BioHackathon

Whatsapp Group: https://chat.whatsapp.com/BbfrXA2Beuf3SFVNqF5nzc?mode=gi_t BioHackathon is where code meets chromosomes in an intensive competition where computational biology takes center stage. Whether you are wrangling RNA sequences, analyzing genomic datasets, or training ML models to decode biological mysteries, this is your playground for innovation. Bring your laptops, your A-game, and your caffeine because we are solving biotech's complex, data-driven puzzles in real time. Join us as we push the boundaries of healthcare, neuroscience, and AI-ML research! Event Description: Biothon 2.0 is the flagship computational biology competition organized by BioSoc, DTU, as part of Invictus. This intensive hackathon challenges participants to apply cutting-edge computational techniques to real-world biological problems. Competitors will choose between two specialized tracks: AI/ML-Based Biological Data Pipeline or RNA-Seq Data Analysis Pipeline, testing their skills in bioinformatics, machine learning, and data interpretation over a rigorous 3-4 hour competition. Event Structure & Tracks: Biothon 2.0 comprises two independent tracks. Participants must register for ONE track only: Track 1: AI/ML-Based Biological Data Pipeline A hands-on machine learning challenge where teams build predictive models on biological datasets. Track 2: RNA-Seq Data Analysis Pipeline A theory and application-based examination testing deep knowledge of RNA sequencing analysis, bioinformatics tools, and computational workflows. Track 1: AI/ML-Based Biological Data Pipeline: Format: Problem Statement Release: A computational biology problem statement and dataset will be released on the day of the competition. Objective: Teams must develop, train, and validate a machine learning model to solve the given problem. Duration: Strictly 3 hours from problem statement release. Submission: Teams must submit a CSV file containing predictions in the specified format. Team Structure: Team Size: 4-5 members per team (strictly enforced). Eligibility: Open to all undergraduate and postgraduate students from any college/university. Composition: Teams can have members from different colleges, departments, or years. Permitted Resources: Use of Google, web browsers, and online documentation. Access to standard ML libraries (scikit-learn, TensorFlow, PyTorch, pandas, NumPy, etc.). Biological databases and bioinformatics resources. Pre-existing code templates and notebooks (non-AI generated). Prohibited: Use of AI/LLM models (ChatGPT, Claude, Gemini, Copilot, or any AI code generation tools). Pre-trained models specifically designed for the exact problem (unless explicitly allowed). Communication with external mentors or experts during the competition. Evaluation Criteria: Primary Metric: Model accuracy on a held-out test dataset. Secondary Considerations: Code quality and documentation (if requested). Innovation in feature engineering and model architecture. Computational efficiency. Submission Guidelines: Submissions must be made through the designated platform before the deadline. Late submissions will NOT be accepted. File naming convention: TeamName_Predictions.csv In case of ties, the team that submits first will be ranked higher. Track 2: RNA-Seq Data Analysis Pipeline: Format: Type: Online examination covering RNA-Seq analysis concepts, tools, and applications. Duration: 1 hour 30 min. Total Questions: 25 questions divided into three sections of increasing difficulty. Total Marks: 225 marks. Team Structure: Team Size: 1 member per team (individual participation). Eligibility: Open to all undergraduate and postgraduate students from any college/university. Permitted Resources: Allowed: Access to biological databases (NCBI, Ensembl, UCSC Genome Browser, etc.). Bioinformatics tools documentation (BLAST, STAR, DESeq2, edgeR, etc.). Prohibited: Use of AI/LLM models (ChatGPT, Claude, Gemini, or similar tools). Communication with others during the examination. Pre-downloaded answer keys or solution guides. Use of Google and web browsers for research. Examination Structure: Section 1: Fundamentals (10 Questions): Marks per Question: +4 for correct answer. Negative Marking: -1 for incorrect answer. Unattempted: 0 marks. Total Section Marks: 40 marks. Focus: Basic concepts of RNA-Seq, sequencing technologies, quality control, and fundamental bioinformatics. Section 2: Intermediate Applications (10 Questions): Marks per Question: +8 for correct answer. Negative Marking: -3 for incorrect answer. Unattempted: 0 marks. Total Section Marks: 80 marks. Focus: Alignment algorithms, differential expression analysis, normalization methods, and tool-specific workflows. Section 3: Advanced Analysis (5 Questions): Marks per Question: +15 for correct answer. Negative Marking: -5 for incorrect answer. Unattempted: 0 marks. Total Section Marks: 75 marks (actual total should be 105 for consistency). Focus: Complex analytical pipelines, multi-omics integration, advanced statistical methods, and research interpretation. Submission Guidelines: All answers must be submitted through the online examination portal. Questions can be attempted in any order. Review and revision of answers is permitted until time expires. Automatic submission will occur when time expires. All submissions are timestamped automatically by the examination portal. In the event of identical scores, the participant who submits their answers first will be ranked higher. Participants are encouraged to manage their time efficiently and submit before the deadline. General Rules & Regulations: Registration: Each participant/team must provide valid contact information and institutional details. Registration closes 24 hours before the event or when capacity is reached. Identification & Verification: All participants must carry valid student ID cards and registration confirmation. Identity verification will be conducted before the competition begins. Participants without proper identification may be denied entry. Code Of Conduct: Academic Integrity: All work must be original. Plagiarism or submission of pre-existing solutions will result in immediate disqualification. Prohibited Devices: Mobile phones, smartwatches, or unauthorized electronic devices must be switched off and stored away during the competition (laptops/computers provided or designated for the competition are permitted). Professional Behavior: Participants must maintain respectful conduct towards fellow competitors, organizers, and judges. Zero Tolerance: Any form of cheating, data theft, sabotage, or violation of rules will lead to immediate disqualification and potential ban from future BioSoc events. Technical Requirements: Track 1 (AI/ML): Participants must bring their own laptops with required software pre-installed (Python, R, Jupyter notebooks, etc.). Power outlets will be provided, but teams are responsible for backup batteries. Teams will have to use their own internet during the exam. Track 2 (RNA-Seq): Participants must bring their personal laptops and Teams will have to use their own internet during the exam. Internet: WiFi will be provided, but teams should prepare for potential connectivity issues. Judging & Results: All decisions made by the judges and organizing committee are final and binding. Evaluation will be conducted by a panel of faculty members and industry experts. Results will be announced on the same day following evaluation. Top teams will be awarded certificates and prizes during the Invictus closing ceremony. Disputes & Clarifications: Any clarifications regarding problem statements or questions must be raised through designated channels only. Disputes must be filed within 30 minutes of the competition's conclusion. The organizing committee will review all disputes and provide final rulings. Awards & Recognition: Track 1 Winners: Top 3 teams will be awarded prizes, certificates, and recognition. Track 2 Winners: Top 3 individual performers will be awarded prizes, certificates, and recognition. All participants will receive participation certificates. Outstanding solutions may be featured on BioSoc's official platforms. Important Notes: The competition will begin promptly at the scheduled time. Late arrivals may not be accommodated. Lunch/refreshments will be provided (if applicable - confirm with organizers). Participants are advised to arrive 30 minutes before the scheduled start time for registration and setup. Any changes to the schedule or rules will be communicated via email and official BioSoc channels.