RESUMEN

INTRODUCTION: Optimal management of outpatients with heart failure (HF) requires serially updating the estimates of their risk for adverse clinical outcomes to guide treatment. Patient-reported outcomes (PROs) are becoming increasingly used in clinical care. The purpose of this study was to determine whether inclusion of PROs can improve the risk prediction for HF hospitalization and death in ambulatory HF patients. METHODS: We included consecutive patients with HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF) seen in a HF clinic between 2015 and 2019 who completed PROs as part of routine care. Cox regression with a least absolute shrinkage and selection operator (LASSO) regularization and gradient boosting machine (GBM) analyses were used to estimate risk for a combined outcome of HF hospitalization, heart transplant, left ventricular assist device implantation or death. The performance of the prediction models was evaluated with the time-dependent concordance index (Cτ). RESULTS: Among 1165 patients with HFrEF (mean age 59.1±16.1, 68% male) the median follow-up was 487 days and among 456 patients with HFpEF (mean age: 64.2±16.0 years, 55% male) the median follow-up was 494 days. Gradient boosting regression that included PROs had the best prediction performance - Cτ 0.73 for patients with HFrEF and 0.74 in patients with HFpEF, and showed very good stratification of risk by time to event analysis by quintile of risk. The Kansas City Cardiomyopathy Questionnaire overall summary score (KCCQ-12 OSS), Visual Analogue Scale (VAS) and Patient Reported Outcomes Measurement Information System (PROMIS) dimensions of Satisfaction with social roles and Physical function had high variable importance measure in the models. CONCLUSIONS: PROs improve risk prediction in both HFrEF and HFpEF, independent of traditional clinical factors. Routine assessment of PROs and leveraging the comprehensive data in the electronic health record in routine clinical care could help more accurately assess risk and support the intensification of treatment in patients with HF.

RESUMEN

Protein S-palmitoylation is a reversible lipophilic posttranslational modification regulating a diverse number of signaling pathways. Within transmembrane proteins (TMPs), S-palmitoylation is implicated in conditions from inflammatory disorders to respiratory viral infections. Many small-scale experiments have observed S-palmitoylation at juxtamembrane Cys residues. However, most large-scale S-palmitoyl discovery efforts rely on trypsin-based proteomics within which hydrophobic juxtamembrane regions are likely underrepresented. Machine learning- by virtue of its freedom from experimental constraints - is particularly well suited to address this discovery gap surrounding TMP S-palmitoylation. Utilizing a UniProt-derived feature set, a gradient boosted machine learning tool (TopoPalmTree) was constructed and applied to a holdout dataset of viral S-palmitoylated proteins. Upon application to the mouse TMP proteome, 1591 putative S-palmitoyl sites (i.e. not listed in SwissPalm or UniProt) were identified. Two lung-expressed S-palmitoyl candidates (synaptobrevin Vamp5 and water channel Aquaporin-5) were experimentally assessed. Finally, TopoPalmTree was used for rational design of an S-palmitoyl site on KDEL-Receptor 2. This readily interpretable model aligns the innumerable small-scale experiments observing juxtamembrane S-palmitoylation into a proteomic tool for TMP S-palmitoyl discovery and design, thus facilitating future investigations of this important modification.

RESUMEN

Maritime operations face significant challenges in environmental stewardship, particularly in managing oil discharges from tankers as mandated by the International Convention for the Prevention of Pollution from Ships (MARPOL) Annex I, Regulation 34. Traditional Oil Discharge Monitoring Equipment (ODME) methods rely on manual decision-making, often failing to accurately identify MARPOL-defined no-go zones, estimate operation completion times, and recommend course alterations during decanting operations. This study introduces a novel approach by integrating advanced machine learning techniques-Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM)-to enhance ODME operations. Specifically, these models automate the identification of no-go zones and optimize operational decisions, leading to a 99 % accuracy rate in compliance with MARPOL regulations and an operational time estimation error margin of <1 %. Unlike traditional methods, our approach leverages large datasets and real-time GPS (Global Positioning System) data, significantly reducing human error and enhancing both environmental compliance and operational efficiency. To our knowledge, this is the first study to specifically address the application of machine learning to decanting operations under MARPOL Annex I, marking a significant advancement in maritime environmental management.

RESUMEN

Objective: Readmission to the coronary care unit (CCU) has significant implications for patient outcomes and healthcare expenditure, emphasizing the urgency to accurately identify patients at high readmission risk. This study aims to construct and externally validate a predictive model for CCU readmission using machine learning (ML) algorithms across multiple hospitals. Methods: Patient information, including demographics, medical history, and laboratory test results were collected from electronic health record system and contributed to a total of 40 features. Five ML models: logistic regression, random forest, support vector machine, gradient boosting, and multilayer perceptron were employed to estimate the readmission risk. Results: The gradient boosting model was selected demonstrated superior performance with an area under the receiver operating characteristic curve (AUC) of 0.887 in the internal validation set. Further external validation in hold-out test set and three other medical centers upheld the model's robustness with consistent high AUCs, ranging from 0.852 to 0.879. Conclusion: The results endorse the integration of ML algorithms in healthcare to enhance patient risk stratification, potentially optimizing clinical interventions, and diminishing the burden of CCU readmissions.

RESUMEN

Heyndrickxia coagulans (formerly Bacillus coagulans) has been increasingly utilized as an immunomodulatory probiotics. Oral administration of H. coagulans HOM5301 significantly boosted both innate and adaptive immunity in mice, particularly by increasing the phagocytic capacity of monocytes/macrophages. Lipoteichoic acid (LTA), a major microbe-associated molecular pattern (MAMP) in Gram-positive bacteria, exhibits differential immunomodulatory effects due to its structural heterogeneity. We extracted, purified, and characterized LTA from H. coagulans HOM5301. The results showed that HOM5301 LTA consists of a glycerophosphate backbone. Its molecular weight is in the range of 10-16 kDa. HOM5301 LTA induced greater productions of nitric oxide, TNFα, and IL-6 in RAW 264.7 macrophages compared to Staphylococcus aureus LTA. Comparative transcriptome and proteome analyses identified the differentially expressed genes and proteins triggered by HOM5301 LTA. KEGG analyses revealed that HOM5301 LTA transcriptionally and translationally activated macrophages through two immune-related pathways: cytokine-cytokine receptor interaction and phagosome formation. Protein-protein interaction network analysis indicated that the pro-inflammatory response elicited by HOM5301 LTA was TLR2-dependent, possibly requiring the coreceptor CD14, and is mediated via the MAPK and NF-kappaB pathways. Our results demonstrate that LTA is an important MAMP of H. coagulans HOM5301 that boosts immune responses, suggesting that HOM5301 LTA may be a promising immunoadjuvant.

Asunto(s)

RESUMEN

This study presents a comparative analysis of various Machine Learning (ML) techniques for predicting water consumption using a comprehensive dataset from Kocaeli Province, Turkey. Accurate prediction of water consumption is crucial for effective water resource management and planning, especially considering the significant impact of the COVID-19 pandemic on water usage patterns. A total of four ML models, Artificial Neural Networks (ANN), Random Forest (RF), Support Vector Machines (SVM), and Gradient Boosting Machines (GBM), were evaluated. Additionally, optimization techniques such as Particle Swarm Optimization (PSO) and the Second-Order Optimization (SOO) Levenberg-Marquardt (LM) algorithm were employed to enhance the performance of the ML models. These models incorporate historical data from previous months to enhance model accuracy and generalizability, allowing for robust predictions that account for both short-term fluctuations and long-term trends. The performance of each model was assessed using cross-validation. The R2 and correlation values obtained in this study for the best-performing models are highlighted in the results section. For instance, the GBM model achieved an R2 value of 0.881, indicating a strong capability in capturing the underlying patterns in the data. This study is one of the first to conduct a comprehensive analysis of water consumption prediction using machine learning algorithms on a large-scale dataset of 5000 subscribers, including the unique conditions imposed by the COVID-19 pandemic. The results highlight the strengths and limitations of each technique, providing insights into their applicability for water consumption prediction. This study aims to enhance the understanding of ML applications in water management and offers practical recommendations for future research and implementation.

RESUMEN

INTRODUCTION: The FLAME trial demonstrated that the dose to the gross tumor volume (GTV) is associated with tumour control in prostate cancer patients. This raises the question if dose de-escalation to the remaining prostate gland can be considered. Therefore, we investigated if intraprostatic recurrences occur at the location of the GTV and which dose was delivered at that location. MATERIALS AND METHODS: For FLAME trial patients with an intra-prostatic recurrence, we collected pre-treatment images, GTV delineations, dose distributions and post-recurrence images. Pre-treatment images were registered to the post-recurrence images (PSMA-PET CT). An overlap between GTV and PSMA-PET activity was considered an intra-prostatic recurrence at the location of the primary tumor. RESULTS: Twenty eight out of 535 patients in the FLAME trial had an intra-prostatic recurrence. Its location could be determined for 24 patients. One patient recurred in the prostate gland outside the GTV. The median D98% to the GTV was 76.5 Gy (range: 73.3-86.5 Gy). Only one patient with a recurrence in the GTV received a substantial focal boost of 86.5 Gy. The D98% of all remaining patients was < 81 Gy. CONCLUSION: Intra-prostatic recurrences of intermediate- and high-risk prostate cancer patients treated with radiotherapy appeared predominantly at the location of the primary tumor. All but one patient did not receive a high dose to the GTV. Intra-prostatic failure is likely a consequence of the undertreatment of the primary tumor rather than the undertreatment of the remaining prostate gland.

RESUMEN

Traumatic experiences have the potential to give rise to post-traumatic stress disorder (PTSD), a debilitating psychiatric condition associated with impairments in both social and occupational functioning. There has been great interest in utilizing machine learning approaches to predict the development of PTSD in trauma patients from clinician assessment or survey-based psychological assessments. However, these assessments require a large number of questions, which is time consuming and not easy to administer. In this paper, we aim to predict PTSD development of patients 3 months post-trauma from multiple survey-based assessments taken within 2 weeks post-trauma. Our objective is to minimize the number of survey questions that patients need to answer while maintaining the prediction accuracy from the full surveys. We formulate this as a feature selection problem and consider 4 different feature selection approaches. We demonstrate that it is possible to achieve up to 72% accuracy for predicting the 3-month PTSD diagnosis from 10 survey questions using a mean decrease in impurity-based feature selector followed by a gradient boosting classifier.

RESUMEN

BACKGROUND: Genome DNA methylation profiling is a promising yet costly method for cancer classification, involving substantial data. We developed an ensemble learning model to identify cancer types using methylation profiles from a limited number of CpG sites. METHODS: Analyzing methylation data from 890 samples across 10 cancer types from the TCGA database, we utilized ANOVA and Gain Ratio to select the most significant CpG sites, then employed Gradient Boosting to reduce these to just 100 sites. RESULTS: This approach maintained high accuracy across multiple machine learning models, with classification accuracy rates between 87.7% and 93.5% for methods including Extreme Gradient Boosting, CatBoost, and Random Forest. This method effectively minimizes the number of features needed without losing performance, helping to classify primary organs and uncover subgroups within specific cancers like breast and lung. CONCLUSIONS: Using a gradient boosting feature selector shows potential for streamlining methylation-based cancer classification.

RESUMEN

Acute lung injury (ALI) is a serious adverse event in the management of acute type A aortic dissection (ATAAD). Using a large-scale cohort, we applied artificial intelligence-driven approach to stratify patients with different outcomes and treatment responses. A total of 2,499 patients from China 5A study database (2016-2022) from 10 cardiovascular centers were divided into 70% for derivation cohort and 30% for validation cohort, in which extreme gradient boosting algorithm was used to develop ALI risk model. Logistic regression was used to assess the risk under anti-inflammatory strategies in different risk probability. Eight top features of importance (leukocyte, platelet, hemoglobin, base excess, age, creatinine, glucose, and left ventricular end-diastolic dimension) were used to develop and validate an ALI risk model, with adequate discrimination ability regarding area under the receiver operating characteristic curve of 0.844 and 0.799 in the derivation and validation cohort, respectively. By the individualized treatment effect prediction, ulinastatin use was significantly associated with significantly lower risk of developing ALI (odds ratio [OR] 0.623 [95% CI 0.456, 0.851]; P = 0.003) in patients with a predicted ALI risk of 32.5-73.0%, rather than in pooled patients with a risk of <32.5 and >73.0% (OR 0.929 [0.682, 1.267], P = 0.642) (Pinteraction = 0.075). An artificial intelligence-driven risk stratification of ALI following ATAAD surgery were developed and validated, and subgroup analysis showed the heterogeneity of anti-inflammatory pharmacotherapy, which suggested individualized anti-inflammatory strategies in different risk probability of ALI.

RESUMEN

BACKGROUND: Accurately predicting the walking independence of stroke patients is important. Our objective was to determine and compare the performance of logistic regression (LR) and three machine learning models (eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest (RF)) in predicting walking independence at discharge in stroke patients, as well as to explore the variables that predict prognosis. METHODS: 778 (80% for the training set and 20% for the test set) stroke patients admitted to China Rehabilitation Research Center between February 2020 and January 2023 were retrospectively included. The training set was used for training models. The test set was used to validate and compare the performance of the four models in terms of area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: Among the three ML models, the AUC of the XGBoost model is significantly higher than that of the SVM and RF models (P < 0.001, P = 0.024, respectively). There was no significant difference in the AUCs between the XGBoost model and the LR model (0.891 vs. 0.880, P = 0.560). The XGBoost model demonstrated superior accuracy (87.82% vs. 86.54%), sensitivity (50.00% vs. 39.39%), PPV (73.68% vs. 73.33%), NPV (89.78% vs. 87.94%), and F1 score (59.57% vs. 51.16%), with only slightly lower specificity (96.09% vs. 96.88%). Together, the XGBoost model and the stepwise LR model identified age, FMA-LE at admission, FAC at admission, and lower limb spasticity as key factors influencing independent walking. CONCLUSION: Overall, the XGBoost model performed best in predicting independent walking after stroke. The XGBoost and LR models together confirm that age, admission FMA-LE, admission FAC, and lower extremity spasticity are the key factors influencing independent walking in stroke patients at hospital discharge. TRIAL REGISTRATION: Not applicable.

Asunto(s)

RESUMEN

Antimicrobial resistance (AMR) is a major threat to public health worldwide. It is a promising way to improve appropriate prescription by the review and stewardship of antimicrobials, and Post-Prescription Review (PPR) is currently the main tool used in hospitals. Existing methods of PPR typically focus on the dichotomy of antimicrobial prescription based on binary classification which, however, is usually a multi-label classification problem. Moreover, previous research did not explain the causes beneath the inappropriate antimicrobial used in the clinical setting, which could be practically important for problem location and decision improvement. In this paper, we collected antimicrobial prescriptions and related data from clean surgery in a hospital in northeastern China, and proposed a Multi-label Antimicrobial Post-Prescription Review System (MAPRS). MAPRS first uses NLP techniques to process unstructured data in prescriptions and explores the value of clinical record text for solving medical problems. Then, Classifier Chains are used to deal with multi-label problems and fused with machine learning algorithms to construct a classifier. At last, a SHAP explanation module is introduced to explain the inappropriate prescriptions. The experimental results show that MAPRS could achieve great performance in a challenging six-category multi-label task, with a subset accuracy of 90.7 % and an average AUROC of 94.3 %. Our results can help hospitals to perform intelligent prescription review and improve the antimicrobial stewardship.

RESUMEN

Refactoring is a well-established topic in contemporary software engineering, focusing on enhancing software's structural design without altering its external behavior. Commit messages play a vital role in tracking changes to the codebase. However, determining the exact refactoring required in the code can be challenging due to various refactoring types. Prior studies have attempted to classify refactoring documentation by type, achieving acceptable results in accuracy, precision, recall, F1-Score, and other performance metrics. Nevertheless, there is room for improvement. To address this, we propose a novel approach using four ensemble Machine Learning algorithms to detect refactoring types. Our experimentation utilized a dataset containing 573 commits, with text cleaning and preprocessing applied to address data imbalances. Various techniques, including hyperparameter optimization, feature engineering with TF-IDF and bag-of-words, and binary transformation using one-vs-one and one-vs-rest classifiers, were employed to enhance accuracy. Results indicate that the experiment involving feature engineering using the TF-IDF technique outperformed other methods. Notably, the XGBoost algorithm with the same technique achieved superior performance across all metrics, attaining 100% accuracy. Moreover, our results surpass the current state-of-the-art performance using the same dataset. Our proposed approach bears significant implications for software engineering, particularly in enhancing the internal quality of software.

RESUMEN

BACKGROUND: Understanding the factors contributing to mental well-being in youth is a public health priority. Self-reported enthusiasm for the future may be a useful indicator of well-being and has been shown to forecast social and educational success. Typically, cross-domain measures of ecological and health-related factors with relevance to public policy and programming are analyzed either in isolation or in targeted models assessing bivariate interactions. Here, we capitalize on a large provincial data set and machine learning to identify the sociodemographic, experiential, behavioral, and other health-related factors most strongly associated with levels of subjective enthusiasm for the future in a large sample of elementary and secondary school students. OBJECTIVE: The aim of this study was to identify the sociodemographic, experiential, behavioral, and other health-related factors associated with enthusiasm for the future in elementary and secondary school students using machine learning. METHODS: We analyzed data from 13,661 participants in the 2019 Ontario Student Drug Use and Health Survey (OSDUHS) (grades 7-12) with complete data for our primary outcome: self-reported levels of enthusiasm for the future. We used 50 variables as model predictors, including demographics, perception of school experience (i.e., school connectedness and academic performance), physical activity and quantity of sleep, substance use, and physical and mental health indicators. Models were built using a nonlinear decision tree-based machine learning algorithm called extreme gradient boosting to classify students as indicating either high or low levels of enthusiasm. Shapley additive explanations (SHAP) values were used to interpret the generated models, providing a ranking of feature importance and revealing any nonlinear or interactive effects of the input variables. RESULTS: The top 3 contributors to higher self-rated enthusiasm for the future were higher self-rated physical health (SHAP value=0.62), feeling that one is able to discuss problems or feelings with their parents (SHAP value=0.49), and school belonging (SHAP value=0.32). Additionally, subjective social status at school was a top feature and showed nonlinear effects, with benefits to predicted enthusiasm present in the mid-to-high range of values. CONCLUSIONS: Using machine learning, we identified key factors related to self-reported enthusiasm for the future in a large sample of young students: perceived physical health, subjective school social status and connectedness, and quality of relationship with parents. A focus on perceptions of physical health and school connectedness should be considered central to improving the well-being of youth at the population level.

Asunto(s)

RESUMEN

The global impact of the ongoing COVID-19 pandemic, while somewhat contained, remains a critical challenge that has tested the resilience of humanity. Accurate and timely prediction of COVID-19 transmission dynamics and future trends is essential for informed decision-making in public health. Deep learning and mathematical models have emerged as promising tools, yet concerns regarding accuracy persist. This research suggests a novel model for forecasting the COVID-19's future trajectory. The model combines the benefits of machine learning models and mathematical models. The SIRVD model, a mathematical based model that depicts the reach of the infection via population, serves as basis for the proposed model. A deep prediction model for COVID-19 using XGBoost-SIRVD-LSTM is presented. The suggested approach combines Susceptible-Infected-Recovered-Vaccinated-Deceased (SIRVD), and a deep learning model, which includes Long Short-Term Memory (LSTM) and other prediction models, including feature selection using XGBoost method. The model keeps track of changes in each group's membership over time. To increase the SIRVD model's accuracy, machine learning is applied. The key properties for forecasting the spread of the infection are found using a method called feature selection. Then, in order to learn from these features and create predictions, a model involving deep learning is applied. The performance of the model proposed was assessed with prediction metrics such as R 2, root mean square error (RMSE), mean absolute percentage error (MAPE), and normalized root mean square error (NRMSE). The results are also validated to those of other prediction models. The empirical results show that the suggested model outperforms similar models. Findings suggest its potential as a valuable tool for pandemic management and public health decision-making.

RESUMEN

Granular activated carbon (GAC) adsorption is frequently used to remove recalcitrant organic micropollutants (MPs) from water. The overarching aim of this research was to develop machine learning (ML) models to predict GAC performance from adsorbent, adsorbate, and background water matrix properties. For model calibration, MP breakthrough curves were compiled and analyzed to determine the bed volumes of water that can be treated until MP breakthrough reaches ten percent of the influent MP concentration (BV10). Over 400 data points were split into training, validation, and testing sets. Seventeen variables describing MP, background water matrix, and GAC properties were explored in ML models to predict log10-transformed BV10 values. Using the ML models on the testing set, predicted BV10 values exhibited mean absolute errors of ∼0.12 log units and were highly correlated with experimentally determined values (R2 ≥ 0.88). The top three drivers influencing BV10 predictions were the air-hexadecane partition coefficient and hydrogen bond acidity (Abraham parameters L and A) of the MPs and the dissolved organic carbon concentration of the GAC influent water. The model can be used to rapidly estimate the GAC bed life, select effective GAC products for a given treatment scenario, and explore the suitability of GAC treatment for remediating emerging MPs.

RESUMEN

Accurate crop yield predictions are crucial for farmers and policymakers. Despite the widespread use of ensemble machine learning (ML) models in computer science, their application in crop yield prediction remains relatively underexplored. This study, conducted in Canada, aims to assess the potential of five distinct ensemble ML models-Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), XGBoost, LightGBM, and Random Forest (RF)-in predicting crop yields chosen for their ability to manage complex datasets and their strong performance potential. The study integrated various factors, including climate variables, satellite-derived vegetation indices, soil characteristics, and honeybee census data. Data preparation comprised two main steps: first, climate variables were interpolated and averaged for croplands in ArcGIS Pro, along with averaging vegetation indices and soil characteristics. Honeybee census data was also incorporated. Second, the data was organized in Python to create a structured format for models' input. The models' accuracy was assessed using Root Mean Squared Error (RMSE), R-squared, and Mean Absolute Error (MAE). XGBoost emerged as the most accurate model, with the lowest MAE (68.70 for canola and 39.47 for soybeans), lowest RMSE (119.48 for canola and 102.39 for soybeans), and highest R-squared values (0.95 for canola and 0.96 for soybeans) on the test dataset. The study also assessed crop yields under various climate change scenarios, finding minimal variations across the scenarios, but significant negative impacts on canola and soybean yields across Canada. Honeybee colonies were identified as the most influential factor on crop yields, contributing 52.34 % to canola and 57.18 % to soybean yields. This research provides detailed crop yield maps of canola and soybeans at the Census Consolidated Subdivisions (CCS) level across Canada's agricultural landscape, offering valuable forecasts for localized decision-making. Additionally, it offers a proactive strategy for climate change preparedness, assisting farmers and stakeholders optimise resource allocation and manage risks effectively.

Asunto(s)

RESUMEN

Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission. METHODS: The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence. RESULTS: The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were:'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'. CONCLUSIONS: The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

Asunto(s)

RESUMEN

Current medical research has been demonstrating the roles of miRNAs in a variety of cellular mechanisms, lending credence to the association between miRNA dysregulation and multiple diseases. Understanding the mechanisms of miRNA is critical for developing effective diagnostic and therapeutic strategies. miRNA-mRNA interactions emerge as the most important mechanism to be understood despite their experimental validation constraints. Accordingly, several computational models have been developed to predict miRNA-mRNA interactions, albeit presenting limited predictive capabilities, poor characterisation of miRNA-mRNA interactions, and low usability. To address these drawbacks, we developed PRIMITI, a PRedictive model for the Identification of novel miRNA-Target mRNA Interactions. PRIMITI is a novel machine learning model that utilises CLIP-seq and expression data to characterise functional target sites in 3'-untranslated regions (3'-UTRs) and predict miRNA-target mRNA repression activity. The model was trained using a reliable negative sample selection approach and the robust extreme gradient boosting (XGBoost) model, which was coupled with newly introduced features, including sequence and genetic variation information. PRIMITI achieved an area under the receiver operating characteristic (ROC) curve (AUC) up to 0.96 for a prediction of functional miRNA-target site binding and 0.96 for a prediction of miRNA-target mRNA repression activity on cross-validation and an independent blind test. Additionally, the model outperformed state-of-the-art methods in recovering miRNA-target repressions in an unseen microarray dataset and in a collection of validated miRNA-mRNA interactions, highlighting its utility for preliminary screening. PRIMITI is available on a reliable, scalable, and user-friendly web server at https://biosig.lab.uq.edu.au/primiti.

RESUMEN

Applying machine-learning techniques for imbalanced data sets presents a significant challenge in materials science since the underrepresented characteristics of minority classes are often buried by the abundance of unrelated characteristics in majority of classes. Existing approaches to address this focus on balancing the counts of each class using oversampling or synthetic data generation techniques. However, these methods can lead to loss of valuable information or overfitting. Here, we introduce a deep learning framework to predict minority-class materials, specifically within the realm of metal-insulator transition (MIT) materials. The proposed approach, termed boosting-CGCNN, combines the crystal graph convolutional neural network (CGCNN) model with a gradient-boosting algorithm. The model effectively handled extreme class imbalances in MIT material data by sequentially building a deeper neural network. The comparative evaluations demonstrated the superior performance of the proposed model compared to other approaches. Our approach is a promising solution for handling imbalanced data sets in materials science.