Image 3_Transcriptomic profiling of diabetic retinopathy: insights into RPL11 and bisphenol A.jpeg by Jian Zhang (1682)

“…To validate the core gene, we conducted Gene Set Enrichment Analysis (GSEA, fgsea R package, version 1.35.8), immune cell infiltration profiling (CIBERSORT algorithm, version 1.03), molecular docking (AutoDock Vina, version 1.2.0), and molecular dynamics simulations (GROMACS, version 2022.4).…”

Image 6_Transcriptomic profiling of diabetic retinopathy: insights into RPL11 and bisphenol A.jpeg by Jian Zhang (1682)

“…To validate the core gene, we conducted Gene Set Enrichment Analysis (GSEA, fgsea R package, version 1.35.8), immune cell infiltration profiling (CIBERSORT algorithm, version 1.03), molecular docking (AutoDock Vina, version 1.2.0), and molecular dynamics simulations (GROMACS, version 2022.4).…”

Image 4_Transcriptomic profiling of diabetic retinopathy: insights into RPL11 and bisphenol A.jpeg by Jian Zhang (1682)

“…To validate the core gene, we conducted Gene Set Enrichment Analysis (GSEA, fgsea R package, version 1.35.8), immune cell infiltration profiling (CIBERSORT algorithm, version 1.03), molecular docking (AutoDock Vina, version 1.2.0), and molecular dynamics simulations (GROMACS, version 2022.4).…”

Image 1_Transcriptomic profiling of diabetic retinopathy: insights into RPL11 and bisphenol A.jpeg by Jian Zhang (1682)

“…To validate the core gene, we conducted Gene Set Enrichment Analysis (GSEA, fgsea R package, version 1.35.8), immune cell infiltration profiling (CIBERSORT algorithm, version 1.03), molecular docking (AutoDock Vina, version 1.2.0), and molecular dynamics simulations (GROMACS, version 2022.4).…”

Image 2_Transcriptomic profiling of diabetic retinopathy: insights into RPL11 and bisphenol A.jpeg by Jian Zhang (1682)

“…To validate the core gene, we conducted Gene Set Enrichment Analysis (GSEA, fgsea R package, version 1.35.8), immune cell infiltration profiling (CIBERSORT algorithm, version 1.03), molecular docking (AutoDock Vina, version 1.2.0), and molecular dynamics simulations (GROMACS, version 2022.4).…”

Code and data for evaluating oil spill amount from text-form incident information by Yiming Liu (18823387)

“…These are separately stored in the folders “description” and “posts”.</p><h2>Algorithms for Evaluating Release Amount (RA)</h2><p dir="ltr">The algorithms are split into the following three notebooks based on their functions:</p><ol><li><b>"1_RA_extraction.ipynb"</b>:</li><li><ul><li>Identifies oil spill-related incidents from raw incident data.…”

CSPP instance by peixiang wang (19499344)

“…</b></p><p dir="ltr">Its primary function is to create structured datasets that simulate container terminal operations, which can then be used for developing, testing, and benchmarking optimization algorithms (e.g., for yard stacking strategies, vessel stowage planning).…”

Spatiotemporal Soil Erosion Dataset for the Yarlung Tsangpo River Basin (1990–2100) by peng xin (21382394)

“…Bias correction was conducted using a 25-year baseline (1990–2014), with adjustments made monthly to correct for seasonal biases. The corrected bias functions were then applied to adjust the years (2020–2100) of daily rainfall data using the "ibicus" package, an open-source Python tool for bias adjustment and climate model evaluation. …”

Image 4_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.jpeg by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Table 2_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.xlsx by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Table 1_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.xlsx by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Image 3_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.jpeg by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Image 2_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.jpeg by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Table 3_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.xlsx by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Image 1_Integrated machine learning analysis of 30 cell death patterns identifies a novel prognostic signature in glioma.jpeg by Minhao Huang (4952764)

“…Through literature mining and GeneCards database screening, 30 programmed cell death (PCD)-related gene sets (total 11,681 genes) were curated, identifying 428 differentially expressed genes (DEGs; |log₂FC|>1, p < 0.05). A pan-death prognostic signature (Cell-Death Score, CDS) was constructed using 114 machine learning algorithm combinations, refined via CoxBoost to select 25 key genes. …”

Code by Baoqiang Chen (21099509)

“…We implemented machine learning algorithms using the following R packages: rpart for Decision Trees, gbm for Gradient Boosting Machines (GBM), ranger for Random Forests, the glm function for Generalized Linear Models (GLM), and xgboost for Extreme Gradient Boosting (XGB). …”

Core data by Baoqiang Chen (21099509)

“…We implemented machine learning algorithms using the following R packages: rpart for Decision Trees, gbm for Gradient Boosting Machines (GBM), ranger for Random Forests, the glm function for Generalized Linear Models (GLM), and xgboost for Extreme Gradient Boosting (XGB). …”

Landscape17 by Vlad Carare (22092515)

“…</p><p dir="ltr">We utilized TopSearch, an open-source Python package, to perform landscape exploration, at an estimated cost of 10⁵CPUh. …”

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

“…</p><h2>Project Structure</h2><pre><pre>Perception_based_neighbourhoods/<br>├── raw_data/<br>│ ├── ET_cells_glasgow/ # Glasgow grid cells for analysis<br>│ └── glasgow_open_built/ # Built area boundaries<br>├── svi_module/ # Street View Image processing<br>│ ├── svi_data/<br>│ │ ├── svi_info.csv # Image metadata (output)<br>│ │ └── images/ # Downloaded images (output)<br>│ ├── get_svi_data.py # Download street view images<br>│ └── trueskill_score.py # Generate TrueSkill scores<br>├── perception_module/ # Perception prediction<br>│ ├── output_data/<br>│ │ └── glasgow_perception.nc # Perception scores (demo data)<br>│ ├── trained_models/ # Pre-trained models<br>│ ├── pred.py # Predict perceptions from images<br>│ └── readme.md # Training instructions<br>└── cluster_module/ # Neighbourhood clustering<br> ├── output_data/<br> │ └── clusters.shp # Final neighbourhood boundaries<br> └── cluster_perceptions.py # Clustering algorithm<br></pre></pre><h2>Prerequisites</h2><ul><li>Python 3.8 or higher</li><li>GDAL/OGR libraries (for geospatial processing)</li></ul><h2>Installation</h2><ol><li>Clone this repository:</li></ol><p dir="ltr">Download the zip file</p><pre><pre>cd perception_based_neighbourhoods<br></pre></pre><ol><li>Install required dependencies:</li></ol><pre><pre>pip install -r requirements.txt<br></pre></pre><p dir="ltr">Required libraries include:</p><ul><li>geopandas</li><li>pandas</li><li>numpy</li><li>xarray</li><li>scikit-learn</li><li>matplotlib</li><li>torch (PyTorch)</li><li>efficientnet-pytorch</li></ul><h2>Usage Guide</h2><h3>Step 1: Download Street View Images</h3><p dir="ltr">Download street view images based on the Glasgow grid sampling locations.…”

Table 1_Mitochondrial non-coding RNAs as novel biomarkers and therapeutic targets in lung cancer integration of traditional bioinformatics and machine learning approaches.xlsx by Liu Haoming (22524473)

“…</p>Methods<p>We analyzed TCGA-LUAD/LUSC miRNA-seq data to identify mtRNAs via mitochondrial genome alignment. Machine learning algorithms (SVM, Random Forest, Logistic Regression) classified samples using differentially expressed mtRNAs (P < 0.01, |log2FC| > 1). …”