Machine Learning Classifiers Research Articles

Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning.

This study aimed to utilize MR radiomics-based machine learning classifiers on a large-sample, multicenter dataset to develop an optimal model for predicting malignant sinonasal tumors and tumor-like lesions. This study included 1711 adult patients (875 benign and 836 malignant) with sinonasal tumors or tumor-like lesions from three institutions. Patients from institution 1 (n = 1367) constituted both the training and validation cohorts, while those from institution 2 and 3 (n = 158/186) made up the test cohorts. Manual segmentation of the region of interest of the tumor was performed on T1WI, T2WI, and contrast-enhanced T1WI (CE-T1WI). Data normalization, dimensional reductions, feature selection, and classifications were performed using ten machine-learning classifiers. Four fusion models, namely T1WI + T2WI, T1WI + CE-T1WI, T2WI + CE-T1WI, and T1WI + T2WI + CE-T1WI, were constructed using the top ten features with the highest contribution in feature selection in the optimal models of T1WI, T2WI, and CE-T1WI. The Delong test compared areas under the curve (AUC) between models. The AUCs of training/validation/test1/test2 datasets for T1WI, T2WI, and CE-T1WI were 0.900/0.842/0.872/0.839, 0.876/0.789/0.842/0.863, and 0.899/0.824/0.831/0.707, respectively. The fusion model from T1WI + T2WI + CE-T1WI had the highest AUC. The AUCs of training/validation/test1/test2 datasets were 0.947/0.849/0.871/0.887. The T1WI + T2WI + CE-T1WI model demonstrated a significantly higher AUC than the T2WI + CE-T1WI model in both cohorts (p < 0.05) and outperformed the T2WI model in test 1 (p = 0.008) and the T1WI model in test 2 (p = 0.006). This fusion model based on radiomics from T1WI + T2WI + CE-T1WI images and machine learning can improve the power in predicting malignant sinonasal tumors with high accuracy, resilience, and robustness. Our study proposes a radiomics-based machine learning fusion model from T1- and T2-weighted images and contrast-enhanced T1-weighted images, which can non-invasively identify the nature of sinonasal tumors and improve the performance in predicting malignant sinonasal tumors. Differentiating benign and malignant sinonasal tumors is difficult due to similar clinical presentations. A radiomics model from T1 + T2 + contrast-enhanced T1 images can identify the nature of sinonasal tumors. This model can help distinguish benign and malignant sinonasal tumors.

Unsupervised machine learning classification for accelerating FE[formula omitted] multiscale fracture simulations

An approach is proposed to accelerate multiscale simulations of heterogeneous quasi-brittle materials exhibiting an anisotropic damage response. The present technique uses unsupervised machine learning classification based on k-means clustering to select integration points in the macro mesh within an FE2 strategy to track redundant micro nonlinear problems and to avoid unnecessary Representative Volume Element (RVE) calculations. More specifically, a classification vector including strains and internal damage variables is defined for each macro integration point. The macro internal damage variables are constructed using harmonic analysis of damage. At each step of the macro iterations, the integrations points are grouped into clusters and only one nonlinear problem is solved for each cluster. As a result, the computations are accelerated within an FE2 scheme by reducing the total number of RVE problems to be solved. The developed algorithm includes a macro regularization and an arc-length technique to capture macro snap-back due to the softening. Applications are proposed to simulate the response of different heterogeneous quasi-brittle materials with strong anisotropic responses. speed-up factors of the order of 12 to 15 can be achieved without the need to build a database, and without reduced-order modeling approximations at the micro level. Estimates of structural strength can be obtained with Speed-up factors between 45 and 85.

Movements classification system for transhumeral amputees using myoelectric signals

The extent of loss of functionality in people with transhumeral amputation or elbow disarticulation is considered highly compromised. The person with this impairment loses the primary muscle involved in the movement of the hand and fingers, and the elbow flexion/extension. In this sense, the development of myoelectric prostheses must include mechanisms that replicate these movements. Moreover, the control system for controlling a prosthesis must be robust and intuitive, where pattern recognition and artificial intelligence techniques represent an important and increasingly explored alternative. This study aims to develop a movement intention classification system based on myoelectric signals (MES) obtained from an elbow disarticulation amputee. Different features were extracted from the MES as the Mean absolute value (MAV), zero crossings (ZC), slope sign changes (SSC), waveform length (WL), and autoregressive (AR) coefficients. Machine learning classifiers (Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forests (RF), and Multilayer Perceptron (MLP)) were used to predict seven gestures: elbow flexion (EF), elbow extension (EE), forearm pronation (FP), forearm supination (FS), hand opening (HO), hand closing (HC), and rest (R). The results obtained with LDA, QDA, KNN, MLP, SVM, and RF were 60.84%, 71.05%, 77.10%, 78.06%, 78.57%, and 79.72% of accuracy, respectively. These results are promising and will allow the development of a myoelectric prosthesis control system for people with transhumeral amputation or elbow disarticulation.

Obfuscated Computer Malware Classification Based on Significant Opcode

Computer malware has greatly impacted the computer network securities and even personal computer users. Signature-based detection is incapable to recognize the obfuscated computer malware since it is being covered by the obfuscation techniques. Therefore, machine learning is being explored and equipped in the malware detection to withstand the threaten of malware. In fact, there are many features available, i.e., text string to be implemented for malware classification. Nevertheless, opcode could be one of the features owing to its relative smaller data size compared to the text string. In this research, the significant opcodes of executable malware files which referring to the prevalent content from malware-to-malware generation are extracted as training dataset. Several machine learning classifiers are generated and compared in terms of classification accuracy and speed, as well as the comparison is done with text string-based detection and signature-based detection. From the finding, it is shown that machine learning detection performs more than 2 times better than signature based and machine learning generated based-on significant opcode features is able to detect obfuscated malware over 10 times faster than text string feature and still achieve up to 98% of accuracy.

CT-based radiomics for predicting breast cancer radiotherapy side effects

Skin inflammation with the potential sequel of moist epitheliolysis and edema constitute the most frequent breast radiotherapy (RT) acute side effects. The aim of this study was to compare the predictive value of tissue-derived radiomics features to the total breast volume (TBV) for the moist cells epitheliolysis as a surrogate for skin inflammation, and edema. Radiomics features were extracted from computed tomography (CT) scans of 252 breast cancer patients from two volumes of interest: TBV and glandular tissue (GT). Machine learning classifiers were trained on radiomics and clinical features, which were evaluated for both side effects. The best radiomics model was a least absolute shrinkage and selection operator (LASSO) classifier, using TBV features, predicting moist cells epitheliolysis, achieving an area under the receiver operating characteristic (AUROC) of 0.74. This was comparable to TBV breast volume (AUROC of 0.75). Combined models of radiomics and clinical features did not improve performance. Exclusion of volume-correlated features slightly reduced the predictive performance (AUROC 0.71). We could demonstrate the general propensity of planning CT-based radiomics models to predict breast RT-dependent side effects. Mammary tissue was more predictive than glandular tissue. The radiomics features performance was influenced by their high correlation to TBV volume.

Good results from sensor data: Performance of machine learning algorithms for regression problems in chemical sensors

Accurately predicting unseen data, instead of mere memorization of training examples, is a critical goal of machine learning. This generalization is particularly important in the field of chemical sensors, where the ability to accurately predict the chemical properties or concentration levels of unknown samples is crucial. The paper presents a comprehensive yet accessible introduction to various machine learning concepts, highlighting the importance of model interpretability and generalization in ensuring reliable and accurate results in this context. Nonlinear sensor array data are utilized to introduce key concepts (e.g., bias-variance tradeoff) and techniques (linear models, partial least squares regression, support vector machines, k-nearest neighbors, decision trees, ensemble methods, automated machine learning, symbolic regression, and artificial neural networks), providing a solid foundation to make informed decisions when selecting machine learning techniques for sensor-specific regression applications. The results clearly indicate a number of conclusions. First, overparameterized deep feedforward neural networks show great accuracy and generalization when trained on a sufficiently large dataset. Second, symbolic regression models proved to be more accurate than deep feedforward neural networks and classical machine learning techniques on smaller datasets. Third, the performance of various machine learning models was dataset-dependent, showing the importance of comparative studies to determine the most suitable approach. It is clear that the optimal model cannot be known a priori. This paper aims to provide a starting point for investigations on the performance of different machine learning techniques in chemical sensor applications.

Leveraging artificial intelligence to identify the psychological factors associated with conspiracy theory beliefs online

Given the profound societal impact of conspiracy theories, probing the psychological factors associated with their spread is paramount. Most research lacks large-scale behavioral outcomes, leaving factors related to actual online support for conspiracy theories uncertain. We bridge this gap by combining the psychological self-reports of 2506 Twitter (currently X) users with machine-learning classification of whether the textual data from their 7.7 million social media engagements throughout the pandemic supported six common COVID-19 conspiracy theories. We assess demographic factors, political alignment, factors derived from theory of reasoned action, and individual psychological differences. Here, we show that being older, self-identifying as very left or right on the political spectrum, and believing in false information constitute the most consistent risk factors; denialist tendencies, confidence in one’s ability to spot misinformation, and political conservativism are positively associated with support for one conspiracy theory. Combining artificial intelligence analyses of big behavioral data with self-report surveys can effectively identify and validate risk factors for phenomena evident in large-scale online behaviors.

A Novel Hierarchical Clustering Sequential Forward Feature Selection Method for Paddy Rice Agriculture Mapping Based on Time-Series Images

Timely and accurate mapping of rice distribution is crucial to estimate yield, optimize agriculture spatial patterns, and ensure global food security. Feature selection (FS) methods have significantly improved computational efficiency by reducing redundancy in spectral and temporal feature sets, playing a vital role in identifying and mapping paddy rice. However, the optimal feature sets selected by existing methods suffer from issues such as information redundancy or local optimality, limiting their accuracy in rice identification. Moreover, the effects of these FS methods on rice recognition in various machine learning classifiers and regions with different climatic conditions and planting structures is still unclear. To overcome these limitations, we conducted a comprehensive evaluation of the potential applications of major FS methods, including the wrapper method, embedded method, and filter method for rice mapping. A novel hierarchical lustering sequential forward selection (HCSFS) method for precisely extracting the optimal feature set for rice identification is proposed. The accuracy of the HCSFS and other FS methods for rice identification was tested with nine common machine learning classifiers. The results indicated that, among the three FS methods, the wrapper method achieved the best rice mapping performance, followed by the embedded method, and lastly, the filter method. The new HCSFS significantly reduced redundant features compared with eleven typical FS methods, demonstrating higher precision and stability, with user accuracy and producer accuracy exceeding 0.9548 and 0.9487, respectively. Additionally, the spatial distribution of rice maps generated using the optimal feature set selected by HCSFS closely aligned with actual planting patterns, markedly outperforming existing rice products. This research confirms the effectiveness and transferability of the HCSFS method for rice mapping across different climates and cultivation structures, suggesting its enormous potential for classifying other crops using time-series remote sensing images.

Utilizing multiclassifier radiomics analysis of ultrasound to predict high axillary lymph node tumour burden in node-positive breast cancer patients: a multicentre study

Background The tumor burden within the axillary lymph nodes (ALNs) constitutes a pivotal factor in breast cancer, serving as the primary determinant for treatment decisions and exhibiting a close correlation with prognosis. Objective This study aimed to investigate the potential of ultrasound-based radiomics and clinical characteristics in non-invasively distinguishing between low tumor burden (1-2 positive nodes) and high tumor burden (more than 2 positive nodes) in patients with node-positive breast cancer. Methods A total of 215 patients with node-positive breast cancer, who underwent preoperative ultrasound examinations, were enrolled in this study. Among these patients, 144 cases were allocated to the training set, 37 cases to the validation set, and 34 cases to the testing set. Postoperative histopathology was used to determine the status of ALN tumor burden. The region of interest for breast cancer was delineated on the ultrasound image. Nine models were developed to predict high ALN tumor burden, employing a combination of three feature screening methods and three machine learning classifiers. Ultimately, the optimal model was selected and tested on both the validation and testing sets. In addition, clinical characteristics were screened to develop a clinical model. Furthermore, Shapley additive explanations (SHAP) values were utilized to provide explanations for the machine learning model. Results During the validation and testing sets, the models demonstrated area under the curve (AUC) values ranging from 0.577 to 0.733 and 0.583 to 0.719, and accuracies ranging from 64.9% to 75.7% and 64.7% to 70.6%, respectively. Ultimately, the Boruta_XGB model, comprising five radiomics features, was selected as the final model. The AUC values of this model for distinguishing low from high tumor burden were 0.828, 0.715, and 0.719 in the training, validation, and testing sets, respectively, demonstrating its superiority over the clinical model. Conclusions The developed radiomics models exhibited a significant level of predictive performance. The Boruta_XGB radiomics model outperformed other radiomics models in this study.

Optimizing machine learning algorithms for diabetes data: A metaheuristic approach to balancing and tuning classifiers parameters

Diabetes mellitus poses a global health concern, prompting the development of machine learning algorithms designed to construct a model for the accurate classification of patients, enabling precise diagnoses and early-stage treatment. However, the efficacy of classifying diabetes patients through machine learning relies on datasets, often plagued by imbalance, leading to biased classification and inaccurate diagnoses. Previous research attempts, employing techniques like random sampling (under-sampling and oversampling) and the Synthetic Minority Oversampling Technique (SMOTE), have struggled to achieve optimally balanced datasets. Additionally, setting the best parameters for machine learning classifiers remains a challenging task. To address these issues, this research focuses on devising a methodological metaheuristic optimization, a machine learning algorithm tailored for diabetes data balancing, and classifier hyperparameter tuning. Leveraging Particle Swarm Optimization (PSO) algorithm for diabetes data balancing and a genetic algorithm to select the optimal architecture for various machine learning classifiers. The study compares the performance of the proposed metaheuristic data balancer and classifier architecture parameter tuner using classification metrics (F1 score, Average Precision–Recall (APR), AUC, and accuracy). The PSO balanced dataset emerges as the most effective in classifying diabetes, with an Average Percentage Improvement (API) in classification performance metrics: 20.78% accuracy, 16.79% area under the curve for receiver operating characteristics, and a significant 32.78% enhancement in APR. Moreover, the XGBOOST classifier trained with a genetic algorithm demonstrates minimal computational training time for the Centre for Disease Control and Prevention (CDC) diabetes dataset compared to the artificial neural network and random forest classifier. Notably, the imbalanced CDC diabetes dataset exhibits the least APR compared to random under-sampling and the PSO data balancing technique.

Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia

ABSTRACT Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements and computational expenses. As an alternative solution, this paper explores the use of machine learning (ML) techniques to map flood hazards based on readily available geo-environmental variables. We employed various ML classifiers, including decision tree (DT), random forest (RF), XGBoost (XGB), and k-nearest neighbor (kNN), to assess their performance in flood hazard mapping. Model evaluation was conducted using the area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). Our results demonstrated promising outcomes, with AUC values of 93% (DT), 97% (RF), 98% (XGB), and 91% (kNN) for the validation dataset. RF and XGB have slightly higher performance than DT and kNN and distance to river was the most important factor. The study highlights the potential of ML for urban flood modeling, offering reasonable accuracy and supporting early warning systems. By leveraging available geo-environmental variables, ML techniques provide valuable insights into flood hazard mapping, aiding in effective urban planning and disaster management strategies.

METAPLANTCODE: Harmonizing Plant Metabarcoding Pipelines in Europe

The METAPLANTCODE project is dedicated to advancing and optimizing pan-European case studies on metabarcoding. The project's objectives include providing best practice recommendations, optimizing analysis pipelines for species identification, and creating user-friendly reference databases. To accomplish these objectives, METAPLANTCODE will identify and address gaps in current methodologies, publish best practice documents on FAIR (Findable, Accessible, Interoperable, Reusable) data publishing for plant metabarcode data to GBIF (Global Biodiversity Information Facility) and the INSDC (International Nucleotide Sequence Database Collaboration), and implement ELIXIR-compatible multimodal deep learning (DL) models in novel tools for standalone metabarcoding analyses using various data sources. A significant focus of the project is enhancing species identification accuracy through GBIF records and metadata. This involves mapping regional, national, and international botanical taxonomic checklists, red lists, and floras to the Catalogue of Life (COL) via the COL ChecklistBank. Additionally, taxonomic and floristic literature will be semantically enriched with new entity recognition and relationship extraction modules, supporting the enhanced identification of species through domain-specific descriptive and phenotypic features. An interface will link taxonomic names to treatments, identify homonyms and synonyms, and facilitate the conversion and annotation of floras, red lists, and ecological treatments. All METAPLANTCODE products will adhere to FAIR standards by the project's end. The project emphasizes knowledge transfer from the outset, engaging with associated partners and stakeholders. Key stakeholders will be identified, priorities set, and communication channels established, monitored, and adjusted as necessary. Efforts to enhance stakeholder engagement, training, and outreach will ensure that plant metabarcoding becomes a routine standard for biodiversity monitoring in Europe and beyond. Deep Learning for Plant Metabarcoding Within the METAPLANTCODE project, our team is tasked with improving taxonomic precision by integrating deep learning on metabarcoding data and metadata. Previous studies have demonstrated the applicability of deep learning to non-plant barcoding data and its computational efficiency compared to traditional bioinformatics approaches (Flück et al. 2022). Deep Learning Models for Metabarcoding Data Our approach involves evaluating the efficacy of several deep learning models—such as Convolutional Neural Networks (CNN)(LeCun et al. 2015), Transformer models (Vaswani et al. 2017), Hyena (Poli et al. 2023), and Mamba architectures (Gu et al. 2023)—on plant barcoding datasets. Preliminary results will be presented, highlighting the application of these models and the proposed ensemble method (Mohammed and Kora 2023), which combines multiple barcode sequence representations and learning strategies. The ensemble approach, when integrated with classical machine learning models such as logistic regression and Support Vector Machines (SVM) (Noble 2006), is anticipated to offer improved precision and robustness compared to individual model applications (Fig. 1). Multimodal Refinement of Predictions In the subsequent phase, we aim to refine genetic sequence classifications by employing a multimodal strategy. This approach will integrate genetic information with traditional botanical knowledge. We will utilize biological interaction lists (e.g., species-species, species-habitat) provided by the METAPLANTCODE project to train a large language model (LLM) on relevant scientific literature. This LLM, specifically tailored for plant biodiversity, will incorporate metadata associated with genetic samples (including location, temporality, and climatic conditions). By merging embeddings of both metadata and genetic data, we aim to enhance the accuracy of taxonomic predictions (Fig. 2). Conclusion Through this research, we aim to develop an effective method for integrating genetic data with textual information from various sources. We anticipate that this approach will not only enhance plant metabarcoding but also be applicable to other barcoding fields, such as bacteria, fish, fungi, and more. Additionally, we expect this methodology to find broader applications in genomic research, providing valuable insights and improvements across diverse biological disciplines.

Applications of Machine Learning in Meniere's Disease Assessment Based on Pure-Tone Audiometry.

To apply machine learning models based on air conduction thresholds of pure-tone audiometry for automatic diagnosis of Meniere's disease (MD) and prediction of endolymphatic hydrops (EH). Retrospective study. Tertiary medical center. Gadolinium-enhanced magnetic resonance imaging sequences and pure-tone audiometry data were collected. Subsequently, basic and multiple analytical features were engineered based on the air conduction thresholds of pure-tone audiometry. Later, 5 classical machine learning models were trained to diagnose MD using the engineered features. The models demonstrating excellent performance were also selected to predict EH. The model's effectiveness in MD diagnosis was compared with experienced otolaryngologists. First, the winning light gradient boosting (LGB) machine learning model trained by multiple features demonstrates a remarkable performance on the diagnosis of MD, achieving an accuracy rate of 87%, sensitivity of 83%, specificity of 90%, and a robust area under the receiver operating characteristic curve of 0.95, which compares favorably with experienced clinicians. Second, the LGB model, with an accuracy of 78% on EH prediction, outperformed the other 3 machine learning models. Finally, a feature importance analysis reveals a pivotal role of the specific pure-tone audiometry features that are essential for both MD diagnosis and EH prediction. Highlighted features include standard deviation and mean of the whole-frequency hearing, the peak of the audiogram, and hearing at low frequencies, notably at 250 Hz. An efficient machine learning model based on pure-tone audiometry features was produced to diagnose MD, which also showed the potential to predict the subtypes of EH. The innovative approach demonstrated a game-changing strategy for MD screening and promising cost-effective benefits for the health care enterprise.

Computational study on the bifurcation mechanism in the H2CO− + CH3Cl →CH3CH2O + Cl−/H2CO + CH3 + Cl− reaction: The importance of intramolecular vibrational redistributions

We have investigated the bifurcation dynamics of the H2CO− + CH3Cl →CH3CH2O + Cl− (C-substitution channel)/H2CO + CH3 + Cl− (electron transfer channel) reaction using three different molecular dynamics (MD) methods: quasi-classical trajectory (QCT), classical MD, and ring-polymer MD simulations. All MD calculations were performed using the on-the-fly approach at the ab initio molecular orbital theory level. We found that the C-substitution channel is dominant in the classical and ring-polymer MD calculations, while the electron transfer channel is dominant in the QCT calculations. The different bifurcation mechanisms in the types of MD simulations were investigated using supervised machine-learning classification. This difference is attributed to the varying efficiency of the intramolecular vibrational redistribution process among the different MD methods. Thus, in the bifurcation mechanism of the H2CO− + CH3Cl reaction, the bifurcation fractions are primarily determined by the vibrational dynamics occurring in the later stages of the reaction.

Indonesian GDP movement detection using online news classification

Gross Domestic Product (GDP) stands as a pivotal indicator, offering strategic insights into economic dynamics. Recent technological advancements, particularly in real-time information dissemination through online economic news platforms, provide an accessible and alternative data source for analyzing GDP movements. This study employs online news classification to identify patterns in the movement and growth rate of Indonesia’s GDP. Utilizing a web scraping technique, we collected data for analysis. The classification models employed include transfer learning from pre-trained language model transformers, with classical machine learning methods serving as baseline models. The results indicate superior performance by the pre-trained language model transformers, achieving the highest accuracy of 0.8880 and 0.7899. In comparison, hyperparameter-tuned classical machine learning models also demonstrated commendable results, with the best accuracy reaching 0.845 and 0.7811. This research underscores the efficacy of leveraging online news classification, particularly through advanced language models. The findings contribute to a nuanced understanding of economic dynamics, aligning with the contemporary landscape of information accessibility and technological progress.

A novel profit-driven framework for model evaluation in credit scoring

Credit scoring is a prominent problem in machine learning (ML). ML classifiers used to assess creditworthiness need to be evaluated using appropriate metrics. Common metrics fall into two categories: cost-sensitive and traditional cost-insensitive. Traditional cost-insensitive metrics like accuracy and area under the curve (AUC) have several drawbacks. They can be difficult for managers to understand, potentially misleading in certain scenarios, and often overlook the business realities of credit scoring. Conversely, existing cost-sensitive metrics are imperfect, leading many studies to rely on classic AUC metrics. In this study, we introduce the expected profit ratio (EPR), a novel framework for evaluating classifiers in credit scoring. EPR does not require a base scenario and accurately calculates the profit. Its flexibility makes it suitable for all types of credit-scoring problems, and its simplicity aids in comprehension and explanation. By enabling accurate profit calculation, EPR helps managers, executives, and administrators make informed decisions and investments. This metric lays the foundation for more sophisticated and precise model evaluation and comparison in credit scoring. Additionally, it can be used as a performance measure, alongside fairness and other criteria needed to achieve trustworthy artificial intelligence (AI).

Non-linear machine learning coupled near infrared spectroscopy enhanced model performance and insights for coffee origin traceability

Over the past decade, there has been overwhelming interest in rapid and routine origin tracing and authentication methods, such as near infrared (NIR) spectroscopy. In a systematic and comprehensive approach, this study coupled NIR with advanced machine learning models to explore the origin classification of coffee at various scales (continental to regional level). Speciality green coffee beans were sourced from three continents, eight countries, and 22 regions. The dispersive bulk NIR spectra were used for spectral registration in the reflectance mode, and the obtained spectra were preprocessed with extended multiplicative scatter correction and mean centering. The classical linear partial least squares-discriminant analysis adequately predicted origin at the continental and country level, and showed promise at the regional level. Non-linear machine learning models improved predictions further, with the best accuracy found using random forest with accuracies up to 0.99. Discriminating wavelength regions and constituents were identified at each origin scale, with more minor wavelength regions selected by random forest. This proof of concept work demonstrated the potential of NIR spectroscopy coupled with machine learning for rapid origin classification of coffee from the continental to the regional level.

Cell-free DNA from germline TP53 mutation carriers reflect cancer-like fragmentation patterns

Germline pathogenic TP53 variants predispose individuals to a high lifetime risk of developing multiple cancers and are the hallmark feature of Li-Fraumeni syndrome (LFS). Our group has previously shown that LFS patients harbor shorter plasma cell-free DNA fragmentation; independent of cancer status. To understand the functional underpinning of cfDNA fragmentation in LFS, we conducted a fragmentomic analysis of 199 cfDNA samples from 82 TP53 mutation carriers and 30 healthy TP53-wildtype controls. We find that LFS individuals exhibit an increased prevalence of A/T nucleotides at fragment ends, dysregulated nucleosome positioning at p53 binding sites, and loci-specific changes in chromatin accessibility at development-associated transcription factor binding sites and at cancer-associated open chromatin regions. Machine learning classification resulted in robust differentiation between TP53 mutant versus wildtype cfDNA samples (AUC-ROC = 0.710–1.000) and intra-patient longitudinal analysis of ctDNA fragmentation signal enabled early cancer detection. These results suggest that cfDNA fragmentation may be a useful diagnostic tool in LFS patients and provides an important baseline for cancer early detection.

1H NMR Spectroscopy Combined with Machine-Learning Algorithm for Origin Recognition of Chinese Famous Green Tea Longjing Tea.

Premium green tea is a high-value agricultural product significantly influenced by its geographical origin, making it susceptible to food fraud. This study utilized nuclear magnetic resonance (NMR) spectroscopy to perform chemical fingerprint analysis on 78 Longjing tea (LJT) samples from both protected designation of origin (PDO) regions (Zhejiang) and non-PDO regions (Sichuan, Guangxi, and Guizhou) in China. Unsupervised algorithms and heatmaps were employed for the visual analysis of the data from PDO and non-PDO teas while exploring the feasibility of linear and nonlinear machine-learning algorithms in discriminating the origin of LJT. The findings revealed that the nonlinear model random forest (92.2%), exhibited superior performance compared to the linear model linear discriminant analysis (85.6%). The random forest model identified 15 key marker metabolites for the geographical origin of LJT, such as kaempferol glycoside, glutamine, and ECG. The results support the conclusion that the integration of NMR with machine-learning classification serves as an effective tool for the quality assessment and origin identification of LJT.

DDSBC: A Stacking Ensemble Classifier-Based Approach for Breast Cancer Drug-Pair Cell Synergy Prediction.

Breast cancer (BC) ranks as a leading cause of mortality among women worldwide, with incidence rates continuing to rise. The quest for effective treatments has led to the adoption of drug combination therapy, aiming to enhance drug efficacy. However, identifying synergistic drug combinations remains a daunting challenge due to the myriad of potential drug pairs. Current research leverages machine learning (ML) and deep learning (DL) models for drug-pair synergy prediction and classification. Nevertheless, these models often underperform on specific cancer types, including BC, as they are trained on data spanning various cancers without any specialization. Here, we introduce a stacking ensemble classifier, the drug-drug synergy for breast cancer (DDSBC), tailored explicitly for BC drug-pair cell synergy classification. Unlike existing models that generalize across cancer types, DDSBC is exclusively developed for BC, offering a more focused approach. Our comparative analysis against classical ML methods as well as DL models developed for drug synergy prediction highlights DDSBC's superior performance across test and independent datasets on BC data. Despite certain metrics where other methods narrowly surpass DDSBC by 1-2%, DDSBC consistently emerges as the top-ranked model, showcasing significant differences in scoring metrics and robust performance in ablation studies. DDSBC's performance and practicality position it as a preferred choice or an adjunctive validation tool for identifying synergistic or antagonistic drug pairs in BC, providing valuable insights for treatment strategies.