Community Bonding Period - Second Meeting and Weekly work update
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...