Image 2_Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques.tif by Liuqing Yang (128705)

“…Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). …”

Data Sheet 1_Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques.zip by Liuqing Yang (128705)

“…Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). …”

Table 1_Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques.docx by Liuqing Yang (128705)

“…Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). …”

Image 5_Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques.tif by Liuqing Yang (128705)

“…Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). …”

Supplementary Data: Biodiversity and Energy System Planning - Queensland 2025 by Andrew Rogers (17623239)

“…</li></ul><h3>Analysis Scripts</h3><p dir="ltr">Complete set of R scripts for reproducing all analyses:</p><ul><li><b>percent cost increase_line plot.R</b>: Creates visualizations of energy cost impacts under different conservation scenarios</li><li><b>Zonation curves.R</b>: Generates conservation performance curves and coverage statistics</li><li><b>NPV_bar_plot.R</b>: Produces economic analysis plots with Net Present Value breakdowns</li><li><b>domestic_export_map_iterations.R</b>: Creates spatial maps of renewable energy infrastructure for domestic and export scenarios</li></ul><h2>Technical Specifications</h2><h3>Data Formats</h3><ul><li><b>Spatial Data</b>: ESRI Geodatabase (.gdb), Shapefile (.shp), GeoTIFF (.tif)</li><li><b>Tabular Data</b>: CSV, Microsoft Excel (.xlsx, .xls)</li><li><b>Analysis Code</b>: R scripts (.R)</li></ul><h3>Software Requirements</h3><ul><li><b>R</b> (≥4.0.0) with packages: sf, dplyr, ggplot2, readr, readxl, tidyr, furrr, ozmaps, ggpattern</li><li><b>ESRI ArcGIS</b> or <b>QGIS</b> for geodatabase access and spatial analysis</li><li><b>Zonation</b> conservation planning software (for methodology understanding)</li></ul><h3>Hardware Recommendations</h3><ul><li><b>RAM</b>: 16GB minimum (32GB recommended for full spatial analysis)</li><li><b>Storage</b>: 15GB free space for data extraction and processing</li><li><b>CPU</b>: Multi-core processor recommended for parallel processing scripts</li></ul><h2>Detailed Description of the VRE Siting and Cost-Minimization Model</h2><p><br></p><p dir="ltr">This section provides an in-depth description of the Variable Renewable Energy (VRE) siting model, including the software, the core algorithm, and the optimisation process used to determine the least-cost, spatially constrained development trajectory for VRE infrastructure in Queensland, Australia.…”

Supplementary file 1_A real-world disproportionality analysis of FDA adverse event reporting system (FAERS) events for lecanemab.docx by Linlin Yan (4480570)

“…Using the Reporting Odds Ratio (ROR), Proportional Reporting Ratio (PRR), Bayesian Confidence Propagation Neural Network (BCPNN), and Multi-item Gamma Poisson Shrinker (MGPS) algorithms, we conducted a comprehensive analysis of lecanemab-related AEs, restricting the analysis to AEs with the role code of primary suspect (PS).…”

Data Sheet 1_Forestry climate adaptation with HarvesterSeasons service—a gradient boosting model to forecast soil water index SWI from a comprehensive set of predictors in Destinat... by Mikko Strahlendorff (20458865)

“…<p>Soil wetness forecasts on a local level are needed to ensure sustainable forestry operations during summer when the soil is neither frozen nor covered with snow. …”

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

“…</p><p dir="ltr"><b>Reference:</b> <code>cluster_perceptions.py</code> script logic</p><p dir="ltr">Stages:</p><ul><li>(a) Data input</li><li>(b) K-nearest neighbours spatial weights matrix</li><li>(c) Initial agglomerative clustering</li><li>(d) Merging small clusters</li><li>(e-f) Iterative splitting of largest clusters</li></ul><h4>Figure 7: Predicted Urban Perception Scores</h4><p dir="ltr">ET cell-level perception scores across the study area.…”

Additional file 1 of The origin and evolution of cultivated rice and genomic signatures of heterosis for yield traits in super-hybrid rice by Yiyong Zhao (21466062)

“…This table delineates the results of gene expression clustering using the MFUZZ algorithm for three super-hybrid rice varieties, namely LYP9, Y900, and XLY900, along with their progenitor strains. …”

Integrating urinary metabolomics and clinical datasets for multi-cancer detection by Dongyong Lee (18786694)

“…</p><p dir="ltr">- `group_code`: short group code </p><p dir="ltr"> - e.g., `Normal`, `HTN`, `DM`, `HTN+DM`, `CRC`, `LungCA`, `PancreasCA`.…”

archive.zip by Tasneem Fatima (21976946)

“…The dataset extracted from the archive consists of a large number of labeled images of wheat grains, organized in directories such as <code>wheat_for_cnn</code>, with filenames reflecting numerical categories (e.g., <code>10_1.jpg</code>, <code>100_5.jpg</code>, <code>200_0003.jpg</code>). …”

Performance evaluation of SpaVGN on melanoma ST dataset. by Haiyan Wang (25821)

“…Color-coded regions correspond to different tissue domains. …”

Collaborative Research: SCIPE: Interdisciplinary Research Support Community for Artificial Intelligence and Data Sciences by Sanmukh Kuppannagari (21798863)

“…<br><br>To achieve 10x-100x reduction in DNN energy consumption, a holistic approach is pursued, which encompasses: (1) new circuit designs that leverage emerging CMOS+X technologies; (2) a novel near-memory architecture in which processing elements are seamlessly integrated with traditional Dynamic RAM (DRAM); (3) novel 3D-matrix-based per-layer DNN computations and data-layout optimizations for kernel weights; and (4) algorithms and hardware/software co-design tailored for near-real-time DNN-based signal classification in next-generation wireless systems. …”

Monotone Cubic B-Splines with a Neural-Network Generator by Lijun Wang (176511)

“…We evaluate our method against several existing methods, some of which do not use the monotonicity constraint, on some monotone curves with varying noise levels. We demonstrate that our method outperforms the other methods, especially in high-noise scenarios. …”

Massive Mixed Models in Julia by Phillip M. Alday (2814652)

“…<p dir="ltr">Traditional approaches to mixed effects models using generalized least squares or expectation-maximization approaches struggle to scale to datasets with many thousands of observations and hundreds of levels of a single blocking variable. Special casing of nesting or crossing of random effects is required to achieve acceptable computational performance, but this special casing often makes it very difficult to handle less-than-idealized cases, such partial crossing or multiple levels of nesting. …”

Climate anomalies due to Cerrado native vegetation loss by Argemiro Leite-Filho (10283801)

“…</li></ul><p dir="ltr"><b>Code/software</b></p><p dir="ltr">To analyze the CSV files in your dataset, you can use various software options, such as R and Microsoft Excel. …”