A novel series of inhibitors of the interaction of IL-17A with its cognate receptor has been discovered using DNA-encoded library (DEL) technology. The lead compound (JNJ627, Compound 1) of the series occupies the interior interface of the IL-17A homodimer and disables receptor binding. The mechanism of action involves allosteric disruption of the IL-17A quaternary structure to prevent adoption of the receptor-binding conformation, rather than direct orthosteric inhibition at the receptor-binding site. Molecules of this series exhibit remarkably slow on-rate kinetics and potent inhibition of IL-17A signaling in human primary cells.

Machine learning (ML) has begun to realize its promise in many domains in the last several years. While small molecule drug discovery has lagged in comparison to other areas, developments in computing capabilities, data generation, and algorithms have enabled significant progress in molecule prediction. DNA-encoded libraries (DELs) represent an efficient way to generate the quantity of data required for effective model building, providing a mechanism for protein-target specific prediction with economics that permit individual organizations to operate. DEL-based machine learning (DEL-ML) has been demonstrated to work for a variety of targets and continues to expand in its usage in the industry and in the approaches reported. With this initial success, a number of challenges and considerations faced by the DEL-ML practitioner have been identified including denoising of DEL data, choice of ML algorithm, hyperparameters and molecule representations, and the need for relevant metrics for assessment, particularly given the high resource and time costs of testing predictions. In order to fully realize the potential of DEL-ML, key improvements in drug discovery infrastructure and broad availability of DEL data are needed.

Target class-focused drug discovery has a strong track record in pharmaceutical research, yet public domain data indicate that many members of protein families remain unliganded. Here we present a systematic approach to scale up the discovery and characterization of small molecule ligands for the WD40 repeat (WDR) protein family. We developed a comprehensive suite of protocols for protein production, crystallography, and biophysical, biochemical, and cellular assays. A pilot hit-finding campaign using DNA-encoded chemical library selection followed by machine learning (DEL-ML) to predict ligands from virtual libraries yielded first-in-class, drug-like ligands for 7 of the 16 WDR domains screened, thus demonstrating the broader ligandability of WDRs. This study establishes a template for evaluation of protein family wide ligandability and provides an extensive resource of WDR protein biochemical and chemical tools, knowledge, and protocols to discover potential therapeutics for this highly disease-relevant, but underexplored target class.

Protein class-focused drug discovery has a long and successful history in pharmaceutical research, yet most members of druggable protein families remain unliganded, often for practical reasons. Here we combined experiment and computation to enable discovery of ligands for WD40 repeat (WDR) proteins, one of the largest human protein families. This resource includes expression clones, purification protocols, and a comprehensive assessment of the druggability for hundreds of WDR proteins. We solved 21 high resolution crystal structures, and have made available a suite of biophysical, biochemical, and cellular assays to facilitate the discovery and characterization of small molecule ligands. To this end, we use the resource in a hit-finding pilot involving DNA-encoded library (DEL) selection followed by machine learning (ML). This led to the discovery of first-in-class, drug-like ligands for 9 of 20 targets. This result demonstrates the broad ligandability of WDRs. This extensive resource of reagents and knowledge will enable further discovery of chemical tools and potential therapeutics for this important class of proteins.### Competing Interest StatementBLS, BG, JSD, JZ, JWC, MvR, PR, SK, and TK are employees and shareholders of Relay Therapeutics.* BLI : Biolayer Interferometry DEL : DNA Encoded Library DLID : drug-like density DSF : Differential Scanning Fluorimetry FP : Fluorescence Polarization GCNN : Graph Convolutional Neural Network HDX : Hydrogen-Deuterium eXchange HTS : High-Throughput Screening ML : Machine Learning NanoBRET : NanoLuciferase Bioluminescence Resonance Energy Transfer PPI : Protein-Protein Interaction PROTAC : Proteolysis Targeting Chimera SPR : Surface Plasmon Resonance Tm : Protein melting temperature WDR : Tryptophan-Aspartate Repeat

Evasion of apoptosis is critical for the development and growth of tumors. The pro-survival protein myeloid cell leukemia 1 (Mcl-1) is an antiapoptotic member of the Bcl-2 family, associated with tumor aggressiveness, poor survival, and drug resistance. Development of Mcl-1 inhibitors implies blocking of protein-protein interactions, generally requiring a lengthy optimization process of large, complex molecules. Herein, we describe the use of DNA-encoded chemical library synthesis and screening to directly generate complex, yet conformationally privileged macrocyclic hits that serve as Mcl-1 inhibitors. By applying a conceptual combination of conformational analysis and structure-based design in combination with a robust synthetic platform allowing rapid analoging, we optimized in vitro potency of a lead series into the low nanomolar regime. Additionally, we demonstrate fine-tuning of the physicochemical properties of the macrocyclic compounds, resulting in the identification of lead candidates 57/59 with a balanced profile, which are suitable for future development toward therapeutic use.

This study describes a novel series of UDP-N-acetylglucosamine acyltransferase (LpxA) inhibitors that was identified through affinity-mediated selection from a DNA-encoded compound library. The original hit was a selective inhibitor of Pseudomonas aeruginosa LpxA with no activity against Escherichia coli LpxA. The biochemical potency of the series was optimized through an X-ray crystallography-supported medicinal chemistry program, resulting in compounds with nanomolar activity against P. aeruginosa LpxA (best half-maximal inhibitory concentration (IC50) <5 nM) and cellular activity against P. aeruginosa (best minimal inhibitory concentration (MIC) of 4 μg/mL). Lack of activity against E. coli was maintained (IC50 > 20 μM and MIC > 128 μg/mL). The mode of action of analogues was confirmed through genetic analyses. As expected, compounds were active against multidrug-resistant isolates. Further optimization of pharmacokinetics is needed before efficacy studies in mouse infection models can be attempted. To our knowledge, this is the first reported LpxA inhibitor series with selective activity against P. aeruginosa.

DNA-encoded small molecule libraries (DELs) have enabled discovery of novel inhibitors for many distinct protein targets of therapeutic value through screening of libraries with up to billions of unique small molecules. We demonstrate a new approach applying machine learning to DEL selection data by identifying active molecules from a large commercial collection and a virtual library of easily synthesizable compounds. We train models using only DEL selection data and apply automated or automatable filters with chemist review restricted to the removal of molecules with potential for instability or reactivity. We validate this approach with a large prospective study (nearly 2000 compounds tested) across three diverse protein targets: sEH (a hydrolase), ER{\alpha} (a nuclear receptor), and c-KIT (a kinase). The approach is effective, with an overall hit rate of {\sim}30% at 30 {\textmu}M and discovery of potent compounds (IC50 <10 nM) for every target. The model makes useful predictions even for molecules dissimilar to the original DEL and the compounds identified are diverse, predominantly drug-like, and different from known ligands. Collectively, the quality and quantity of DEL selection data; the power of modern machine learning methods; and access to large, inexpensive, commercially-available libraries creates a powerful new approach for hit finding.

The activity of the secreted phosphodiesterase autotaxin produces the inflammatory signaling molecule LPA and has been associated with a number of human diseases including idiopathic pulmonary fibrosis (IPF). We screened a single DNA-encoded chemical library (DECL) of 225 million compounds and identified a series of potent inhibitors. Optimization of this series led to the discovery of compound 1 (X-165), a highly potent, selective, and bioavailable small molecule. Cocrystallization of compound 1 with human autotaxin demonstrated that it has a novel binding mode occupying both the hydrophobic pocket and a channel near the autotaxin active site. Compound 1 inhibited the production of LPA in human and mouse plasma at nanomolar levels and showed efficacy in a mouse model of human lung fibrosis. After successfully completing IND-enabling studies, compound 1 was approved by the FDA for a Phase I clinical trial. These results demonstrate that DECL hits can be readily optimized into clinical candidates.

The discovery of ligands via affinity-mediated selection of DNA-encoded chemical libraries is driven by the quality and concentration of the protein target. G-protein-coupled receptors (GPCRs) and other membrane-bound targets can be difficult to isolate in their functional state and at high concentrations, and therefore have been challenging for affinity-mediated selection. Here, we report a successful selection campaign against protease-activated receptor 2 (PAR2). Using a thermo-stabilized mutant of PAR2, we conducted affinity selection using our >100-billion-compound DNA-encoded library. We observed a number of putative ligands enriched upon selection, and subsequent cellular profiling revealed these ligands to comprise both agonists and antagonists. The agonist series shared structural similarity with known agonists. The antagonists were shown to bind in a novel allosteric binding site on the PAR2 protein. This report serves to demonstrate that cell-free affinity selection against GPCRs can be achieved with mutant stabilized protein targets.

Abstract ATAD2 (ATPase family AAA-domain containing protein 2, also called ANCCA) is an epigenetic regulator that binds to chromatin through its bromodomain (BD), a motif specialized for acetyl-lysine recognition. ATAD2 directly associates with multiple transcription factors such as ERα, AR, E2F, and Myc; hence, ATAD2 has been proposed to act as a co-factor for oncogenic transcription factors. Furthermore, we have recently reported a novel role for ATAD2 during DNA replication, uncovering interactions between ATAD2 and histone acetylation marks on newly synthesized histone H4. High expression of ATAD2 strongly correlates with poor patient prognosis in multiple tumor types, including gastric, endometrial, hepatocellular, ovarian, breast and lung cancers. However, the exact function of ATAD2 in these tumor types remains unclear. A more thorough validation of ATAD2 as a therapeutic target is hampered by the lack of isoform-selective, potent and cellularly active ATAD2 inhibitors. A systematic assessment of crystal structures of BD-containing protein family predicted that development of selective inhibitors of ATAD2 would be challenging. In line with this prediction, only limited progress in developing lead compounds targeting ATAD2 has been reported so far. A few notable exceptions relied on fragments as starting points, however, their weak potency, insufficient selectivity against other BDs, permeability limitations or modest cellular activity have curbed their further development towards drug candidates. Here we embarked on a novel strategy to identify ATAD2 inhibitors: 11 different DNA-encoded libraries adding up to 67 billion unique encoded compounds were combined and incubated with ATAD2 BD followed by two rounds of affinity-mediated selection. This approach provided with several series of binders, for which specific target engagement of their SMOL moiety upon off-DNA synthesis was confirmed in biochemical and biophysical assays. Several rounds of potency optimization led to the identification of BAY-850, a highly potent and ATAD2 (isoform A) mono-selective inhibitor, which holds an amine substituted 3-(2-furyl)benzamide core. This compound shows - as revealed by size exclusion chromatography and native mass spectrometry - a novel mode of action for a BD inhibitor based on specific target dimerization. In a cellular fluorescence recovery after photobleaching (FRAP) assay BAY-850 displaced wild-type ATAD2 from the chromatin to the same extent as the genetic mutagenesis of ATAD2 BD. In contrast, chemically very similar inactive control compounds showed no major effects on ATAD2 association with the chromatin. These results qualify BAY-850 as the first biologically active ATAD2 isoform A-specific chemical probe, which will enable further elucidation of the cancer biology of this intriguing protein. Citation Format: Amaury E. Fernández-Montalván, Markus Berger, Benno Kuropka, Seong Joo Koo, Volker Badock, Joerg Weiske, Simon J. Holton, Apirat Chaikuad, Laura Díaz-Sáez, James Bennett, Oleg Federov, Kilian Huber, Paolo Centrella, Matthew A. Clark, Christoph E. Dumelin, Eric A. Sigel, Holly S. Soutter, Dawn M. Troast, Ying Zhang, John W. Cuozzo, Anthony D. Keefe, Didier Roche, Vincent Rodeschini, Jan Hübner, Hilmar Weinmann, Ingo V. Hartung, Matyas Gorjanacz. Potent and isoform-selective ATAD2 bromodomain inhibitor with unprecedented chemical structure and mode of action [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr 5084. doi:10.1158/1538-7445.AM2017-5084

We have identified and characterized novel potent inhibitors of Bruton's tyrosine kinase (BTK) from a single DNA-encoded library of over 110 million compounds by using multiple parallel selection conditions, including variation in target concentration and addition of known binders to provide competition information. Distinct binding profiles were observed by comparing enrichments of library building block combinations under these conditions; one enriched only at high concentrations of BTK and was competitive with ATP, and another enriched at both high and low concentrations of BTK and was not competitive with ATP. A compound representing the latter profile showed low nanomolar potency in biochemical and cellular BTK assays. Results from kinetic mechanism of action studies were consistent with the selection profiles. Analysis of the co-crystal structure of the most potent compound demonstrated a novel binding mode that revealed a new pocket in BTK. Our results demonstrate that profile-based selection strategies using DNA-encoded libraries form the basis of a new methodology to rapidly identify small molecule inhibitors with novel binding modes to clinically relevant targets.

ATAD2 (ANCCA) is an epigenetic regulator and transcriptional cofactor, whose overexpression has been linked to the progress of various cancer types. Here, we report a DNA-encoded library screen leading to the discovery of BAY-850, a potent and isoform selective inhibitor that specifically induces ATAD2 bromodomain dimerization and prevents interactions with acetylated histones in vitro, as well as with chromatin in cells. These features qualify BAY-850 as a chemical probe to explore ATAD2 biology.

[This corrects the article DOI: 10.1021/acsmedchemlett.6b00464.].

Millions of individuals are infected with and die from tuberculosis (TB) each year, and multidrug-resistant (MDR) strains of TB are increasingly prevalent. As such, there is an urgent need to identify novel drugs to treat TB infections. Current frontline therapies include the drug isoniazid, which inhibits the essential NADH-dependent enoyl-acyl-carrier protein (ACP) reductase, InhA. To inhibit InhA, isoniazid must be activated by the catalase-peroxidase KatG. Isoniazid resistance is linked primarily to mutations in the katG gene. Discovery of InhA inhibitors that do not require KatG activation is crucial to combat MDR TB. Multiple discovery efforts have been made against InhA in recent years. Until recently, despite achieving high potency against the enzyme, these efforts have been thwarted by lack of cellular activity. We describe here the use of DNA-encoded X-Chem (DEX) screening, combined with selection of appropriate physical properties, to identify multiple classes of InhA inhibitors with cell-based activity. The utilization of DEX screening allowed the interrogation of very large compound libraries (1011 unique small molecules) against multiple forms of the InhA enzyme in a multiplexed format. Comparison of the enriched library members across various screening conditions allowed the identification of cofactor-specific inhibitors of InhA that do not require activation by KatG, many of which had bactericidal activity in cell-based assays.

A chemical ligation method for construction of DNA-encoded small-molecule libraries has been developed. Taking advantage of the ability of the Klenow fragment of DNA polymerase to accept templates with triazole linkages in place of phosphodiesters, we have designed a strategy for chemically ligating oligonucleotide tags using cycloaddition chemistry. We have utilized this strategy in the construction and selection of a small molecule library and successfully identified inhibitors of the enzyme soluble epoxide hydrolase.