-clinical and clinical studies. Early identification of off-target compound activity can reduce safety-related attrition in development. In vitro profiling of drug candidates against a broad range of targets is an important part of the compound selection process. Many compounds are synthesized during early drug discovery, making it necessary to assess poly-pharmacology at a limited number of targets. This paper describes how a rational, statistical-ranking approach was used to generate a cost-effective, optimized panel of assays that allows selectivity focused structure-activity relationships to be explored for many molecules. This panel of 50 targets has been used to routinely screen Roche small molecules generated across a diverse range of therapeutic targets. Target hit rates from the Bioprint® database and internal Roche compounds are discussed. We further describe an example of how this panel was used within an anti-infective project to reduce in vivo testing. METHOD: To select the optimized panel of targets, IC50 values of compounds in the BioPrint® database were used to identify assay "hits" i.e. IC50 ≤ 1 µM in 123 different in vitro pharmacological assays. If groups of compounds hit the same targets, the target with the higher hit rate was selected, while others were considered redundant. Using a step-wise analysis, an assay panel was identified to maximize diversity and minimize redundancy. Over a five-year period, this panel of 50 off-targets was used to screen ≈1200 compounds synthesized for Roche drug discovery programs. Compounds were initially tested at 10 µM and hit rates generated are reported. Within one project, the number of hits was used to refine the choice of compounds being assessed in vivo. RESULTS: 95% of compounds from the BioPrint® panel were identified within the top 47-ranked assays. Based on this analytical approach and the addition of three targets with established safety concerns, a Roche panel was created for external screening. hERG is screened internally and not included in this analysis. Screening at 10 µM in the Roche panel identified that adenosine A3 and 5HT2B receptors had the highest hit rates (~30%), with 50% of the targets having a hit rate of ≤4%. An anti-infective program identified that a high number of hits in the Roche panel was associated with mortality in 19 mouse tolerability studies. To reduce the severity and number of such studies, future compound selections integrated the panel hit score into the selection process for in vivo studies. It was identified that compounds which hit less targets in the panel and had free plasma exposures of ~2 µM were generally better tolerated. DISCUSSION: This paper describes how an optimized panel of 50 assays was selected on the basis of hit similarity at 123 targets. This reduced panel, provides a cost-effective screening panel for assessing compound promiscuity, whilst also including many safety-relevant targets. Frequent use of the panel in early drug discovery has provided promiscuity and safety-relevant information to inform pre-clinical drug development at Roche.

On the Effects of Reactive Oxygen Species and Nitric Oxide on Red Blood Cell Deformability.

The main function of red blood cells (RBCs) is the transport of respiratory gases along the vascular tree. To fulfill their task, RBCs are able to elastically deform in response to mechanical forces and, pass through the narrow vessels of the microcirculation. Decreased RBC deformability was observed in pathological conditions linked to increased oxidative stress or decreased nitric oxide (NO) bioavailability, like hypertension. Treatments with oxidants and with NO were shown to affect RBC deformability ex vivo, but the mechanisms underpinning these effects are unknown. In this study we investigate whether changes in intracellular redox status/oxidative stress or nitrosation reactions induced by reactive oxygen species (ROS) or NO may affect RBC deformability. In a case-control study comparing RBCs from healthy and hypertensive participants, we found that RBC deformability was decreased, and levels of ROS were increased in RBCs from hypertensive patients as compared to RBCs from aged-matched healthy controls, while NO levels in RBCs were not significantly different. To study the effects of oxidants on RBC redox state and deformability, RBCs from healthy volunteers were treated with increasing concentrations of tert-butylhydroperoxide (t-BuOOH). We found that high concentrations of t-BuOOH (≥ 1 mM) significantly decreased the GSH/GSSG ratio in RBCs, decreased RBC deformability and increased blood bulk viscosity. Moreover, RBCs from Nrf2 knockout (KO) mice, a strain genetically deficient in a number of antioxidant/reducing enzymes, were more susceptible to t-BuOOH-induced impairment in RBC deformability as compared to wild type (WT) mice. To study the role of NO in RBC deformability we treated RBC suspensions from human volunteers with NO donors and nitrosothiols and analyzed deformability of RBCs from mice lacking the endothelial NO synthase (eNOS). We found that NO donors induced S-nitrosation of the cytoskeletal protein spectrin, but did not affect human RBC deformability or blood bulk viscosity; moreover, under unstressed conditions RBCs from eNOS KO mice showed fully preserved RBC deformability as compared to WT mice. Pre-treatment of human RBCs with nitrosothiols rescued t-BuOOH-mediated loss of RBC deformability. Taken together, these findings suggest that NO does not affect RBC deformability per se, but preserves RBC deformability in conditions of oxidative stress.

mmpdb: An Open-Source Matched Molecular Pair Platform for Large Multiproperty Data Sets.

Matched molecular pair analysis (MMPA) enables the automated and systematic compilation of medicinal chemistry rules from compound/property data sets. Here we present mmpdb, an open-source matched molecular pair (MMP) platform to create, compile, store, retrieve, and use MMP rules. mmpdb is suitable for the large data sets typically found in pharmaceutical and agrochemical companies and provides new algorithms for fragment canonicalization and stereochemistry handling. The platform is written in Python and based on the RDKit toolkit. It is freely available from https://github.com/rdkit/mmpdb .

Learning Medicinal Chemistry Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) Rules from Cross-Company Matched Molecular Pairs Analysis (MMPA).

The first large scale analysis of in vitro absorption, distribution, metabolism, excretion, and toxicity (ADMET) data shared across multiple major pharma has been performed. Using advanced matched molecular pair analysis (MMPA), we combined data from three pharmaceutical companies and generated ADMET rules, avoiding the need to disclose the full chemical structures. On top of the very large exchange of knowledge, all companies involved synergistically gained approximately 20% more rules from the shared transformations. There is good quantitative agreement between the rules based on shared data compared to both individual companies' rules and rules published in the literature. Known correlations between log  D, solubility, in vitro clearance, and plasma protein binding also hold in transformation space, but there are also interesting exceptions. Data pools such as this allow focusing on particular functional groups and characterizing their ADMET profile. Finally the role of a corpus of robustly tested medicinal chemistry knowledge in the training of medicinal chemistry is discussed.

Identification of a soluble guanylate cyclase in RBCs: preserved activity in patients with coronary artery disease.

Endothelial dysfunction is associated with decreased NO bioavailability and impaired activation of the NO receptor soluble guanylate cyclase (sGC) in the vasculature and in platelets. Red blood cells (RBCs) are known to produce NO under hypoxic and normoxic conditions; however evidence of expression and/or activity of sGC and downstream signaling pathway including phopshodiesterase (PDE)-5 and protein kinase G (PKG) in RBCs is still controversial. In the present study, we aimed to investigate whether RBCs carry a functional sGC signaling pathway and to address whether this pathway is compromised in coronary artery disease (CAD). Using two independent chromatographic procedures, we here demonstrate that human and murine RBCs carry a catalytically active α1ß1-sGC (isoform 1), which converts 32P-GTP into 32P-cGMP, as well as PDE5 and PKG. Specific sGC stimulation by NO+BAY 41-2272 increases intracellular cGMP-levels up to 1000-fold with concomitant activation of the canonical PKG/VASP-signaling pathway. This response to NO is blunted in α1-sGC knockout (KO) RBCs, but fully preserved in α2-sGC KO. In patients with stable CAD and endothelial dysfunction red cell eNOS expression is decreased as compared to aged-matched controls; by contrast, red cell sGC expression/activity and responsiveness to NO are fully preserved, although sGC oxidation is increased in both groups. Collectively, our data demonstrate that an intact sGC/PDE5/PKG-dependent signaling pathway exists in RBCs, which remains fully responsive to NO and sGC stimulators/activators in patients with endothelial dysfunction. Targeting this pathway may be helpful in diseases with NO deficiency in the microcirculation like sickle cell anemia, pulmonary hypertension, and heart failure.

Dilatation of Vascular Prostheses in Ascending Aortic Position: A Long-Term Follow-Up Computed Tomography Study with Comparison of Different Measurement Methods.

BACKGROUND: The aim of this study was to evaluate long-term dilatation of Hemashield Gold and Hemashield Platinum vascular prostheses in ascending aortic position using different measurement methods to obtain precise results. METHODS: Between 1999 and 2007, 73 patients with Stanford type A dissection received ascending aortic replacement with Hemashield Gold and Hemashield Platinum prostheses. Measurements were performed using multiplanar reconstruction mode of electrocardiogram (ECG)-gated, multislice spiral computed tomography (MSCT) in strictly orthogonal cross-sectional planes. Different methods of measurement were compared and maximum dilatation was estimated for different time spans. RESULTS: Diameters calculated from the measured circumference showed a significant (p = 0.037) but clinically not relevant difference (0.1 mm) to the mean between the largest and the shortest cross-sectional diameter of the prosthesis. Dilatation after 24.2 ± 10.2 months was 8.5 ± 4.5%. Long-term dilatation after 91.8 ± 34 months amounted to 11.8 ± 4.2%. CONCLUSION: Based on ECG-gated MSCT images, the presented methods of measurement provided reliable results. Long-term analysis shows low dilatation rates for Hemashield prostheses, which therefore can be considered as safe from this point of view. Nevertheless, a maximal dilatation of 20% could be relevant in valve sparing root replacement. It remains unclear if a dilatation like this contributes to the formation of suture aneurysms.

Matched Molecular Series: Measuring SAR Similarity.

Suggesting novel compounds to be made on the basis of similarity to a previously seen structure-activity relationship (SAR) requires a measure for SAR similarity. While SAR similarity has intuitively been used by medicinal chemists for decades, no systematic comparison of candidate similarity metrics has been published to date. With this publication, we attempt to close that gap by providing a statistical framework that allows comparison of SAR similarity metrics by their ability to rank series that provide the best activity prediction of novel substituents. This prediction is a result of a two-step process that involves (a) judging the similarity between series and (b) transferring the SAR from one series to the other. We tested several SAR similarity metrics and found that a centered RMSD (cRMSD) in combination with a lineaar-regression-based prediction interpolation ranks SAR profiles best. Based on that ranking we can, with a given confidence, suggest novel substituents to be tested. The superiority of the cRMSD can be explained on the basis of experimental uncertainty of affinity data and measured affinity differences. The ability to measure SAR similarity is central to applications like matched molecular series (MMS) analysis, whose applicability depends on whether there is a potential for SAR transferability between series. With the new SAR similarity metric introduced here, we show how MMS can be used in a medicinal chemistry setting as an idea generator and a semiquantitative prediction tool.

Discovery and Characterization of Diazenylaryl Sulfonic Acids as Inhibitors of Viral and Bacterial Neuraminidases.

Viral neuraminidases are an established drug target to combat influenza. Severe complications observed in influenza patients are primarily caused by secondary infections with e.g., Streptococcus pneumoniae. These bacteria engage in a lethal synergism with influenza A viruses (IAVs) and also express neuraminidases. Therefore, inhibitors with dual activity on viral and bacterial neuraminidases are expected to be advantageous for the treatment of influenza infections. Here we report on the discovery and characterization of diazenylaryl sulfonic acids as dual inhibitors of viral and Streptococcus pneumoniae neuraminidase. The initial hit came from a virtual screening campaign for inhibitors of viral neuraminidases. For the most active compound, 7-[2-[4-[2-[4-[2-(2-hydroxy-3,6-disulfo-1-naphthalenyl)diazenyl]-2-methylphenyl]diazenyl]-2-methylphenyl]diazenyl]-1,3-naphthalenedisulfonic acid (NSC65847; 1), the Ki-values measured in a fluorescence-based assay were lower than 1.5 µM for both viral and pneumococcal neuraminidases. The compound also inhibited N1 virus variants containing neuraminidase inhibitor resistance-conferring substitutions. Via enzyme kinetics and nonlinear regression modeling, 1 was suggested to impair the viral neuraminidases and pneumococcal neuraminidase with a mixed-type inhibition mode. Given its antiviral and antipneumococcal activity, 1 was identified as a starting point for the development of novel, dual-acting anti-infectives.