Analysis of Iterative Screening with Stepwise Compound Selection Based on Novartis In-house HTS Data

Bioactivity profile of dissolved organic matter and its relation to molecular composition

Dissolved organic matter (DOM) occupies a huge and uncharted molecular space. Given its properties, DOM can be presented as a promising biotechnological resource. However, research into bioactivities of DOM is still in early stages. In this study, the biotechnological potential of terrestrial and marine DOM, its molecular composition and their relationships are investigated. Samples were screened for their in vitro antibacterial, antifungal, anticancer and antioxidant activities. Antibacterial activity was detected against Staphylococcus aureus in almost all DOM samples, with freshwater DOM showing the lowest IC50 values. Most samples also inhibited Staphylococcus epidermidis, and four DOM extracts showed up to fourfold higher potency than the reference drug. Antifungal activity was limited to only porewater DOM towards human dermatophyte Trichophyton rubrum. No significant in vitro anticancer activity was observed. Low antioxidant potential was exerted. The molecular characterization by FT-ICR MS allowed a broad compositional overview. Three main distinguished groups have been identified by PCoA analyses. Antibacterial activities are related to high aromaticity content and highly-unsaturated molecular formulae (O-poor). Antifungal effect is correlated with highly-unsaturated molecular formulae (O-rich). Antioxidant activity is positively related to the presence of double bonds and polyphenols. This study evidenced for the first time antibacterial and antifungal activity in DOM with potential applications in cosmeceutical, pharmaceutical and aquaculture industry. The lack of cytotoxicity and the almost unlimited presence of this organic material may open new avenues in future marine bioprospecting efforts.

Applying deep learning to iterative screening of medium-sized molecules for protein-protein interaction-targeted drug discovery

We combined a library of medium-sized molecules with iterative screening using multiple machine learning algorithms that were ligand-based, which resulted in a large increase of the hit rate against a protein-protein interaction target. This was demonstrated by inhibition assays using a PPI target, Kelch-like ECH-associated protein 1/nuclear factor erythroid 2-related factor 2 (Keap1/Nrf2), and a deep neural network model based on the first-round assay data showed a highest hit rate of 27.3%. Using the models, we identified novel active and non-flat compounds far from public datasets, expanding the chemical space.

Maximizing the integration of virtual and experimental screening in hit discovery

INTRODUCTION

Experimental and virtual screening contributes to the discovery of more than 50% of clinical candidates. Considering the similar concept and goals, early-phase drug discovery would benefit from the effective integration of these approaches.

AREAS COVERED

After reviewing the recent trends in both experimental and virtual screening, the authors discuss different integration strategies from parallel, focused, sequential, and iterative screening. Strategic considerations are demonstrated in a number of real-life case studies.

EXPERT OPINION

Experimental and virtual screening are complementary approaches that should be integrated in lead discovery settings. Virtual screening can access extremely large synthetically feasible chemical space that can be effectively searched on GPU clusters or cloud architectures. Experimental screening provides reliable datasets by quantitative HTS applications, and DNA-encoded libraries (DEL) have enlarged the chemical space covered by these technologies. These developments, together with the use of artificial intelligence methods, represent new options for their efficient integration. The case studies discussed here demonstrate the benefits of complementary strategies, such as focused and iterative screening.

Evolution of Novartis' Small Molecule Screening Deck Design

This article summarizes the evolution of the screening deck at the Novartis Institutes for BioMedical Research (NIBR). Historically, the screening deck was an assembly of all available compounds. In 2015, we designed a first deck to facilitate access to diverse subsets with optimized properties. We allocated the compounds as plated subsets on a 2D grid with property based ranking in one dimension and increasing structural redundancy in the other. The learnings from the 2015 screening deck were applied to the design of a next generation in 2019. We found that using traditional leadlikeness criteria (mainly MW, clogP) reduces the hit rates of attractive chemical starting points in subset screening. Consequently, the 2019 deck relies on solubility and permeability to select preferred compounds. The 2019 design also uses NIBR's experimental assay data and inferred biological activity profiles in addition to structural diversity to define redundancy across the compound sets.

Successive Statistical and Structure-Based Modeling to Identify Chemically Novel Kinase Inhibitors

Kinases are frequently studied in the context of anticancer drugs. Their involvement in cell responses, such as proliferation, differentiation, and apoptosis, makes them interesting subjects in multitarget drug design. In this study, a workflow is presented that models the bioactivity spectra for two panels of kinases: (1) inhibition of RET, BRAF, SRC, and S6K, while avoiding inhibition of MKNK1, TTK, ERK8, PDK1, and PAK3, and (2) inhibition of AURKA, PAK1, FGFR1, and LKB1, while avoiding inhibition of PAK3, TAK1, and PIK3CA. Both statistical and structure-based models were included, which were thoroughly benchmarked and optimized. A virtual screening was performed to test the workflow for one of the main targets, RET kinase. This resulted in 5 novel and chemically dissimilar RET inhibitors with remaining RET activity of <60% (at a concentration of 10 μM) and similarities with known RET inhibitors from 0.18 to 0.29 (Tanimoto, ECFP6). The four more potent inhibitors were assessed in a concentration range and proved to be modestly active with a pIC₅₀ value of 5.1 for the most active compound. The experimental validation of inhibitors for RET strongly indicates that the multitarget workflow is able to detect novel inhibitors for kinases, and hence, this workflow can potentially be applied in polypharmacology modeling. We conclude that this approach can identify new chemical matter for existing targets. Moreover, this workflow can easily be applied to other targets as well.

Changing the HTS Paradigm: AI-Driven Iterative Screening for Hit Finding

Iterative screening is a process in which screening is done in batches, with each batch filled by using machine learning to select the most promising compounds from the library based on the previous results. We believe iterative screening is poised to enhance the screening process by improving hit finding while at the same time reducing the number of compounds screened. In addition, we see this process as a key enabler of next-generation high-throughput screening (HTS), which uses more complex assays that better describe the biology but demand more resource per screened compound. To demonstrate the utility of these methods, we retrospectively analyze HTS data from PubChem with a focus on machine learning–based screening strategies that can be readily implemented in practice. Our results show that over a variety of HTS experimental paradigms, an iterative screening setup that screens a total of 35% of the screening collection over as few as three iterations has a median return rate of approximately 70% of the active compounds. Increasing the portion of the library screened to 50% yields median returns of approximately 80% of actives. Using six iterations increases these return rates to 78% and 90%, respectively. The best results were achieved with machine learning models that can be run on a standard desktop. By demonstrating that the utility of iterative screening holds true even with a small number of iterations, and without requiring significant computational resources, we provide a roadmap for the practical implementation of these techniques in hit finding.

Practical considerations for active machine learning in drug discovery

Active machine learning enables the automated selection of the most valuable next experiments to improve predictive modelling and hasten active retrieval in drug discovery. Although a long established theoretical concept and introduced to drug discovery approximately 15 years ago, the deployment of active learning technology in the discovery pipelines across academia and industry remains slow. With the recent re-discovered enthusiasm for artificial intelligence as well as improved flexibility of laboratory automation, active learning is expected to surge and become a key technology for molecular optimizations. This review recapitulates key findings from previous active learning studies to highlight the challenges and opportunities of applying adaptive machine learning to drug discovery. Specifically, considerations regarding implementation, infrastructural integration, and expected benefits are discussed. By focusing on these practical aspects of active learning, this review aims at providing insights for scientists planning to implement active learning workflows in their discovery pipelines.

QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping

An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (~ 0.65 and ~ 0.70 for similarity searching depending on data sets, and ~ 0.85 for classification) and EF5 (~ 4.67 and ~ 5.82 for similarity searching depending on data sets, and ~ 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of ~ 0.57 and ~ 0.66, and EF5 of ~ 4.09 and ~ 6.41, depending on data sets, classification AUC of ~ 0.87, and EF5 of ~ 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds.

Augmenting Hit Identification by Virtual Screening Techniques in Small Molecule Drug Discovery

Two orthogonal approaches for hit identification in drug discovery are large-scale in vitro and in silico screening. In recent years, due to the emergence of new targets and a rapid increase in the size of the readily synthesizable chemical space, there is a growing emphasis on the integration of the two techniques to improve the hit finding efficiency. Here, we highlight three examples of drug discovery projects at Merck & Co., Inc., Kenilworth, NJ, USA in which different virtual screening (VS) techniques, each specifically tailored to leverage knowledge available for the target, were utilized to augment the selection of high-quality chemical matter for in vitro assays and to enhance the diversity and tractability of hits. Central to success is a fully integrated workflow combining in silico and experimental expertise at every stage of the hit identification process. We advocate that workflows encompassing VS as part of an integrated hit finding plan should be widely adopted to accelerate hit identification and foster cross-functional collaborations in modern drug discovery.

Current methods and challenges for deep learning in drug discovery

Driven by rapid advances in computer hardware and publicly available datasets over the past decade, deep learning has achieved tremendous success in the transformation of many computational disciplines. These novel technologies have had considerable impact on computer-aided drug design as well, throughout all stages of the development pipeline. A flexible toolbox of neural architectures has been developed that are well-suited to represent the sequential, topological, or geometrical concepts of chemistry and biology; and that are able to either discriminate existing molecules or to generate new ones from scratch. For some biochemical prediction tasks, the state of the art has been advanced; however, for complex and practically relevant projects, the outcomes are less clear-cut. Current deep learning methods rely on massive amounts of labeled examples, but drug discovery data is comparatively limited in quantity and quality. These problems need to be resolved and existing sources used more effectively to demonstrate that deep learning can revolutionize the field in general.

Applications of Deep-Learning in Exploiting Large-Scale and Heterogeneous Compound Data in Industrial Pharmaceutical Research

In recent years, the development of high-throughput screening (HTS) technologies and their establishment in an industrialized environment have given scientists the possibility to test millions of molecules and profile them against a multitude of biological targets in a short period of time, generating data in a much faster pace and with a higher quality than before. Besides the structure activity data from traditional bioassays, more complex assays such as transcriptomics profiling or imaging have also been established as routine profiling experiments thanks to the advancement of Next Generation Sequencing or automated microscopy technologies. In industrial pharmaceutical research, these technologies are typically established in conjunction with automated platforms in order to enable efficient handling of screening collections of thousands to millions of compounds. To exploit the ever-growing amount of data that are generated by these approaches, computational techniques are constantly evolving. In this regard, artificial intelligence technologies such as deep learning and machine learning methods play a key role in cheminformatics and bio-image analytics fields to address activity prediction, scaffold hopping, de novo molecule design, reaction/retrosynthesis predictions, or high content screening analysis. Herein we summarize the current state of analyzing large-scale compound data in industrial pharmaceutical research and describe the impact it has had on the drug discovery process over the last two decades, with a specific focus on deep-learning technologies.

Combining structural and bioactivity-based fingerprints improves prediction performance and scaffold hopping capability

This study aims at improving upon existing activity predictions methods by augmenting chemical structure fingerprints with bio-activity based fingerprints derived from high-throughput screening (HTS) data (HTSFPs) and thereby showcasing the benefits of combining different descriptor types. This type of descriptor would be applied in an iterative screening scenario for more targeted compound set selection. The HTSFPs were generated from HTS data obtained from PubChem and combined with an ECFP4 structural fingerprint. The bioactivity-structure hybrid (BaSH) fingerprint was benchmarked against the individual ECFP4 and HTSFP fingerprints. Their performance was evaluated via retrospective analysis of a subset of the PubChem HTS data. Results showed that the BaSH fingerprint has improved predictive performance as well as scaffold hopping capability. The BaSH fingerprint identified unique compounds compared to both the ECFP4 and the HTSFP fingerprint indicating synergistic effects between the two fingerprints. A feature importance analysis showed that a small subset of the HTSFP features contribute most to the overall performance of the BaSH fingerprint. This hybrid approach allows for activity prediction of compounds with only sparse HTSFPs due to the supporting effect from the structural fingerprint.

Predicting kinase inhibitors using bioactivity matrix derived informer sets

Prediction of compounds that are active against a desired biological target is a common step in drug discovery efforts. Virtual screening methods seek some active-enriched fraction of a library for experimental testing. Where data are too scarce to train supervised learning models for compound prioritization, initial screening must provide the necessary data. Commonly, such an initial library is selected on the basis of chemical diversity by some pseudo-random process (for example, the first few plates of a larger library) or by selecting an entire smaller library. These approaches may not produce a sufficient number or diversity of actives. An alternative approach is to select an informer set of screening compounds on the basis of chemogenomic information from previous testing of compounds against a large number of targets. We compare different ways of using chemogenomic data to choose a small informer set of compounds based on previously measured bioactivity data. We develop this Informer-Based-Ranking (IBR) approach using the Published Kinase Inhibitor Sets (PKIS) as the chemogenomic data to select the informer sets. We test the informer compounds on a target that is not part of the chemogenomic data, then predict the activity of the remaining compounds based on the experimental informer data and the chemogenomic data. Through new chemical screening experiments, we demonstrate the utility of IBR strategies in a prospective test on three kinase targets not included in the PKIS.

In the early stages of drug discovery efforts, computational models are used to predict activity and prioritize compounds for experimental testing. New targets commonly lack the data necessary to build effective models, and the screening needed to generate that experimental data can be costly. We seek to improve the efficiency of the initial screening phase, and of the process of prioritizing compounds for subsequent screening.

We choose a small informer set of compounds based on publicly available prior screening data on distinct targets. We then collect experimental data on these informer compounds and use that data to predict the activity of other compounds in the set for the target of interest. Computational and statistical tools are needed to identify informer compounds and to prioritize other compounds for subsequent phases of screening. We find that selection of informer compounds on the basis of bioactivity data from previous screening efforts is superior to the traditional approach of selection of a chemically diverse subset of compounds. We demonstrate the success of this approach in retrospective tests on the Published Kinase Inhibitor Sets (PKIS) chemogenomic data and in prospective experimental screens against three additional non-human kinase targets.

Accurate Hit Estimation for Iterative Screening Using Venn-ABERS Predictors

Iterative screening has emerged as a promising approach to increase the efficiency of high-throughput screening (HTS) campaigns in drug discovery. By learning from a subset of the compound library, inferences on what compounds to screen next can be made by predictive models. One of the challenges of iterative screening is to decide how many iterations to perform. This is mainly related to difficulties in estimating the prospective hit rate in any given iteration. In this article, a novel method based on Venn-ABERS predictors is proposed. The method provides accurate estimates of the number of hits retrieved in any given iteration during an HTS campaign. The estimates provide the necessary information to support the decision on the number of iterations needed to maximize the screening outcome. Thus, this method offers a prospective screening strategy for early-stage drug discovery.

Real-World Synthetic Biology: Is It Founded on an Engineering Approach, and Should It Be?

Authors often assert that a key feature of 21st-century synthetic biology is its use of an 'engineering approach'; design using predictive models, modular architecture, construction using well-characterized standard parts, and rigorous testing using standard metrics. This article examines whether this is, or even should be, the case. A brief survey of synthetic biology projects that have reached, or are near to, commercial application outside laboratories shows that they showed very few of these attributes. Instead, they featured much trial and error, and the use of specialized, custom components and assays. What is more, consideration of the special features of living systems suggest that a conventional engineering approach will often not be helpful. The article concludes that the engineering approach may be useful in some projects, but it should not be used to define or constrain synthetic biological endeavour, and that in fact the conventional engineering has more to gain by expanding and embracing more biological ways of working.

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures

The parasite Plasmodium falciparum is the most lethal species of Plasmodium to cause serious malaria infection in humans, and with resistance developing rapidly novel treatment modalities are currently being sought, one of which being combinations of existing compounds. The discovery of combinations of antimalarial drugs that act synergistically with one another is hence of great importance; however an exhaustive experimental screen of large drug space in a pairwise manner is not an option. In this study we apply our machine learning approach, Combination Synergy Estimation (CoSynE), which can predict novel synergistic drug interactions using only prior experimental combination screening data and knowledge of compound molecular structures, to a dataset of 1,540 antimalarial drug combinations in which 22.2% were synergistic. Cross validation of our model showed that synergistic CoSynE predictions are enriched 2.74 × compared to random selection when both compounds in a predicted combination are known from other combinations among the training data, 2.36 × when only one compound is known from the training data, and 1.5 × for entirely novel combinations. We prospectively validated our model by making predictions for 185 combinations of 23 entirely novel compounds. CoSynE predicted 20 combinations to be synergistic, which was experimentally validated for nine of them (45%), corresponding to an enrichment of 1.70 × compared to random selection from this prospective data set. Such enrichment corresponds to a 41% reduction in experimental effort. Interestingly, we found that pairwise screening of the compounds CoSynE individually predicted to be synergistic would result in an enrichment of 1.36 × compared to random selection, indicating that synergy among compound combinations is not a random event. The nine novel and correctly predicted synergistic compound combinations mainly (where sufficient bioactivity information is available) consist of efflux or transporter inhibitors (such as hydroxyzine), combined with compounds exhibiting antimalarial activity alone (such as sorafenib, apicidin, or dihydroergotamine). However, not all compound synergies could be rationalized easily in this way. Overall, this study highlights the potential for predictive modeling to expedite the discovery of novel drug combinations in fight against antimalarial resistance, while the underlying approach is also generally applicable.

Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening

The versatility of similarity searching and quantitative structure-activity relationships to model the activity of compound sets within given bioactivity ranges (i.e., interpolation) is well established. However, their relative performance in the common scenario in early stage drug discovery where lots of inactive data but no active data points are available (i.e., extrapolation from the low-activity to the high-activity range) has not been thoroughly examined yet. To this aim, we have designed an iterative virtual screening strategy which was evaluated on 25 diverse bioactivity data sets from ChEMBL. We benchmark the efficiency of random forest (RF), multiple linear regression, ridge regression, similarity searching, and random selection of compounds to identify a highly active molecule in the test set among a large number of low-potency compounds. We use the number of iterations required to find this active molecule to evaluate the performance of each experimental setup. We show that linear and ridge regression often outperform RF and similarity searching, reducing the number of iterations to find an active compound by a factor of 2 or more. Even simple regression methods seem better able to extrapolate to high-bioactivity ranges than RF, which only provides output values in the range covered by the training set. In addition, examination of the scaffold diversity in the data sets used shows that in some cases similarity searching and RF require two times as many iterations as random selection depending on the chemical space covered in the initial training data. Lastly, we show using bioactivity data for COX-1 and COX-2 that our framework can be extended to multitarget drug discovery, where compounds are selected by concomitantly considering their activity against multiple targets. Overall, this study provides an approach for iterative screening where only inactive data are present in early stages of drug discovery in order to discover highly potent compounds and the best experimental set up in which to do so.

Integration of Lead Discovery Tactics and the Evolution of the Lead Discovery Toolbox

There has been much debate around the success rates of various screening strategies to identify starting points for drug discovery. Although high-throughput target-based and phenotypic screening has been the focus of this debate, techniques such as fragment screening, virtual screening, and DNA-encoded library screening are also increasingly reported as a source of new chemical equity. Here, we provide examples in which integration of more than one screening approach has improved the campaign outcome and discuss how strengths and weaknesses of various methods can be used to build a complementary toolbox of approaches, giving researchers the greatest probability of successfully identifying leads. Among others, we highlight case studies for receptor-interacting serine/threonine-protein kinase 1 and the bromo- and extra-terminal domain family of bromodomains. In each example, the unique insight or chemistries individual approaches provided are described, emphasizing the synergy of information obtained from the various tactics employed and the particular question each tactic was employed to answer. We conclude with a short prospective discussing how screening strategies are evolving, what this screening toolbox might look like in the future, how to maximize success through integration of multiple tactics, and scenarios that drive selection of one combination of tactics over another.

Data-driven approaches used for compound library design, hit triage and bioactivity modeling in high-throughput screening

High-throughput screening (HTS) campaigns are routinely performed in pharmaceutical companies to explore activity profiles of chemical libraries for the identification of promising candidates for further investigation. With the aim of improving hit rates in these campaigns, data-driven approaches have been used to design relevant compound screening collections, enable effective hit triage and perform activity modeling for compound prioritization. Remarkable progress has been made in the activity modeling area since the recent introduction of large-scale bioactivity-based compound similarity metrics. This is evidenced by increased hit rates in iterative screening strategies and novel insights into compound mode of action obtained through activity modeling. Here, we provide an overview of the developments in data-driven approaches, elaborate on novel activity modeling techniques and screening paradigms explored and outline their significance in HTS.

Maximizing gain in high-throughput screening using conformal prediction

Iterative screening has emerged as a promising approach to increase the efficiency of screening campaigns compared to traditional high throughput approaches. By learning from a subset of the compound library, inferences on what compounds to screen next can be made by predictive models, resulting in more efficient screening. One way to evaluate screening is to consider the cost of screening compared to the gain associated with finding an active compound. In this work, we introduce a conformal predictor coupled with a gain-cost function with the aim to maximise gain in iterative screening. Using this setup we were able to show that by evaluating the predictions on the training data, very accurate predictions on what settings will produce the highest gain on the test data can be made. We evaluate the approach on 12 bioactivity datasets from PubChem training the models using 20% of the data. Depending on the settings of the gain-cost function, the settings generating the maximum gain were accurately identified in 8-10 out of the 12 datasets. Broadly, our approach can predict what strategy generates the highest gain based on the results of the cost-gain evaluation: to screen the compounds predicted to be active, to screen all the remaining data, or not to screen any additional compounds. When the algorithm indicates that the predicted active compounds should be screened, our approach also indicates what confidence level to apply in order to maximize gain. Hence, our approach facilitates decision-making and allocation of the resources where they deliver the most value by indicating in advance the likely outcome of a screening campaign.

Prediction of Antibiotic Interactions Using Descriptors Derived from Molecular Structure

Combination antibiotic therapies are clinically important in the fight against bacterial infections. However, the search space of drug combinations is large, making the identification of effective combinations a challenging task. Here, we present a computational framework that uses substructure profiles derived from the molecular structures of drugs and predicts antibiotic interactions. Using a previously published data set of 153 drug pairs, we showed that substructure profiles are useful in predicting synergy. We experimentally measured the interaction of 123 new drug pairs, as a prospective validation set for our approach, and identified 37 new synergistic pairs. Of the 12 pairs predicted to be synergistic, 10 were experimentally validated, corresponding to a 2.8-fold enrichment. Having thus validated our methodology, we produced a compendium of interaction predictions for all pairwise combinations among 100 antibiotics. Our methodology can make reliable antibiotic interaction predictions for any antibiotic pair within the applicability domain of the model since it solely requires chemical structures as an input.

Prospective Assessment of Virtual Screening Heuristics Derived Using a Novel Fusion Score

High-throughput screening (HTS) is a widespread method in early drug discovery for identifying promising chemical matter that modulates a target or phenotype of interest. Because HTS campaigns involve screening millions of compounds, it is often desirable to initiate screening with a subset of the full collection. Subsequently, virtual screening methods prioritize likely active compounds in the remaining collection in an iterative process. With this approach, orthogonal virtual screening methods are often applied, necessitating the prioritization of hits from different approaches. Here, we introduce a novel method of fusing these prioritizations and benchmark it prospectively on 17 screening campaigns using virtual screening methods in three descriptor spaces. We found that the fusion approach retrieves 15% to 65% more active chemical series than any single machine-learning method and that appropriately weighting contributions of similarity and machine-learning scoring techniques can increase enrichment by 1% to 19%. We also use fusion scoring to evaluate the tradeoff between screening more chemical matter initially in lieu of replicate samples to prevent false-positives and find that the former option leads to the retrieval of more active chemical series. These results represent guidelines that can increase the rate of identification of promising active compounds in future iterative screens.

Iterative Focused Screening with Biological Fingerprints Identifies Selective Asc-1 Inhibitors Distinct from Traditional High Throughput Screening

N-methyl-d-aspartate receptors (NMDARs) mediate glutamatergic signaling that is critical to cognitive processes in the central nervous system, and NMDAR hypofunction is thought to contribute to cognitive impairment observed in both schizophrenia and Alzheimer's disease. One approach to enhance the function of NMDAR is to increase the concentration of an NMDAR coagonist, such as glycine or d-serine, in the synaptic cleft. Inhibition of alanine-serine-cysteine transporter-1 (Asc-1), the primary transporter of d-serine, is attractive because the transporter is localized to neurons in brain regions critical to cognitive function, including the hippocampus and cortical layers III and IV, and is colocalized with d-serine and NMDARs. To identify novel Asc-1 inhibitors, two different screening approaches were performed with whole-cell amino acid uptake in heterologous cells stably expressing human Asc-1: (1) a high-throughput screen (HTS) of 3 M compounds measuring ³⁵S l-cysteine uptake into cells attached to scintillation proximity assay beads in a 1536 well format and (2) an iterative focused screen (IFS) of a 45 000 compound diversity set using a ³H d-serine uptake assay with a liquid scintillation plate reader in a 384 well format. Critically important for both screening approaches was the implementation of counter screens to remove nonspecific inhibitors of radioactive amino acid uptake. Furthermore, a 15 000 compound expansion step incorporating both on- and off-target data into chemical and biological fingerprint-based models for selection of additional hits enabled the identification of novel Asc-1-selective chemical matter from the IFS that was not identified in the full-collection HTS.

Applications of Systematic Molecular Scaffold Enumeration to Enrich Structure-Activity Relationship Information

Establishing structure–activity relationships (SARs) in hit identification during early stage drug discovery is important in accelerating hit confirmation and expansion. We describe the development of EnCore, a systematic molecular scaffold enumeration protocol using single atom mutations, to enhance the application of objective scaffold definitions and to enrich SAR information from analysis of high-throughput screening output. A list of 43 literature medicinal chemistry compound series, each containing a minimum of 100 compounds, published in the Journal of Medicinal Chemistry was collated to validate the protocol. Analysis using the top representative Level 1 scaffolds this list of literature compound series demonstrated that EnCore could mimic the scaffold exploration conducted when establishing SAR. When EnCore was applied to analyze an HTS library containing over 200 000 compounds, we observed that over 70% of the molecular scaffolds matched extant scaffolds within the library after enumeration. In particular, over 60% of the singleton scaffolds with only one representative compound were found to have structurally related compounds after enumeration. These results illustrate the potential of EnCore to enrich SAR information. A case study using literature cyclooxygenase-2 inhibitors further demonstrates the advantage of EnCore application in establishing SAR from structurally related scaffolds. EnCore complements literature enumeration methods in enabling changes to the physicochemical properties of molecular scaffolds and structural modifications to aliphatic rings and linkers. The enumerated scaffold clusters generated would constitute a comprehensive collection of scaffolds for scaffold morphing and hopping.

Data-Driven Derivation of an "Informer Compound Set" for Improved Selection of Active Compounds in High-Throughput Screening

Despite the usefulness of high-throughput screening (HTS) in drug discovery, for some systems, low assay throughput or high screening cost can prohibit the screening of large numbers of compounds. In such cases, iterative cycles of screening involving active learning (AL) are employed, creating the need for smaller "informer sets" that can be routinely screened to build predictive models for selecting compounds from the screening collection for follow-up screens. Here, we present a data-driven derivation of an informer compound set with improved predictivity of active compounds in HTS, and we validate its benefit over randomly selected training sets on 46 PubChem assays comprising at least 300,000 compounds and covering a wide range of assay biology. The informer compound set showed improvement in BEDROC(α = 100), PRAUC, and ROCAUC values averaged over all assays of 0.024, 0.014, and 0.016, respectively, compared to randomly selected training sets, all with paired t-test p-values <10(-15). A per-assay assessment showed that the BEDROC(α = 100), which is of particular relevance for early retrieval of actives, improved for 38 out of 46 assays, increasing the success rate of smaller follow-up screens. Overall, we showed that an informer set derived from historical HTS activity data can be employed for routine small-scale exploratory screening in an assay-agnostic fashion. This approach led to a consistent improvement in hit rates in follow-up screens without compromising scaffold retrieval. The informer set is adjustable in size depending on the number of compounds one intends to screen, as performance gains are realized for sets with more than 3,000 compounds, and this set is therefore applicable to a variety of situations. Finally, our results indicate that random sampling may not adequately cover descriptor space, drawing attention to the importance of the composition of the training set for predicting actives.