Precision Medicine Initiative Research Articles

Machine learning approaches for the genomic prediction of rheumatoid arthritis and systemic lupus erythematosus

BackgroundRheumatoid arthritis (RA) and systemic lupus erythematous (SLE) are autoimmune rheumatic diseases that share a complex genetic background and common clinical features. This study’s purpose was to construct machine learning (ML) models for the genomic prediction of RA and SLE.MethodsA total of 2,094 patients with RA and 2,190 patients with SLE were enrolled from the Taichung Veterans General Hospital cohort of the Taiwan Precision Medicine Initiative. Genome-wide single nucleotide polymorphism (SNP) data were obtained using Taiwan Biobank version 2 array. The ML methods used were logistic regression (LR), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and extreme gradient boosting (XGB). SHapley Additive exPlanation (SHAP) values were calculated to clarify the contribution of each SNPs. Human leukocyte antigen (HLA) imputation was performed using the HLA Genotype Imputation with Attribute Bagging package.ResultsCompared with LR (area under the curve [AUC] = 0.8247), the RF approach (AUC = 0.9844), SVM (AUC = 0.9828), GTB (AUC = 0.9932), and XGB (AUC = 0.9919) exhibited significantly better prediction performance. The top 20 genes by feature importance and SHAP values included HLA class II alleles. We found that imputed HLA-DQA1*05:01, DQB1*0201 and DRB1*0301 were associated with SLE; HLA-DQA1*03:03, DQB1*0401, DRB1*0405 were more frequently observed in patients with RA.ConclusionsWe established ML methods for genomic prediction of RA and SLE. Genetic variations at HLA-DQA1, HLA-DQB1, and HLA-DRB1 were crucial for differentiating RA from SLE. Future studies are required to verify our results and explore their mechanistic explanation.

Abstract 10361: Cardiovascular Risk Factor Control and Treatment Across the Spectrum of Patients with Atherosclerotic Cardiovascular Disease: The Precision Medicine Initiative - All of Us Study

Objective: The 2018 Multisociety Cholesterol Guideline categorized patients with atherosclerotic cardiovascular disease (ASCVD) according to very high risk status, but there are few reports of recent medication use and risk factor control by risk group. We examined in a current cohort of US adults the extent of ASCVD risk factor control and treatment by these ASCVD groups. Methods: The NIH Precision Medicine Initiative (All of Us Study) is an ongoing program aiming to enroll > 1 million adults across the US. Since May 2018, >315,000 participants have been recruited from >340 sites nationwide, oversampling underrepresented groups. We studied adults age > 18 years with prior ASCVD, classified based on the 2018 guideline as 1) very high risk with > 2 major ASCVD events, 2) very high risk with 1 major event and > 2 major ASCVD conditions, or 3) ASCVD not at very high risk. We examined proportions at recommended therapies (high intensity statin, blood pressure [BP] and diabetes [DM] medication, and aspirin) and desired levels of risk factors (LDL-C, BP, HbA1c, and non-smoking status) across ASCVD risk categories. Results: Our 34,195 participants with ASCVD included 49% female, 20.5% non-Hispanic Black and 12.9% Hispanic or Latino adults, with an overall age of 66.0 + 12.4 years. 44.6% were classified as very high risk, of which 10.8% had > 2 prior ASCVD evets. The table shows the proportion of each risk group on recommended therapies and risk factor targets. Across ASCVD risk groups use of high intensity statins (10-14%) and attainment of acceptable LDL-C levels (17-27%) and BP levels (42-47%) are markedly suboptimal. Across risk groups only 3-8% were on all 4 recommended therapies and <5% were at all desired levels of all 4 risk factors. Conclusions: Improved efforts are needed to communicate the importance of multiple risk factor control and recommended therapies across the spectrum of ASCVD patients, and especially those at very high risk.

Sex-Specific Metabolic Pathways Were Associated with Alzheimer's Disease (AD) Endophenotypes in the European Medical Information Framework for AD Multimodal Biomarker Discovery Cohort.

Background: physiological differences between males and females could contribute to the development of Alzheimer’s Disease (AD). Here, we examined metabolic pathways that may lead to precision medicine initiatives. Methods: We explored whether sex modifies the association of 540 plasma metabolites with AD endophenotypes including diagnosis, cerebrospinal fluid (CSF) biomarkers, brain imaging, and cognition using regression analyses for 695 participants (377 females), followed by sex-specific pathway overrepresentation analyses, APOE ε4 stratification and assessment of metabolites’ discriminatory performance in AD. Results: In females with AD, vanillylmandelate (tyrosine pathway) was increased and tryptophan betaine (tryptophan pathway) was decreased. The inclusion of these two metabolites (area under curve (AUC) = 0.83, standard error (SE) = 0.029) to a baseline model (covariates + CSF biomarkers, AUC = 0.92, SE = 0.019) resulted in a significantly higher AUC of 0.96 (SE = 0.012). Kynurenate was decreased in males with AD (AUC = 0.679, SE = 0.046). Conclusions: metabolic sex-specific differences were reported, covering neurotransmission and inflammation pathways with AD endophenotypes. Two metabolites, in pathways related to dopamine and serotonin, were associated to females, paving the way to personalised treatment.

A Genome-Wide Association Study Identifies Novel Risk Loci for Sarcopenia in a Taiwanese Population.

PurposeA genome-wide association study (GWAS) of sarcopenia unraveled the importance of genetic contribution to decline in muscle. The current study investigated sarcopenia-related single nucleotide polymorphisms (SNPs) in Asian older adults, and further constructed a genotype score that tests the combined effect of these SNPs on risk of sarcopenia.Patients and MethodsNinety-six subjects aged 60 or above were recruited from the database of annual geriatric health examination at Tri-Service General Hospital during 2020. Eligible criteria included: 1) not having severe comorbidities; 2) agreed to join the Taiwan Precision Medicine Initiative project; and 3) having sufficient information of required sarcopenic measurements. Genotype–phenotype association analysis was performed to find SNPs that were significantly associated with each of three sarcopenic indices (low muscle mass, muscle strength, and physical performance). Subsequently, these SNPs comprised a sarcopenia-related genotype score that summed up the number of SNPs carrying unfavorable allele(s).ResultsTwelve SNPs revealed suggestive genome-wide significance with the three sarcopenic indices, and eight of them revealed a relationship with more than one index. Low muscle strength was the item that had the most (eight) related SNPs. Among them, rs10282247 affects cholesterol binding and rs7022373 participates in cellular apoptosis. In addition, higher genotype score demonstrated higher risk of sarcopenia (≥4 points: OR=630.6; 2–3 points: OR=408, p-value<0.001).ConclusionSeveral newly discovered SNPs suggest that genetic contribution plays a part in the pathogenesis of sarcopenia. Further studies are warranted to verify the underlying mechanisms. Moreover, a genotype score provides an estimate of the combined effect of genetic association with sarcopenia, which may modestly improve clinical risk classification.

Newer Treatments and Glycemic Control in US Adults With Diabetes Across Risk Groups, Sex, and Ethnicity: The NIH Precision Medicine Initiative (All Of Us Study)

Objective: There are limited data on the extent of evidence-based SGLT2is and GLP1-RAs among real-world cohorts of patients with DM. We examined the use of these therapies and glycemic control among current US adults with DM by risk groups, sex, and ethnicity. MethodsIn adults ≥ 18 years of age with DM from the NIH Precision Medicine Initiative All of Us Study including 340 US sites, we categorized DM groups as 1) low risk with ≤ 1 DM risk factor, 2) high risk with ≥ 2 DM risk factors, and 3) DM with known ASCVD. Risk factors included age > 60 years, hypertension, LDL-C ≥ 160 mg/dL, cigarette smoking, and HDL-C < 40 mg/dL (men) and < 50 mg/dL (women). We examined the % on any DM therapy, on SGLT2-i and GLP1-RA, and with HbA1c <7%, 7-<8%, and >8%. We also examined the % on SGLT2-i among those with heart failure (HF) or chronic kidney disease (CKD) (eGFR<60 ml/minute/1.73 m²). ResultsOur 42,064 participants with DM included 27.2% non-Hispanic Black and 21.7% Hispanic or Latino; overall 29.5%, 31.2%, and 39.3% were at lower risk, higher risk, or with ASCVD, respectively. Across risk groups, sex and ethnicity, there remains underutilization of SGLT-is and GLP1-RAs, and few people with HF or CKD are on SGLT2i (Table). ConclusionsDespite recent guidelines for usage of SGLT2-is or GLP1-RAs among higher risk people with DM, few are actually taking them, and use is overall lower among underserved ethnic groups.

Statin and Icosapent Ethyl Use and Lipid Control in US Adults with Diabetes According to DM Risk Groups, Sex and Ethnicity in the NIH Precision Medicine Initiative All of Us Study

ObjectiveData on statin therapy intensity and icosapent ethyl use among adults with diabetes mellitus (DM) are limited. We studied statin intensity and icosapent ethyl use with lipid levels among US adults with DM across risk groups, sex and ethnicity. MethodsAmong adults ≥18 years of age with DM from the NIH Precision Medicine Initiative All of Us Study, we categorized risk groups as 1) low risk with ≤1 DM risk factor, 2) high risk with ≥2 DM risk factors, and 3) DM with known ASCVD. Risk factors included age >60 years, hypertension, LDL-C ≥160 mg/dL, cigarette smoking, and HDL-C <40 mg/dL (males) and <50 mg/dL (females). We examined the % of people on low, moderate, and high-intensity statin therapy and at LDL-C levels <70 mg/dL, 70-99 mg/dL, and ≥100 mg/dL. We also studied the % of people on icosapent ethyl and examined triglyceride (TG) levels <100 mg/dL, 100-149 mg/dL, and ≥150 mg/dL. ResultsOur 42,064 participants with DM included 27.1% non-Hispanic black and 21.7% Hispanic. Inadequate statin use and improperly controlled LDL-C remain common, with 33.8% of people on high-intensity statins having LDL-C levels ≥100 mg/dL. Additionally, 1.7% of those with TG levels ≥150 mg/dL were on icosapent ethyl. ConclusionsGuideline-recommended use of high intensity statins among our higher risk DM patients is lacking, with many having inadequately controlled LDL-C levels. Moreover, icosapent ethyl use remains low, even among those with high TG levels. Further provider and patient education need to be prioritized— especially among those at highest risk.

A KCNQ4 c.546C>G Genetic Variant Associated with Late Onset Non-Syndromic Hearing Loss in a Taiwanese Population.

Clinical presentation is heterogeneous for autosomal dominant nonsyndromic hearing loss (ADNSHL). Variants of KCNQ4 gene is a common genetic factor of ADNSHL. Few studies have investigated the association between hearing impairment and the variant c.546C>G of KCNQ4. Here, we investigated the phenotype and clinical manifestations of the KCNQ4 variant. Study subjects were selected from the participants of the Taiwan Precision Medicine Initiative. In total, we enrolled 12 individuals with KCNQ4 c.546C>G carriers and 107 non-carriers, and performed pure tone audiometry (PTA) test and phenome-wide association (PheWAS) analysis for the patients. We found that c.546C>G variant was related to an increased risk of hearing loss. All patients with c.546C>G variant were aged >65 years and had sensorineural and high frequency hearing loss. Of these patients, a third (66.7%) showed moderate and progressive hearing loss, 41.7% complained of tinnitus and 16.7% complained of vertigo. Additionally, we found a significant association between KCNQ4 c.546C>G variant, aortic aneurysm, fracture of lower limb and polyneuropathy in diabetes. KCNQ4 c.546C>G is likely a potentially pathogenic variant of ADNSHL in the elderly population. Genetic counseling, annual audiogram and early assistive listening device intervention are highly recommended to prevent profound hearing impairment in this patient group.

A Comprehensive Review of HLA and Severe Cutaneous Adverse Drug Reactions: Implication for Clinical Pharmacogenomics and Precision Medicine.

Human leukocyte antigen (HLA) encoded by the HLA gene is an important modulator for immune responses and drug hypersensitivity reactions as well. Genetic polymorphisms of HLA vary widely at population level and are responsible for developing severe cutaneous adverse drug reactions (SCARs) such as Stevens–Johnson syndrome (SJS), toxic epidermal necrolysis (TEN), drug reaction with eosinophilia and systemic symptoms (DRESS), maculopapular exanthema (MPE). The associations of different HLA alleles with the risk of drug induced SJS/TEN, DRESS and MPE are strongly supportive for clinical considerations. Prescribing guidelines generated by different national and international working groups for translation of HLA pharmacogenetics into clinical practice are underway and functional in many countries, including Thailand. Cutting edge genomic technologies may accelerate wider adoption of HLA screening in routine clinical settings. There are great opportunities and several challenges as well for effective implementation of HLA genotyping globally in routine clinical practice for the prevention of drug induced SCARs substantially, enforcing precision medicine initiatives.

Statistical Process Control Charts for Monitoring Next-Generation Sequencing and Bioinformatics Turnaround in Precision Medicine Initiatives

PurposePrecision oncology, such as next generation sequencing (NGS) molecular analysis and bioinformatics are used to guide targeted therapies. The laboratory turnaround time (TAT) is a key performance indicator of laboratory performance. This study aims to formally apply statistical process control (SPC) methods such as CUSUM and EWMA to a precision medicine programme to analyze the learning curves of NGS and bioinformatics processes.Patients and MethodsTrends in NGS and bioinformatics TAT were analyzed using simple regression models with TAT as the dependent variable and chronologically-ordered case number as the independent variable. The M-estimator “robust” regression and negative binomial regression were chosen to serve as sensitivity analyses to each other. Next, two popular statistical process control (SPC) approaches which are CUSUM and EWMA were utilized and the CUSUM log-likelihood ratio (LLR) charts were also generated. All statistical analyses were done in Stata version 16.0 (StataCorp), and nominal P < 0.05 was considered to be statistically significant.ResultsA total of 365 patients underwent successful molecular profiling. Both the robust linear model and negative binomial model showed statistically significant reductions in TAT with accumulating experience. The EWMA and CUSUM charts of overall TAT largely corresponded except that the EWMA chart consistently decreased while the CUSUM analyses indicated improvement only after a nadir at the 82nd case. CUSUM analysis found that the bioinformatics team took a lower number of cases (54 cases) to overcome the learning curve compared to the NGS team (85 cases).ConclusionAs NGS and bioinformatics lead precision oncology into the forefront of cancer management, characterizing the TAT of NGS and bioinformatics processes improves the timeliness of data output by potentially spotlighting problems early for rectification, thereby improving care delivery.

Precision Nursing.

Precision Nursing.

Whole genome sequence analysis of platelet traits in the NHLBI Trans-Omics for Precision Medicine (TOPMed) initiative.

Platelets play a key role in thrombosis and hemostasis. Platelet count (PLT) and mean platelet volume (MPV) are highly heritable quantitative traits, with hundreds of genetic signals previously identified, mostly in European ancestry populations. We here utilize whole genome sequencing (WGS) from NHLBI's Trans-Omics for Precision Medicine initiative (TOPMed) in a large multi-ethnic sample to further explore common and rare variation contributing to PLT (n = 61 200) and MPV (n = 23 485). We identified and replicated secondary signals at MPL (rs532784633) and PECAM1 (rs73345162), both more common in African ancestry populations. We also observed rare variation in Mendelian platelet-related disorder genes influencing variation in platelet traits in TOPMed cohorts (not enriched for blood disorders). For example, association of GP9 with lower PLT and higher MPV was partly driven by a pathogenic Bernard-Soulier syndrome variant (rs5030764, p.Asn61Ser), and the signals at TUBB1 and CD36 were partly driven by loss of function variants not annotated as pathogenic in ClinVar (rs199948010 and rs571975065). However, residual signal remained for these gene-based signals after adjusting for lead variants, suggesting that additional variants in Mendelian genes with impacts in general population cohorts remain to be identified. Gene-based signals were also identified at several genome-wide association study identified loci for genes not annotated for Mendelian platelet disorders (PTPRH, TET2, CHEK2), with somatic variation driving the result at TET2. These results highlight the value of WGS in populations of diverse genetic ancestry to identify novel regulatory and coding signals, even for well-studied traits like platelet traits.

The song of power

In this paper I take the form of the fugue in music to query a contemporary dynamic. It is one where hopefulness entwines with worrisome, oppressive realities that pervade biosocial trends concerning race. Genetic ancestry testing, forensic uses of DNA, and President Obama’s Precision Medicine Initiative are all examined as aspects of this cultural moment where biosociality must be engaged for its potential contradictory outcomes, which I argue are regenerative in form, yet often dystopian.

PhenoDB, GeneMatcher and VariantMatcher, tools for analysis and sharing of sequence data

BackgroundWith the advent of whole exome (ES) and genome sequencing (GS) as tools for disease gene discovery, rare variant filtering, prioritization and data sharing have become essential components of the search for disease genes and variants potentially contributing to disease phenotypes. The computational storage, data manipulation, and bioinformatic interpretation of thousands to millions of variants identified in ES and GS, respectively, is a challenging task. To aid in that endeavor, we constructed PhenoDB, GeneMatcher and VariantMatcher.ResultsPhenoDB is an accessible, freely available, web-based platform that allows users to store, share, analyze and interpret their patients’ phenotypes and variants from ES/GS data. GeneMatcher is accessible to all stakeholders as a web-based tool developed to connect individuals (researchers, clinicians, health care providers and patients) around the globe with interest in the same gene(s), variant(s) or phenotype(s). Finally, VariantMatcher was developed to enable public sharing of variant-level data and phenotypic information from individuals sequenced as part of multiple disease gene discovery projects. Here we provide updates on PhenoDB and GeneMatcher applications and implementation and introduce VariantMatcher.ConclusionEach of these tools has facilitated worldwide data sharing and data analysis and improved our ability to connect genes to phenotypic traits. Further development of these platforms will expand variant analysis, interpretation, novel disease-gene discovery and facilitate functional annotation of the human genome for clinical genomics implementation and the precision medicine initiative.

Abstract 1410: Chemotherapy resistance pathways identified in ovarian cancer patients treated with neoadjuvant chemotherapy using single cell RNA sequencing of matched tumor biopsies

Abstract Background: Women with ovarian cancer suffer from a high rate of mortality due to the development of chemotherapy resistance. To better understand the mechanisms of chemotherapy resistance we initiated a prospective study of women with ovarian cancer, which we refer to as the Ovarian Cancer Precision Medicine Initiative (OCPMI) where we collect tumor biopsies and perform comprehensive molecular analyses. Our goal is to use the molecular data from these specimens to understand the mechanisms of chemo-resistance and use that information to improve therapeutic approaches. Methods: In this study, we report our analysis of pairs of matched tumor specimens taken from seven ovarian cancer patients enrolled in OCPMI who were treated using neoadjuvant chemotherapy (NACT). The first tumor specimen was taken at time of initial diagnostic biopsy (pre-NACT), while the matched second tumor biopsy was taken after NACT administration (post-NACT), during interval debulking surgery. All fourteen tumor biopsies were subjected to single cell RNA sequencing to generate gene expression data on 54,827 pre-NACT cells and 30,661 post-NACT cells. Bioinformatic techniques were used to compare the post-NACT tumor cells that had experienced chemotherapy to the chemo-naïve pre-NACT tumor cells. Gene/pathway enrichment tests were performed to identify genes and pathways that correlated with the chemo resistance phenotype. Results: In all matched biopsies we found that the majority of cells in the chemo-experienced post-NACT samples could be mapped to a subset of the cells in the chemo-naïve, pre-NACT samples based on gene expression patterns. We hypothesize that this subset of pre-NACT cells are the precursor cells that are able to withstand chemotherapy and could be the cause of recurrence. Analysis of the genes and signaling pathways that were upregulated in the chemo-resistant subset of pre-NACT cells identified potential novel therapeutic targets including TNFa signaling, JAK-STAT signaling, interferon signaling, TGFb signaling, and STK33 kinase activation. Conclusions: Single cell RNA sequencing combined with sequential biopsies provides an unprecedented ability to understand mechanisms of response to chemotherapy. This type of analysis can be used to identify novel therapeutic approaches targeting the chemo-resistance phenotype. Citation Format: Timothy K. Starr, Shobhana Talukdar, Zenas Chang, Jason Cepela, Christopher Tastad, Mihir Shetty, Isaac Schneider, Jun Woo, Marissa Macchietto, Christine Henzler, Ying Zhang, Joshua Baller, Constantin Aiferis, Sarah Munro, Andrew C. Nelson, Jinhua Wang, Boris J. Winterhoff. Chemotherapy resistance pathways identified in ovarian cancer patients treated with neoadjuvant chemotherapy using single cell RNA sequencing of matched tumor biopsies [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 1410.

Synchronized Tissue Acquisition Techniques for Novel Biomarker Discovery: Are You Ready to Waltz?

Synchronized Tissue Acquisition Techniques for Novel Biomarker Discovery: Are You Ready to Waltz?

Lupus nephritis and ANCA-associated vasculitis: towards precision medicine?

Historically the treatment of lupus nephritis (LN) and anti-neutrophil cytoplasmic antibody (ANCA) vasculitis was 'one size fits all'; however, with the emergence of precision medicine initiatives, the field is moving towards more personalized treatment approaches. The recent development of a more accurate and reproducible histopathological classification system for LN could lead to better disease categorization and therefore more targeted therapies. A better understanding of the pathophysiology of LN has provided evidence that not only T but also B cells play an important role, opening new opportunities for individualized treatment approaches. Recent trials have shown calcineurin inhibitors and the anti-CD20 antibodies rituximab and ofatumumab to be effective in the treatment of LN, adding new treatment options. State-of-the-art targeted therapy in ANCA-associated vasculitis (AAV) takes interindividual heterogeneity in disease severity, type of ANCA antibody [myeloperoxidase versus proteinase 3 (PR3)] and the risk for side effects of therapy into consideration. In addition, within an individual, induction therapy differs from maintenance therapy, the same holding true in incident and relapsing disease. Rituximab is now widely used in AAV and it has become clear that prolonged B cell depletion, as in LN, must be achieved to obtain a long-lasting clinical response, especially in anti-PR3-associated disease. Still, despite these advances, molecular and genetic markers are rarely incorporated into diagnostic and treatment algorithms and true precision medicine remains an aspiration that hopefully can be achieved.

Implementing Personalized Genetic Medicine

Implementing Personalized Genetic Medicine

The imprecise promise of the Precision Medicine Initiative (PMI): Where we got it wrong and how can we fix it?

e15102 Background: Over the last several years, science has taken strides in how we understand and treat cancer. We have learned that each person’s cancer is unique, in part because it is influenced by a patient’s biological characteristics, environmental exposures, lifestyle and epigenetic influence. There is excitement about the potential of PMI to transform healthcare delivery and improve population health. Targeted therapies developed based on specific mutations can result in improved outcomes and reduced toxicities. Limited knowledge of cancer biology and the genomic underpinnings of cancer in racial and ethnic minorities diminishes the potential of PMI. Previous efforts of obtaining biospecimens from institutional or local biobanks presents a challenge of inadequate representation of racial and ethnic diversity. This can result in exacerbation in the therapies efficaciousness. Methods: Numerous research studies have surfaced indicating that PMI has resulted in widening racial and ethnic health care disparities since state-of-the art diagnostic and treatment options are unequally distributed across the entire cancer population. A literature review highlighted the racial inequalities and disparities. Results: A report examining the racial diversity of samples in TCGA found that whites were overrepresented in the U.S. population while Asian and Hispanic patients were underrepresented at a 5 percent frequency. In the BATTLE study, 82 percent of participants were white, and only 6% were African American (AA). The NCI-MATCH trial preliminary numbers show that AAs accounted for about 10 percent of patients. Therefore, it should not be assumed that the response rates or clinical effectiveness of the therapeutics tested in these trials will generalize to all racial and ethnic groups. The underrepresentation of racial and ethnic minorities in cancer clinical trials and prevention research, along with the documented challenges to enrolling these individuals into studies pose a barrier for the implementation of precision medicine in these populations. Collectively, these challenges can slow the pace of medical innovation, decrease the generalizability of research findings, lead to incorrect interpretations, and limit our full understanding of precision medicine. Conclusions: It is imperative we develop solutions to solve for issues identified related to precision medicine testing and treatment development. We have developed a framework to address disparities in PMI through community-based initiatives. A two-step solution could be considered to address this unmet need. Through the development of a registry and biospecimen banking as well as just in time trials that include pharmacogenomics, we can follow the patient journey to identify unique characteristics by race and/or socioeconomic status to begin solving for the disparities across the population.

Current and future state of clinical pharmacist‐led precision medicine initiatives

AbstractThis white paper evaluates the current and future state of clinical pharmacist‐led precision medicine initiatives, focusing on an overview of pharmacogenomics (PGx) in three key areas: clinical practice, education, and research. These key facets are described in detail, followed by a review of potential and perceived barriers concerning PGx and recommendations for the clinical pharmacist's role in overcoming these barriers. This paper reviews the current state of clinical pharmacist‐led precision medicine and presents a vision for the future of pharmacy practice in this quickly evolving field.

Integrated Analysis of Whole Genome and Epigenome Data Using Machine Learning Technology: Toward the Establishment of Precision Oncology.

With the completion of the International Human Genome Project, we have entered what is known as the post-genome era, and efforts to apply genomic information to medicine have become more active. In particular, with the announcement of the Precision Medicine Initiative by U.S. President Barack Obama in his State of the Union address at the beginning of 2015, “precision medicine,” which aims to divide patients and potential patients into subgroups with respect to disease susceptibility, has become the focus of worldwide attention. The field of oncology is also actively adopting the precision oncology approach, which is based on molecular profiling, such as genomic information, to select the appropriate treatment. However, the current precision oncology is dominated by a method called targeted-gene panel (TGP), which uses next-generation sequencing (NGS) to analyze a limited number of specific cancer-related genes and suggest optimal treatments, but this method causes the problem that the number of patients who benefit from it is limited. In order to steadily develop precision oncology, it is necessary to integrate and analyze more detailed omics data, such as whole genome data and epigenome data. On the other hand, with the advancement of analysis technologies such as NGS, the amount of data obtained by omics analysis has become enormous, and artificial intelligence (AI) technologies, mainly machine learning (ML) technologies, are being actively used to make more efficient and accurate predictions. In this review, we will focus on whole genome sequencing (WGS) analysis and epigenome analysis, introduce the latest results of omics analysis using ML technologies for the development of precision oncology, and discuss the future prospects.