Deep Learning in Drug Discovery and Medicine; Scratching the Surface.

The practice of medicine is ever evolving. Diagnosing disease, which is often the first step in a cure, has seen a sea change from the discerning hands of the neighborhood physician to the use of sophisticated machines to use of information gleaned from biomarkers obtained by the most minimally invasive of means. The last 100 or so years have borne witness to the enormous success story of allopathy, a practice that found favor over earlier practices of medical purgatory and homeopathy. Nevertheless, failures of this approach coupled with the omics and bioinformatics revolution spurred precision medicine, a platform wherein the molecular profile of an individual patient drives the selection of therapy. Indeed, precision medicine-based therapies that first found their place in oncology are rapidly finding uses in autoimmune, renal and other diseases. More recently a new renaissance that is shaping everyday life is making its way into healthcare. Drug discovery and medicine that started with Ayurveda in India are now benefiting from an altogether different artificial intelligence (AI)-one which is automating the invention of new chemical entities and the mining of large databases in health-privacy-protected vaults. Indeed, disciplines as diverse as language, neurophysiology, chemistry, toxicology, biostatistics, medicine and computing have come together to harness algorithms based on transfer learning and recurrent neural networks to design novel drug candidates, a priori inform on their safety, metabolism and clearance, and engineer their delivery but only on demand, all the while cataloging and comparing omics signatures across traditionally classified diseases to enable basket treatment strategies. This review highlights inroads made and being made in directed-drug design and molecular therapy.

Late intervention with the small molecule BB3 mitigates postischemic kidney injury.

Ischemia-reperfusion-mediated acute kidney injury can necessitate renal replacement therapy and is a major cause of morbidity and mortality. We have identified BB3, a small molecule, which when first administered at 24 h after renal ischemia in rats, improved survival, augmented urine output, and reduced the increase in serum creatinine and blood urea nitrogen. Compared with control kidneys, the kidneys of BB3-treated animals exhibited reduced levels of kidney injury molecule-1, neutrophil gelatinase-associated lipocalin, and reduced tubular apoptosis and acute tubular necrosis but enhanced tubular regeneration. Consistent with its hepatocyte growth factor-like mode of action, BB3 treatment promoted phosphorylation of renal cMet and Akt and upregulated renal expression of the survival protein Bcl-2. These data suggest that the kidney is amenable to pharmacotherapy even 24 h after ischemia-reperfusion and that activation of the hepatocyte growth factor signaling pathway with the small molecule BB3 confers interventional benefits late into ischemia-reperfusion injury. These data formed, in part, the basis for the use of BB3 in a clinical trial in kidney recipients presenting with delayed graft function.

A small molecule fibrokinase inhibitor in a model of fibropolycystic hepatorenal disease.

AIM: To evaluate the novel platelet-derived growth factor receptor and vascular endothelial growth factor receptor dual kinase inhibitor ANG3070 in a polycystic kidney disease-congenital hepatic fibrosis model. METHODS: At 6 wk of age, PCK rats were randomized to vehicle or ANG3070 for 4 wk. At 10 wk, 24 h urine and left kidneys were collected and rats were continued on treatment for 4 wk. At 14 wk, 24 h urine was collected, rats were sacrificed, and liver and right kidneys were collected for histological evaluation. For Western blot studies, PCK rats were treated with vehicle or ANG3070 for 7 d and sacrificed approximately 30 min after the last treatments. RESULTS: Compared to the wild-type cohort, the PCK kidney (Vehicle cohort) exhibited a marked increase in kidney and liver mass, hepato-renal cystic volume, hepato-renal fibrosis and hepato-renal injury biomarkers. Intervention with ANG3070 in PCK rats decreased kidney weight, reduced renal cystic volume and reduced total kidney hydroxyproline, indicating significantly reduced rental interstitial fibrosis compared to the PCK-Vehicle cohort. ANG3070 treatment also mitigated several markers of kidney injury, including urinary neutrophil gelatinase-associated lipocalin, kidney injury molecule-1, cystatin C and interleukin-18 levels. In addition, this treatment attenuated key indices of renal dysfunction, including proteinuria, albuminuria and serum blood urea nitrogen and creatinine, and significantly improved renal function compared to the PCK-Vehicle cohort. ANG3070 treatment also significantly decreased liver enlargement, hepatic lesions, and liver fibrosis, and mitigated liver dysfunction compared to the PCK-Vehicle cohort. CONCLUSION: These results suggest that ANG3070 has the potential to slow disease, and may serve as a bridge toward hepato-renal transplantation in patients with fibropolycystic disease.

A modified elliptical formula to estimate kidney collagen content in a model of chronic kidney disease.

The extent of scarring or renal interstitial collagen deposition in chronic kidney disease (CKD) can only be ascertained by highly invasive, painful and sometimes risky, tissue biopsy. Interestingly, while CKD-related abnormalities in kidney size can often be visualized using ultrasound, not only does the ellipsoid formula used today underestimate true renal size, but the calculated renal size does not inform tubulointerstitial collagen content. We used coronal kidney sections from healthy mice and mice with kidney disease to develop a new formula for estimating renal parenchymal area. While treating the kidney as an ellipse with the major axis (a) the polar distance, this technique involves extending the minor axis (b) into the renal pelvis to obtain a new minor axis, be. The calculated renal parenchymal area is remarkably similar to the true or measured area. Biochemically determined kidney collagen content revealed a strong and positive correlation with the calculated renal parenchymal area. Picrosirius red staining for tubulointerstitial collagen also correlated with calculated renal parenchymal area. The extent of renal scarring, i.e. kidney interstitial collagen content, can now be computed by making just two axial measurements which can easily be accomplished via noninvasive imaging of this organ.

Supervised learning reveals circulating biomarker levels diagnostic of hepatocellular carcinoma in a clinically relevant model of non-alcoholic steatohepatitis; An OAD to NASH.

Although cirrhosis is a key risk factor for the development of hepatocellular carcinoma (HCC), mounting evidence indicates that in a subset of patients presenting with non-alcoholic steatohepatitis (NASH) HCC manifests in the absence of cirrhosis. Given the sheer size of the ongoing non-alcoholic fatty liver disease (NAFLD) epidemic and the dismal prognosis associated with late-stage primary liver cancer there is an urgent need for HCC surveillance in the NASH population. Using serum levels of HCC biomarkers as vectors and biopsy-proven HCC or no HCC as outputs / binary classifier, a supervised learning campaign was undertaken to develop a minimally invasive technique for making a diagnosis of HCC in a clinically relevant model of NASH. Adult mice randomized to control diet or a fast food diet (FFD) were followed for up to 14 mo and serum level of a panel of HCC-relevant biomarkers was compared with liver biopsies at 3 and 14 mo. Both NAFLD Activity Score (NAS) and hepatic hydroxyproline content were elevated at 3 and 14 mo on FFD. Picrosirius red staining of liver sections revealed a filigree pattern of fibrillar collagen deposition with no cirrhosis at 14 mo on FFD. Nevertheless, 46% of animals bore one or more tumors on their livers confirmed as HCC in hematoxylin-eosin-stained liver sections. In this training set, receiver operating characteristic (ROC) curves analysis for serum levels of the HCC biomarkers osteopontin (OPN), alpha-fetoprotein (AFP) and Dickkopf-1 (DKK1) returned concordance-statistic/area under ROC curve of ≥ 0.89. Serum levels of OPN (threshold, 218 ng/mL; sensitivity, 82%; specificity, 86%), AFP (136 ng/mL; 91%; 97%) and DKK1 (2.4 ng/mL; 82%; 81%) diagnostic for HCC were confirmed in a test set comprising mice on control diet or FFD and mice subjected to hepatic ischemia-reperfusion injury. These data suggest that levels of circulating OPN, AFP and DKK1 can be used to make a diagnosis of HCC in a clinically relevant model of NASH.

Anti-steatotic and anti-fibrotic effects of the KCa3.1 channel inhibitor, Senicapoc, in non-alcoholic liver disease.

AIM: To evaluate a calcium activated potassium channel (KCa3.1) inhibitor attenuates liver disease in models of non-alcoholic fatty liver disease (NAFLD). METHODS: We have performed a series of in vitro and in vivo studies using the KCa3.1 channel inhibitor, Senicapoc. Efficacy studies of Senicapoc were conducted in toxin-, thioacetamide (TAA) and high fat diet (HFD)-induced models of liver fibrosis in rats. Efficacy and pharmacodynamic effects of Senicapoc was determined through biomarkers of apoptosis, inflammation, steatosis and fibrosis. RESULTS: Upregulation of KCa3.1 expression was recorded in TAA-induced and high fat diet-induced liver disease. Treatment with Senicapoc decreased palmitic acid-driven HepG2 cell death. (P < 0.05 vs control) supporting the finding that Senicapoc reduces lipid-driven apoptosis in HepG2 cell cultures. In animals fed a HFD for 6 wk, co-treatment with Senicapoc, (1) reduced non-alcoholic fatty liver disease (NAFLD) activity score (NAS) (0-8 scale), (2) decreased steatosis and (3) decreased hepatic lipid content (Oil Red O, P < 0.05 vs vehicle). Randomization of TAA animals and HFD fed animals to Senicapoc was associated with a decrease in liver fibrosis as evidenced by hydroxyproline and Masson's trichrome staining (P < 0.05 vs vehicle). These results demonstrated that Senicapoc mitigates both steatosis and fibrosis in liver fibrosis models. CONCLUSION: These data suggest that Senicapoc interrupts more than one node in progressive fatty liver disease by its anti-steatotic and anti-fibrotic activities, serving as a double-edged therapeutic sword.

Distinct effects of glucose and glucosamine on vascular endothelial and smooth muscle cells: evidence for a protective role for glucosamine in atherosclerosis.

Accelerated atherosclerosis is one of the major vascular complications of diabetes. Factors including hyperglycemia and hyperinsulinemia may contribute to accelerated vascular disease. Among the several mechanisms proposed to explain the link between hyperglycemia and vascular dysfunction is the hexosamine pathway, where glucose is converted to glucosamine. Although some animal experiments suggest that glucosamine may mediate insulin resistance, it is not clear whether glucosamine is the mediator of vascular complications associated with hyperglycemia. Several processes may contribute to diabetic atherosclerosis including decreased vascular heparin sulfate proteoglycans (HSPG), increased endothelial permeability and increased smooth muscle cell (SMC) proliferation. In this study, we determined the effects of glucose and glucosamine on endothelial cells and SMCs in vitro and on atherosclerosis in apoE null mice. Incubation of endothelial cells with glucosamine, but not glucose, significantly increased matrix HSPG (perlecan) containing heparin-like sequences. Increased HSPG in endothelial cells was associated with decreased protein transport across endothelial cell monolayers and decreased monocyte binding to subendothelial matrix. Glucose increased SMC proliferation, whereas glucosamine significantly inhibited SMC growth. The antiproliferative effect of glucosamine was mediated via induction of perlecan HSPG. We tested if glucosamine affects atherosclerosis development in apoE-null mice. Glucosamine significantly reduced the atherosclerotic lesion in aortic root. (P < 0.05) These data suggest that macrovascular disease associated with hyperglycemia is unlikely due to glucosamine. In fact, glucosamine by increasing HSPG showed atheroprotective effects.