Gsoc2025: Enhancing SBOannotator with LLM Integration & Dynamic Term Retrieval

Hi, This week focused on the design and implementation of a dynamic update mechanism for SBO (Systems Biology Ontology) data. Key Decisions and Progress 1. Data Update Strategy Decision : On application startup → Check for updates → Download new data → Application becomes available Reason : Prioritize data consistency Status : ✅ Implemented and Pull Request submitted 2. User Control Over Updates Draeger’s Suggestion : Allow users to skip updates to support reproducibility of specific versions Nantia’s  Suggestion : Enforce updates to ensure data consistency Status :  Further discussion and decision in Wednesday's meeting 3. Data Version Management Strategy System Version History Management strategy1 :  Only retain the latest version to save storage  startegy 2:Retain up to 3 versions (2 historical + 1 latest) Status :  Further discussion and decision in  Wednesday's meeting User Import History Management strategy：...

Hi, On the June 23th, I met with the mentors again for the second time on Zoom. It was great meeting after a long discussion on the slacks. Now, here's the summary of the meeting. Topic 1 : ols No need to update the current rule based system. Local sbo table fields: no need to save the tree Topic 2:llm Use rule based system first to set sbo  Pseudo reaction ， transporter reaction and other element of reaction would totally rely on rule based system to set sbo Biochemical reaction would get sbo first from the rule based system.  Then we should hard code to filter reactions that are assigned the parent level of sbo . LLM would be used to find suitable leave level  sbo for these reactions. Only one type of prompt template here , since only one type of reaction would be assigned abo by llm We would use Explore enz to fetch 6000+ ec numbers and turn them into vector.We would use ols to fetch 40+ sbo , and turn them into vectors. When we input a reaction with ec, we would parse...

Hi,   On the May 15, 2025 (23:00–24:00 PDT 14 th of May (which is 08:00–09:00 CEST 15 th of May), I had my first online meeting with my mentors on Zoom meeting. It was a fantastic experience meeting them. We discussed how to start with the project. Here’s the summary of the meeting   Introduction   Established Slack as communication channel Half of my time will be for GSoC, half of the time will be preparing for interviews in job hunting market Discussed and filled out the Contributor-Mentor Agreement Create Shared Google Drive Discussed about proposed timeline and next steps By Friday 23 rd , we will have a fixes schedule Use blogpost.com to document brief weekly updates: https://gsoc2025jiahui.blogspot.com/ Use GitHub issues with comments to document updates on code The weekly work I have done: Play with the current Web application hosted at  TueVis  . Read the article of sbo Read the code in the repository line by line Regards!

  Hi, I am Jiahui Hu, 2nd year CSE student at the Northeastern University, Roorkee, India. I am incredibly excited to share that I was selected in the Google Summer of Code (GSoC) this year with the National Resource for Network Biology (NRNB) as a mentoring organization. I will be working on the project "Optimization of SBOannotator for Dynamic Term Integration and AI Enhancement" in this program. I am incredibly thankful to the wonderful mentors, namely Dr Nantia Leonidou，Dr. Andreas Dräger, who helped me to get selected and will guide me throughout this project. This blog series is dedicated mainly to share my progress for the project. The official coding period started from 23nd June, and the community bonding period begun from 8th May. In this period, I will be exploring the codebase with solving some small issues and will discuss the implementation details with the mentors and finalize them. What is NRNB? The National Resource for Network Biology (NRNB, https://www.nrnb...