GitHub Repository Research Articles

Expectation maximisation pseudo labels

In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes’ theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational approach to generate these Bayesian Pseudo Labels, involving the learning of a threshold to automatically select high-quality pseudo labels. In the remainder of the paper, we showcase the applications of pseudo-labelling and its generalised form, Bayesian Pseudo-Labelling, in the semi-supervised segmentation of medical images. Specifically, we focus on: (1) 3D binary segmentation of lung vessels from CT volumes; (2) 2D multi-class segmentation of brain tumours from MRI volumes; (3) 3D binary segmentation of whole brain tumours from MRI volumes; and (4) 3D binary segmentation of prostate from MRI volumes. We further demonstrate that pseudo-labels can enhance the robustness of the learned representations. The code is released in the following GitHub repository: https://github.com/moucheng2017/EMSSL.

ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet

The advancement of autonomous driving heavily relies on the ability to accurate lane lines detection. As deep learning and computer vision technologies evolve, a variety of deep learning-based methods for lane line detection have been proposed by researchers in the field. However, owing to the simple appearance of lane lines and the lack of distinctive features, it is easy for other objects with similar local appearances to interfere with the process of detecting lane lines. The precision of lane line detection is limited by the unpredictable quantity and diversity of lane lines. To address the aforementioned challenges, we propose a novel deep learning approach for lane line detection. This method leverages the Swin Transformer in conjunction with LaneNet (called ST-LaneNet). The experience results showed that the true positive detection rate can reach 97.53% for easy lanes and 96.83% for difficult lanes (such as scenes with severe occlusion and extreme lighting conditions), which can better accomplish the objective of detecting lane lines. In 1000 detection samples, the average detection accuracy can reach 97.83%, the average inference time per image can reach 17.8 ms, and the average number of frames per second can reach 64.8 Hz. The programming scripts and associated models for this project can be accessed openly at the following GitHub repository: https://github.com/Duane711/Lane-line-detection-ST-LaneNet.

Nanometa Live: a user-friendly application for real-time metagenomic data analysis and pathogen identification.

Nanometa Live presents a user-friendly interface designed for real-time metagenomic data analysis and pathogen identification utilizing Oxford Nanopore Technologies' MinION and Flongle flow cells. It offers an efficient workflow and graphical interface for the visualization and interpretation of metagenomic data as it is being generated. Key features include automated BLAST validation, streamlined handling of custom Kraken2 databases, and a simplified graphical user interface for enhanced user experience. Nanometa Live is particularly notable for its capability to run without constant internet or server access once installed, setting it apart from similar tools. It provides a comprehensive view of taxonomic composition and facilitates the detection of user-defined pathogens or other species of interest, catering to both researchers and clinicians. Nanometa Live has been implemented as a local web application using the Dash framework with Snakemake handling the data processing. The source code is freely accessible on the GitHub repository at https://github.com/FOI-Bioinformatics/nanometa_live and it is easily installable using Bioconda. It includes containerization support via Docker and Singularity, ensuring ease of use, reproducibility, and portability.

Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise.

As part of the ongoing quest to find or construct large data sets for use in validating new machine learning (ML) approaches for bioactivity prediction, it has become distressingly common for researchers to combine literature IC50 data generated using different assays into a single data set. It is well-known that there are many situations where this is a scientifically risky thing to do, even when the assays are against exactly the same target, but the risks of assays being incompatible are even higher when pulling data from large collections of literature data like ChEMBL. Here, we estimate the amount of noise present in combined data sets using cases where measurements for the same compound are reported in multiple assays against the same target. This approach shows that IC50 assays selected using minimal curation settings have poor agreement with each other: almost 65% of the points differ by more than 0.3 log units, 27% differ by more than one log unit, and the correlation between the assays, as measured by Kendall's τ, is only 0.51. Requiring that most of the assay metadata in ChEMBL matches ("maximal curation") in order to combine two assays improves the situation (48% of the points differ by more than 0.3 log units, 13% by more than one log unit, and Kendall's τ is 0.71) at the expense of having smaller data sets. Surprisingly, our analysis shows similar amounts of noise when combining data from different literature Ki assays. We suggest that good scientific practice requires careful curation when combining data sets from different assays and hope that our maximal curation strategy will help to improve the quality of the data that are being used to build and validate ML models for bioactivity prediction. To help achieve this, the code and ChEMBL queries that we used for the maximal curation approach are available as open-source software in our GitHub repository, https://github.com/rinikerlab/overlapping_assays.

Storing Images in DNA via base128 Encoding.

Current DNA storage schemes lack flexibility and consistency in processing highly redundant and correlated image data, resulting in low sequence stability and image reconstruction rates. Therefore, according to the characteristics of image storage, this paper proposes storing images in DNA via base128 encoding (DNA-base128). In the data writing stage, data segmentation and probability statistics are carried out, and then, the data block frequency and constraint encoding set are associated with achieving encoding. When the image needs to be recovered, DNA-base128 completes internal error correction by threshold setting and drift comparison. Compared with representative work, the DNA-base128 encoding results show that the undesired motifs were reduced by 71.2-90.7% and that the local guanine-cytosine content variance was reduced by 3 times, indicating that DNA-base128 can store images more stably. In addition, the structural similarity index (SSIM) and multiscale structural similarity (MS-SSIM) of image reconstruction using DNA-base128 were improved by 19-102 and 6.6-20.3%, respectively. In summary, DNA-base128 provides image encoding with internal error correction and provides a potential solution for DNA image storage. The data and code are available at the GitHub repository: https://github.com/123456wk/DNA_base128.

Developing a Radiomics Atlas Dataset of normal Abdominal and Pelvic computed Tomography (RADAPT)

Atlases of normal genomics, transcriptomics, proteomics, and metabolomics have been published in an attempt to understand the biological phenotype in health and disease and to set the basis of comprehensive comparative omics studies. No such atlas exists for radiomics data. The purpose of this study was to systematically create a radiomics dataset of normal abdominal and pelvic radiomics that can be used for model development and validation. Young adults without any previously known disease, aged > 17 and ≤ 36 years old, were retrospectively included. All patients had undergone CT scanning for emergency indications. In case abnormal findings were identified, the relevant anatomical structures were excluded. Deep learning was used to automatically segment the majority of visible anatomical structures with the TotalSegmentator model as applied in 3DSlicer. Radiomics features including first order, texture, wavelet, and Laplacian of Gaussian transformed features were extracted with PyRadiomics. A Github repository was created to host the resulting dataset. Radiomics data were extracted from a total of 531 patients with a mean age of 26.8 ± 5.19 years, including 250 female and 281 male patients. A maximum of 53 anatomical structures were segmented and used for subsequent radiomics data extraction. Radiomics features were derived from a total of 526 non-contrast and 400 contrast-enhanced (portal venous) series. The dataset is publicly available for model development and validation purposes.

Novel symmetry-preserving neural network model for phylogenetic inference.

Scientists world-wide are putting together massive efforts to understand how the biodiversity that we see on Earth evolved from single-cell organisms at the origin of life and this diversification process is represented through the Tree of Life. Low sampling rates and high heterogeneity in the rate of evolution across sites and lineages produce a phenomenon denoted "long branch attraction" (LBA) in which long nonsister lineages are estimated to be sisters regardless of their true evolutionary relationship. LBA has been a pervasive problem in phylogenetic inference affecting different types of methodologies from distance-based to likelihood-based. Here, we present a novel neural network model that outperforms standard phylogenetic methods and other neural network implementations under LBA settings. Furthermore, unlike existing neural network models in phylogenetics, our model naturally accounts for the tree isomorphisms via permutation invariant functions which ultimately result in lower memory and allows the seamless extension to larger trees. We implement our novel theory on an open-source publicly available GitHub repository: https://github.com/crsl4/nn-phylogenetics.

The Strong Force meets the Dark Sector: a robust estimate of QCD uncertainties for anti-matter dark matter searches

In dark-matter annihilation channels to hadronic final states, stable particles — such as positrons, photons, antiprotons, and antineutrinos — are produced via complex sequences of phenomena including QED/QCD radiation, hadronisation, and hadron decays. These processes are normally modelled by Monte Carlo (MC) event generators whose limited accuracy imply intrinsic QCD uncertainties on the predictions for indirect-detection experiments like Fermi-LAT, Pamela, IceCube or Ams–02. In this article, we perform a comprehensive analysis of QCD uncertainties, meaning both perturbative and nonperturbative sources of uncertainty are included — estimated via variations of MC renormalization-scale and fragmentation-function parameters, respectively — in antimatter spectra from dark-matter annihilation, based on parametric variations of the Pythia 8 event generator. After performing several retunings of light-quark fragmentation functions, we define a set of variations that span a conservative estimate of the QCD uncertainties. We estimate the effects on antimatter spectra for various annihilation channels and final-state particle species, and discuss their impact on fitted values for the dark-matter mass and thermally-averaged annihilation cross section. We find dramatic impacts which can go up to O\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$ \\mathcal{O} $$\\end{document}(40) GeV for uncertainties on the dark-matter mass and up to O\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$ \\mathcal{O} $$\\end{document}(10%) for the annihilation cross section. We provide the spectra in tabulated form including QCD uncertainties and code snippets to perform fast dark-matter fits, in this github repository.

Variable Selection in Data Analysis: A Synthetic Data Toolkit

Variable (feature) selection plays an important role in data analysis and mathematical modeling. This paper aims to address the significant lack of formal evaluation benchmarks for feature selection algorithms (FSAs). To evaluate FSAs effectively, controlled environments are required, and the use of synthetic datasets offers significant advantages. We introduce a set of ten synthetically generated datasets with known relevance, redundancy, and irrelevance of features, derived from various mathematical, logical, and geometric sources. Additionally, eight FSAs are evaluated on these datasets based on their relevance and novelty. The paper first introduces the datasets and then provides a comprehensive experimental analysis of the performance of the selected FSAs on these datasets including testing the FSAs’ resilience on two types of induced data noise. The analysis has guided the grouping of the generated datasets into four groups of data complexity. Lastly, we provide public access to the generated datasets to facilitate bench-marking of new feature selection algorithms in the field via our Github repository. The contributions of this paper aim to foster the development of novel feature selection algorithms and advance their study.

A building imagery database for the calibration of machine learning algorithms

In the last decades, most efforts to catalog and characterize the built environment for multi-hazard risk assessment have focused on the exploration of census data, cadastral data sets, and local surveys. Typically, these sources of information are not updated regularly and lack sufficient information to characterize the seismic vulnerability of the building stock. Some recent efforts have demonstrated how machine learning algorithms can be used to automatically recognize specific architectural and structural features of buildings. However, such methods require large sets of labeled images to train, verify, and test the algorithms. This article presents a database of 5276 building images from a parish in Lisbon (Alvalade), whose buildings have been classified according to a uniform taxonomy. This database can be used for the testing and calibration of machine learning algorithms, as well as for the direct assessment of earthquake risk in Alvalade. The data are accessible through an open Github repository (DOI: 10.5281/zenodo.7625940).

Ontologies4Cat: investigating the landscape of ontologies for catalysis research data management

As scientific digitization advances it is imperative ensuring data is Findable, Accessible, Interoperable, and Reusable (FAIR) for machine-processable data. Ontologies play a vital role in enhancing data FAIRness by explicitly representing knowledge in a machine-understandable format. Research data in catalysis research often exhibits complexity and diversity, necessitating a respectively broad collection of ontologies. While ontology portals such as EBI OLS and BioPortal aid in ontology discovery, they lack deep classification, while quality metrics for ontology reusability and domains are absent for the domain of catalysis research. Thus, this work provides an approach for systematic collection of ontology metadata with focus on the catalysis research data value chain. By classifying ontologies by subdomains of catalysis research, the approach is offering efficient comparison across ontologies. Furthermore, a workflow and codebase is presented, facilitating representation of the metadata on GitHub. Finally, a method is presented to automatically map the classes contained in the ontologies of the metadata collection against each other, providing further insights on relatedness of the ontologies listed. The presented methodology is designed for its reusability, enabling its adaptation to other ontology collections or domains of knowledge. The ontology metadata taken up for this work and the code developed and described in this work are available in a GitHub repository at: https://github.com/nfdi4cat/Ontology-Overview-of-NFDI4Cat.

Practitioners' expectations on automated release note generation techniques

AbstractThe software development life cycle relies heavily on the software release note, a crucial document. Various practitioners, including project managers and clients, benefit from release notes as they provide an overview of the latest software release. However, the manual generation of release notes is a time‐consuming and stressful task. Researchers have recently proposed automated techniques to generate release notes, saving developers' time and enhancing their understanding of software projects. Unfortunately, the adoption of these tools in practice remains limited. To address this gap, we have taken steps to understand the expectations and requirements of practitioners regarding release note generation techniques before implementing new automated approaches. Consequently, our approach involves two main stages: First, we conduct a comprehensive review of the relevant literature and analyze existing release notes from GitHub repositories to gain insights into the current practices. Second, we conduct an online survey study to gather input from practitioners and understand their expectations regarding release notes. We have reviewed 16 papers related to release notes and explored 3347 release notes from 21 GitHub repositories. Our analysis revealed key artifacts present in release note contents, including issues (29%), pull requests (32%), commits (19%), and common vulnerabilities and exposures (CVE) issues (6%). Additionally, we conducted a survey study involving 32 professionals to understand the essential information that should be included in release notes based on users' roles. For instance, project managers were more interested in learning about new features rather than less critical bug fixes. Furthermore, we identified gaps in existing systems and essential factors to consider when implementing release notes techniques in software engineering. The insights gained from our study can guide future research directions and assist practitioners in generating release notes with relevant content, thus improving the overall quality of documentation in software development.

MetDIT: Transforming and Analyzing Clinical Metabolomics Data with Convolutional Neural Networks.

Clinical metabolomics is growing as an essential tool for precision medicine. However, classical machine learning algorithms struggle to comprehensively encode and analyze the metabolomics data due to their high dimensionality and complex intercorrelations. This article introduces a new method called MetDIT, designed to analyze intricate metabolomics data effectively using deep convolutional neural networks (CNN). MetDIT comprises two components: TransOmics and NetOmics. Since CNN models have difficulty in processing one-dimensional (1D) sequence data efficiently, we developed TransOmics, a framework that transforms sequence data into two-dimensional (2D) images while maintaining a one-to-one correspondence between the sequences and images. NetOmics, the second component, leverages a CNN architecture to extract more discriminative representations from the transformed samples. To overcome the overfitting due to the small sample size and class imbalance, we introduced a feature augmentation module (FAM) and a loss function to improve the model performance. Furthermore, we systematically optimized the model backbone and image resolution to balance the model parameters and computational costs. To demonstrate the performance of the proposed MetDIT, we conducted extensive experiments using three different clinical metabolomics data sets and achieved better classification performance than classical machine learning methods used in metabolomics, including Random Forest, SVM, XGBoost, and LightGBM. The source code is available at the GitHub repository at https://github.com/Li-OmicsLab/MetDIT, and the WebApp can be found at http://metdit.bioinformatics.vip/.

AI models for automated segmentation of engineered polycystic kidney tubules

Autosomal dominant polycystic kidney disease (ADPKD) is a monogenic, rare disease, characterized by the formation of multiple cysts that grow out of the renal tubules. Despite intensive attempts to develop new drugs or repurpose existing ones, there is currently no definitive cure for ADPKD. This is primarily due to the complex and variable pathogenesis of the disease and the lack of models that can faithfully reproduce the human phenotype. Therefore, the development of models that allow automated detection of cysts’ growth directly on human kidney tissue is a crucial step in the search for efficient therapeutic solutions. Artificial Intelligence methods, and deep learning algorithms in particular, can provide powerful and effective solutions to such tasks, and indeed various architectures have been proposed in the literature in recent years. Here, we comparatively review state-of-the-art deep learning segmentation models, using as a testbed a set of sequential RGB immunofluorescence images from 4 in vitro experiments with 32 engineered polycystic kidney tubules. To gain a deeper understanding of the detection process, we implemented both pixel-wise and cyst-wise performance metrics to evaluate the algorithms. Overall, two models stand out as the best performing, namely UNet++ and UACANet: the latter uses a self-attention mechanism introducing some explainability aspects that can be further exploited in future developments, thus making it the most promising algorithm to build upon towards a more refined cyst-detection platform. UACANet model achieves a cyst-wise Intersection over Union of 0.83, 0.91 for Recall, and 0.92 for Precision when applied to detect large-size cysts. On all-size cysts, UACANet averages at 0.624 pixel-wise Intersection over Union. The code to reproduce all results is freely available in a public GitHub repository.

Probabilistic Model Checking GitHub Repositories for Software Project Analysis

GitHub serves as a platform for collaborative software development, where contributors engage, evolve projects, and shape the community. This study presents a novel approach to analyzing GitHub activity that departs from traditional methods. Using Discrete-Time Markov Chains and probabilistic Computation Tree Logic for model checking, we aim to uncover temporal dynamics, probabilities, and key factors influencing project behavior. By explicitly modeling state transitions, our approach provides transparency and explainability for sequential properties. The application of our method to five repositories demonstrates its feasibility and scalability and provides insights into the long-term probabilities of various activities. In particular, the analysis provides valuable perspectives for project managers to optimize team dynamics and resource allocation. The query specifications developed for model checking allow users to generate and execute queries for specific aspects, demonstrating scalability beyond the queries we present. In conclusion, our analysis provides an understanding of GitHub repository properties, branch management, and subscriber behavior. We anticipate its applicability to various open-source projects, revealing trends among contributors based on the unique characteristics of repositories.

(Mis)leading the COVID-19 Vaccination Discourse on Twitter: An Exploratory Study of Infodemic Around the Pandemic

In this work, we collect a moderate-sized representative corpus of tweets (200,000 approx.) pertaining Covid-19 vaccination spanning over a period of seven months (September 2020 - March 2021). Following a Transfer Learning approach, we utilize the pre-trained Transformer-based XLNet model to classify tweets as Misleading or Non-Misleading and validate against a random subset of results manually. We build on this to study and contrast the characteristics of tweets in the corpus that are misleading in nature against non-misleading ones. This exploratory analysis enables us to design features (such as sentiments, hashtags, nouns, pronouns, etc) that can, in turn, be exploited for classifying tweets as (Non-)Misleading using various ML models in an explainable manner. Specifically, several ML models are employed for prediction, with up to 90% accuracy, and the importance of each feature is explained using SHAP Explainable AI (XAI) tool. While the thrust of this work is principally exploratory analysis in order to obtain insights on the online discourse on Covid-19 vaccination, we conclude the paper by outlining how these insights provide the foundations for a more actionable approach to mitigate misinformation. The curated dataset and code is made available (Github repository) so that the research community at large can reproduce, compare against, or build upon this work.

Pycallingcards: an integrated environment for visualizing, analyzing, and interpreting Calling Cards data.

Unraveling the transcriptional programs that control how cells divide, differentiate, and respond to their environments requires a precise understanding of transcription factors' (TFs) DNA-binding activities. Calling cards (CC) technology uses transposons to capture transient TF binding events at one instant in time and then read them out at a later time. This methodology can also be used to simultaneously measure TF binding and mRNA expression from single-cell CC and to record and integrate TF binding events across time in any cell type of interest without the need for purification. Despite these advantages, there has been a lack of dedicated bioinformatics tools for the detailed analysis of CC data. We introduce Pycallingcards, a comprehensive Python module specifically designed for the analysis of single-cell and bulk CC data across multiple species. Pycallingcards introduces two innovative peak callers, CCcaller and MACCs, enhancing the accuracy and speed of pinpointing TF binding sites from CC data. Pycallingcards offers a fully integrated environment for data visualization, motif finding, and comparative analysis with RNA-seq and ChIP-seq datasets. To illustrate its practical application, we have reanalyzed previously published mouse cortex and glioblastoma datasets. This analysis revealed novel cell-type-specific binding sites and potential sex-linked TF regulators, furthering our understanding of TF binding and gene expression relationships. Thus, Pycallingcards, with its user-friendly design and seamless interface with the Python data science ecosystem, stands as a critical tool for advancing the analysis of TF functions via CC data. Pycallingcards can be accessed on the GitHub repository: https://github.com/The-Mitra-Lab/pycallingcards.

Measuring stomatal and guard cell metrics for plant physiology and growth using StoManager1.

Automated guard cell detection and measurement are vital for understanding plant physiological performance and ecological functioning in global water and carbon cycles. Most current methods for measuring guard cells and stomata are laborious, time-consuming, prone to bias, and limited in scale. We developed StoManager1, a high-throughput tool utilizing geometrical, mathematical algorithms, and convolutional neural networks to automatically detect, count, and measure over 30 guard cell and stomatal metrics, including guard cell and stomatal area, length, width, stomatal aperture area/guard cell area, orientation, stomatal evenness, divergence, and aggregation index. Combined with leaf functional traits, some of these StoManager1-measured guard cell and stomatal metrics explained 90% and 82% of tree biomass and intrinsic water use efficiency (iWUE) variances in hardwoods, making them substantial factors in leaf physiology and tree growth. StoManager1 demonstrated exceptional precision and recall (mAP@0.5 over 0.96), effectively capturing diverse stomatal properties across over 100 species. StoManager1 facilitates the automation of measuring leaf stomatal and guard cells, enabling broader exploration of stomatal control in plant growth and adaptation to environmental stress and climate change. This has implications for global gross primary productivity (GPP) modeling and estimation, as integrating stomatal metrics can enhance predictions of plant growth and resource usage worldwide. Easily accessible open-source code and standalone Windows executable applications are available on a GitHub repository (https://github.com/JiaxinWang123/StoManager1) and Zenodo (https://doi.org/10.5281/zenodo.7686022).

Dynamical Classifications of Multi-opposition TNOs as of 2023 December

We report the dynamical classifications of 3357 observed outer solar system objects listed as transneptunian objects (TNOs) or Centaurs by the Minor Planet Center. We use the Gladman et al. classification scheme to identify 28 Jupiter-coupled objects (all secure), 168 Centaurs (all secure), 234 scattering TNOs (70 secure/164 insecure), 204 detached TNOs (118 secure/86 insecure), 1650 classical TNOs (1494 secure/156 insecure), and 1073 resonant TNOs (907 secure, 166 insecure). Among the resonant TNOs, the most observationally populated resonance is the close-in 3:2 MMR with 452 objects, followed by the 2:1 with 105 objects, the 7:4 with 103 objects, the 5:3 with 68 objects, and the 5:2 with 56 objects. We discuss a few notable objects here, but all classifications and plots of the 10 Myr integrations are available in a linked GitHub repository.

Dynamic Malware Classification and API Categorisation of Windows Portable Executable Files Using Machine Learning

The rise of malware attacks presents a significant cyber-security challenge, with advanced techniques and offline command-and-control (C2) servers causing disruptions and financial losses. This paper proposes a methodology for dynamic malware analysis and classification using a malware Portable Executable (PE) file from the MalwareBazaar repository. It suggests effective strategies to mitigate the impact of evolving malware threats. For this purpose, a five-level approach for data management and experiments was utilised: (1) generation of a customised dataset by analysing a total of 582 malware and 438 goodware samples from Windows PE files; (2) feature extraction and feature scoring based on Chi2 and Gini importance; (3) empirical evaluation of six state-of-the-art baseline machine learning (ML) models, including Logistic Regression (LR), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), XGBoost (XGB), and K-Nearest Neighbour (KNN), with the curated dataset; (4) malware family classification using VirusTotal APIs; and, finally, (5) categorisation of 23 distinct APIs from 266 malware APIs. According to the results, Gini’s method takes a holistic view of feature scoring, considering a wider range of API activities. The RF achieved the highest precision of 0.99, accuracy of 0.96, area under the curve (AUC) of 0.98, and F1-score of 0.96, with a 0.93 true-positive rate (TPR) and 0.0098 false-positive rate (FPR), among all applied ML models. The results show that Trojans (27%) and ransomware (22%) are the most risky among 11 malware families. Windows-based APIs (22%), the file system (12%), and registry manipulation (8.2%) showcased their importance in detecting malicious activity in API categorisation. This paper considers a dual approach for feature reduction and scoring, resulting in an improved F1-score (2%), and the inclusion of AUC and specificity metrics distinguishes it from existing research (Section Comparative Analysis with Existing Approaches). The newly generated dataset is publicly available in the GitHub repository (Data Availability Statement) to facilitate aspirant researchers’ dynamic malware analysis.