菜单
Deep variational autoencoder binning of metagenome contigs. Use this skill when working with vamb: installing, choosing parameters, running commands, interpreting outputs, or troubleshooting. Upstream: https://github.com/RasmussenLab/vamb. For stage routing use tool-selection / metagenomics-workflow.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/PKU-EMBL/Metagenomics-Skills --skill vamb命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
ABRicate — mass screening of contigs for AMR/virulence/plasmid markers against bundled databases (ResFinder, CARD, NCBI, VFDB, PlasmidFinder, EcoLI_VF, ARG-ANNOT, MEGARES, …). Use for fast multi-DB isolate or MAG screens and database concordance checks. Upstream: https://github.com/tseemann/abricate. Route via cge-finders / microbial-mining; official CGE CLI still via resfinder/plasmidfinder when phenotype mapping or PointFinder is required.
Route Center for Genomic Epidemiology (CGE) Finder-style screens and related isolate typing: PlasmidFinder, ResFinder, PointFinder, DisinFinder, VirulenceFinder, MobileElementFinder, pMLST, plus staramr / ABRicate wrappers and chromosomal mlst. Use for clinical/One-Health isolate typing and plasmid-borne AMR context — not community-wide dark-matter discovery. Child skills: plasmidfinder, resfinder, pointfinder, disinfinder, virulencefinder, mobileelementfinder, pmlst, staramr, abricate, mlst. Complements genomad, mob-suite, rgi, mobileog. Route via microbial-mining.
DisinFinder — CGE disinfectant / biocide resistance gene screen via the DisinFinder database, typically run through ResFinder. Use for isolate biocide-resistance markers alongside acquired AMR. DB: https://bitbucket.org/genomicepidemiology/disinfinder_db. Route via cge-finders / resfinder / microbial-mining.
| name | vamb |
| description | Deep variational autoencoder binning of metagenome contigs. Use this skill when working with vamb: installing, choosing parameters, running commands, interpreting outputs, or troubleshooting. Upstream: https://github.com/RasmussenLab/vamb. For stage routing use tool-selection / metagenomics-workflow. |
| license | MIT |
| category | analysis-tools |
| tags | ["binning","vae","deep-learning"] |
| upstream | https://github.com/RasmussenLab/vamb |
| stage | binning |
Upstream: VAMB
Nissen, J. N. et al. Improved metagenome binning and assembly using deep variational autoencoders. Nat. Biotechnol. 39, 555–560 (2021). https://doi.org/10.1038/s41587-020-00777-4
See also docs/references.md.
VAMB encodes coabundance + k-mer features with a VAE, then clusters the latent space. Key design claims from the paper:
Use VAMB as a diverse ensemble member vs MetaBAT2/MaxBin2. Still run
CheckM2; prefer basalt ★ / metawrap / dastool for multi-binner consensus
when publishing catalogues.
conda install -c bioconda vamb # if packaged; else follow upstream
vamb --outdir temp/bins/vamb --fasta contigs.fa --bamfiles temp/map/*.bam -p 16
# GPU optional depending on VAMB version / docs
| Flag | Notes |
|---|---|
--bamfiles | Sorted BAMs; multi-sample improves coabundance signal |
| multisplit / clustering | Follow upstream defaults unless reproducing a paper |
| GPU | Optional acceleration |
skani / instrain.semibin2 · comebin · metabat2 · dastool · basalt · skani ·
tool-selection · metagenomics-workflow