Idea2Data: Toward a New Paradigm for Drug Discovery

Abstract

Increasing the success rate and throughput of drug discovery will require efficiency improvements throughout the process that is currently used in the pharmaceutical community, including the crucial step of identifying hit compounds to act as drivers for subsequent optimization. Hit identification can be carried out through large compound collection screening and often involves the generation and testing of many hypotheses based on available knowledge. In practice, hypothesis generation can involve the selection of promising chemical structures from compound collections using predictive models built from previous screening/ assay results. Available physical collections, typically used during hit identification, are of the order of 10 6 compounds but represent only a small fraction of the small molecule drug-like chemical space. In an effort to survey a larger portion of chemical space and eliminate inefficiencies during hit identification, we introduce a new process, termed Idea2Data (I2D) that tightly integrates computational and experimental components of the drug discovery process. I2D provides the ability to connect a vast virtual collection of compounds readily synthesizable on automated synthesis systems with computational predictive models for the identification of promising structures. This new paradigm enables researchers to process billions of virtual molecules and select structures that can be prepared on automated systems and made available for biological testing, allowing for timely hypothesis testing and follow-up. Since its introduction, I2D has positively impacted several portfolio efforts through identification of new chemical scaffolds and functionalization of existing scaffolds. In this Innovations paper, we describe the I2D process and present an application for the discovery of new ULK inhibitors.

A Pan-Cancer assessment of alterations of the kinase domain of ULK1, an upstream regulator of autophagy

“…Using a dimensionality reduction approach based on Principal Component Analysis (PCA), we compared the sampling [103] achieved with the two force fields ( Figure 3A) and we identified a good overlap, suggesting that the two simulations give a consistent view on the ULK1 dynamics. We also evaluated the principal motions described by the first PC (Figure 3B-C) and we noticed that there is concerted motion between the loop 148-158 and a part of the activation loop (172-183), along with the loop adjacent to the catalytic lysine (in the region [35][36][37][38][39][40][41]. The two disordered regions 148-158 and 172-183 feature closing motions toward the rest of the ULK1 structure.…”

“…It could thus be expected that these mutations could impair its functional dynamics. In addition, the regulatory spine residue L78 and F81 in the proximity of the other disordered loop (35)(36)(37)(38)(39)(40)(41) also involved in the concerted conformational changes are also mutation sites. In particular, PSN approaches can also be used to infer functionally-damaging sites if the paths of communication between the mutation sites and other important functional sites for the kinase activity are taken into account.…”

“…ULK1 is the only serine/threonine kinase of the autophagy pathway and it is involved in the first biochemical steps of autophagy, thus representing an amenable druggable target in the pathway. X-ray structures of ULK1 in complex with the inhibitors are available (PDB entries: 4WNO [34], 4WNP [34], 5CI7 [35], 6QAS [37], and 6MNH [38]). The N-terminal kinase domain of ULK1 includes the activation loops (165-174 and 178-191) and the catalytic loop (136-145), which are required for its function.…”

Autonomous Discovery in the Chemical Sciences Part II: Outlook

“…These constraints on the design space to ensure compatibility with automated validation prevent us from addressing many interesting questions and optimization objectives. Chow et al describe several case studies where certain steps in the drug discovery have been integrated with each other for increased efficiency, but acknowledge-as others have-that all stages must be automated and integrated for maximal efficiency [239][240][241].…”

Neural Network Guided Tree-Search Policies for Synthesis Planning

“…With the increasing availability of reaction data, developments and accessibility of computational methods, and a drive to further automate design, make, test, analyze (DMTA) cycles within drug discovery [1], computer assisted synthesis planning (CASP) has seen renewed interest as of late [2]. This has been spurred by recent achievements in the application of neural networks combined with search algorithms [3,4], learning from breakthroughs in their application to games such as chess and Go [5].…”