Industrializing AI-powered drug discovery: lessons learned from the Patrimony computing platform.

INTRODUCTION: As a mid-size international pharmaceutical company, we initiated 4 years ago the launch of a dedicated high-throughput computing platform supporting drug discovery. The platform named 'Patrimony' was built up on the initial predicate to capitalize on our proprietary data while leveraging public data sources in order to foster a Computational Precision Medicine approach with the power of artificial intelligence. AREAS COVERED: Specifically, Patrimony is designed to identify novel therapeutic target candidates. With several successful use cases in immuno-inflammatory diseases, and current ongoing extension to applications to oncology and neurology, we document how this industrial computational platform has had a transformational impact on our R&D, making it more competitive, as well time and cost effective through a model-based educated selection of therapeutic targets and drug candidates. EXPERT OPINION: We report our achievements, but also our challenges in implementing data access and governance processes, building up hardware and user interfaces, and acculturing scientists to use predictive models to inform decisions.

Network-based repurposing identifies anti-alarmins as drug candidates to control severe lung inflammation in COVID-19.

While establishing worldwide collective immunity with anti SARS-CoV-2 vaccines, COVID-19 remains a major health issue with dramatic ensuing economic consequences. In the transition, repurposing existing drugs remains the fastest cost-effective approach to alleviate the burden on health services, most particularly by reducing the incidence of the acute respiratory distress syndrome associated with severe COVID-19. We undertook a computational repurposing approach to identify candidate therapeutic drugs to control progression towards severe airways inflammation during COVID-19. Molecular profiling data were obtained from public sources regarding SARS-CoV-2 infected epithelial or endothelial cells, immune dysregulations associated with severe COVID-19 and lung inflammation induced by other respiratory viruses. From these data, we generated a protein-protein interactome modeling the evolution of lung inflammation during COVID-19 from inception to an established cytokine release syndrome. This predictive model assembling severe COVID-19-related proteins supports a role for known contributors to the cytokine storm such as IL1ß, IL6, TNFα, JAK2, but also less prominent actors such as IL17, IL23 and C5a. Importantly our analysis points out to alarmins such as TSLP, IL33, members of the S100 family and their receptors (ST2, RAGE) as targets of major therapeutic interest. By evaluating the network-based distances between severe COVID-19-related proteins and known drug targets, network computing identified drugs which could be repurposed to prevent or slow down progression towards severe airways inflammation. This analysis confirmed the interest of dexamethasone, JAK2 inhibitors, estrogens and further identified various drugs either available or in development interacting with the aforementioned targets. We most particularly recommend considering various inhibitors of alarmins or their receptors, currently receiving little attention in this indication, as candidate treatments for severe COVID-19.

Clinical evaluation of medicinal products for acceleration of fracture healing in patients with osteoporosis.

Pre-clinical studies indicate that pharmacologic agents can augment fracture union. If these pharmacologic approaches could be translated into clinical benefit and offered to patients with osteoporosis or patients with other risks for impaired fracture union (e.g. in subjects with large defects or open fractures with high complication rate), they could provide an important adjunct to the treatment of fractures. However, widely accepted guidelines are important to encourage the conduct of studies to evaluate bioactive substances, drugs, and new agents that may promote fracture union and subsequent return to normal function. A consensus process was initiated to provide recommendations for the clinical evaluation of potential therapies to augment fracture repair in patients with meta- and diaphyseal fractures. Based on the characteristics of fracture healing and fixation, the following study objectives of a clinical study may be appropriate: a) acceleration of fracture union, b) acceleration of return to normal function and c) reduction of fracture healing complications. The intended goal(s) should determine subsequent study methodology. While an acceleration of return to normal function or a reduction of fracture healing complications in and of themselves may be sufficient primary study endpoints for a phase 3 pivotal study, acceleration of fracture union alone is not. Radiographic evaluation may either occur at multiple time points during the healing process with the aim of measuring the time taken to reach a defined status (e.g. cortical bridging of three cortices or disappearance of fracture lines), or could be obtained at a single pre-determined timepoint, were patients are expected to reach a common clinical milestone (i.e. pain free full weight-bearing in weight-bearing fracture cases). Validated Patient Reported Outcomes (PRO's) measures will need to support the return to normal function co-primary endpoints. If reduction of complication rate (e.g. non-union) is the primary objective, the anticipated complications must be defined in the study protocol, along with their possible associations with the specified fracture type and fixation device. The study design should be randomized, parallel, double-blind, and placebo-controlled, and all fracture subjects should receive a standardized method of fracture fixation, defined as Standard of Care.

Preclinical assessment of gastrooesophageal tolerance of the new antiosteoporotic drug strontium ranelate: an endoscopic study in monkeys.

This study was aimed at evaluating the digestive tolerance of the new antiosteoporotic drug, strontium ranelate, and to compare it to that of another strontium salt, strontium chloride (SrCl2). Strontium ranelate, SrCl2, or placebo were administered orally (capsules) to 3 groups of 2 male and 2 female cynomolgus monkeys (Macaca fascicularis) once a day for 7 days at a dose of 2 g/day, which is the recommended therapeutic dose in man. Endoscopic examination of the oesophagus, the stomach and the first part of the duodenum was performed on fasted animals approximately 3 hr after the first (Day 1) and last dosing (Day 7), and, on Day 8 and Day 14 in case of lesions on Day 7. Strontium ranelate did not induce any acute or subchronic toxic effect on the gastric mucosa, the oesophagus and the first part of the duodenum. On the contrary, acute and superficial damages were noted on all animals receiving SrCl2 such as haemorrhagic and erosive lesions (formation of an ulcer in one male and a marked congestive antritis in one female). These effects were reversible after cessation of treatment. The microscopic examination of biopsies sampled at the site of gastric lesions revealed moderate granulocyte infiltration, indicating a local irritating origin of the lesions. Strontium ranelate by oral route is safe for the gastric mucosa while SrCl2 induced superficial and reversible lesions.

Induction of a program gene expression during osteoblast differentiation with strontium ranelate.

Strontium ranelate, a new agent for the treatment of osteoporosis, has been shown stimulate bone formation in various experimental models. This study examines the effect of strontium ranelate on gene expression in osteoblasts, as well as the formation of mineralized (von Kossa-positive) colony-forming unit-osteoblasts (CFU-obs). Bone marrow-derived stromal cells cultured for 21 days under differentiating conditions, when exposed to strontium ranelate, displayed a significant time- and concentration-dependent increase in the expression of the master gene, Runx2, as well as bone sialoprotein (BSP), but interestingly without effects on osteocalcin. This was associated with a significant increase in the formation of CFU-obs at day 21 of culture. In U-33 pre-osteoblastic cells, strontium ranelate significantly enhanced the expression of Runx2 and osteocalcin, but not BSP. Late, more mature osteoblastic OB-6 cells showed significant elevations in BSP and osteocalcin, but with only minimal effects on Runx2. In conclusion, strontium ranelate stimulates osteoblast differentiation, but the induction of the program of gene expression appears to be cell type-specific. The increased osteoblastic differentiation is the likely basis underlying the therapeutic bone-forming actions of strontium ranelate.