ABSTRACT
INTRODUCTION: Using GWAS data derived from a large collaborative trial (ECOG-5103), we identified a cluster of 267 SNPs which predicted CIPN in treatment-naive patients as reported in Part 1 of this study. To assess the functional and pathological implications of this set, we identified collective gene signatures were and evaluated the informational value of those signatures in defining CIPN's pathogenesis. METHODS: In Part 1, we analyzed GWAS data derived from ECOG-5103, first identifying those SNPs that were most strongly associated with CIPN using Fisher's ratio. After identifying those SNPs which differentiated CIPN-positive from CIPN-negative phenotypes, we ranked them in order of their discriminatory power to produce a cluster of SNPs which provided the highest predictive accuracy using leave-one-out cross validation (LOOCV). An uncertainty analysis was included. Using the best predictive SNP cluster, we performed gene attribution for each SNP using NCBI Phenotype Genotype Integrator and then assessed functionality by applying GeneAnalytics, Gene Set Enrichment Analysis, and PCViz. RESULTS: Using aggregate data derived from the GWAS, we identified a 267 SNP cluster which was associated with a CIPN+ phenotype with an accuracy of 96.1%. We could attribute 173 genes to the 267 SNP cluster. Six long intergenic non-protein coding genes were excluded. Ultimately, the functional analysis was based on 138 genes. Of the 17 pathways identified by Gene Analytics (GA) software, the irinotecan pharmacokinetic pathway had the highest score. Highly matching gene ontology attributions included flavone metabolic process, flavonoid glucuronidation, xenobiotic glucuronidation, nervous system development, UDP glycosyltransferase activity, retinoic acid binding, protein kinase C binding, and glucoronosyl transferase activity. Gene Set Enrichment Analysis (GSEA) GO terms identified neuron-associated genes as most significant (p = 5.45e-10). Consistent with the GA's output, flavone, and flavonoid associated terms, glucuronidation were noted as were GO terms associated with neurogenesis. CONCLUSION: The application of functional analyses to phenotype-associated SNP clusters provides an independent validation step in assessing the clinical meaningfulness of GWAS-derived data. Functional analyses following gene attribution of a CIPN-predictive SNP cluster identified pathways, gene ontology terms, and a network which were consistent with a neuropathic phenotype.
Subject(s)
Neoplasms , Peripheral Nervous System Diseases , Humans , Polymorphism, Single Nucleotide , Genome-Wide Association Study , Taxoids/adverse effects , Peripheral Nervous System Diseases/chemically induced , Neoplasms/drug therapyABSTRACT
BACKGROUND: Chemotherapy-induced peripheral neuropathy (CIPN) is a common toxicity of taxanes for which there is no effective intervention. Genomic CIPN risk determination has yielded promising, but inconsistent results. The present study assessed the utility of a collective SNP cluster identified using novel analytics to describe taxane-associated CIPN risk. METHODS: We analyzed GWAS data derived from ECOG-5103, first identifying SNPs that were most strongly associated with CIPN using Fisher's ratio (FR). We then ranked ordered those SNPs which discriminated CIPN-positive (CIPN +) from CIPN-negative phenotypes based on their discriminatory power and developed the cluster of SNPs which provided the highest predictive accuracy using leave-one-out cross-validation (LOOCV). RESULTS: Using aggregated genotype data obtained from the previously reported ECOG-5103 clinical trial (in which two different arrays were used, HumanOmniExpress (727,227 SNPs) and HumanOmni1-Quad1 (1,131,857 SNPs)), we identified a 267 SNP cluster which was associated with a CIPN + phenotype with an accuracy of 96.1%. CONCLUSIONS: A cluster of SNPs was identified which prospectively discriminated patients most likely to develop symptomatic CIPN following taxane exposure as part of a breast cancer chemotherapy regimen. Validation using an independent patient cohort should be performed.
Subject(s)
Antineoplastic Agents , Breast Neoplasms , Peripheral Nervous System Diseases , Taxoids , Humans , Antineoplastic Agents/adverse effects , Genome-Wide Association Study , Peripheral Nervous System Diseases/chemically induced , Peripheral Nervous System Diseases/genetics , Polymorphism, Single Nucleotide , Taxoids/adverse effects , Clinical Trials as Topic , Breast Neoplasms/drug therapy , Breast Neoplasms/genetics , FemaleABSTRACT
Given the high prevalence of imported diseases in immigrant populations, it has postulated the need to establish screening programs that allow their early diagnosis and treatment. We present a mathematical model based on machine learning methodologies to contribute to the design of screening programs in this population. We conducted a retrospective cross-sectional screening program of imported diseases in all immigrant patients who attended the Tropical Medicine Unit between January 2009 and December 2016. We designed a mathematical model based on machine learning methodologies to establish the set of most discriminatory prognostic variables to predict the onset of the: HIV infection, malaria, chronic hepatitis B and C, schistosomiasis, and Chagas in immigrant population. We analyzed 759 patients. HIV was predicted with an accuracy of 84.9% and the number of screenings to detect the first HIV-infected person was 26, as in the case of Chagas disease (with a predictive accuracy of 92.9%). For the other diseases the averages were 12 screenings to detect the first case of chronic hepatitis B (85.4%), or schistosomiasis (86.9%), 23 for hepatitis C (85.6%) or malaria (93.3%), and eight for syphilis (79.4%) and strongyloidiasis (88.4%). The use of machine learning methodologies allowed the prediction of the expected disease burden and made it possible to pinpoint with greater precision those immigrants who are likely to benefit from screening programs, thus contributing effectively to their development and design.
Subject(s)
Communicable Diseases, Imported/diagnosis , Early Diagnosis , Emigrants and Immigrants/statistics & numerical data , Machine Learning , Mass Screening/methods , Adolescent , Adult , Africa , Aged , Aged, 80 and over , Asia , Central America , Child , Child, Preschool , Communicable Diseases, Imported/epidemiology , Cross-Sectional Studies , Female , Humans , Infant , Infant, Newborn , Male , Mexico , Middle Aged , Models, Theoretical , Prevalence , Retrospective Studies , South America , Spain/epidemiology , Young AdultABSTRACT
We present the analysis of the defective genetic pathways of the Late-Onset Alzheimer's Disease (LOAD) compared to the Mild Cognitive Impairment (MCI) and Healthy Controls (HC) using different sampling methodologies. These algorithms sample the uncertainty space that is intrinsic to any kind of highly underdetermined phenotype prediction problem, by looking for the minimum-scale signatures (header genes) corresponding to different random holdouts. The biological pathways can be identified performing posterior analysis of these signatures established via cross-validation holdouts and plugging the set of most frequently sampled genes into different ontological platforms. That way, the effect of helper genes, whose presence might be due to the high degree of under determinacy of these experiments and data noise, is reduced. Our results suggest that common pathways for Alzheimer's disease and MCI are mainly related to viral mRNA translation, influenza viral RNA transcription and replication, gene expression, mitochondrial translation, and metabolism, with these results being highly consistent regardless of the comparative methods. The cross-validated predictive accuracies achieved for the LOAD and MCI discriminations were 84% and 81.5%, respectively. The difference between LOAD and MCI could not be clearly established (74% accuracy). The most discriminatory genes of the LOAD-MCI discrimination are associated with proteasome mediated degradation and G-protein signaling. Based on these findings we have also performed drug repositioning using Dr. Insight package, proposing the following different typologies of drugs: isoquinoline alkaloids, antitumor antibiotics, phosphoinositide 3-kinase PI3K, autophagy inhibitors, antagonists of the muscarinic acetylcholine receptor and histone deacetylase inhibitors. We believe that the potential clinical relevance of these findings should be further investigated and confirmed with other independent studies.
Subject(s)
Alzheimer Disease/drug therapy , Alzheimer Disease/genetics , Drug Repositioning , Signal Transduction , Age of Onset , Case-Control Studies , Cognitive Dysfunction/genetics , Gene Regulatory Networks , Humans , Linear Models , Machine Learning , PhenotypeABSTRACT
We present the analysis of defective pathways in multiple myeloma (MM) using two recently developed sampling algorithms of the biological pathways: The Fisher's ratio sampler, and the holdout sampler. We performed the retrospective analyses of different gene expression datasets concerning different aspects of the disease, such as the existing difference between bone marrow stromal cells in MM and healthy controls (HC), the gene expression profiling of CD34+ cells in MM and HC, the difference between hyperdiploid and non-hyperdiploid myelomas, and the prediction of the chromosome 13 deletion, to provide a deeper insight into the molecular mechanisms involved in the disease. Our analysis has shown the importance of different altered pathways related to glycosylation, infectious disease, immune system response, different aspects of metabolism, DNA repair, protein recycling and regulation of the transcription of genes involved in the differentiation of myeloid cells. The main difference in genetic pathways between hyperdiploid and non-hyperdiploid myelomas are related to infectious disease, immune system response and protein recycling. Our work provides new insights on the genetic pathways involved in this complex disease and proposes novel targets for future therapies.
Subject(s)
Bone Marrow Cells/metabolism , Chromosomes, Human, Pair 13/genetics , Hematopoietic Stem Cells/metabolism , Multiple Myeloma/metabolism , Algorithms , Aneuploidy , Antigens, CD34/immunology , Chromosomes, Human, Pair 13/metabolism , Gene Expression Profiling , Hematopoietic Stem Cells/immunology , Humans , Multiple Myeloma/genetics , Multiple Myeloma/immunology , Retrospective Studies , Signal Transduction , Stromal Cells/metabolismABSTRACT
Sarcopenia is an age-related multifactorial process that involved several biological mechanisms, whose specific contribution and interplay is still unknown. The present study proposes prognostic networks based on machine learning approaches to unravel the interplay among those biological mechanisms mainly involved in the development of Sarcopenia. After analyzing 114 biological and clinical variables in adults older than 70 years, and using all the biological prognostic networks detected by machine learning with accuracy higher than 82%, we designed a consensus classifier based on majority vote that improve the predictive accuracy of Sarcopenia up to 91%. Additionally, we applied logistic regression analysis to propose the interplay among the most discriminative biological variables of Sarcopenia: anthropometry, body composition, functional performance of lower limbs, systemic oxidative stress, presence of depression and medication for the digestive system based on proton-pump inhibitors. Our data also demonstrate that besides a loss of muscle mass, impairments on functional performance of lower limbs are more relevant for develop Sarcopenia than those affecting the muscle strength.
Subject(s)
Machine Learning , Sarcopenia , Aged , Aged, 80 and over , Female , Humans , Male , Prognosis , Sarcopenia/diagnosis , Sarcopenia/metabolism , Sarcopenia/pathologyABSTRACT
Accurate prediction of protein stability changes resulting from amino acid substitutions is of utmost importance in medicine to better understand which mutations are deleterious, leading to diseases, and which are neutral. Since conducting wet lab experiments to get a better understanding of protein mutations is costly and time consuming, and because of huge number of possible mutations the need of computational methods that could accurately predict effects of amino acid mutations is of greatest importance. In this research, we present a robust methodology to predict the energy changes of a proteins upon mutations. The proposed prediction scheme is based on two step algorithm that is a Holdout Random Sampler followed by a neural network model for regression. The Holdout Random Sampler is utilized to analysis the energy change, the corresponding uncertainty, and to obtain a set of admissible energy changes, expressed as a cumulative distribution function. These values are further utilized to train a simple neural network model that can predict the energy changes. Results were blindly tested (validated) against experimental energy changes, giving Pearson correlation coefficients of 0.66 for Single Point Mutations and 0.77 for Multiple Point Mutations. These results confirm the successfulness of our method, since it outperforms majority of previous studies in this field.
Subject(s)
Neural Networks, Computer , Protein Stability , Proteins/genetics , Amino Acids/chemistry , Amino Acids/genetics , Databases, Protein , Machine Learning , Point Mutation/genetics , Proteins/chemistry , ThermodynamicsABSTRACT
Many breast cancer (BC) patients treated with aromatase inhibitors (AIs) develop aromatase inhibitor-related arthralgia (AIA). Candidate gene studies to identify AIA risk are limited in scope. We evaluated the potential of a novel analytic algorithm (NAA) to predict AIA using germline single nucleotide polymorphisms (SNP) data obtained before treatment initiation. Systematic chart review of 700 AI-treated patients with stage I-III BC identified asymptomatic patients (n = 39) and those with clinically significant AIA resulting in AI termination or therapy switch (n = 123). Germline DNA was obtained and SNP genotyping performed using the Affymetrix UK BioBank Axiom Array to yield 695,277 SNPs. SNP clusters that most closely defined AIA risk were discovered using an NAA that sequentially combined statistical filtering and a machine-learning algorithm. NCBI PhenGenI and Ensemble databases defined gene attribution of the most discriminating SNPs. Phenotype, pathway, and ontologic analyses assessed functional and mechanistic validity. Demographics were similar in cases and controls. A cluster of 70 SNPs, correlating to 57 genes, was identified. This SNP group predicted AIA occurrence with a maximum accuracy of 75.93%. Strong associations with arthralgia, breast cancer, and estrogen phenotypes were seen in 19/57 genes (33%) and were functionally consistent. Using a NAA, we identified a 70 SNP cluster that predicted AIA risk with fair accuracy. Phenotype, functional, and pathway analysis of attributed genes was consistent with clinical phenotypes. This study is the first to link a specific SNP/gene cluster to AIA risk independent of candidate gene bias.
Subject(s)
Antineoplastic Agents, Hormonal/adverse effects , Aromatase Inhibitors/adverse effects , Arthralgia/diagnosis , Breast Neoplasms/drug therapy , Machine Learning , Arthralgia/chemically induced , Arthralgia/genetics , Breast Neoplasms/genetics , Breast Neoplasms/pathology , Case-Control Studies , Female , Genetic Predisposition to Disease , Genomics/methods , Germ-Line Mutation , Humans , Middle Aged , Neoplasm Staging , Polymorphism, Single Nucleotide , PrognosisABSTRACT
Despite the evidence regarding the influence of certain polyphenol food sources on the metabolic profile in feces, the association between the different phenolics provided by the diet and the fecal phenolic profile has not been elucidated. In this study, the composition of phenolic metabolites in fecal solutions was analyzed by UPLC-ESI-MS/MS in 74 volunteers. This fecal phenolic profile showed a high interindividual variation of the different compounds analyzed, phenylacetic and phenylpropionic acids being the major classes of phenolic metabolites excreted in feces. Subjects with higher adherence to a Mediterranean dietary pattern presented greater fecal concentrations of benzoic and 3-hydroxyphenylacetic acids, positively correlated with the intake of the principal classes and subclasses of polyphenols and fibers, and higher levels of Clostridium cluster XVIa and Faecalibacterium prausnitzii. These results provide a link among the Mediterranean dietary pattern, the bioactive compounds of the diet, and the fecal metabolic phenolic profile.
Subject(s)
Feces/chemistry , Feces/microbiology , Gastrointestinal Microbiome , Phenols/chemistry , Aged , Aged, 80 and over , Aging/metabolism , Aging/psychology , Bacteria/classification , Bacteria/genetics , Bacteria/isolation & purification , Bacteria/metabolism , Cross-Sectional Studies , Diet, Mediterranean , Female , Humans , Male , Metabolome , Middle Aged , Spain , Tandem Mass SpectrometryABSTRACT
With advancements in genomics technology, health care has been improving and new paradigms of medicine such as genomic medicine have evolved. The education of clinicians, researchers and students to face the challenges posed by these new approaches, however, has been often lagging behind. From this the Genomic Medicine Game, an educational tool, was created for the purpose of conceptualizing the key components of Genomic Medicine. A number of phenotype-genotype associations were found through a literature review, which was used to be a base for the concepts the Genomic Medicine Game would focus on. Built in Java, the game was successfully tested with promising results.