RESUMO
BACKGROUND: In many applications of bioinformatics, data stem from distinct heterogeneous sources. One of the well-known examples is the identification of drug-target interactions (DTIs), which is of significant importance in drug discovery. In this paper, we propose a novel framework, manifold optimization based kernel preserving embedding (MOKPE), to efficiently solve the problem of modeling heterogeneous data. Our model projects heterogeneous drug and target data into a unified embedding space by preserving drug-target interactions and drug-drug, target-target similarities simultaneously. RESULTS: We performed ten replications of ten-fold cross validation on four different drug-target interaction network data sets for predicting DTIs for previously unseen drugs. The classification evaluation metrics showed better or comparable performance compared to previous similarity-based state-of-the-art methods. We also evaluated MOKPE on predicting unknown DTIs of a given network. Our implementation of the proposed algorithm in R together with the scripts that replicate the reported experiments is publicly available at https://github.com/ocbinatli/mokpe .
Assuntos
Algoritmos , Desenvolvimento de Medicamentos , Desenvolvimento de Medicamentos/métodos , Descoberta de Drogas/métodos , Biologia Computacional/métodos , Interações MedicamentosasRESUMO
MOTIVATION: Dataset sizes in computational biology have been increased drastically with the help of improved data collection tools and increasing size of patient cohorts. Previous kernel-based machine learning algorithms proposed for increased interpretability started to fail with large sample sizes, owing to their lack of scalability. To overcome this problem, we proposed a fast and efficient multiple kernel learning (MKL) algorithm to be particularly used with large-scale data that integrates kernel approximation and group Lasso formulations into a conjoint model. Our method extracts significant and meaningful information from the genomic data while conjointly learning a model for out-of-sample prediction. It is scalable with increasing sample size by approximating instead of calculating distinct kernel matrices. RESULTS: To test our computational framework, namely, Multiple Approximate Kernel Learning (MAKL), we demonstrated our experiments on three cancer datasets and showed that MAKL is capable to outperform the baseline algorithm while using only a small fraction of the input features. We also reported selection frequencies of approximated kernel matrices associated with feature subsets (i.e. gene sets/pathways), which helps to see their relevance for the given classification task. Our fast and interpretable MKL algorithm producing sparse solutions is promising for computational biology applications considering its scalability and highly correlated structure of genomic datasets, and it can be used to discover new biomarkers and new therapeutic guidelines. AVAILABILITY AND IMPLEMENTATION: MAKL is available at https://github.com/begumbektas/makl together with the scripts that replicate the reported experiments. MAKL is also available as an R package at https://cran.r-project.org/web/packages/MAKL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Análise de Dados , Genômica , Algoritmos , Biologia Computacional/métodos , Humanos , Aprendizado de MáquinaRESUMO
BACKGROUND: Glioblastoma is the most common and aggressive primary brain tumor with extremely poor prognosis, highlighting an urgent need for developing novel treatment options. Identifying epigenetic vulnerabilities of cancer cells can provide excellent therapeutic intervention points for various types of cancers. METHOD: In this study, we investigated epigenetic regulators of glioblastoma cell survival through CRISPR/Cas9 based genetic ablation screens using a customized sgRNA library EpiDoKOL, which targets critical functional domains of chromatin modifiers. RESULTS: Screens conducted in multiple cell lines revealed ASH2L, a histone lysine methyltransferase complex subunit, as a major regulator of glioblastoma cell viability. ASH2L depletion led to cell cycle arrest and apoptosis. RNA sequencing and greenCUT&RUN together identified a set of cell cycle regulatory genes, such as TRA2B, BARD1, KIF20B, ARID4A and SMARCC1 that were downregulated upon ASH2L depletion. Mass spectrometry analysis revealed the interaction partners of ASH2L in glioblastoma cell lines as SET1/MLL family members including SETD1A, SETD1B, MLL1 and MLL2. We further showed that glioblastoma cells had a differential dependency on expression of SET1/MLL family members for survival. The growth of ASH2L-depleted glioblastoma cells was markedly slower than controls in orthotopic in vivo models. TCGA analysis showed high ASH2L expression in glioblastoma compared to low grade gliomas and immunohistochemical analysis revealed significant ASH2L expression in glioblastoma tissues, attesting to its clinical relevance. Therefore, high throughput, robust and affordable screens with focused libraries, such as EpiDoKOL, holds great promise to enable rapid discovery of novel epigenetic regulators of cancer cell survival, such as ASH2L. CONCLUSION: Together, we suggest that targeting ASH2L could serve as a new therapeutic opportunity for glioblastoma. Video Abstract.
Assuntos
Glioblastoma , Proteínas Nucleares , Humanos , Sobrevivência Celular , Proteínas Nucleares/metabolismo , Glioblastoma/genética , Sistemas CRISPR-Cas/genética , RNA Guia de Sistemas CRISPR-Cas , Proteínas de Ligação a DNA/metabolismo , Fatores de Transcrição/genética , Fatores de Transcrição/metabolismo , Cinesinas/genética , Cinesinas/metabolismoRESUMO
PURPOSE: Tocilizumab, a monoclonal IL-6 receptor blocker, is an effective agent for severe-to-critical cases of COVID-19; however, its target patients for the optimum use need to be detailed. We performed a systematic review and meta-analysis to define its effect among severely ill but non-intubated cases with COVID-19. METHODS: We searched PubMed, Scopus, Web of Science, MEDLINE, Cochrane Central Register of Controlled Trials (CENTRAL), Medrxiv, and Biorxiv until February 13, 2022, for non-intubated cases, and included randomized-controlled trials (RCT) based on bias assessment. The primary outcomes were the requirement of invasive mechanical ventilation and mortality. Random effect and fixed-effect models were used. The heterogeneity was measured using the χ2 and I2 statistics, with χ2 p ≤ 0.05 and I2 ≥ 50% indicating the presence of significant heterogeneity. We registered the study to the International Prospective Register of Systematic Reviews (PROSPERO) with the registration number CRD42021232575. RESULTS: Among 261 articles, 11 RCTs were included. The pooled analysis of the 11 RCTs demonstrated that the rate of mortality was significantly lower in the tocilizumab group than in the control group (20.0% and 24.2%, OR: 0.84, 95% CI 0.73-0.96, and heterogeneity I2 = 0%. p = 0.82.). The mechanical ventilation rate was lower in the tocilizumab group than the control group (27% vs 35.2%, OR: 0.76, 95% CI 0.67-0.86, and heterogeneity I2 = 6%. p = 0.39). CONCLUSION: Among non-intubated severe COVID-19 cases, tocilizumab reduces the risk of invasive mechanical ventilation and mortality compared to standard-of-care treatment.
Assuntos
COVID-19 , Humanos , Tratamento Farmacológico da COVID-19 , Anticorpos Monoclonais Humanizados/uso terapêutico , Respiração ArtificialRESUMO
We aimed to describe the effect of aminoglycosides and tigecycline to reduce the mortality in colistin- and carbapenem-resistant Klebsiella pneumoniae (ColR-CR-Kp) infections. We included the studies with defined outcomes after active or non-active antibiotic treatment of ColR-CR-Kp infections. The active treatment was defined as adequate antibiotic use for at least 3 days (72 h) after the diagnosis of ColR-CR-Kp infection by culture. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement and the checklist of PRISMA 2020 was applied. Crude and adjusted odds ratios (OR) with 95% confidence interval (CI) were calculated and pooled in the random effects model. Adding aminoglycosides to the existing treatment regimen reduced overall mortality significantly (OR 0.34, 95% CI 0.20-0.58). Overall mortality was 34% in patients treated with aminoglycoside-combined regimens and was 60% in patients treated with non-aminoglycoside regimens. Treatment with tigecycline is not found to reduce mortality (OR: 0.76, 95% CI: 0.47-1.23). Our results suggest that aminoglycoside addition to the existing regimen of colistin- and carbapenem-resistant Klebsiella pneumoniae infections reduces mortality significantly.
Assuntos
Enterobacteriáceas Resistentes a Carbapenêmicos , Infecções por Klebsiella , Sepse , Aminoglicosídeos/farmacologia , Aminoglicosídeos/uso terapêutico , Antibacterianos/farmacologia , Antibacterianos/uso terapêutico , Carbapenêmicos/farmacologia , Carbapenêmicos/uso terapêutico , Colistina/farmacologia , Colistina/uso terapêutico , Humanos , Infecções por Klebsiella/microbiologia , Klebsiella pneumoniae , Testes de Sensibilidade Microbiana , Sepse/tratamento farmacológico , Tigeciclina/farmacologia , Tigeciclina/uso terapêuticoRESUMO
A prospective, multicentre observational cohort study of carbapenem-resistant Klebsiella spp. (CRK) bloodstream infections was conducted in Turkey from June 2018 to June 2019. One hundred eighty-seven patients were recruited. Single OXA-48-like carbapenemases predominated (75%), followed by OXA-48-like/NDM coproducers (16%). OXA-232 constituted 31% of all OXA-48-like carbapenemases and was mainly carried on ST2096. Thirty-day mortality was 44% overall and 51% for ST2096. In the multivariate cox regression analysis, SOFA score and immunosuppression were significant predictors of 30-day mortality and ST2096 had a non-significant effect. All OXA-48-like producers remained susceptible to ceftazidime-avibactam.
Assuntos
Infecções por Klebsiella , Sepse , Antibacterianos/farmacologia , Antibacterianos/uso terapêutico , Proteínas de Bactérias/genética , Carbapenêmicos/farmacologia , Carbapenêmicos/uso terapêutico , Humanos , Infecções por Klebsiella/tratamento farmacológico , Infecções por Klebsiella/epidemiologia , Infecções por Klebsiella/microbiologia , Klebsiella pneumoniae , Testes de Sensibilidade Microbiana , Estudos Prospectivos , Sepse/tratamento farmacológico , beta-Lactamases/genéticaRESUMO
OBJECTIVE: To develop machine learning (ML) models that predict postoperative remission, remission at last visit, and resistance to somatostatin receptor ligands (SRL) in patients with acromegaly and to determine the clinical features associated with the prognosis. METHODS: We studied outcomes using the area under the receiver operating characteristics (AUROC) values, which were reported as the performance metric. To determine the importance of each feature and easy interpretation, Shapley Additive explanations (SHAP) values, which help explain the outputs of ML models, are used. RESULTS: One-hundred fifty-two patients with acromegaly were included in the final analysis. The mean AUROC values resulting from 100 independent replications were 0.728 for postoperative 3 months remission status classification, 0.879 for remission at last visit classification, and 0.753 for SRL resistance status classification. Extreme gradient boosting model demonstrated that preoperative growth hormone (GH) level, age at operation, and preoperative tumor size were the most important predictors for early remission; resistance to SRL and preoperative tumor size represented the most important predictors of remission at last visit, and postoperative 3-month insulin-like growth factor 1 (IGF1) and GH levels (random and nadir) together with the sparsely granulated somatotroph adenoma subtype served as the most important predictors of SRL resistance. CONCLUSIONS: ML models may serve as valuable tools in the prediction of remission and SRL resistance.
Assuntos
Acromegalia , Adenoma , Sistemas de Apoio a Decisões Clínicas , Adenoma Hipofisário Secretor de Hormônio do Crescimento , Hormônio do Crescimento Humano , Acromegalia/metabolismo , Acromegalia/cirurgia , Adenoma/metabolismo , Adenoma/cirurgia , Adenoma Hipofisário Secretor de Hormônio do Crescimento/metabolismo , Adenoma Hipofisário Secretor de Hormônio do Crescimento/cirurgia , Humanos , Fator de Crescimento Insulin-Like I/metabolismo , Aprendizado de Máquina , Estudos Retrospectivos , Resultado do TratamentoRESUMO
BACKGROUND: Identification of molecular mechanisms that determine tumour progression in cancer patients is a prerequisite for developing new disease treatment guidelines. Even though the predictive performance of current machine learning models is promising, extracting significant and meaningful knowledge from the data simultaneously during the learning process is a difficult task considering the high-dimensional and highly correlated nature of genomic datasets. Thus, there is a need for models that not only predict tumour volume from gene expression data of patients but also use prior information coming from pathway/gene sets during the learning process, to distinguish molecular mechanisms which play crucial role in tumour progression and therefore, disease prognosis. RESULTS: In this study, instead of initially choosing several pathways/gene sets from an available set and training a model on this previously chosen subset of genomic features, we built a novel machine learning algorithm, PrognosiT, that accomplishes both tasks together. We tested our algorithm on thyroid carcinoma patients using gene expression profiles and cancer-specific pathways/gene sets. Predictive performance of our novel multiple kernel learning algorithm (PrognosiT) was comparable or even better than random forest (RF) and support vector regression (SVR). It is also notable that, to predict tumour volume, PrognosiT used gene expression features less than one-tenth of what RF and SVR algorithms used. CONCLUSIONS: PrognosiT was able to obtain comparable or even better predictive performance than SVR and RF. Moreover, we demonstrated that during the learning process, our algorithm managed to extract relevant and meaningful pathway/gene sets information related to the studied cancer type, which provides insights about its progression and aggressiveness. We also compared gene expressions of the selected genes by our algorithm in tumour and normal tissues, and we then discussed up- and down-regulated genes selected by our algorithm while learning, which could be beneficial for determining new biomarkers.
Assuntos
Aprendizado de Máquina , Neoplasias , Algoritmos , Humanos , Neoplasias/genética , Oncogenes , Carga TumoralRESUMO
Recently, it has been showed that cancer missense mutations selectively target the neighborhood of hinge residues, which are key sites in protein dynamics. Here, we show that this approach can be extended to find previously unknown candidate mutations and genes. To this aim, we developed a computational pipeline to detect significantly enriched three-dimensional (3D) clustering of missense mutations around hinge residues. The hinge residues were detected by applying a Gaussian network model. By systematically analyzing the PanCancer compendium of somatic mutations in nearly 10 000 tumors from the Cancer Genome Atlas, we identified candidate genes and mutations in addition to well known ones. For instance, we found significantly enriched 3D clustering of missense mutations in known cancer genes including CDK4, CDKN2A, TCL1A, and MAPK1. Beside these known genes, we also identified significantly enriched 3D clustering of missense mutations around hinge residues in PLA2G4A, which may lead to excessive phosphorylation of the extracellular signal-regulated kinases. Furthermore, we demonstrated that hinge-based features improves pathogenicity prediction for missense mutations. Our results show that the consideration of clustering around hinge residues can help us explain the functional role of the mutations in known cancer genes and identify candidate genes.
Assuntos
Biologia Computacional/métodos , Fosfolipases A2 do Grupo IV/genética , Mutação de Sentido Incorreto , Proteínas de Neoplasias/genética , Neoplasias/genética , Atlas como Assunto , Quinase 4 Dependente de Ciclina/genética , Quinase 4 Dependente de Ciclina/metabolismo , Inibidor p16 de Quinase Dependente de Ciclina/genética , Inibidor p16 de Quinase Dependente de Ciclina/metabolismo , Regulação Neoplásica da Expressão Gênica , Fosfolipases A2 do Grupo IV/metabolismo , Humanos , Proteína Quinase 1 Ativada por Mitógeno/genética , Proteína Quinase 1 Ativada por Mitógeno/metabolismo , Modelos Moleculares , Família Multigênica , Proteínas de Neoplasias/metabolismo , Neoplasias/metabolismo , Neoplasias/patologia , Fosforilação , Conformação Proteica , Proteínas Proto-Oncogênicas/genética , Proteínas Proto-Oncogênicas/metabolismoRESUMO
MOTIVATION: Micro-RNAs (miRNAs) are known as the important components of RNA silencing and post-transcriptional gene regulation, and they interact with messenger RNAs (mRNAs) either by degradation or by translational repression. miRNA alterations have a significant impact on the formation and progression of human cancers. Accordingly, it is important to establish computational methods with high predictive performance to identify cancer-specific miRNA-mRNA regulatory modules. RESULTS: We presented a two-step framework to model miRNA-mRNA relationships and identify cancer-specific modules between miRNAs and mRNAs from their matched expression profiles of more than 9000 primary tumors. We first estimated the regulatory matrix between miRNA and mRNA expression profiles by solving multiple linear programming problems. We then formulated a unified regularized factor regression (RFR) model that simultaneously estimates the effective number of modules (i.e. latent factors) and extracts modules by decomposing regulatory matrix into two low-rank matrices. Our RFR model groups correlated miRNAs together and correlated mRNAs together, and also controls sparsity levels of both matrices. These attributes lead to interpretable results with high predictive performance. We applied our method on a very comprehensive data collection by including 32 TCGA cancer types. To find the biological relevance of our approach, we performed functional gene set enrichment and survival analyses. A large portion of the identified modules are significantly enriched in Hallmark, PID and KEGG pathways/gene sets. To validate the identified modules, we also performed literature validation as well as validation using experimentally supported miRTarBase database. AVAILABILITY AND IMPLEMENTATION: Our implementation of proposed two-step RFR algorithm in R is available at https://github.com/MiladMokhtaridoost/2sRFR together with the scripts that replicate the reported experiments. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
MicroRNAs , Neoplasias , Biologia Computacional , Perfilação da Expressão Gênica , Regulação da Expressão Gênica , Regulação Neoplásica da Expressão Gênica , Redes Reguladoras de Genes , Humanos , MicroRNAs/genética , Neoplasias/genética , RNA Mensageiro/genéticaRESUMO
MOTIVATION: Genomic information is increasingly being used in diagnosis, prognosis and treatment of cancer. The severity of the disease is usually measured by the tumor stage. Therefore, identifying pathways playing an important role in progression of the disease stage is of great interest. Given that there are similarities in the underlying mechanisms of different cancers, in addition to the considerable correlation in the genomic data, there is a need for machine learning methods that can take these aspects of genomic data into account. Furthermore, using machine learning for studying multiple cancer cohorts together with a collection of molecular pathways creates an opportunity for knowledge extraction. RESULTS: We studied the problem of discriminating early- and late-stage tumors of several cancers using genomic information while enforcing interpretability on the solutions. To this end, we developed a multitask multiple kernel learning (MTMKL) method with a co-clustering step based on a cutting-plane algorithm to identify the relationships between the input tasks and kernels. We tested our algorithm on 15 cancer cohorts and observed that, in most cases, MTMKL outperforms other algorithms (including random forests, support vector machine and single-task multiple kernel learning) in terms of predictive power. Using the aggregate results from multiple replications, we also derived similarity matrices between cancer cohorts, which are, in many cases, in agreement with available relationships reported in the relevant literature. AVAILABILITY AND IMPLEMENTATION: Our implementations of support vector machine and multiple kernel learning algorithms in R are available at https://github.com/arezourahimi/mtgsbc together with the scripts that replicate the reported experiments. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Neoplasias , Máquina de Vetores de Suporte , Algoritmos , Análise por Conglomerados , Humanos , Aprendizado de Máquina , Neoplasias/diagnóstico , Neoplasias/genéticaRESUMO
We performed a systematic review and meta-analysis for the effectiveness of Favipiravir on the fatality and the requirement of mechanical ventilation for the treatment of moderate to severe COVID-19 patients. We searched available literature and reported it by using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Until June 1, 2021, we searched PubMed, bioRxiv, medRxiv, ClinicalTrials.gov, Cochrane Central Register of Controlled Trials (CENTRAL), and Google Scholar by using the keywords "Favipiravir" and terms synonymous with COVID-19. Studies for Favipiravir treatment compared to standard of care among moderate and severe COVID-19 patients were included. Risk of bias assessment was performed using Revised Cochrane risk of bias tool for randomized trials (RoB 2) and ROBINS-I assessment tool for non-randomized studies. We defined the outcome measures as fatality and requirement for mechanical ventilation. A total of 2702 studies were identified and 12 clinical trials with 1636 patients were analyzed. Nine out of 12 studies were randomized controlled trials. Among the randomized studies, one study has low risk of bias, six studies have moderate risk of bias, and 2 studies have high risk of bias. Observational studies were identified as having moderate risk of bias and non-randomized study was found to have serious risk of bias. Our meta-analysis did not reveal any significant difference between the intervention and the comparator on fatality rate (OR 1.11, 95% CI 0.64-1.94) and mechanical ventilation requirement (OR 0.50, 95% CI 0.13-1.95). There is no significant difference in fatality rate and mechanical ventilation requirement between Favipiravir treatment and the standard of care in moderate and severe COVID-19 patients.
Assuntos
Amidas/administração & dosagem , Antivirais/administração & dosagem , Tratamento Farmacológico da COVID-19 , Pirazinas/administração & dosagem , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Amidas/efeitos adversos , Antivirais/efeitos adversos , COVID-19/mortalidade , COVID-19/terapia , COVID-19/virologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Observacionais como Assunto , Pirazinas/efeitos adversos , Ensaios Clínicos Controlados Aleatórios como Assunto , Respiração Artificial , SARS-CoV-2/efeitos dos fármacos , SARS-CoV-2/genética , SARS-CoV-2/fisiologia , Adulto JovemRESUMO
BACKGROUND: There is limited evidence on the modification or stopping of antiretroviral therapy (ART) regimens, including novel antiretroviral drugs. The aim of this study was to evaluate the discontinuation of first ART before and after the availability of better tolerated and less complex regimens by comparing the frequency, reasons and associations with patient characteristics. METHODS: A total of 3019 ART-naive patients registered in the HIV-TR cohort who started ART between Jan 2011 and Feb 2017 were studied. Only the first modification within the first year of treatment for each patient was included in the analyses. Reasons were classified as listed in the coded form in the web-based database. Cumulative incidences were analysed using competing risk function and factors associated with discontinuation of the ART regimen were examined using Cox proportional hazards models and Fine-Gray competing risk regression models. RESULTS: The initial ART regimen was discontinued in 351 out of 3019 eligible patients (11.6%) within the first year. The main reason for discontinuation was intolerance/toxicity (45.0%), followed by treatment simplification (9.7%), patient willingness (7.4%), poor compliance (7.1%), prevention of future toxicities (6.0%), virologic failure (5.4%), and provider preference (5.4%). Non-nucleoside reverse transcriptase inhibitor (NNRTI)-based (aHR = 4.4, [95% CI 3.0-6.4]; p < 0.0001) or protease inhibitor (PI)-based regimens (aHR = 4.3, [95% CI 3.1-6.0]; p < 0.0001) relative to integrase strand transfer inhibitor (InSTI)-based regimens were significantly associated with ART discontinuation. ART initiated at a later period (2015-Feb 2017) (aHR = 0.6, [95% CI 0.4-0.9]; p < 0.0001) was less likely to be discontinued. A lower rate of treatment discontinuation for intolerance/toxicity was observed with InSTI-based regimens (2.0%) than with NNRTI- (6.6%) and PI-based regimens (7.5%) (p < 0.001). The percentage of patients who achieved HIV RNA < 200 copies/mL within 12 months of ART initiation was 91% in the ART discontinued group vs. 94% in the continued group (p > 0.05). CONCLUSION: ART discontinuation due to intolerance/toxicity and virologic failure decreased over time. InSTI-based regimens were less likely to be discontinued than PI- and NNRTI-based ART.
Assuntos
Fármacos Anti-HIV , Antirretrovirais , Infecções por HIV , Minorias Sexuais e de Gênero , Fármacos Anti-HIV/uso terapêutico , Antirretrovirais/uso terapêutico , Terapia Antirretroviral de Alta Atividade , Feminino , Infecções por HIV/tratamento farmacológico , Homossexualidade Masculina , Humanos , Masculino , Carga ViralRESUMO
The Fbw7 (F-box/WD repeat-containing protein 7) ubiquitin ligase targets multiple oncoproteins for degradation and is commonly mutated in cancers. Like other pleiotropic tumor suppressors, Fbw7's complex biology has impeded our understanding of how Fbw7 mutations promote tumorigenesis and hindered the development of targeted therapies. To address these needs, we employed a transfer learning approach to derive gene-expression signatures from The Cancer Gene Atlas datasets that predict Fbw7 mutational status across tumor types and identified the pathways enriched within these signatures. Genes involved in mitochondrial function were highly enriched in pan-cancer signatures that predict Fbw7 mutations. Studies in isogenic colorectal cancer cell lines that differed in Fbw7 mutational status confirmed that Fbw7 mutations increase mitochondrial gene expression. Surprisingly, Fbw7 mutations shifted cellular metabolism toward oxidative phosphorylation and caused context-specific metabolic vulnerabilities. Our approach revealed unexpected metabolic reprogramming and possible therapeutic targets in Fbw7-mutant cancers and provides a framework to study other complex, oncogenic mutations.
Assuntos
Neoplasias Colorretais/metabolismo , Neoplasias Colorretais/patologia , Proteína 7 com Repetições F-Box-WD/genética , Proteína 7 com Repetições F-Box-WD/metabolismo , Metaboloma , Mitocôndrias/metabolismo , Mutação , Respiração Celular , Neoplasias Colorretais/genética , Perfilação da Expressão Gênica , Humanos , Mitocôndrias/patologia , Fosforilação Oxidativa , Estresse Oxidativo , Fosforilação , Ubiquitina , UbiquitinaçãoRESUMO
MOTIVATION: Survival analysis methods that integrate pathways/gene sets into their learning model could identify molecular mechanisms that determine survival characteristics of patients. Rather than first picking the predictive pathways/gene sets from a given collection and then training a predictive model on the subset of genomic features mapped to these selected pathways/gene sets, we developed a novel machine learning algorithm (Path2Surv) that conjointly performs these two steps using multiple kernel learning. RESULTS: We extensively tested our Path2Surv algorithm on 7655 patients from 20 cancer types using cancer-specific pathway/gene set collections and gene expression profiles of these patients. Path2Surv statistically significantly outperformed survival random forest (RF) on 12 out of 20 datasets and obtained comparable predictive performance against survival support vector machine (SVM) using significantly fewer gene expression features (i.e. less than 10% of what survival RF and survival SVM used). AVAILABILITY AND IMPLEMENTATION: Our implementations of survival SVM and Path2Surv algorithms in R are available at https://github.com/mehmetgonen/path2surv together with the scripts that replicate the reported experiments. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Neoplasias , Humanos , Aprendizado de Máquina , Software , Máquina de Vetores de Suporte , Análise de SobrevidaRESUMO
Missense mutations have various effects on protein structures, also leading to distorted protein dynamics that plausibly affects the function. We hypothesized that missense mutations in cancer-related genes selectively target hinge-neighboring residues that orchestrate collective structural dynamics. To test our hypothesis, we selected 69 cancer-related genes from the Cancer Gene Census database and their representative protein structures from the Protein Data Bank. We first identified the hinge residues in two global modes of motion by applying the Gaussian Network Model. We then showed that missense mutations are significantly enriched on hinge-neighboring residues in oncogenes and tumor suppressor genes. We observed that several oncogenes (eg, MAP2K1, PTPN11, and KRAS) and tumor suppressor genes (eg, EZH2, CDKN2C, and RHOA) strongly exhibit this phenomenon. This study highlights and rationalizes the functional importance of missense mutations on hinge-neighboring residues in cancer.
Assuntos
Mutação de Sentido Incorreto/genética , Neoplasias/genética , Bases de Dados de Proteínas , Humanos , Mutação/genéticaRESUMO
Motivation: Identifying molecular mechanisms that drive cancers from early to late stages is highly important to develop new preventive and therapeutic strategies. Standard machine learning algorithms could be used to discriminate early- and late-stage cancers from each other using their genomic characterizations. Even though these algorithms would get satisfactory predictive performance, their knowledge extraction capability would be quite restricted due to highly correlated nature of genomic data. That is why we need algorithms that can also extract relevant information about these biological mechanisms using our prior knowledge about pathways/gene sets. Results: In this study, we addressed the problem of separating early- and late-stage cancers from each other using their gene expression profiles. We proposed to use a multiple kernel learning (MKL) formulation that makes use of pathways/gene sets (i) to obtain satisfactory/improved predictive performance and (ii) to identify biological mechanisms that might have an effect in cancer progression. We extensively compared our proposed MKL on gene sets algorithm against two standard machine learning algorithms, namely, random forests and support vector machines, on 20 diseases from the Cancer Genome Atlas cohorts for two different sets of experiments. Our method obtained statistically significantly better or comparable predictive performance on most of the datasets using significantly fewer gene expression features. We also showed that our algorithm was able to extract meaningful and disease-specific information that gives clues about the progression mechanism. Availability and implementation: Our implementations of support vector machine and multiple kernel learning algorithms in R are available at https://github.com/mehmetgonen/gsbc together with the scripts that replicate the reported experiments.
Assuntos
Perfilação da Expressão Gênica/métodos , Aprendizado de Máquina , Neoplasias/genética , Análise de Sequência de RNA/métodos , Feminino , Genoma Humano , Humanos , Masculino , Redes e Vias Metabólicas , Estadiamento de Neoplasias , Neoplasias/metabolismo , Neoplasias/patologia , Máquina de Vetores de SuporteRESUMO
BACKGROUND: Short and long ambulatory electrocardiographic monitoring with different systems is a widely used method to detect cardiac arrhythmias. In this study, we aimed to evaluate the effectiveness of a novel monitoring device on cardiac arrhythmia detection. METHODS: We used two different protocols to evaluate device performance. For the first one, 36 healthy subjects were enrolled. The standard 12lead, 24-h Holter monitoring and the novel single lead electrocardiogram (ECG) Patch Monitor (EPM) device (BeyondCare®, Rooti Labs Ltd., Taipei, Taiwan) were simultaneously applied to all subjects for 24â¯h. The quality of ECG data acquisition of novel system was compared to that of standard Holter. The second phase included 73 patients that were referred from our outpatient arrhythmia clinic for evaluation of their symptoms relevant to the cardiac arrhythmias. Advanced algorithms, statistical methods (cross-correlation method, Pearson's correlation coefficient, Bland-Altman plots) were used to process and verify the acquired data. RESULTS: The overall average beat per minute correlation between BeyondCare® and standard 12lead Holter was found 98% in 33 healthy subjects. The mean percentage of invalid measurements in BeyondCare® was 1.6% while the Holter's was 1.7%. In the second protocol of the study, prospective data from 67 patients who were referred for evaluation of their symptoms relevant to cardiac arrhythmias, showed that the mean BeyondCare® wear time was 4.7⯱â¯0.5â¯days out of five total days per protocol. The mean analyzable wear time was 93.6%. The water-resistant design enabled 73.5% of the participants to take a shower. 7.3% of participants had minor skin irritations related to the electrodes. Among the patients with detected arrhythmia (40.2% of all patients), 29.6% had their first arrhythmia after the initial two days period. A clinically significant pause was detected in one patient, ventricular tachycardia was detected in four patients, and supraventricular tachycardia was detected in 15 patients. Paroxysmal atrial fibrillation was identified in seven patients. Three of them had their first episodes after the second day of monitoring. CONCLUSION: BeyondCare® Patch was well-tolerated and allowed prolonged time periods for continuous ECG monitoring, may result in an improvement in clinical accuracy and detection of arrhythmias by cloud-based artificial intelligence operating system.
Assuntos
Arritmias Cardíacas/diagnóstico , Eletrocardiografia Ambulatorial/instrumentação , Adulto , Algoritmos , Interpretação Estatística de Dados , Desenho de Equipamento , Humanos , Pessoa de Meia-Idade , Satisfação do Paciente , Estudos ProspectivosRESUMO
We performed a systematic review and meta-analysis on the effectiveness of ribavirin use for the prevention of infection and death of healthcare workers exposed to patients with Crimean-Congo hemorrhagic fever virus (CCHFV) infection. Splashes with blood or bodily fluids (odds ratio [OR] 4.2), being a nurse or physician (OR 2.1), and treating patients who died from CCHFV infection (OR 3.8) were associated with healthcare workers acquiring CCHFV infection; 7% of the workers who received postexposure prophylaxis (PEP) with ribavirin and 89% of those who did not became infected. PEP with ribavirin reduced the odds of infection (OR 0.01, 95% CI 0-0.03), and ribavirin use <48 hours after symptom onset reduced the odds of death (OR 0.03, 95% CI 0-0.58). The odds of death increased 2.4-fold every day without ribavirin treatment. Ribavirin should be recommended as PEP and early treatment for workers at medium-to-high risk for CCHFV infection.
Assuntos
Pessoal de Saúde , Vírus da Febre Hemorrágica da Crimeia-Congo/isolamento & purificação , Febre Hemorrágica da Crimeia/epidemiologia , Profilaxia Pós-Exposição , Antivirais/administração & dosagem , Antivirais/uso terapêutico , Saúde Global , Febre Hemorrágica da Crimeia/tratamento farmacológico , Febre Hemorrágica da Crimeia/mortalidade , Humanos , Ribavirina/administração & dosagem , Ribavirina/uso terapêuticoRESUMO
Objectives: We describe the molecular characteristics of colistin resistance and its impact on patient mortality. Methods: A prospective cohort study was performed in seven different Turkish hospitals. The genotype of each isolate was determined by MLST and repetitive extragenic palindromic PCR (rep-PCR). Alterations in mgrB were detected by sequencing. Upregulation of pmrCAB, phoQ and pmrK was quantified by RT-PCR. mcr-1 and the genes encoding OXA-48, NDM-1 and KPC were amplified by PCR. Results: A total of 115 patients diagnosed with colistin-resistant K. pneumoniae (ColR-Kp) infection were included. Patients were predominantly males (55%) with a median age of 63 (IQR 46-74) and the 30 day mortality rate was 61%. ST101 was the most common ST and accounted for 68 (59%) of the ColR-Kp. The 30 day mortality rate in patients with these isolates was 72%. In ST101, 94% (64/68) of the isolates had an altered mgrB gene, whereas the alteration occurred in 40% (19/47) of non-ST101 isolates. The OXA-48 and NDM-1 carbapenemases were found in 93 (81%) and 22 (19%) of the total 115 isolates, respectively. In multivariate analysis for the prediction of 30 day mortality, ST101 (OR 3.4, CI 1.46-8.15, P = 0.005) and ICU stay (OR 7.4, CI 2.23-29.61, P = 0.002) were found to be significantly associated covariates. Conclusions: Besides ICU stay, ST101 was found to be a significant independent predictor of patient mortality among those infected with ColR-Kp. A significant association was detected between ST101 and OXA-48. ST101 may become a global threat in the dissemination of colistin resistance and the increased morbidity and mortality of K. pneumoniae infection.