<b>Alpha-Synuclein Degradome Foundation Atlas</b> حسب Axel Petzold (7076261)

"…All scripts are provided and fully documented in the accompanying publication [1] and dataset/code repositories [2,3].</p><p dir="ltr">This Atlas is ideal for researchers in neuroscience, proteomics, bioinformatics, and AI who are building tools to understand, predict, and intervene in protein degradation pathways relevant to human disease.…"

<b>Rethinking neighbourhood boundaries for urban planning: A data-driven framework for perception-based delineation</b> حسب Shubham Pawar (22471285)

"…</p><p dir="ltr"><b>Input:</b></p><ul><li><code>raw_data/glasgow_open_built/glasgow_open_built_areas.shp</code> - Grid defining sampling points</li></ul><p dir="ltr"><b>Command:</b></p><pre><pre>python svi_module/get_svi_data.py<br></pre></pre><p dir="ltr"><b>Output:</b></p><ul><li><code>svi_module/svi_data/svi_info.csv</code> - Image metadata (IDs, coordinates)</li><li><code>svi_module/svi_data/images/</code> - Downloaded street view images</li></ul><h3>Step 2: Predict Perceptions</h3><p dir="ltr">Use pre-trained deep learning models to predict perceptual qualities (safety, beauty, liveliness, etc.) from street view images.…"

The data of the paper "Remote spectral detection of canopy functional strategies varying within and across forest types". حسب Fengqi Wu (20149158)

"…Canopy_2024_PLSR_ST_canopy_run_refit.py</p><p dir="ltr">This is the python code used for PLSR modeling.</p><p dir="ltr"><br></p><p dir="ltr">3. python_code_get_model_details.zip</p><p dir="ltr">This is the python code to get model performance, coefficients, VIPs, and so on.…"

<b>MSLU-100K: A multi-source land use dataset of Chinese major cities</b> حسب Yao Yao (7903457)

"…</li><li>The Manual Filtering.py-Based Multilevel Model Classification Method includes code to perform multilevel model predictions.</li></ul><h3>5.requirements.txt</h3><ul><li>Lists environment configurations and version specifications, including Python 3.7 and Pytorch 2.2.…"

Monte Carlo Simulation for SAPAL Framework: AI-Augmented CI/CD Reliability حسب Rohit Dhawan (22457026)

"…</p><p dir="ltr">Files included: <br>- simulation.py: Python simulation code <br>- README.md: Complete documentation and methodology <br><br>This code supports the paper "AI-Augmented Reliability in Continuous Integration and Deployment: A Conceptual Framework for Predictive, Adaptive, and Self-Correcting Pipelines".…"

The Transcriptional Gradient in Negative-Strand RNA Viruses Suggest a Common RNA Transcription Mechanism: Model حسب Jean Peccoud (275555)

"…</p><p dir="ltr">Notebook2 contains the python code for making predictions of transcriptional gradients for gene-shuffled variants.…"

The Kidmose CANid Dataset (KCID) حسب Brooke Elizabeth Kidmose (13626754)

"…</p><h2>FILE TYPES</h2><p dir="ltr">The dataset provides data in three formats to support different use cases:</p><p dir="ltr"><b>.mf4 (MDF4) Format:</b> Measurement Data Format version 4 (MDF4)</p><ul><li>Binary format standardized by the Association for Standardization of Automation (ASAM)</li><li><b>Advantages:</b> Compact size, popular with automotive/CAN tools</li><li><b>Use case:</b> Native format from CSS Electronics CANEdge2</li><li><b>Reference:</b> <a href="https://www.csselectronics.com/pages/mf4-mdf4-measurement-data-format" rel="noreferrer" target="_blank">https://www.csselectronics.com/pages/mf4-mdf4-measurement-data-format</a></li></ul><p dir="ltr"><b>.log Format:</b> Text-based log format</p><ul><li><b>Compatibility:</b> Linux SocketCAN can-utils</li><li><b>Advantages:</b> Compatibility with SocketCAN can-utils; if a .log file is replayed, then data can be captured and monitored using Python's python-can library</li><li><b>References:</b> <a href="https://github.com/linux-can/can-utils" rel="noreferrer" target="_blank">https://github.com/linux-can/can-utils</a>, <a href="https://packages.debian.org/sid/can-utils" rel="noreferrer" target="_blank">https://packages.debian.org/sid/can-utils</a>, <a href="https://python-can.readthedocs.io/en/stable/" rel="noreferrer" target="_blank">https://python-can.readthedocs.io/en/stable/</a></li></ul><p dir="ltr"><b>.csv Format:</b> Text-based comma-separated values (CSV) format</p><ul><li><b>Advantages:</b> Easy to load with Python using the pandas library; easy to use with Python-based machine learning frameworks (e.g., scikit-learn, Keras, TensorFlow, PyTorch)</li><li><b>Usage:</b> Load with Python pandas: pd.read_csv()</li><li><b>Reference:</b> <a href="https://pandas.pydata.org/" rel="noreferrer" target="_blank">https://pandas.pydata.org/</a></li></ul><h2>SPECIALIZED EXPERIMENTS</h2><p dir="ltr">The KCID Dataset includes five specialized experiments:</p><p dir="ltr"><b>Fixed Routes Experiment</b></p><ul><li><b>Vehicles:</b> 2011 Chevrolet Traverse, 2017 Subaru Forester</li><li><b>Drivers:</b> male-30-55-3, male-30-55-4, male-over55-1, female-all-ages-1, female-all-ages-2, female-all-ages-5</li><li><b>Location:</b> Florida, USA (specific routes)</li><li><b>Data Collection Methods:</b> CSS Electronics CANEdge2, Kvaser Hybrid CAN-LIN</li><li><b>Purpose:</b> Capture CAN traces for specific, mappable routes; eliminate route-based variations in driver authentication data (e.g., low-speed local routes vs. high-speed long-distance routes)</li></ul><p dir="ltr"><b>OBD Requests and Responses Experiment</b></p><ul><li><b>Vehicle:</b> 2011 Chevrolet Traverse</li><li><b>Driver:</b> female-all-ages-5</li><li><b>Location:</b> Florida, USA</li><li><b>Data Collection Method:</b> CSS Electronics CANEdge2</li><li><b>Purpose:</b> Capture OBD requests and responses Arbitration IDs: <i>Requests:</i> 0x7DF, <i>Responses:</i> 0x7E8</li></ul><p dir="ltr"><b>Tire Pressure Experiment</b></p><ul><li><b>Vehicle:</b> 2011 Chevrolet Traverse</li><li><b>Driver:</b> female-all-ages-5</li><li><b>Location:</b> Florida, USA</li><li><b>Data Collection Method:</b> Kvaser Hybrid CAN-LIN</li><li><b>Purpose:</b> Capture normal and low tire pressure scenarios</li><li><b>Applications:</b> Detect tire pressure issues via CAN bus analysis; develop predictive maintenance strategies</li></ul><p dir="ltr"><b>Driving Modes and Features Experiment</b></p><ul><li><b>Vehicle:</b> 2017 Ford Focus</li><li><b>Driver:</b> male-30-55-1</li><li><b>Location:</b> Denmark</li><li><b>Data Collection Method:</b> Korlan USB2CAN</li><li><b>Purpose:</b> Capture different driving (and non-driving) modes and features</li><li><b>Examples:</b> gear (park, reverse, neutral, drive, sport); headlights on/off</li></ul><p dir="ltr"><b>Stationary Vehicles Experiment</b></p><ul><li><b>Vehicles:</b> 2024 Chevrolet Malibu, 2025 Toyota Corolla</li><li><b>Driver:</b> N/A (vehicles remained stationary)</li><li><b>Location:</b> Florida, USA</li><li><b>Data Collection Method:</b> Kvaser Hybrid CAN-LIN</li><li><b>Purpose:</b> Capture CAN bus traffic from very new, very modern vehicles; identify differences between an older vehicle's CAN bus (e.g., 2011 Chevrolet Traverse), and a newer vehicle's CAN bus (e.g., 2024 Chevrolet Malibu)</li></ul><h2>ADDITIONAL DOCUMENTATION</h2><p dir="ltr">Each "specialized experiment" directory contains a detailed README.md file with specific information about the experiment and the data collected.…"

PepENS حسب Abel Chandra (16854753)

"…For the EfficientNetB0 model, the model weights can be downloaded from <a href="https://figshare.com/articles/software/EfficientNetB0_model_weights/27126339" rel="nofollow" target="_blank">here</a>.</p><h2>3. Predicting peptide binding sites on user input</h2><p dir="ltr">The PepENS tool allows users to predict peptide binding sites in their protein(s). …"

SI files for "Addressing Hemolysis-Induced Loss of Sensitivity in Lateral Flow Assays of Blood Samples with Platinum-Coated Gold Nanoparticles and Machine Learning" حسب An Le (20473628)

"…</p><p dir="ltr">2) Model_testing.ipynb: Jupyter Notebook containing Python code for generate predictions for the 112 test strips</p><p dir="ltr">3) Best_model.keras: The final optimized machine learning model saved in Keras format.…"

Albumin Degradome Foundation Atlas حسب Axel Petzold (7076261)

"…</p><h2><b>Data Format and Access</b></h2><ul><li><b>Primary file:</b> <code>Albumin_Degradome_Foundation_Atlas_v1.tar.xz</code><br>(contains all peptide tables in standard CSV format)</li><li><b>File Type:</b> ASCII comma-separated values (CSV)</li><li><b>Compression:</b> <code>xz -9 -T0</code> for maximal CPU-parallelised compression</li><li><b>Compatibility:</b></li><li><ul><li>R, Python, MATLAB, SAS</li><li>Excel, LibreOffice</li><li>Any proteomics workflow (e.g., Skyline, MaxQuant preprocessing, MS/MS spectral libraries)</li></ul></li></ul><h2><b>FAIR Principles</b></h2><p dir="ltr">This dataset is fully aligned with FAIR data standards:</p><ul><li><b>Findable:</b> Rich metadata, stable DOI, search-optimised description</li><li><b>Accessible:</b> Open-access Figshare repository</li><li><b>Interoperable:</b> Standard numeric and CSV formats</li><li><b>Reusable:</b> Transparent, reproducible Python source code included</li></ul><h2><b>Applications</b></h2><p dir="ltr">The Albumin Degradome Foundation Atlas supports research across multiple biomedical domains:</p><ul><li>Biomarker development in liver disease, kidney dysfunction, inflammation, and systemic disorders</li><li>Mass-spectrometry method development</li><li>Computational proteomics and peptide modelling</li><li>Autoimmunity and neo-epitope analysis</li><li>Protein–peptide interaction studies</li><li>Proteolytic pathway mapping and degradomics</li></ul><h2><b>Versioning and Future Work</b></h2><p dir="ltr">This is <b>Version 1</b> of the Albumin Degradome Foundation Atlas. …"

Missing Value Imputation in Relational Data Using Variational Inference حسب Simon Fontaine (7046618)

"…Additional results, implementation details, a Python implementation, and the code reproducing the results are available online. …"

LNP drug delivery image data حسب Philip Harrison (8899735)

"…</div><div><br></div><div><u>Python code:</u></div><div><a href="https://github.com/pharmbio/phil_LNP_modelling">https://github.com/pharmbio/phil_LNP_modelling</a><br></div><div><br></div><div><br></div><div><br></div><div><br></div><div><br></div><p></p>…"

Horuss Research: methodology for validating unstructured data using large language models حسب Fabiano Castello (6803171)

"…First, data is collected via RPA tools like Python/Selenium. The data is then passed to three distinct LLMs, producing three JSON outputs to minimize hallucinations—errors where AI generates inaccurate details. …"

Synthetic Mental Health Survey Dataset حسب Shakil Hossain (22546658)

"…Data were generated using Python code to simulate realistic patterns and scoring based on psychological constructs.This dataset was to develop a machine learning model for predicting severity of multiple mental health disorders & overall Mental Health Status based on survey responses and psychological features.…"

<b>Antibiotics in the Global River System Arising from Human Consumption</b> حسب Heloisa Ehalt Macedo (10319300)

"…</p><p dir="ltr">The data repository includes 3 datasets:</p><p dir="ltr">1. Python code: python project repository including the structure necessary for the model to run.…"

Enhancing Healthcare Transparency: Leveraging Machine Learning, GIS Mapping and Power BI for Private Hospital Insurance Claims Analysis حسب Maryam Binti Haji Abdul Halim (20249544)

"…</p><p dir="ltr">Key Features and Tools:</p><ul><li><b>Machine Learning Algorithms:</b> Leveraging <b>Python (pandas, numpy, scikit-learn)</b> for predictive modeling to assess claim validity and treatment outcomes.…"

<b>Effects of Lifestyle and GLP-1RA based Interventions on Waist Circumference: A Systematic Review and Meta-Analysis</b> حسب Samit Ghosal (22024556)

"…</li><li><b>R scripts (00–06)</b> — reproducible code for primary, sensitivity, subgroup, and meta-regression analyses, forest plots, funnel plots, ROB2 templates, and prediction intervals.…"

Accompanying data files (Melbourne, Washington DC, Singapore, and NYC-Manhattan) حسب Winston Yap (13771969)

"…Each folder contains the training and validation data, graph adjacency information, compiled reported energy consumption data for each city, and generated predictions.</p><p dir="ltr">Each zipped folder consists the following files:</p><ul><li>Graph data - City object nodes (.parquet) and COO format edges (.txt)</li><li>predictions.txt (model predictions from GraphSAGE model)</li><li>final_energy.parquet (Compiled training and validation building energy data)</li></ul><p dir="ltr">The provided files are supplementary to the code repository which provides Python notebooks stepping through the data preprocessing, GNN training, and satellite imagery download processes. …"

Leveraging explainable causal artificial intelligence to study forest gross primary productivity dynamics in China's protected areas حسب Pedro Cabral (18947566)

"…<p dir="ltr">A Python script used for modeling forest GPP in China´s Protected Areas, including mean encoding of the categorical variable climate zone (CZ), multicollinearity testing using Variance Inflation Factor (VIF), implementation of four machine learning models to predict forest GPP, XAI and causality analysis.…"

Seattle Demo Accompanying Files حسب Winston Yap (13771969)

"…<p dir="ltr">We release the data, code, and prepared city graph objects to facilitate city scale building operating energy prediction with Seattle as a case study. …"