Rethinking drug design in the artificial intelligence era.

Artificial intelligence (AI) tools are increasingly being applied in drug discovery. While some protagonists point to vast opportunities potentially offered by such tools, others remain sceptical, waiting for a clear impact to be shown in drug discovery projects. The reality is probably somewhere in-between these extremes, yet it is clear that AI is providing new challenges not only for the scientists involved but also for the biopharma industry and its established processes for discovering and developing new medicines. This article presents the views of a diverse group of international experts on the 'grand challenges' in small-molecule drug discovery with AI and the approaches to address them.

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.

Outcome of the First wwPDB/CCDC/D3R Ligand Validation Workshop.

Crystallographic studies of ligands bound to biological macromolecules (proteins and nucleic acids) represent an important source of information concerning drug-target interactions, providing atomic level insights into the physical chemistry of complex formation between macromolecules and ligands. Of the more than 115,000 entries extant in the Protein Data Bank (PDB) archive, ∼75% include at least one non-polymeric ligand. Ligand geometrical and stereochemical quality, the suitability of ligand models for in silico drug discovery and design, and the goodness-of-fit of ligand models to electron-density maps vary widely across the archive. We describe the proceedings and conclusions from the first Worldwide PDB/Cambridge Crystallographic Data Center/Drug Design Data Resource (wwPDB/CCDC/D3R) Ligand Validation Workshop held at the Research Collaboratory for Structural Bioinformatics at Rutgers University on July 30-31, 2015. Experts in protein crystallography from academe and industry came together with non-profit and for-profit software providers for crystallography and with experts in computational chemistry and data archiving to discuss and make recommendations on best practices, as framed by a series of questions central to structural studies of macromolecule-ligand complexes. What data concerning bound ligands should be archived in the PDB? How should the ligands be best represented? How should structural models of macromolecule-ligand complexes be validated? What supplementary information should accompany publications of structural studies of biological macromolecules? Consensus recommendations on best practices developed in response to each of these questions are provided, together with some details regarding implementation. Important issues addressed but not resolved at the workshop are also enumerated.

Fragment-based discovery of potent ERK2 pyrrolopyrazine inhibitors.

A fragment-based lead discovery approach was used to discover novel ERK2 inhibitors. The crystal structure of N-benzyl-9H-purin-6-amine 1 in complex with ERK2 elucidated its hinge-binding mode. In addition, the simultaneous binding of an imidazole molecule adjacent to 1 suggested a direction for fragment expansion. Structure-based core hopping applied to 1 led to 5H-pyrrolo[3,2-b]pyrazine (3) that afforded direct vectors to probe the pockets of interest while retaining the essential hinge binding elements. Utilizing the new vectors for SAR exploration, the new core 3 was quickly optimized to compound 39 resulting in a greater than 6600-fold improvement in potency.

An integrated suite of modeling tools that empower scientists in structure- and property-based drug design.

Structure- and property-based drug design is an integral part of modern drug discovery, enabling the design of compounds aimed at improving potency and selectivity. However, building molecules using desktop modeling tools can easily lead to poor designs that appear to form many favorable interactions with the protein's active site. Although a proposed molecule looks good on screen and appears to fit into the protein site X-ray crystal structure or pharmacophore model, doing so might require a high-energy small molecule conformation, which would likely be inactive. To help scientists make better design decisions, we have built integrated, easy-to-use, interactive software tools to perform docking experiments, de novo design, shape and pharmacophore based database searches, small molecule conformational analysis and molecular property calculations. Using a combination of these tools helps scientists in assessing the likelihood that a designed molecule will be active and have desirable drug metabolism and pharmacokinetic properties. Small molecule discovery success requires project teams to rapidly design and synthesize potent molecules with good ADME properties. Empowering scientists to evaluate ideas quickly and make better design decisions with easy-to-access and easy-to-understand software on their desktop is now a key part of our discovery process.

Discovery of potent and selective pyrazolopyrimidine janus kinase 2 inhibitors.

The discovery of somatic Jak2 mutations in patients with chronic myeloproliferative neoplasms has led to significant interest in discovering selective Jak2 inhibitors for use in treating these disorders. A high-throughput screening effort identified the pyrazolo[1,5-a]pyrimidine scaffold as a potent inhibitor of Jak2. Optimization of lead compounds 7a-b and 8 in this chemical series for activity against Jak2, selectivity against other Jak family kinases, and good in vivo pharmacokinetic properties led to the discovery of 7j. In a SET2 xenograft model that is dependent on Jak2 for growth, 7j demonstrated a time-dependent knock-down of pSTAT5, a downstream target of Jak2.

SGX523 is an exquisitely selective, ATP-competitive inhibitor of the MET receptor tyrosine kinase with antitumor activity in vivo.

The MET receptor tyrosine kinase has emerged as an important target for the development of novel cancer therapeutics. Activation of MET by mutation or gene amplification has been linked to kidney, gastric, and lung cancers. In other cancers, such as glioblastoma, autocrine activation of MET has been demonstrated. Several classes of ATP-competitive inhibitor have been described, which inhibit MET but also other kinases. Here, we describe SGX523, a novel, ATP-competitive kinase inhibitor remarkable for its exquisite selectivity for MET. SGX523 potently inhibited MET with an IC50 of 4 nmol/L and is >1,000-fold selective versus the >200-fold selectivity of other protein kinases tested in biochemical assays. Crystallographic study revealed that SGX523 stabilizes MET in a unique inactive conformation that is inaccessible to other protein kinases, suggesting an explanation for the selectivity. SGX523 inhibited MET-mediated signaling, cell proliferation, and cell migration at nanomolar concentrations but had no effect on signaling dependent on other protein kinases, including the closely related RON, even at micromolar concentrations. SGX523 inhibition of MET in vivo was associated with the dose-dependent inhibition of growth of tumor xenografts derived from human glioblastoma and lung and gastric cancers, confirming the dependence of these tumors on MET catalytic activity. Our results show that SGX523 is the most selective inhibitor of MET catalytic activity described to date and is thus a useful tool to investigate the role of MET kinase in cancer without the confounding effects of promiscuous protein kinase inhibition.

Fragment-based discovery of hepatitis C virus NS5b RNA polymerase inhibitors.

Non-nucleoside inhibitors of HCV NS5b RNA polymerase were discovered by a fragment-based lead discovery approach, beginning with crystallographic fragment screening. The NS5b binding affinity and biochemical activity of fragment hits and inhibitors was determined by surface plasmon resonance (Biacore) and an enzyme inhibition assay, respectively. Crystallographic fragment screening hits with approximately 1-10mM binding affinity (K(D)) were iteratively optimized to give leads with approximately 200nM biochemical activity and low microM cellular activity in a Replicon assay.