Hierarchical Deep Learning Framework for Automated Marine Vegetation and Fauna Analysis Using ROV Video Data by Bjørn Christian Weinbach (16918707)

“…</p><ol><li><b>MaskRCNN-Segmented Objects</b>:</li></ol><p dir="ltr"> - `.jpg` files representing segmented objects detected by the MaskRCNN model.…”

Supplementary Material for: The prediction of hematoma growth in acute intracerebral hemorrhage: from 2-dimensional shape to 3-dimensional morphology by figshare admin karger (2628495)

“…We subsequently constructed the 3-dimensional morphology models, including the probability of hematoma morphology (PHM) and the probability of comprehensive model (PCM), to predict HG. …”

Predictive Analysis of Mushroom Toxicity Based Exclusively on Their Natural Habitat. by Enrico Bertozzi (22461709)

“…Analysis of the confusion matrix revealed a critical limitation: although the model correctly identified 785 poisonous mushrooms, it misclassified 313 as edible (false negatives), which represents an unacceptable risk in a practical application.…”

Data Sheet 1_Nationwide epidemiological study of subarachnoid hemorrhage: trends in admissions, mortality, seasonality, costs, clipping, embolization, and the impact of COVID-19.pd... by Thiago Oscar Goulart (22485604)

“…</p>Methods<p>This retrospective study analyzed secondary data from the Brazilian public health system (DataSUS) using ICD-10 code I60 for aSAH. Key metrics included the evaluation of admissions with time-series in Python, and mortality rates, procedures, and costs.…”

Electrical Tactile Dataset (Piezoelectric and Accelerometer) for textures by Dexter Shepherd (13238508)

“…</p><p dir="ltr">X shape: (Number, frame, sensor index)</p><p dir="ltr">y shape: (Number,)</p><p dir="ltr">All files are in compressed numpy format. Python users can load in the dataset using the code provided in the ReadMe.…”

Machine Learning-Driven Discovery and Database of Cyanobacteria Bioactive Compounds: A Resource for Therapeutics and Bioremediation by Renato Soares (20348202)

“…The biochemical descriptors were then used to determine the most promising protein targets for human therapeutic approaches and environmental bioremediation using the best machine learning (ML) model. The creation of our database, coupled with the integration of computational docking protocols, represents an innovative approach to understanding the potential of cyanobacteria bioactive compounds. …”

Phylogenomics of aquatic bacteria by Krzysztof Jurdzinski (12519700)

“…</p> <p><br></p> <p>all_MSG_ids.txt - a text file with names of all the representative MAGs within all the MSG pairs.</p> <p><br></p> <p>filter_MSGs.py - a Python script to extract the MAGs from within the MSGs (given all_MSG_ids.txt) from a folder containing a larger set of sequences.…”

Optical Tactile (TacTip) Dataset for texture classification by Dexter Shepherd (13238508)

“…</p><p dir="ltr">X shape: (Number, frame, h, w)</p><p dir="ltr">y shape: (Number,)</p><p dir="ltr"><br></p><p dir="ltr">All files are in compressed numpy format. Python users can load in the dataset using the code provided in the ReadMe.…”

<b>Challenges and Strategies for the Management of Quality-Oriented Education Bases in Universities under Informatization Background</b> by Yang Yanxi (21571568)

“…Final codes, together with basic demographic attributes supplied by the institutions’ HR offices, were exported to Excel and cleaned in Python 3.10 using pandas 2.2.1 and numpy 1.26. …”

<b>Engineered Muscle-Derived Extracellular Vesicles Boost Insulin Sensitivity and Glucose Regulation</b> by Hagit Shoyhet (21090650)

“…</p><p dir="ltr"><b>miR_path_target_enrichment.csv</b></p><p dir="ltr"><b>Description:</b> KEGG pathway enrichment analysis results of shared mRNA targets of miRNAs miR-16-5p, miR-122-5p and miR-486-5p ranked by their interaction score defined in our paper. this includes the pathway name, the enrichment p-value, number of genes found in the term and number of miRNAs targeting these genes</p><p dir="ltr"><b>Code/software</b></p><p dir="ltr">Data were analyzed using R-V4.0.4, Python-V3.9.2 and GraphPad software. miRNA analyses were run in R-V4.0.4 Differential expression analysis was conducted using the “DEseq2” package and corrected for multiple hypotheses by FDR. …”

Daily histograms of wind speed (100m), wind direction (100m) and atmospheric stability derived from ERA5 by Marc Imberger (6226619)

“…The following bins (left edges) have been used to create the histograms:</p><p dir="ltr">Wind speed: [0, 40) m/s (bin width 1 m/s)<br>Wind direction: [0,360) deg (bin width 15 deg)<br>Stability: 5 discrete stability classes (1: very unstable, 2: unstable, 3: neutral, 4: stable, 5: very stable)</p><p><br></p><p dir="ltr"><b>Main Purpose:</b> The dataset serves as minimum input data for the CLIMatological REPresentative PERiods (climrepper) python package (https://gitlab.windenergy.dtu.dk/climrepper/climrepper) in preparation for public release).…”

Modules organization over different course editions. by Gabriele Pozzati (21094166)

“…<p>Course editions starting from 2019 are represented side-by-side, while different working days and weeks of the same course edition are displayed vertically. …”

Core data by Baoqiang Chen (21099509)

“…</p><p><br></p><p dir="ltr">For the 5′ UTR library, we developed a Python script to extract sequences and Unique Molecular Identifiers (UMIs) from the FASTQ files. …”

Chromosomal rearrangements among clade A pathogenic <i>Cryptococcus</i> species. by Marco A. Coelho (7353659)

“…<p>(A) Synteny comparisons between <i>C. neoformans</i> strain 125.91 (reference) and representative strains from 7 other clade A species (8 species total). …”

Data Sheet 1_Feasibility of predicting next-day fatigue levels using heart rate variability and activity-sleep metrics in people with post-COVID fatigue.csv by Nana Yaw Aboagye (22637360)

“…Background<p>Post-COVID fatigue (pCF) represents a significant burden for many individuals following SARS-CoV-2 infection. …”

Microscopic Detection and Quantification of Microplastic Particles in Environmental Water Samples by Derek Lam (11944213)

“…Image processing algorithms, implemented in Python using adaptive thresholding techniques, were applied to segment particles from the background. …”

Automatically Generated Chemical KG by Connor Oryan (19851477)

“…After a detailed exposition of the modeling method, the approach is demonstrated specifically for the synthetic chemistry of organic molecules from the text of approximately 100,000 full-length patents. …”

Nucleotide analogue tolerant synthetic RdRp mutant construct for Surveillance and Therapeutic Resistance Monitoring in SARS-CoV-2 by Tahir Bhatti (20961974)

“…From that massive dataset all publicly available sequences were extracted then a representative consensus genome was built.</p><p dir="ltr">A local custom AI model was trained on 10 Million historical genomes and data for Q1 of 2025 simulating remdesivir pressure to predict which mutations are likely to emerge under therapeutic selection.…”

Metaverse Gait Authentication Dataset (MGAD) by sandeep ravikanti (20704127)

“…How to Use the Dataset</b></h2><ul><li>Load the dataset in Python using Pandas:</li></ul><p><br></p><ul><li>Use the features for machine learning models in biometric authentication.…”