AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
아직 감지된 업데이트가 없습니다. GitHub 릴리스가 나오면 여기에 보입니다.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기Molecular biology design and analysis tools for DNA sequences, plasmids, enzymes, primers and cloning.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Molecular biology design and analysis tools for DNA sequences, enzymes, primers and cloning.
This repo uses pixi and nothing else — no pip, no conda, no uv.
Clone it, then:
Plan a Golden Gate cloning job from a vector file and an insert file:
Four files land in plan/. product.dna is the assembled plasmid, with its features and
primers marked. primers.tsv is the oligos to order. protocol.json is the protocol written
as data. protocol.html is the page made from that data, one page you can follow at the bench:
reagents, reaction tables, programs, expected bands and troubleshooting.README 전문 보기 ↗Molecular biology design and analysis tools for DNA sequences, enzymes, primers and cloning.
This repo uses pixi and nothing else — no pip, no conda, no uv. Clone it, then:
pixi install
Plan a Golden Gate cloning job from a vector file and an insert file:
pixi run mbio cloning goldengate plan vector.dna insert.dna --out plan/
Four files land in plan/. product.dna is the assembled plasmid, with its features and
primers marked. primers.tsv is the oligos to order. protocol.json is the protocol written
as data. protocol.html is the page made from that data, one page you can follow at the bench:
reagents, reaction tables, programs, expected bands and troubleshooting.
If you edit protocol.json, turn it back into a page:
pixi run mbio protocol render plan/protocol.json
The same thing from Python:
from mbio.cloning.goldengate import plan_assembly
plan = plan_assembly("vector.dna", "insert.dna")
plan.write("plan/")
Sequence files are read into one shared model, whatever their format:
from mbio.io import read_record
record = read_record("vector.dna")
One wheel, two import packages. mbio is the general toolkit above; synbio
holds the lab's own named methods and has its own command, so a barcoded combinatorial library
is planned with pixi run synbio igga plan.
A primer pair can also be checked against a whole genome, so you learn where else it would amplify before you order it: check primers on a genome.
The docs have a worked example: GFP into pUC19, with the protocol it writes.
pixi run check
That runs the linters, the type checker and the tests. It reports every failure at once, so read to the bottom before you fix anything.
The site is at https://liuhlab.github.io/liulab-mbio/.
Build it yourself with pixi run docs-build.
Skills for coding agents live in skills/. Link them into each agent's own folder:
python skills/install.py --target all
If you work on the lab's clusters, add the shared plugin once per machine:
/plugin marketplace add liuhlab/liulab-compute-skills
/plugin install lab-compute@liulab