Supplementary file 1_ParaDeep: sequence-based deep learning for residue-level paratope prediction using chain-aware BiLSTM-CNN models.docx by Piyachat Udomwong (22563212)

“…Its efficiency and scalability make it well-suited for early-stage antibody discovery, repertoire profiling, and therapeutic design, particularly in the absence of structural data. The implementation is freely available at https://github.com/PiyachatU/ParaDeep, with Python (PyTorch) code and a Google Colab interface for ease of use.…”

Concurrent spin squeezing and field tracking with machine learning by Junlei Duan (18393642)

“…<p dir="ltr">The dataset contains:</p><ol><li>Steady_squeezing.zip <b>a)</b> data for steady squeezing data and characteraztion <b>b)</b> data for pulse RF magnetormeter</li><li>Tracking1.zip <b>a)</b> data of OU process for Deep learning <b>b)</b> data of OU-jump process for Deep learning</li><li>Tracking2.zip <b>a)</b> data of white noise process in backaction experiment <b>b) </b>data of white noise process in rearrange experiment</li><li>Code <b>a)</b> Randomly signal generating code <b>b)</b> Deep learning codec.data pre-processing code</li></ol><p dir="ltr">The network is implemented using the torch 1.13.1 framework and CUDA 11.6 on Python 3.8.8. …”

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

“…</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. …”

face recognation with Flask by Muammar, SST, M.Kom (21435692)

“…Built using the <b>Flask</b> web framework (Python), this system provides a lightweight and scalable solution for implementing facial recognition capabilities in real-time or on-demand through a browser interface.…”

Single Cell DNA methylation data for Human Brain altas (MajorType+Region CG allc files) by Wubin Ding (11823941)

“…</p><p dir="ltr">PMID: 37824674</p><p><br></p><h2>How to download</h2><p dir="ltr">To quickly download the whole folder, Python package <a href="https://github.com/DingWB/pyfigshare" rel="noreferrer" target="_blank">pyfigshare</a> can be implemented. please refer to pyfigshare documentation: <a href="https://github.com/DingWB/pyfigshare" rel="noreferrer" target="_blank">https://github.com/DingWB/pyfigshare</a></p><p dir="ltr">for example: <code>figshare download 28424780 -o downlnoaded_data</code></p>…”

IGD-cyberbullying-detection-AI by Bryan James (19921044)

“…</p><h2>Requirements</h2><p dir="ltr">To run this code, you'll need the following dependencies:</p><ul><li>Python 3.x</li><li>TensorFlow</li><li>scikit-learn</li><li>pandas</li><li>numpy</li><li>matplotlib</li><li>imbalanced-learn</li></ul><p dir="ltr">You can install the required dependencies using the provided <code>requirements.txt</code> file.…”

Automatic data reduction for the typical astronomer by Bradford Holden (21789524)

“…PypeIt has been developed by a small team of astronomers with two leading philosophies: (1) build instrument-agnostic code to serve nearly any spectrograph; (2) implement algorithms that achieve Poisson-level sky-subtraction with minimal systematics to yield precisely calibrated spectra with a meaningful noise model. …”

Concurrent spin squeezing and field tracking with machine learning by Junlei Duan (18393642)

“…Randomly signal generating codeb.Deep learning codec.data pre-processing code The network is implemented using the torch 1.13.1 framework and CUDA 11.6 on Python 3.8.8. …”

Neural-Signal Tokenization and Real-Time Contextual Foundation Modelling for Sovereign-Scale AGI Systems by Lakshit Mathur (20894549)

“…</p><p dir="ltr"><b>Availability</b> — The repository includes LaTeX sources, trained model checkpoints, Python/PyTorch code, and synthetic datasets. Data are released under a Creative Commons Attribution-NonCommercial-4.0 (CC BY-NC 4.0) license; code under MIT License.…”

Gene Editing using Transformer Architecture by Rishabh Garg (5261744)

“…., the H-Bot sequence), it facilitates on-screen gene editing, enabling targeted mutations or the insertion of desired genes. Implementation requires Python and deep learning frameworks like TensorFlow or PyTorch, with optional use of Biopython for genetic sequence handling. …”

Supervised Classification of Burned Areas Using Spectral Reflectance and Machine Learning by Baptista Boanha (22424668)

“…Six Python scripts are provided, each implementing a distinct machine learning algorithm—Random Forest, k-Nearest Neighbors (k-NN), Multi-Layer Perceptron (MLP), Decision Tree, Naïve Bayes, and Logistic Regression. …”

Numerical analysis and modeling of water quality indicators in the Ribeirão João Leite reservoir (Goiás, Brazil) by Amanda Bueno de Moraes (22559249)

“…The code implements a statistical–computational workflow for parameter selection (VIF, Bartlett and KMO tests, PCA and FA with <i>varimax</i>) and then trains and evaluates machine-learning models to predict three key physico-chemical indicators: turbidity, true color, and total iron. …”

Core-Based Smart Sampling Framework: A Theoretical and Experimental Study on Randomized Partitioning for SAT Problems by DURGHAM QARALLEH (21904172)

“…We provide theoretical guarantees on complexity reduction and probabilistic completeness, apply the method to SAT instances, and evaluate its performance using experimental Python implementations. The results show that smart sampling drastically reduces the effective complexity of SAT problems and offers new insights into the structure of NP-complete problems.…”

Research Database by Ana Paula Fermiano (22439479)

“…</p><p dir="ltr">Statistical analysis was conducted through <b>multiple regression models</b> implemented in <b>Jamovi</b>, supported by Geographic Information System (GIS) tools to visualize spatial patterns. …”

Data from: Circadian activity predicts breeding phenology in the Asian burying beetle <i>Nicrophorus nepalensis</i> by Hao Chen (20313552)

“…</p><p dir="ltr">The dataset includes:</p><ol><li>Raw locomotor activity measurements (.txt files) with 1-minute resolution</li><li>Breeding experiment data (Pair_breeding.csv) documenting nest IDs, population sources, photoperiod treatments, and breeding success</li><li>Activity measurement metadata (Loc_metadataset.csv) containing detailed experimental parameters and daily activity metrics extracted using tsfresh</li></ol><p dir="ltr">The repository also includes complete analysis pipelines implemented in both Python (3.8.8) and R (4.3.1), featuring:</p><ul><li>Data preprocessing and machine learning model development</li><li>Statistical analyses</li><li>Visualization scripts for generating Shapley plots, activity pattern plots, and other figures</li></ul><p></p>…”

Leue Modulation Coefficients (LMC): A Smooth Continuum Embedding of Bounded Arithmetic Data by Jeanette Leue (22470409)

“…This Zenodo package includes: the full research paper (PDF), a complete Python implementation generating the LMC field and conductivity model, a numerical plot comparing discrete LMC values with the smoothed continuum field, a cover letter and supporting documentation. …”

PTPC v1.0 Numerical Baseline: Stable Multi-Bounce Cosmology Simulation by David Lewis Stewart Parry (22188211)

“…The included Python scripts simulate a low-RAM cosmological oscillator that evolves through successive nonsingular “bounces,” demonstrating a self-consistent cyclic universe in which curvature, tension, and entropy reset in finite, periodic intervals. …”

Fast, FAIR, and Scalable: Managing Big Data in HPC with Zarr by Alfonso Ladino (21447002)

“…(NEXRAD), using open-source tools from the Python ecosystem such as Xarray, Xradar, and Dask to enable efficient parallel processing and scalable analysis. …”

Hippocampal and cortical activity reflect early hyperexcitability in an Alzheimer's mouse model by Marina Diachenko (19739092)

“…</p><p dir="ltr">All data are available upon request. The standalone Python implementation of the fE/I algorithm is available under a CC-BY-NC-SA license at <a href="https://github.com/arthur-ervin/crosci" target="_blank">https://github.com/arthur-ervin/crosci</a>. …”

Ambient Air Pollutant Dynamics (2010–2025) and the Exceptional Winter 2016–17 Pollution Episode: Implications for a Uranium/Arsenic Exposure Event by Thomas Clemens Carmine (19756929)

“…Includes imputation statistics, data dictionary, and the Python imputation code (Imputation_Air_Pollutants_NABEL.py). …”