AI Enabled Precision Medicine: Patient Stratification, Drug Repurposing and Combination Therapies

Gardner, Steve; Das, Sayoni; Taylor, Krystyna

doi:10.5772/intechopen.92594

Cited by 8 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SNPs, transcriptomic, epidemiological or clinical) features at whole genome resolution in large patient cohorts. It has been validated across multiple different disease populations 10,11,12 . This type of analysis is intractable to other existing methods due the combinatorial explosion posed by the analysis of large numbers of patients with combinatorial non-linear additive combinations of features per patient.…”

Section: Methodsmentioning

confidence: 99%

Analysis of Genetic Host Response Risk Factors in Severe COVID-19 Patients

Taylor¹,

Das²,

Pearson³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

BACKGROUND Epidemiological studies indicate that as many as 20% of individuals who test positive for COVID-19 develop severe symptoms that can require hospitalization. These symptoms include low platelet count, severe hypoxia, increased inflammatory cytokines and reduced glomerular filtration rate. Additionally, severe COVID-19 is associated with several chronic co-morbidities, including cardiovascular disease, hypertension and type 2 diabetes mellitus. The identification of genetic risk factors that impact differential host responses to SARS-CoV-2, resulting in the development of severe COVID-19, is important in gaining greater understanding into the biological mechanisms underpinning life-threatening responses to the virus. These insights could be used in the identification of high-risk individuals and for the development of treatment strategies for these patients. METHODS As of June 6, 2020, there were 976 patients who tested positive for COVID-19 and were hospitalized, indicating they had a severe response to SARS-CoV-2. There were however too few patients with a mild form of COVID-19 to use this cohort as our control population. Instead we used similar control criteria to our previous study looking at shared genetic risk factors between severe COVID-19 and sepsis, selecting controls who had not developed sepsis despite having maximum co-morbidity risk and exposure to sepsis-causing pathogens. RESULTS Using a combinatorial (high-order epistasis) analysis approach, we identified 68 protein-coding genes that were highly associated with severe COVID-19. At the time of analysis, nine of these genes have been linked to differential response to SARS-CoV-2. We also found many novel targets that are involved in key biological pathways associated with the development of severe COVID-19, including production of pro-inflammatory cytokines, endothelial cell dysfunction, lipid droplets, neurodegeneration and viral susceptibility factors. CONCLUSION The variants we found in genes relating to immune response pathways and cytokine production cascades, were in equal proportions across all severe COVID-19 patients, regardless of their co-morbidities. This suggests that such variants are not associated with any specific co-morbidity, but are common amongst patients who develop severe COVID-19. Among the 68 severe COVID-19 risk-associated genes, we found several druggable protein targets and pathways. Nine are targeted by drugs that have reached at least Phase I clinical trials, and a further eight have active chemical starting points for novel drug development. Several of these targets were particularly enriched in specific co-morbidities, providing insights into shared pathological mechanisms underlying both the development of severe COVID-19, ARDS and these predisposing co-morbidities. We can use these insights to identify patients who are at greatest risk of contracting severe COVID-19 and develop targeted therapeutic strategies for them, with the aim of improving disease burden and survival rates.

show abstract

Section: Methodsmentioning

confidence: 99%

Analysis of Genetic Host Response Risk Factors in Severe COVID-19 Patients

Taylor¹,

Das²,

Pearson³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…When used to analyze genomic data from patients, precision life can identify high-order epistatic interactions comprising multiple consistently co-associated SNP genotypes. This analytical mining platform has been validated in multiple disease populations 16,17 .…”

Section: Methodsmentioning

confidence: 99%

Identification and Analysis of Shared Risk Factors in Sepsis and High Mortality Risk COVID-19 Patients

Das¹,

Taylor²,

Pearson³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

BACKGROUNDCoronavirus disease 2019 (COVID-19) is a novel coronavirus strain disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The disease is highly transmissible and severe disease including viral sepsis has been reported in up to 16% of hospitalized cases. The admission characteristics associated with increased odds of hospital mortality among confirmed cases of COVID-19 include severe hypoxia, low platelet count, elevated bilirubin, hypoalbuminemia and reduced glomerular filtration rate. These symptoms correlate highly with severe sepsis cases. The diseases also share similar comorbidity risks including dementia, type 2 diabetes mellitus, coronary heart disease, hypertension and chronic renal failure. Sepsis has been observed in up to 59% of hospitalized COVID-19 patients.It is highly desirable to identify risk factors and novel therapy/drug repurposing avenues for late-stage severe COVID-19 patients. This would enable better protection of at-risk populations and clinical stratification of COVID-19 patients according to their risk for developing life threatening disease. METHODSAs there is currently insufficient data available for confirmed COVID-19 patients correlating their genomic profile, disease severity and outcome, co-morbidities and treatments as well as epidemiological risk factors (such as ethnicity, blood group, smoking, BMI etc.), a direct study of the impact of host genomics on disease severity and outcomes is not yet possible. We therefore ran a study on the UK Biobank sepsis cohort as a surrogate to identify sepsis associated signatures and genes, and correlated these with COVID-19 patients.Sepsis is itself a life-threatening inflammatory health condition with a mortality rate of approximately 20%. Like the initial studies for COVID-19 patients, standard genome wide association studies (GWAS) have previously failed to identify more than a handful of genetic variants that predispose individuals to developing sepsis. RESULTSWe used a combinatorial association approach to analyze a sepsis population derived from UK Biobank. We identified 70 sepsis risk-associated genes, which provide insights into the disease mechanisms underlying sepsis pathogenesis. Many of these targets can be grouped by common mechanisms of action such as endothelial cell dysfunction, PI3K/mTOR pathway signaling, immune response regulation, aberrant GABA and neurogenic signaling. CONCLUSIONThis study has identified 70 sepsis related genes, many of them for the first time, that can reasonably be considered to be potentially relevant to severe COVID-19 patients. We have further identified 59 drug repurposing candidates for 13 of these targets that can be used for the development of novel therapeutic strategies to increase the survival rate of patients who develop sepsis and potentially severe COVID-19.

show abstract

“…For each indication, all significant disease signatures were clustered by the patients in whom they co-occur to generate a disease architecture that provides a high-resolution view of the targets and mechanisms of actions associated with specific patient subgroups. 41 The targets were prioritized based on the 5Rs drug discovery framework, 42 and efficacy potential metrics (a measure of how well stratified the disease biology around a chosen target is within the patient population) and patient stratification biomarkers were generated for all prioritized targets.…”

Section: Drug Indication Extension Powered By High-resolution Patient...mentioning

confidence: 99%

Systematic indication extension for drugs using patient stratification insights generated by combinatorial analytics

Das¹,

Taylor²,

Beaulah³

et al. 2022

Patterns

Self Cite

View full text Add to dashboard Cite

AI Enabled Precision Medicine: Patient Stratification, Drug Repurposing and Combination Therapies

Cited by 8 publications

References 51 publications

Analysis of Genetic Host Response Risk Factors in Severe COVID-19 Patients

Analysis of Genetic Host Response Risk Factors in Severe COVID-19 Patients

Identification and Analysis of Shared Risk Factors in Sepsis and High Mortality Risk COVID-19 Patients

Systematic indication extension for drugs using patient stratification insights generated by combinatorial analytics

Contact Info

Product

Resources

About