{"id":25230637,"url":"https://github.com/bibymaths/ifa-2022","last_synced_at":"2025-04-05T15:22:31.299Z","repository":{"id":275216431,"uuid":"702882961","full_name":"bibymaths/IFA-2022","owner":"bibymaths","description":"Computational Algorithms \u0026 Data Science Projects","archived":false,"fork":false,"pushed_at":"2025-01-31T22:24:20.000Z","size":63384,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-11T12:00:01.340Z","etag":null,"topics":["bioinformatics","machine-learning","modelling","pattern-matching"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bibymaths.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-10T07:35:22.000Z","updated_at":"2025-01-31T22:24:24.000Z","dependencies_parsed_at":"2025-01-31T23:28:21.094Z","dependency_job_id":null,"html_url":"https://github.com/bibymaths/IFA-2022","commit_stats":null,"previous_names":["bibymaths/ifa-2022"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bibymaths%2FIFA-2022","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bibymaths%2FIFA-2022/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bibymaths%2FIFA-2022/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bibymaths%2FIFA-2022/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bibymaths","download_url":"https://codeload.github.com/bibymaths/IFA-2022/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247354665,"owners_count":20925479,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bioinformatics","machine-learning","modelling","pattern-matching"],"created_at":"2025-02-11T12:00:49.559Z","updated_at":"2025-04-05T15:22:31.281Z","avatar_url":"https://github.com/bibymaths.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **Group 7 - Computational Algorithms \u0026 Data Science Projects**\n\n## **Overview**\nThis repository contains various projects developed as part of the **Introduction to Focus Areas WS 22/23** at Freie Universität Berlin. The projects explore advanced algorithms, data science, machine learning, and computational techniques applied in real-world biological and medical datasets.\n\n## **Projects \u0026 Reports**\n### **1. Advanced Algorithms - Search Implementation**\n- **Report:** [`here`](Reports/Advanced_Algorithms.pdf)\n- **Poster:** [`here`](Poster/Poster_Advanced_Algorithms.pdf)\n- **Programming Languages:** C++, Perl, R\n- **Description:** Implemented and benchmarked various search algorithms:\n  - **Naive Search**\n  - **Suffix Array Search**\n  - **FM-Index Search**\n  - **FM-Index Search with Pigeonhole Principle**\n  - **Performance evaluation (runtime \u0026 memory usage)**\n- **Key Findings:** FM-Index search was the most efficient for large datasets, while naive search was computationally expensive.\n\n### **2. Complex Systems - Viral Infection Modeling**\n- **Report:** [`here`](Reports/Complex_Systems.pdf)\n- **Programming Language:** Python\n- **Description:**\n  - Developed and simulated **ordinary differential equation (ODE) models** to study viral infections.\n  - Performed **stochastic simulations** with the Stochastic Simulation Algorithm (SSA).\n  - Estimated unknown parameters using **optimization methods**.\n  - Analyzed how **infection probability changes** with viral exposure.\n- **Key Findings:** Identified key parameters affecting infection dynamics and established relationships between viral exposure and infection probability.\n\n### **3. Data Science - Classification \u0026 Machine Learning**\n- **Report:** [`here`](Reports/Data_Science.pdf)\n- **Presentation:** [`here`](Presentation/presentation.pdf)\n- **Programming Language:** R, Python\n- **Description:**\n  - **Project 1:** Classification of heart disease using machine learning models.\n    - Logistic Regression, Random Forest, Boosted Logistic Regression, k-Nearest Neighbors\n    - Performance metrics: Accuracy, Sensitivity, Specificity, AUC-ROC\n  - **Project 2:** Breast cancer classification using deep learning models.\n    - Convolutional Neural Network (CNN)\n    - Fully Connected Neural Network\n    - Shallow Neural Network (SNN)\n- **Key Findings:** CNN outperformed other models for breast cancer classification, while Boosted Logistic Regression had the best accuracy for heart disease classification.\n\n#### **Breast Cancer Image Classification**\n- **Programming Language:** Python (TensorFlow, Scikit-learn)\n- **Dataset:** BreaKHis - 7909 microscopic images from breast cancer tissues\n- **Description:**\n  - Implemented deep learning models to classify **benign vs. malignant** tissues.\n  - Used **CNN, Fully Connected NN, and Shallow NN** for classification.\n  - Evaluated models with **confusion matrices, accuracy plots, ROC curves**.\n- **Key Findings:** CNN performed best, while SNN and Fully Connected NN suffered from imbalanced training data.\n\n## **Installation \u0026 Dependencies**\nTo run the code from the Jupyter notebooks or scripts, ensure you have the following installed:\n\n```bash\npip install numpy pandas matplotlib seaborn tensorflow scikit-learn\n```\n\nFor R-based projects, install the necessary libraries:\n\n```r\ninstall.packages(c(\"caret\", \"ggplot2\", \"randomForest\", \"MLeval\"))\n```\n\n## **Contributors**\n- **Abhinav Mishra** (Bioinformatics) – Algorithm development, data science, and optimization.\n- **Jule Brenningmeyer** (Bioinformatics) – Machine learning and stochastic modeling.\n- **Maike Herkenrath** (Bioinformatics) – Data preprocessing and deep learning.\n- **Se Yeon Kim** (Data Science) – Heart disease classification and neural network training.\n\n## **References**\n- Detrano et al. (1989). *International application of a new probability algorithm for coronary artery disease*.\n- Spanhol et al. (2016). *A Dataset for Breast Cancer Histopathological Image Classification*.\n- Reinert, K. *FM-Index and Suffix Array Algorithms*","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbibymaths%2Fifa-2022","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbibymaths%2Fifa-2022","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbibymaths%2Fifa-2022/lists"}