Improved pathogenicity prediction for rare human missense variants

The success of personalized genomic medicine depends on our ability to assess the pathogenicity of rare human variants, including the important class of missense variation. There are many challenges in training accurate computational systems, e.g., in finding the balance between quantity, quality, and bias in the variant sets used as training examples and avoiding predictive features that can accentuate the effects of bias. Here, we describe VARITY, which judiciously exploits a larger reservoir of training examples with uncertain accuracy and representativity. To limit circularity and bias, VARITY excludes features informed by variant annotation and protein identity. To provide a rationale for each prediction, we quantified the contribution of features and feature combinations to the pathogenicity inference of each variant. VARITY outperformed all previous computational methods evaluated, identifying at least 10% more pathogenic variants at thresholds achieving high (90% precision) stringency.

Drug repositioning by merging active subnetworks validated in cancer and COVID-19

Computational drug repositioning aims at ranking and selecting existing drugs for novel diseases or novel use in old diseases. In silico drug screening has the potential for speeding up considerably the shortlisting of promising candidates in response to outbreaks of diseases such as COVID-19 for which no satisfactory cure has yet been found. We describe DrugMerge as a methodology for preclinical computational drug repositioning based on merging multiple drug rankings obtained with an ensemble of disease active subnetworks. DrugMerge uses differential transcriptomic data on drugs and diseases in the context of a large gene co-expression network. Experiments with four benchmark diseases demonstrate that our method detects in first position drugs in clinical use for the specified disease, in all four cases. Application of DrugMerge to COVID-19 found rankings with many drugs currently in clinical trials for COVID-19 in top positions, thus showing that DrugMerge can mimic human expert judgment.

Early outcome detection for COVID-19 patients

With the outbreak of COVID-19 exerting a strong pressure on hospitals and health facilities, clinical decision support systems based on predictive models can help to effectively improve the management of the pandemic. We present a method for predicting mortality for COVID-19 patients. Starting from a large number of clinical variables, we select six of them with largest predictive power, using a feature selection method based on genetic algorithms and starting from a set of COVID-19 patients from the first wave. The algorithm is designed to reduce the impact of missing values in the set of variables measured, and consider only variables that show good accuracy on validation data. The final predictive model provides accuracy larger than 85% on test data, including a new patient cohort from the second COVID-19 wave, and on patients with imputed missing values. The selected clinical variables are confirmed to be relevant by recent literature on COVID-19.

Artificial intelligence sepsis prediction algorithm learns to say "I don't know"

Sepsis is a leading cause of morbidity and mortality worldwide. Early identification of sepsis is important as it allows timely administration of potentially life-saving resuscitation and antimicrobial therapy. We present COMPOSER (COnformal Multidimensional Prediction Of SEpsis Risk), a deep learning model for the early prediction of sepsis, specifically designed to reduce false alarms by detecting unfamiliar patients/situations arising from erroneous data, missingness, distributional shift and data drifts. COMPOSER flags these unfamiliar cases as indeterminate rather than making spurious predictions. Six patient cohorts (515,720 patients) curated from two healthcare systems in the United States across intensive care units (ICU) and emergency departments (ED) were used to train and externally and temporally validate this model. In a sequential prediction setting, COMPOSER achieved a consistently high area under the curve (AUC) (ICU: 0.925-0.953; ED: 0.938-0.945). Out of over 6 million prediction windows roughly 20% and 8% were identified as indeterminate amongst non-septic and septic patients, respectively. COMPOSER provided early warning within a clinically actionable timeframe (ICU: 12.2 [3.2 22.8] and ED: 2.1 [0.8 4.5] hours prior to first antibiotics order) across all six cohorts, thus allowing for identification and prioritization of patients at high risk for sepsis.

Analysing omics data sets with weighted nodes networks (WNNets)

Current trends in biomedical research indicate data integration as a fundamental step towards precision medicine. In this context, network models allow representing and analysing complex biological processes. However, although effective in unveiling network properties, these models fail in considering the individual, biochemical variations occurring at molecular level. As a consequence, the analysis of these models partially loses its predictive power. To overcome these limitations, Weighted Nodes Networks (WNNets) were developed. WNNets allow to easily and effectively weigh nodes using experimental information from multiple conditions. In this study, the characteristics of WNNets were described and a proteomics data set was modelled and analysed. Results suggested that degree, an established centrality index, may offer a novel perspective about the functional role of nodes in WNNets. Indeed, degree allowed retrieving significant differences between experimental conditions, highlighting relevant proteins, and provided a novel interpretation for degree itself, opening new perspectives in experimental data modelling and analysis. Overall, WNNets may be used to model any high-throughput experimental data set requiring weighted nodes. Finally, improving the power of the analysis by using centralities such as betweenness may provide further biological insights and unveil novel, interesting characteristics of WNNets.

Predicting lethal courses in critically ill COVID-19 patients using a machine learning model trained on patients with non-COVID-19 viral pneumonia

In a pandemic with a novel disease, disease-specific prognosis models are available only with a delay. To bridge the critical early phase, models built for similar diseases might be applied. To test the accuracy of such a knowledge transfer, we investigated how precise lethal courses in critically ill COVID-19 patients can be predicted by a model trained on critically ill non-COVID-19 viral pneumonia patients. We trained gradient boosted decision tree models on 718 (245 deceased) non-COVID-19 viral pneumonia patients to predict individual ICU mortality and applied it to 1054 (369 deceased) COVID-19 patients. Our model showed a significantly better predictive performance (AUROC 0.86 [95% CI 0.86-0.87]) than the clinical scores APACHE2 (0.63 [95% CI 0.61-0.65]), SAPS2 (0.72 [95% CI 0.71-0.74]) and SOFA (0.76 [95% CI 0.75-0.77]), the COVID-19-specific mortality prediction models of Zhou (0.76 [95% CI 0.73-0.78]) and Wang (laboratory: 0.62 [95% CI 0.59-0.65]; clinical: 0.56 [95% CI 0.55-0.58]) and the 4C COVID-19 Mortality score (0.71 [95% CI 0.70-0.72]). We conclude that lethal courses in critically ill COVID-19 patients can be predicted by a machine learning model trained on non-COVID-19 patients. Our results suggest that in a pandemic with a novel disease, prognosis models built for similar diseases can be applied, even when the diseases differ in time courses and in rates of critical and lethal courses.

Prospective validation of an 11-gene mRNA host response score for mortality risk stratification in the intensive care unit

Several clinical calculators predict intensive care unit (ICU) mortality, however these are cumbersome and often require 24 h of data to calculate. Retrospective studies have demonstrated the utility of whole blood transcriptomic analysis in predicting mortality. In this study, we tested prospective validation of an 11-gene messenger RNA (mRNA) score in an ICU population. Whole blood mRNA from 70 subjects in the Stanford ICU Biobank with samples collected within 24 h of Emergency Department presentation were used to calculate an 11-gene mRNA score. We found that the 11-gene score was highly associated with 60-day mortality, with an area under the receiver operating characteristic curve of 0.68 in all patients, 0.77 in shock patients, and 0.98 in patients whose primary determinant of prognosis was acute illness. Subjects with the highest quartile of mRNA scores were more likely to die in hospital (40% vs 7%, p < 0.01) and within 60 days (40% vs 15%, p = 0.06). The 11-gene score improved prognostication with a categorical Net Reclassification Improvement index of 0.37 (p = 0.03) and an Integrated Discrimination Improvement index of 0.07 (p = 0.02) when combined with Simplified Acute Physiology Score 3 or Acute Physiology and Chronic Health Evaluation II score. The test performed poorly in the 95 independent samples collected > 24 h after emergency department presentation. Tests will target a 30-min turnaround time, allowing for rapid results early in admission. Moving forward, this test may provide valuable real-time prognostic information to improve triage decisions and allow for enrichment of clinical trials.

Machine learning analyses of antibody somatic mutations predict immunoglobulin light chain toxicity

In systemic light chain amyloidosis (AL), pathogenic monoclonal immunoglobulin light chains (LC) form toxic aggregates and amyloid fibrils in target organs. Prompt diagnosis is crucial to avoid permanent organ damage, but delayed diagnosis is common because symptoms usually appear only after strong organ involvement. Here we present LICTOR, a machine learning approach predicting LC toxicity in AL, based on the distribution of somatic mutations acquired during clonal selection. LICTOR achieves a specificity and a sensitivity of 0.82 and 0.76, respectively, with an area under the receiver operating characteristic curve (AUC) of 0.87. Tested on an independent set of 12 LCs sequences with known clinical phenotypes, LICTOR achieves a prediction accuracy of 83%. Furthermore, we are able to abolish the toxic phenotype of an LC by in silico reverting two germline-specific somatic mutations identified by LICTOR, and by experimentally assessing the loss of in vivo toxicity in a Caenorhabditis elegans model. Therefore, LICTOR represents a promising strategy for AL diagnosis and reducing high mortality rates in AL.

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

As predicting the trajectory of COVID-19 is challenging, machine learning models could assist physicians in identifying high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) Healthcare database, we developed and internally validated models using patients presenting to the Emergency Department (ED) between March-April 2020 (n = 3597) and further validated them using temporally distinct individuals who presented to the ED between May-August 2020 (n = 1711). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and O2 saturation were important for ICU admission models whereas eGFR <60 ml/min/1.73 m2, and neutrophil and lymphocyte percentages were the most important variables for predicting mortality. Implementing such models could help in clinical decision-making for future infectious disease outbreaks including COVID-19.

Does the LENT score risk-stratify patients with malignant pleural mesothelioma? An observational study

Background

Malignant pleural mesothelioma (MPM) is a rare, highly aggressive and deadly disease with a poor patient life expectancy. A few years ago, the main challenge was the histological diagnosis of this disease; at present, the search for the best therapeutic strategy is now a priority. However, an optimal therapeutic strategy is not yet clear, despite growing efforts in the treatment armamentarium and research, and at the era of tailored and individualized treatment, tools to predict patient survival are needed for therapeutic decision‐making. Among them, the LENT scoring system was developed to predict prognosis in patients with malignant pleural effusion. The aim of this study was to assess the performance of the LENT score in predicting prognosis in patients with MPM.

Methods

A retrospective observational study was conducted by analyzing the prospective collected databases of patients undergoing medical thoracoscopy in a single center with a final diagnosis of MPM confirmed by the MESOPATH National Reference Center.

Results

A total of 41 patients with MPM were studied. All patients underwent platinum‐based chemotherapy combined with pemetrexed ± bevacizumab. No high‐risk category patients were found using the LENT scoring system in this cohort. The median (range) LENT score at the time of medical thoracoscopy was 0 (0–3) and the median survival was 15.5 (2–54) months for the entire cohort. The median survival of low‐risk and moderate‐risk category patients was 21.4 months (2–54, 32 patients) and 6.7 months (2–19, nine patients), respectively. A total of 27 patients with MPM of epithelial subgroup had a median LENT score of 1 (0–2) with a 26 (2–54) months median survival. The median LENT score and median survival of nonepithelial mesothelioma patients (biphasic MPM subgroup, eight patients; sarcomatoid MPM subgroup, six patients) were 0 (0–3) and 11 (2–52) months, respectively.

Conclusions

Applied to a homogenous cohort of MPM patients, the LENT score underestimated prognosis and was not useful per se for the management of this disease, as evidenced in the epithelial mesothelioma subgroup of patients in our study.

Personalized, Predictive, Participatory, Precision, and Preventive (P5) Medicine in Rotator Cuff Tears

Rotator cuff (RC) disease is a common musculoskeletal disorder of the shoulder entailing pain, with reduced functionality and quality of life. The main objective of this study was to present a perspective of the current scientific evidence about personalized, predictive, participatory, precision, and preventive approaches in the management of RC diseases. The personalized, predictive, participatory, precision and preventive (P5) medicine model is an interdisciplinary and multidisciplinary approach that will provide researchers and clinicians with a comprehensive patrimony of knowledge in the management of RC diseases. The ability to define genetic predispositions in conjunction with the evaluation of lifestyle and environmental factors may boost the tailoring of diagnosis and therapy in patients suffering from RC diseases.

Evaluation of serum natural autoantibodies reaction in different hematological disorders with prospective view to their probable utilization in predictive medicine

BACKGROUND

There are some antibodies which are present in healthy individuals without any former exposure to foreign antigens; they are known as natural autoantibodies (NAAbs). In recent years, it was shown that they probably contribute to the homeostasis of the whole body and might be present before beginning of some diseases. Thus, as new biomarkers, they are promising factors to diagnose diseases.

MATERIALS AND METHODS

In this study, we drew upon samples of 924 individuals (600 controls and 324 cases) with underlying diseases of anemia, polycythemia, leukocytosis, thrombocytopenia, thrombocytosis, and pancytopenia. For detection of NAAbs against red blood cell, plasma samples were incubated with their own red cell suspension in 4°C for 18 h. Then, positive samples were evaluated for antibody screening and titration.

RESULTS

Fifty-two (8.6%) controls and 58 (17.9%) cases showed positive reaction (Pv < 0.001). The prevalence of positive antibody screens among auto-positive controls was 53% and 100% among cases; moreover, strength of antibody screen reaction had a mean rank of 22.5 in controls and a mean rank of 38.5 in cases (Pv < 0.001). A significant relation was also observed between ABO blood group and prevalence of NAAbs in controls but not in cases (Pv < 0.05).

CONCLUSION

The prevalence and potency of NAAbs increased along with hematological changes; moreover, the antibody reactions' pattern and titration showed significant differences between the two groups and these may be useful as biomarker for monitoring and prediction of some hematological diseases.

Stigmatization of Not-Knowing as a Public Health Tool

Predictive interventions and practices are becoming a defining feature of medicine. The author points out that according to the inner logic and external supporters (i.e., state, industry, and media) of modern medicine, participating in healthcare increasingly means participating in knowing, sharing, and using of predictive information. At the same time, the author addresses the issue that predictive information may also have problematic side effects like overdiagnosis, health-related anxiety, and worry as well as impacts on personal life plans. The question is raised: Should we resort to stigmatization if doing so would increase participation in predictive interventions, and thereby save healthcare costs and reduce morbidity and premature death? The paper concludes that even if such a strategy cannot be ruled out in some forms and contexts, we ought to be very cautious about the dangers of shame and stigmatization.

Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs

Artificial intelligence and machine learning (ML) promise to transform cancer therapies by accurately predicting the most appropriate therapies to treat individual patients. Here, we present an approach, named Drug Ranking Using ML (DRUML), which uses omics data to produce ordered lists of >400 drugs based on their anti-proliferative efficacy in cancer cells. To reduce noise and increase predictive robustness, instead of individual features, DRUML uses internally normalized distance metrics of drug response as features for ML model generation. DRUML is trained using in-house proteomics and phosphoproteomics data derived from 48 cell lines, and it is verified with data comprised of 53 cellular models from 12 independent laboratories. We show that DRUML predicts drug responses in independent verification datasets with low error (mean squared error < 0.1 and mean Spearman's rank 0.7). In addition, we demonstrate that DRUML predictions of cytarabine sensitivity in clinical leukemia samples are prognostic of patient survival (Log rank p < 0.005). Our results indicate that DRUML accurately ranks anti-cancer drugs by their efficacy across a wide range of pathologies.

Individualized prediction of COVID-19 adverse outcomes with MLHO

The COVID-19 pandemic has devastated the world with health and economic wreckage. Precise estimates of adverse outcomes from COVID-19 could have led to better allocation of healthcare resources and more efficient targeted preventive measures, including insight into prioritizing how to best distribute a vaccination. We developed MLHO (pronounced as melo), an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health Outcomes. MLHO implements iterative sequential representation mining, and feature and model selection, for predicting patient-level risk of hospitalization, ICU admission, need for mechanical ventilation, and death. It bases this prediction on data from patients' past medical records (before their COVID-19 infection). MLHO's architecture enables a parallel and outcome-oriented model calibration, in which different statistical learning algorithms and vectors of features are simultaneously tested to improve prediction of health outcomes. Using clinical and demographic data from a large cohort of over 13,000 COVID-19-positive patients, we modeled the four adverse outcomes utilizing about 600 features representing patients' pre-COVID health records and demographics. The mean AUC ROC for mortality prediction was 0.91, while the prediction performance ranged between 0.80 and 0.81 for the ICU, hospitalization, and ventilation. We broadly describe the clusters of features that were utilized in modeling and their relative influence for predicting each outcome. Our results demonstrated that while demographic variables (namely age) are important predictors of adverse outcomes after a COVID-19 infection, the incorporation of the past clinical records are vital for a reliable prediction model. As the COVID-19 pandemic unfolds around the world, adaptable and interpretable machine learning frameworks (like MLHO) are crucial to improve our readiness for confronting the potential future waves of COVID-19, as well as other novel infectious diseases that may emerge.

Developing Machine-Learning Prediction Algorithm for Bacteremia in Admitted Patients

Purpose

Bloodstream infection among hospitalized patients is associated with serious adverse outcomes. Blood culture is routinely ordered in patients with suspected infections, although 90% of blood cultures do not show any growth of organisms. The evidence regarding the prediction of bacteremia is scarce.

Patients And Methods

A retrospective review of blood cultures requested for a cohort of admitted patients between 2017 and 2019 was undertaken. Several machine-learning models were used to identify the best prediction model. Additionally, univariate and multivariable logistic regression was used to determine the predictive factors for bacteremia.

Results

A total of 36,405 blood cultures of 7157 patients were done. There were 2413 (6.62%) positive blood cultures. The best prediction was by using NN with the high specificity of 88% but low sensitivity. There was a statistical difference in the following factors: longer admission days before the blood culture, presence of a central line, and higher lactic acid—more than 2 mmol/L.

Conclusion

Despite the low positive rate of blood culture, machine learning could predict positive blood culture with high specificity but minimum sensitivity. Yet, the SIRS score, qSOFA score, and other known factors were not good prognostic factors. Further improvement and training would possibly enhance machine-learning performance.

A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction

Seizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms.

A multipurpose machine learning approach to predict COVID-19 negative prognosis in São Paulo, Brazil

The new coronavirus disease (COVID-19) is a challenge for clinical decision-making and the effective allocation of healthcare resources. An accurate prognostic assessment is necessary to improve survival of patients, especially in developing countries. This study proposes to predict the risk of developing critical conditions in COVID-19 patients by training multipurpose algorithms. We followed a total of 1040 patients with a positive RT-PCR diagnosis for COVID-19 from a large hospital from São Paulo, Brazil, from March to June 2020, of which 288 (28%) presented a severe prognosis, i.e. Intensive Care Unit (ICU) admission, use of mechanical ventilation or death. We used routinely-collected laboratory, clinical and demographic data to train five machine learning algorithms (artificial neural networks, extra trees, random forests, catboost, and extreme gradient boosting). We used a random sample of 70% of patients to train the algorithms and 30% were left for performance assessment, simulating new unseen data. In order to assess if the algorithms could capture general severe prognostic patterns, each model was trained by combining two out of three outcomes to predict the other. All algorithms presented very high predictive performance (average AUROC of 0.92, sensitivity of 0.92, and specificity of 0.82). The three most important variables for the multipurpose algorithms were ratio of lymphocyte per C-reactive protein, C-reactive protein and Braden Scale. The results highlight the possibility that machine learning algorithms are able to predict unspecific negative COVID-19 outcomes from routinely-collected data.

Discovery of potential inhibitors against New Delhi metallo-β-lactamase-1 from natural compounds: in silico-based methods

New Delhi metallo-β-lactamase variants and different types of metallo-β-lactamases have attracted enormous consideration for hydrolyzing almost all β-lactam antibiotics, which leads to multi drug resistance bacteria. Metallo-β-lactamases genes have disseminated in hospitals and all parts of the world and became a public health concern. There is no inhibitor for New Delhi metallo-β-lactamase-1 and other metallo-β-lactamases classes, so metallo-β-lactamases inhibitor drugs became an urgent need. In this study, multi-steps virtual screening was done over the NPASS database with 35,032 natural compounds. At first Captopril was extracted from 4EXS PDB code and use as a template for the first structural screening and 500 compounds obtained as hit compounds by molecular docking. Then the best ligand, i.e. NPC120633 was used as templet and 800 similar compounds were obtained. As a final point, ten compounds i.e. NPC171932, NPC100251, NPC18185, NPC98583, NPC112380, NPC471403, NPC471404, NPC472454, NPC473010 and NPC300657 had proper docking scores, and a 50 ns molecular dynamics simulation was performed for calculation binding free energy of each compound with New Delhi metallo-β-lactamase. Protein sequence alignment, 3D conformational alignment, pharmacophore modeling on all New Delhi metallo-β-lactamase variants and all types of metallo-β-lactamases were done. Quantum chemical perspective based on the fragment molecular orbital (FMO) method was performed to discover conserved and crucial residues in the catalytic activity of metallo-β-lactamases. These residues had similar 3D coordinates of spatial location in the 3D conformational alignment. So it is posibble that all types of metallo-β-lactamases can inhibit by these ten compounds. Therefore, these compounds were proper to mostly inhibit all metallo-β-lactamases in experimental studies.

Psychiatric Advance Directives and Artificial Intelligence: A Conceptual Framework for Theoretical and Ethical Principles

The patient's decision-making abilities are often altered in psychiatric disorders. The legal framework of psychiatric advance directives (PADs) has been made to provide care to patients in these situations while respecting their free and informed consent. The implementation of artificial intelligence (AI) within Clinical Decision Support Systems (CDSS) may result in improvements for complex decisions that are often made in situations covered by PADs. Still, it raises theoretical and ethical issues this paper aims to address. First, it goes through every level of possible intervention of AI in the PAD drafting process, beginning with what data sources it could access and if its data processing competencies should be limited, then treating of the opportune moments it should be used and its place in the contractual relationship between each party (patient, caregivers, and trusted person). Second, it focuses on ethical principles and how these principles, whether they are medical principles (autonomy, beneficence, non-maleficence, justice) applied to AI or AI principles (loyalty and vigilance) applied to medicine, should be taken into account in the future of the PAD drafting process. Some general guidelines are proposed in conclusion: AI must remain a decision support system as a partner of each party of the PAD contract; patients should be able to choose a personalized type of AI intervention or no AI intervention at all; they should stay informed, i.e., understand the functioning and relevance of AI thanks to educational programs; finally, a committee should be created for ensuring the principle of vigilance by auditing these new tools in terms of successes, failures, security, and relevance.

Interplay between chromosomal alterations and gene mutations shapes the evolutionary trajectory of clonal hematopoiesis

Stably acquired mutations in hematopoietic cells represent substrates of selection that may lead to clonal hematopoiesis (CH), a common state in cancer patients that is associated with a heightened risk of leukemia development. Owing to technical and sample size limitations, most CH studies have characterized gene mutations or mosaic chromosomal alterations (mCAs) individually. Here we leverage peripheral blood sequencing data from 32,442 cancer patients to jointly characterize gene mutations (n = 14,789) and mCAs (n = 383) in CH. Recurrent composite genotypes resembling known genetic interactions in leukemia genomes underlie 23% of all detected autosomal alterations, indicating that these selection mechanisms are operative early in clonal evolution. CH with composite genotypes defines a patient group at high risk of leukemia progression (3-year cumulative incidence 14.6%, CI: 7-22%). Multivariable analysis identifies mCA as an independent risk factor for leukemia development (HR = 14, 95% CI: 6-33, P < 0.001). Our results suggest that mCA should be considered in conjunction with gene mutations in the surveillance of patients at risk of hematologic neoplasms.

A new precision medicine initiative at the dawn of exascale computing

Which signaling pathway and protein to select to mitigate the patient's expected drug resistance? The number of possibilities facing the physician is massive, and the drug combination should fit the patient status. Here, we briefly review current approaches and data and map an innovative patient-specific strategy to forecast drug resistance targets that centers on parallel (or redundant) proliferation pathways in specialized cells. It considers the availability of each protein in each pathway in the specific cell, its activating mutations, and the chromatin accessibility of its encoding gene. The construction of the resulting Proliferation Pathway Network Atlas will harness the emerging exascale computing and advanced artificial intelligence (AI) methods for therapeutic development. Merging the resulting set of targets, pathways, and proteins, with current strategies will augment the choice for the attending physicians to thwart resistance.

G6PD distribution in sub-Saharan Africa and potential risks of using chloroquine/hydroxychloroquine based treatments for COVID-19

Chloroquine/hydroxychloroquine have been proposed as potential treatments for COVID-19. These drugs have warning labels for use in individuals with glucose-6-phosphate dehydrogenase (G6PD) deficiency. Analysis of whole genome sequence data of 458 individuals from sub-Saharan Africa showed significant G6PD variation across the continent. We identified nine variants, of which four are potentially deleterious to G6PD function, and one (rs1050828) that is known to cause G6PD deficiency. We supplemented data for the rs1050828 variant with genotype array data from over 11,000 Africans. Although this variant is common in Africans overall, large allele frequency differences exist between sub-populations. African sub-populations in the same country can show significant differences in allele frequency (e.g. 16.0% in Tsonga vs 0.8% in Xhosa, both in South Africa, p = 2.4 × 10^-3). The high prevalence of variants in the G6PD gene found in this analysis suggests that it may be a significant interaction factor in clinical trials of chloroquine and hydroxychloroquine for treatment of COVID-19 in Africans.

Using Machine Learning to Predict the Diagnosis, Management and Severity of Pediatric Appendicitis

Background: Given the absence of consolidated and standardized international guidelines for managing pediatric appendicitis and the few strictly data-driven studies in this specific, we investigated the use of machine learning (ML) classifiers for predicting the diagnosis, management and severity of appendicitis in children. Materials and Methods: Predictive models were developed and validated on a dataset acquired from 430 children and adolescents aged 0-18 years, based on a range of information encompassing history, clinical examination, laboratory parameters, and abdominal ultrasonography. Logistic regression, random forests, and gradient boosting machines were used for predicting the three target variables. Results: A random forest classifier achieved areas under the precision-recall curve of 0.94, 0.92, and 0.70, respectively, for the diagnosis, management, and severity of appendicitis. We identified smaller subsets of 6, 17, and 18 predictors for each of targets that sufficed to achieve the same performance as the model based on the full set of 38 variables. We used these findings to develop the user-friendly online Appendicitis Prediction Tool for children with suspected appendicitis. Discussion: This pilot study considered the most extensive set of predictor and target variables to date and is the first to simultaneously predict all three targets in children: diagnosis, management, and severity. Moreover, this study presents the first ML model for appendicitis that was deployed as an open access easy-to-use online tool. Conclusion: ML algorithms help to overcome the diagnostic and management challenges posed by appendicitis in children and pave the way toward a more personalized approach to medical decision-making. Further validation studies are needed to develop a finished clinical decision support system.

Prediction of disease progression and outcomes in multiple sclerosis with machine learning

Multiple Sclerosis is a chronic inflammatory disease, affecting the Central Nervous System and leading to irreversible neurological damage, such as long term functional impairment and disability. It has no cure and the symptoms vary widely, depending on the affected regions, amount of damage, and the ability to activate compensatory mechanisms, which constitutes a challenge to evaluate and predict its course. Additionally, relapsing-remitting patients can evolve its course into a secondary progressive, characterized by a slow progression of disability independent of relapses. With clinical information from Multiple Sclerosis patients, we developed a machine learning exploration framework concerning this disease evolution, more specifically to obtain three predictions: one on conversion to secondary progressive course and two on disease severity with rapid accumulation of disability, concerning the 6th and 10th years of progression. For the first case, the best results were obtained within two years: AUC=[Formula: see text], sensitivity=[Formula: see text] and specificity=[Formula: see text]; and for the second, the best results were obtained for the 6th year of progression, also within two years: AUC=[Formula: see text], sensitivity=[Formula: see text], and specificity=[Formula: see text]. The Expanded Disability Status Scale value, the majority of functional systems, affected functions during relapses, and age at onset were described as the most predictive features. These results demonstrate the possibility of predicting Multiple Sclerosis progression by using machine learning, which may help to understand this disease's dynamics and thus, advise physicians on medication intake.

Data integration for prediction of weight loss in randomized controlled dietary trials

Diet is an important component in weight management strategies, but heterogeneous responses to the same diet make it difficult to foresee individual weight-loss outcomes. Omics-based technologies now allow for analysis of multiple factors for weight loss prediction at the individual level. Here, we classify weight loss responders (N = 106) and non-responders (N = 97) of overweight non-diabetic middle-aged Danes to two earlier reported dietary trials over 8 weeks. Random forest models integrated gut microbiome, host genetics, urine metabolome, measures of physiology and anthropometrics measured prior to any dietary intervention to identify individual predisposing features of weight loss in combination with diet. The most predictive models for weight loss included features of diet, gut bacterial species and urine metabolites (ROC-AUC: 0.84-0.88) compared to a diet-only model (ROC-AUC: 0.62). A model ensemble integrating multi-omics identified 64% of the non-responders with 80% confidence. Such models will be useful to assist in selecting appropriate weight management strategies, as individual predisposition to diet response varies.

Specific decreasing of Na+ channel expression on the lateral membrane of cardiomyocytes causes fatal arrhythmias in Brugada syndrome

Reduced cardiac sodium (Na+) channel current (INa) resulting from the loss-of-function of Na+ channel is a major cause of lethal arrhythmias in Brugada syndrome (BrS). Inspired by previous experimental studies which showed that in heart diseases INa was reduced along with expression changes in Na+ channel within myocytes, we hypothesized that the local decrease in INa caused by the alteration in Na+ channel expression in myocytes leads to the occurrence of phase-2 reentry, the major triggering mechanism of lethal arrhythmias in BrS. We constructed in silico human ventricular myocardial strand and ring models, and examined whether the Na+ channel expression changes in each myocyte cause the phase-2 reentry in BrS. Reducing Na+ channel expression in the lateral membrane of each myocyte caused not only the notch-and-dome but also loss-of-dome type action potentials and slowed conduction, both of which are typically observed in BrS patients. Furthermore, the selective reduction in Na+ channels on the lateral membrane of each myocyte together with spatial tissue heterogeneity of Na+ channel expression caused the phase-2 reentry and phase-2 reentry-mediated reentrant arrhythmias. Our data suggest that the BrS phenotype is strongly influenced by expression abnormalities as well as genetic abnormalities of Na+ channels.

Generating synthetic aging trajectories with a weighted network model using cross-sectional data

We develop a computational model of human aging that generates individual health trajectories with a set of observed health attributes. Our model consists of a network of interacting health attributes that stochastically damage with age to form health deficits, leading to eventual mortality. We train and test the model for two different cross-sectional observational aging studies that include simple binarized clinical indicators of health. In both studies, we find that cohorts of simulated individuals generated from the model resemble the observed cross-sectional data in both health characteristics and mortality. We can generate large numbers of synthetic individual aging trajectories with our weighted network model. Predicted average health trajectories and survival probabilities agree well with the observed data.

A decision support framework for prediction of avian influenza

For years, avian influenza has influenced economies and human health around the world. The emergence and spread of avian influenza virus have been uncertain and sudden. The virus is likely to spread through several pathways such as poultry transportation and wild bird migration. The complicated and global spread of avian influenza calls for surveillance tools for timely and reliable prediction of disease events. These tools can increase situational awareness and lead to faster reaction to events. Here, we aimed to design and evaluate a decision support framework that aids decision makers by answering their questions regarding the future risk of events at various geographical scales. Risk patterns were driven from pre-built components and combined in a knowledge base. Subsequently, questions were answered by direct queries on the knowledge base or through a built-in algorithm. The evaluation of the system in detecting events resulted in average sensitivity and specificity of 69.70% and 85.50%, respectively. The presented framework here can support health care authorities by providing them with an opportunity for early control of emergency situations.

Impact of RNA-seq data analysis algorithms on gene expression estimation and downstream prediction

To use next-generation sequencing technology such as RNA-seq for medical and health applications, choosing proper analysis methods for biomarker identification remains a critical challenge for most users. The US Food and Drug Administration (FDA) has led the Sequencing Quality Control (SEQC) project to conduct a comprehensive investigation of 278 representative RNA-seq data analysis pipelines consisting of 13 sequence mapping, three quantification, and seven normalization methods. In this article, we focused on the impact of the joint effects of RNA-seq pipelines on gene expression estimation as well as the downstream prediction of disease outcomes. First, we developed and applied three metrics (i.e., accuracy, precision, and reliability) to quantitatively evaluate each pipeline's performance on gene expression estimation. We then investigated the correlation between the proposed metrics and the downstream prediction performance using two real-world cancer datasets (i.e., SEQC neuroblastoma dataset and the NIH/NCI TCGA lung adenocarcinoma dataset). We found that RNA-seq pipeline components jointly and significantly impacted the accuracy of gene expression estimation, and its impact was extended to the downstream prediction of these cancer outcomes. Specifically, RNA-seq pipelines that produced more accurate, precise, and reliable gene expression estimation tended to perform better in the prediction of disease outcome. In the end, we provided scenarios as guidelines for users to use these three metrics to select sensible RNA-seq pipelines for the improved accuracy, precision, and reliability of gene expression estimation, which lead to the improved downstream gene expression-based prediction of disease outcome.

Multi-layer Trajectory Clustering: a Network Algorithm for Disease Subtyping

Many diseases display heterogeneity in clinical features and their progression, indicative of the existence of disease subtypes. Extracting patterns of disease variable progression for subtypes has tremendous application in medicine, for example, in early prognosis and personalized medical therapy. This work presents a novel, data-driven, network-based Trajectory Clustering (TC) algorithm for identifying Parkinson's subtypes based on disease trajectory. Modeling patient-variable interactions as a bipartite network, TC first extracts communities of co-expressing disease variables at different stages of progression. Then, it identifies Parkinson's subtypes by clustering similar patient trajectories that are characterized by severity of disease variables through a multi-layer network. Determination of trajectory similarity accounts for direct overlaps between trajectories as well as second-order similarities, i.e., common overlap with a third set of trajectories. This work clusters trajectories across two types of layers: (a) temporal, and (b) ranges of independent outcome variable (representative of disease severity), both of which yield four distinct subtypes. The former subtypes exhibit differences in progression of disease domains (Cognitive, Mental Health etc.), whereas the latter subtypes exhibit different degrees of progression, i.e., some remain mild, whereas others show significant deterioration after 5 years. The TC approach is validated through statistical analyses and consistency of the identified subtypes with medical literature. This generalizable and robust method can easily be extended to other progressive multi-variate disease datasets, and can effectively assist in targeted subtype-specific treatment in the field of personalized medicine.

Development of machine learning-based clinical decision support system for hepatocellular carcinoma

There is a significant discrepancy between the actual choice for initial treatment option for hepatocellular carcinoma (HCC) and recommendations from the currently used BCLC staging system. We develop a machine learning-based clinical decision support system (CDSS) for recommending initial treatment option in HCC and predicting overall survival (OS). From hospital records of 1,021 consecutive patients with HCC treated at a single centre in Korea between January 2010 and October 2010, we collected information on 61 pretreatment variables, initial treatment, and survival status. Twenty pretreatment key variables were finally selected. We developed the CDSS from the derivation set (N = 813) using random forest method and validated it in the validation set (N = 208). Among the 1,021 patients (mean age: 56.9 years), 81.8% were male and 77.0% had positive hepatitis B BCLC stages 0, A, B, C, and D were observed in 13.4%, 26.0%, 18.0%, 36.6%, and 6.3% of patients, respectively. The six multi-step classifier model was developed for treatment decision in a hierarchical manner, and showed good performance with 81.0% of accuracy for radiofrequency ablation (RFA) or resection versus not, 88.4% for RFA versus resection, and 76.8% for TACE or not. We also developed seven survival prediction models for each treatment option. Our newly developed HCC-CDSS model showed good performance in terms of treatment recommendation and OS prediction and may be used as a guidance in deciding the initial treatment option for HCC.

Adaptive immune responses to SARS-CoV-2 infection in severe versus mild individuals

The global Coronavirus disease 2019 (COVID-19) pandemic caused by SARS-CoV-2 has affected more than eight million people. There is an urgent need to investigate how the adaptive immunity is established in COVID-19 patients. In this study, we profiled adaptive immune cells of PBMCs from recovered COVID-19 patients with varying disease severity using single-cell RNA and TCR/BCR V(D)J sequencing. The sequencing data revealed SARS-CoV-2-specific shuffling of adaptive immune repertories and COVID-19-induced remodeling of peripheral lymphocytes. Characterization of variations in the peripheral T and B cells from the COVID-19 patients revealed a positive correlation of humoral immune response and T-cell immune memory with disease severity. Sequencing and functional data revealed SARS-CoV-2-specific T-cell immune memory in the convalescent COVID-19 patients. Furthermore, we also identified novel antigens that are responsive in the convalescent patients. Altogether, our study reveals adaptive immune repertories underlying pathogenesis and recovery in severe versus mild COVID-19 patients, providing valuable information for potential vaccine and therapeutic development against SARS-CoV-2 infection.

Improving the accuracy of medical diagnosis with causal machine learning

Machine learning promises to revolutionize clinical decision making and diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms by determining the diseases causing them. However, existing machine learning approaches to diagnosis are purely associative, identifying diseases that are strongly correlated with a patients symptoms. We show that this inability to disentangle correlation from causation can result in sub-optimal or dangerous diagnoses. To overcome this, we reformulate diagnosis as a counterfactual inference task and derive counterfactual diagnostic algorithms. We compare our counterfactual algorithms to the standard associative algorithm and 44 doctors using a test set of clinical vignettes. While the associative algorithm achieves an accuracy placing in the top 48% of doctors in our cohort, our counterfactual algorithm places in the top 25% of doctors, achieving expert clinical accuracy. Our results show that causal reasoning is a vital missing ingredient for applying machine learning to medical diagnosis.

Causality matters in medical imaging

Causal reasoning can shed new light on the major challenges in machine learning for medical imaging: scarcity of high-quality annotated data and mismatch between the development dataset and the target environment. A causal perspective on these issues allows decisions about data collection, annotation, preprocessing, and learning strategies to be made and scrutinized more transparently, while providing a detailed categorisation of potential biases and mitigation techniques. Along with worked clinical examples, we highlight the importance of establishing the causal relationship between images and their annotations, and offer step-by-step recommendations for future studies.

Early triage of critically ill COVID-19 patients using deep learning

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.

Finding undiagnosed patients with hepatitis C infection: an application of artificial intelligence to patient claims data

Hepatitis C virus (HCV) remains a significant public health challenge with approximately half of the infected population untreated and undiagnosed. In this retrospective study, predictive models were developed to identify undiagnosed HCV patients using longitudinal medical claims linked to prescription data from approximately ten million patients in the United States (US) between 2010 and 2016. Features capturing information on demographics, risk factors, symptoms, treatments and procedures relevant to HCV were extracted from patients' medical history. Predictive algorithms were developed based on logistic regression, random forests, gradient boosted trees and a stacked ensemble. Descriptive analysis indicated that patients exhibited known symptoms of HCV on average 2-3 years prior to their diagnosis. The precision was at least 95% for all algorithms at low levels of recall (10%). For recall levels >50%, the stacked ensemble performed best with a precision of 97% compared with 87% for the gradient boosted trees and just 31% for the logistic regression. For context, the Center for Disease Control recommends screening in an at-risk sub-population with an estimated HCV prevalence of 2.23%. The artificial intelligence (AI) algorithm presented here has a precision which is substantially higher than the screening rates associated with recommended clinical guidelines, suggesting that AI algorithms have the potential to provide a step change in the effectiveness of HCV screening.

Predicting miRNA-based disease-disease relationships through network diffusion on multi-omics biological data

With critical roles in regulating gene expression, miRNAs are strongly implicated in the pathophysiology of many complex diseases. Experimental methods to determine disease related miRNAs are time consuming and costly. Computationally predicting miRNA-disease associations has potential applications in finding miRNA therapeutic pathways and in understanding the role of miRNAs in disease-disease relationships. In this study, we propose the MiRNA-disease Association Prediction (MAP) method, an in-silico method to predict and prioritize miRNA-disease associations. The MAP method applies a network diffusion approach, starting from the known disease genes in a heterogenous network constructed from miRNA-gene associations, protein-protein interactions, and gene-disease associations. Validation using experimental data on miRNA-disease associations demonstrated superior performance to two current state-of-the-art methods, with areas under the ROC curve all over 0.8 for four types of cancer. MAP is successfully applied to predict differential miRNA expression in four cancer types. Most strikingly, disease-disease relationships in terms of shared miRNAs revealed hidden disease subtyping comparable to that of previous work on shared genes between diseases, with applications for multi-omics characterization of disease relationships.

Machine learning for comprehensive forecasting of Alzheimer's Disease progression

Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Synthetic patient data generated by the CRBM accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure in the components of ADAS-Cog, and identifies sub-components associated with word recall as predictive of progression.

Insights about multi-targeting and synergistic neuromodulators in Ayurvedic herbs against epilepsy: integrated computational studies on drug-target and protein-protein interaction networks

Epilepsy, that comprises a wide spectrum of neuronal disorders and accounts for about one percent of global disease burden affecting people of all age groups, is recognised as apasmara in the traditional medicinal system of Indian antiquity commonly known as Ayurveda. Towards exploring the molecular level complex regulatory mechanisms of 63 anti-epileptic Ayurvedic herbs and thoroughly examining the multi-targeting and synergistic potential of 349 drug-like phytochemicals (DPCs) found therein, in this study, we develop an integrated computational framework comprising of network pharmacology and molecular docking studies. Neuromodulatory prospects of anti-epileptic herbs are probed and, as a special case study, DPCs that can regulate metabotropic glutamate receptors (mGluRs) are inspected. A novel methodology to screen and systematically analyse the DPCs having similar neuromodulatory potential vis-à-vis DrugBank compounds (NeuMoDs) is developed and 11 NeuMoDs are reported. A repertoire of 74 DPCs having poly-pharmacological similarity with anti-epileptic DrugBank compounds and those under clinical trials is also reported. Further, high-confidence PPI-network specific to epileptic protein-targets is developed and the potential of DPCs to regulate its functional modules is investigated. We believe that the presented schema can open-up exhaustive explorations of indigenous herbs towards meticulous identification of clinically relevant DPCs against various diseases and disorders.

[Oral cavity microbiocenosis assessment on the basis of bacterial endotoxin and plasmalogens in a saliva by method GAS-liquid chromatography-mass spectrometry.]

The concentration of plasmalogen bacterial and endotoxin levels in the saliva of patients with different severity of periodontal disease, injury prosthetic bed and with various degrees of the oral cavity microbiocenosis violations was studied. Determination of the presence of the pathological process was carried out clinically, according to the condition of periodontal tissues. The degree of microbiological disorders was assessed by the quantitative ratio of the types of microorganisms isolated from the smear taken from the gingival groove. It was found that the concentration of plasmalogen for normal microbiocenosis is not less than 0.7 µg/g. For the intermediate type of microbiocenosis, the concentration of 1.82 µg/g was determined; for dysbiosis - 5.64 µg/g, and for the expressed violation of the microbial composition accompanied by inflammatory processes - 6.54 µg/g. An increase in the concentration of bacterial endotoxin (be) more than 6.25 nanomole/g indicates the pronounced inflammatory process, regardless of the determined intensity of contamination of opportunistic gram-negative microflora.

Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers

Introduction: An increasing number of parameters can be considered when making decisions in oncology. Tumor characteristics can also be extracted from imaging through the use of radiomics and add to this wealth of clinical data. Machine learning can encompass these parameters and thus enhance clinical decision as well as radiotherapy workflow. Methods: We performed a description of machine learning applications at each step of treatment by radiotherapy in head and neck cancers. We then performed a systematic review on radiomics and machine learning outcome prediction models in head and neck cancers. Results: Machine Learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptative radiotherapy workflow automation. It may also provide new approaches for Normal Tissue Complication Probability models. Radiomics may provide additional data on tumors for improved machine learning powered predictive models, not only on survival, but also on risk of distant metastasis, in field recurrence, HPV status and extra nodal spread. However, most studies provide preliminary data requiring further validation. Conclusion: Promising perspectives arise from machine learning applications and radiomics based models, yet further data are necessary for their implementation in daily care.

From Mouth to Brain: Neuroendocrine Markers Play as a Crosstalk Among Oral and Neurodegenerative Diseases

The neuroendocrine system consists of various cells distributed in non-endocrine functional structures, able to synthesize amines and peptides with both local (paracrine) and systemic (endocrine) effects. The presence of such cells, belonging to the neuroendocrine system, is highlighted by the presence of neuroendocrine markers: the most suggestive are chromogranin A, synaptophysin, S-100B protein and glial fibrillary acidic protein. The presence of neuroendocrine markers is commonly associated to the occurrence of neuroendocrine cancers, currently representing the 0.5 percent of all malignant tumors. Nevertheless, neuroendocrine markers have been found to be overexpressed in rare oral neuroendocrine tumors, but also in quite common inflammatory conditions, such as severe periodontitis. The monitoring of neuroendocrine markers is, thus, a common factor of interest among dentistry and neurology: the analysis of neuroendocrine markers in oral diseases may be predictive and prognostic about the severity of neurological diseases, such as lateral amyotrophic sclerosis and traumatic brain injuries. The aim of this mini-review is to highlight the role of neuroendocrine molecules as advantageous diagnostic and prognostic markers for both oral diseases and neurodegenerative disorders.

Unraveling the Complexity of Amyotrophic Lateral Sclerosis Survival Prediction

Objective: The heterogeneity of amyotrophic lateral sclerosis (ALS) survival duration, which varies from <1 year to >10 years, challenges clinical decisions and trials. Utilizing data from 801 deceased ALS patients, we: (1) assess the underlying complex relationships among common clinical ALS metrics; (2) identify which clinical ALS metrics are the "best" survival predictors and how their predictive ability changes as a function of disease progression. Methods: Analyses included examination of relationships within the raw data as well as the construction of interactive survival regression and classification models (generalized linear model and random forests model). Dimensionality reduction and feature clustering enabled decomposition of clinical variable contributions. Thirty-eight metrics were utilized, including Medical Research Council (MRC) muscle scores; respiratory function, including forced vital capacity (FVC) and FVC % predicted, oxygen saturation, negative inspiratory force (NIF); the Revised ALS Functional Rating Scale (ALSFRS-R) and its activities of daily living (ADL) and respiratory sub-scores; body weight; onset type, onset age, gender, and height. Prognostic random forest models confirm the dominance of patient age-related parameters decline in classifying survival at thresholds of 30, 60, 90, and 180 days and 1, 2, 3, 4, and 5 years. Results: Collective prognostic insight derived from the overall investigation includes: multi-dimensionality of ALSFRS-R scores suggests cautious usage for survival forecasting; upper and lower extremities independently degenerate and are autonomous from respiratory decline, with the latter associating with nearer-to-death classifications; height and weight-based metrics are auxiliary predictors for farther-from-death classifications; sex and onset site (limb, bulbar) are not independent survival predictors due to age co-correlation. Conclusion: The dimensionality and fluctuating predictors of ALS survival must be considered when developing predictive models for clinical trial development or in-clinic usage. Additional independent metrics and possible revisions to current metrics, like the ALSFRS-R, are needed to capture the underlying complexity needed for population and personalized forecasting of survival.

Association of Omics Features with Histopathology Patterns in Lung Adenocarcinoma

Adenocarcinoma accounts for more than 40% of lung malignancy, and microscopic pathology evaluation is indispensable for its diagnosis. However, how histopathology findings relate to molecular abnormalities remains largely unknown. Here, we obtained H&E-stained whole-slide histopathology images, pathology reports, RNA sequencing, and proteomics data of 538 lung adenocarcinoma patients from The Cancer Genome Atlas and used these to identify molecular pathways associated with histopathology patterns. We report cell-cycle regulation and nucleotide binding pathways underpinning tumor cell dedifferentiation, and we predicted histology grade using transcriptomics and proteomics signatures (area under curve >0.80). We built an integrative histopathology-transcriptomics model to generate better prognostic predictions for stage I patients (p = 0.0182 ± 0.0021) compared with gene expression or histopathology studies alone, and the results were replicated in an independent cohort (p = 0.0220 ± 0.0070). These results motivate the integration of histopathology and omics data to investigate molecular mechanisms of pathology findings and enhance clinical prognostic prediction.

Comparative drug pair screening across multiple glioblastoma cell lines reveals novel drug-drug interactions

BACKGROUND

Glioblastoma multiforme (GBM) is the most aggressive brain tumor in adults, and despite state-of-the-art treatment, survival remains poor and novel therapeutics are sorely needed. The aim of the present study was to identify new synergistic drug pairs for GBM. In addition, we aimed to explore differences in drug-drug interactions across multiple GBM-derived cell cultures and predict such differences by use of transcriptional biomarkers.

METHODS

We performed a screen in which we quantified drug-drug interactions for 465 drug pairs in each of the 5 GBM cell lines U87MG, U343MG, U373MG, A172, and T98G. Selected interactions were further tested using isobole-based analysis and validated in 5 glioma-initiating cell cultures. Furthermore, drug interactions were predicted using microarray-based transcriptional profiling in combination with statistical modeling.

RESULTS

Of the 5 × 465 drug pairs, we could define a subset of drug pairs with strong interaction in both standard cell lines and glioma-initiating cell cultures. In particular, a subset of pairs involving the pharmaceutical compounds rimcazole, sertraline, pterostilbene, and gefitinib showed a strong interaction in a majority of the cell cultures tested. Statistical modeling of microarray and interaction data using sparse canonical correlation analysis revealed several predictive biomarkers, which we propose could be of importance in regulating drug pair responses.

CONCLUSION

We identify novel candidate drug pairs for GBM and suggest possibilities to prospectively use transcriptional biomarkers to predict drug interactions in individual cases.

What is next after the genes for autoimmunity?

Clinical pathologies draw us to envisage disease as either an independent entity or a diverse set of traits governed by common physiopathological mechanisms, prompted by environmental assaults throughout life. Autoimmune diseases are not an exception, given they represent a diverse collection of diseases in terms of their demographic profile and primary clinical manifestations. Although they are pleiotropic outcomes of non-specific disease genes underlying similar immunogenetic mechanisms, research generally focuses on a single disease. Drastic technologic advances are leading research to organize clinical genomic multidisciplinary approaches to decipher the nature of human biological systems. Once the currently costly omic-based technologies become universally accessible, the way will be paved for a cleaner picture to risk quantification, prevention, prognosis and diagnosis, allowing us to clearly define better phenotypes always ensuring the integrity of the individuals studied. However, making accurate predictions for most autoimmune diseases is an ambitious challenge, since the understanding of these pathologies is far from complete. Herein, some pitfalls and challenges of the genetics of autoimmune diseases are reviewed, and an approximation to the future of research in this field is presented.

Personalized medicine and pharmacogenetic biomarkers: progress in molecular oncology testing

In the field of oncology, clinical molecular diagnostics and biomarker discoveries are constantly advancing as the intricate molecular mechanisms that transform a normal cell into an aberrant state in concert with the dysregulation of alternative complementary pathways are increasingly understood. Progress in biomarker technology, coupled with the companion clinical diagnostic laboratory tests, continue to advance this field, where individualized and customized treatment appropriate for each individual patient define the standard of care. Here, we discuss the current commonly used predictive pharmacogenetic biomarkers in clinical oncology molecular testing: BRAF V600E for vemurafenib in melanoma; EML4-ALK for crizotinib and EGFR for erlotinib and gefitinib in non-small-cell lung cancer; KRAS against the use of cetuximab and panitumumab in colorectal cancer; ERBB2 (HER2/neu) for trastuzumab in breast cancer; BCR-ABL for tyrosine kinase inhibitors in chronic myeloid leukemia; and PML/RARα for all-trans-retinoic acid and arsenic trioxide treatment for acute promyelocytic leukemia.