[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QGAM8Q39WV1DCJWQ509NWV":3,"skill-same:01M6QGAM8Q39WV1DCJWQ509NWV":108},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":14,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":79},"01M6QGAM8Q39WV1DCJWQ509NWV","waypoint-bio",null,"Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"waypoint","waypoint bio","use","for","tables","metagenomics","foundation","datasets","models","hf","python","read","hugging face","atlas","open","checkpoint","Fine-Tuning","pypi","repos","github","2026-11-10 10:12:30",false,"---\nname: waypoint-bio\ndescription: Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format.\nlicense: MIT\ncompatibility: Requires Python 3.10+ with `waypoint-bio` (pulls torch, transformers, datasets, peft, scikit-learn). Needs network access and a Hugging Face token with access granted to the gated outpost-bio repos. A GPU is strongly recommended for pretraining and benchmarking.\nmetadata:\n  version: '1.1'\n  category: life-sciences\n  maintainer: Kalaris Labs\n  upstream-version: waypoint-bio 1.0.2 (PyPI); GitHub main 1.0.4\n  last-reviewed: '2026-08-17'\n  openclaw:\n    primaryEnv: HF_TOKEN\n    envVars:\n    - name: HF_TOKEN\n      required: true\n      description: Hugging Face read token with access to the gated outpost-bio\u002FWaypoint-*, outpost-bio\u002FAtlas, and outpost-bio\u002FCompass repos.\n  tags: microbiome, foundation models, metagenomics, benchmarks\n---\n\n# Waypoint: Outpost Bio's Open Microbiome Foundation Models\n\n## Overview\n\nOutpost Bio open-sourced three artefacts under Apache 2.0, described in\n[Treloar et al., bioRxiv 2026.05.02.722381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.05.02.722381v2):\n\n| Artefact | What it is | Hugging Face |\n| --- | --- | --- |\n| **Waypoint** | GPT-2-style causal LMs over taxonomic tokens, 6M–170M params | `outpost-bio\u002FWaypoint-6m`, `-45m`, `-170m` |\n| **Atlas** | 539,308 microbiome samples scraped from MGnify (485,377 pretrain \u002F 53,931 benchmark) | `outpost-bio\u002FAtlas` |\n| **Compass** | Eight downstream tasks over four studies | `outpost-bio\u002FCompass` |\n\nThe unifying idea: a microbiome sample is a *sentence*. Each taxon is one token, tokens are ordered\nby descending abundance z-score, and the model is trained with next-token prediction. A pretrained\ncheckpoint then supplies sample-level embeddings or a fine-tuning backbone for prediction tasks.\n\nAll of it is driven by one CLI, `waypoint`, with five subcommands: `prepare-dataset`, `embed`,\n`finetune`, `benchmark`, `pretrain`.\n\n## When to use\n\n- Embedding 16S\u002Fshotgun taxonomic profiles into fixed-size vectors for clustering, visualisation, or\n  a downstream classifier.\n- Fine-tuning a Waypoint checkpoint to predict a phenotype, treatment, or continuous readout from\n  community composition.\n- Scoring your own microbiome model against Compass so the number is comparable to the paper.\n- Pretraining a taxonomic language model on Atlas or on your own corpus.\n- Converting profiler output (MetaPhlAn, Kraken2\u002FBracken, QIIME 2, MGnify TSVs) into the input format\n  these tools expect.\n\n**Do not reach for this** when you have fewer than ~1,000 labelled samples — see\n[Scientific caveats](#scientific-caveats). A random forest on relative abundances is the better tool\nthere, and the paper says so.\n\n## Setup\n\n```bash\npip install waypoint-bio       # installs the `waypoint` command\n```\n\nAtlas, Compass, and every Waypoint checkpoint are **gated**. Access is auto-approved, but you must\nclick through once per repo and then authenticate:\n\n1. Request access on each repo page you need: [Waypoint-6m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-6m),\n   [Waypoint-45m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-45m),\n   [Waypoint-170m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-170m),\n   [Atlas](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Foutpost-bio\u002FAtlas),\n   [Compass](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Foutpost-bio\u002FCompass).\n2. Authenticate locally:\n\n   ```bash\n   hf auth login          # or: export HF_TOKEN=hf_...\n   ```\n\nA 401\u002F403 from any subcommand almost always means access was never requested on that specific repo —\na token alone is not enough. Use a read-scoped token. The tokenizer loads via\n`trust_remote_code=True`, so pin a `revision` if you need the remote code fixed across runs.\n\n## The waypoint data format\n\nEverything except `prepare-dataset` consumes **waypoint format**: a `.parquet` \u002F `.csv` \u002F `.tsv`\nwhose rows are samples, with two aligned list-columns plus any label columns you need.\n\n| Column | Type | Notes |\n| --- | --- | --- |\n| `Taxa` | `list[str]` | Full lineage strings, `;`-separated: `k__Bacteria; p__Firmicutes; ...; g__Lactobacillus` |\n| `Relative Abundances` | `list[float]` | Same length as `Taxa`, same order |\n| *(any)* | scalar | Targets, covariates, or a `Split` column |\n\nPrefer parquet. CSV\u002FTSV stores the lists as `repr` strings and round-trips through `ast.literal_eval`.\n\n**Give full lineages, not bare names.** The tokenizer extracts the genus segment (`g__`) from each\nlineage and falls back to the most specific higher rank when genus is missing. Bare names disable\nthat fallback entirely.\n\n## Workflow\n\n### 1. Get your data into waypoint format\n\nIf you already have a sample × taxa (or taxa × sample) abundance matrix with lineage labels:\n\n```bash\nwaypoint prepare-dataset \\\n    --input abundance_matrix.tsv \\\n    --metadata sample_labels.csv \\\n    --output dataset.parquet\n```\n\nOrientation is auto-detected from the first column header (`taxonomy`, `lineage`, `taxon`, `otu`,\n`#otu id` ⇒ taxa-as-rows); override with `--orientation`. Rows are normalised to sum to 1 unless you\npass `--no_normalize`, and zeros are dropped unless you pass `--keep_zeros`.\n\n`prepare-dataset` cannot read profiler output directly — MetaPhlAn uses `|` separators, Kraken2\nreports encode the hierarchy as indentation, and QIIME 2\u002FSILVA prefixes the domain `d__` instead of\n`k__` (which the tokenizer silently ignores). Use the bundled converter for those:\n\n```bash\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input merged_metaphlan.tsv --format metaphlan \\\n    --output dataset.parquet\n\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input reports\u002F*.kreport --format kraken \\\n    --output dataset.parquet\n\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input feature-table.tsv --format qiime2 \\\n    --output dataset.parquet\n```\n\nSee `references\u002Fdata-preparation.md` for every input layout, rank handling, and the `d__`\u002F`|` gotchas.\n\n### 2. Check vocabulary coverage before anything else\n\nWaypoint's vocabulary is fixed at pretraining time from Atlas. Taxa absent from it become `\u003Cunk>` and\nare **silently dropped** by `waypoint embed`; the paper names this as the models' main limitation. A\nsample whose taxa are all out-of-vocabulary yields a degenerate `[BOS][EOS]` embedding.\n\n```bash\npython scripts\u002Fvocab_coverage.py --model outpost-bio\u002FWaypoint-6m --data dataset.parquet\n```\n\nIt reports per-sample and abundance-weighted coverage and flags samples below a threshold. Treat\nmedian abundance-weighted coverage under ~0.8 as a reason to re-examine your taxonomy labels before\ntrusting any downstream number.\n\n### 3. Embed samples\n\n```bash\nwaypoint embed \\\n    --model outpost-bio\u002FWaypoint-6m \\\n    --data dataset.parquet \\\n    --output embeddings.parquet\n```\n\nOutput is indexed by sample ID with columns `dim_0 … dim_{H-1}` (`H` = 256 for 6m, 512 for 45m,\n768 for 170m). Defaults: `--pooling last_token`, `--batch_size 32`, `--max_length 512`, device\nauto-detected (`cuda` → `mps` → `cpu`).\n\nKeep `--pooling last_token` unless you have a reason to change it: it matches how the checkpoints\nwere pretrained and how `benchmark` and `finetune` pool. `mean` is a reasonable alternative for\nunsupervised use; `first_token`\u002F`cls_token` return the BOS position and carry little signal in a\ncausal LM.\n\n### 4. Fine-tune on your labels\n\n```bash\n# classification\nwaypoint finetune \\\n    --model outpost-bio\u002FWaypoint-45m \\\n    --data dataset.parquet \\\n    --output_dir outputs\u002Fft_disease \\\n    --task_type classification \\\n    --target \"Disease Status\" \\\n    --config configs\u002Ffinetune_classification.yaml\n\n# regression, with a categorical covariate one-hot appended to the pooled embedding\nwaypoint finetune \\\n    --model outpost-bio\u002FWaypoint-45m \\\n    --data dataset.parquet \\\n    --output_dir outputs\u002Fft_degradation \\\n    --task_type regression \\\n    --target \"Degradation Rate\" \\\n    --covariate_column Drug \\\n    --config configs\u002Ffinetune_regression.yaml\n```\n\nConfig paths resolve against the bundled `waypoint_bio\u002Fconfigs\u002F` tree, so `configs\u002F...` works from\nany directory without cloning.\n\nDefaults worth overriding for small datasets: `warmup_steps: 1000` (drop to ~50 so warmup finishes\nbefore early stopping), `num_epochs: 1` in the shipped configs (raise it — early stopping on\nvalidation loss is what actually terminates training), and `use_lora: true` when VRAM is tight\n(~1% of parameters trained; adapters are merged back before saving, so the checkpoint stays a plain\n`AutoModel`).\n\nSplits default to a random 80\u002F10\u002F10. **Set `split_column` to a `Split` column whenever samples are\ncorrelated** — repeated measures, one donor sampled over time, technical replicates — or a random\nsplit leaks and the test score is meaningless.\n\nOutputs land in `--output_dir`: `best_model\u002F` (loadable by `embed`\u002F`benchmark`),\n`test_metrics.json`, `training_log.csv` + `.html`, and `finetune_results.json`.\n\n### 5. Benchmark on Compass\n\n```bash\nwaypoint benchmark --model outpost-bio\u002FWaypoint-6m --output_dir outputs\u002Fbenchmark\nwaypoint benchmark --model outputs\u002Fpretrain\u002Fbest_model --tasks 1 6 --output_dir outputs\u002Fsmoke\n```\n\nFine-tunes a fresh head per task and writes `benchmark_results.json`. Classification tasks score\nmacro-F1; the one regression task scores R² clamped to [0, 1]; `final_score` is the unweighted mean\nacross tasks. Full task table, metric keys, and result-file schema: `references\u002Fcompass-benchmark.md`.\n\n### 6. Pretrain\n\n```bash\nwaypoint pretrain \\\n    --model_config configs\u002Fmodels\u002Fgpt2-45m.yaml \\\n    --pretrain_config configs\u002Fpretraining.yaml \\\n    --output_dir outputs\u002Fpretrain_45m\n```\n\nDownloads Atlas, builds a taxonomic tokenizer from the corpus, computes per-token abundance\nmean\u002Fstd for z-score ordering, then trains with next-token prediction and early stopping. Add\n`--data my_corpus.parquet` to pretrain on your own waypoint-format corpus instead, and\n`--max_samples N` for a smoke test.\n\nNine architectures ship, from `gpt2-6m.yaml` (8 layers, 256 hidden) to `gpt2-170m.yaml` (24 layers,\n768 hidden); per-head dimension is fixed at 64 throughout. `references\u002Fcli-reference.md` has the\nfull table and every config key.\n\n## Scientific caveats\n\nThese are load-bearing. Ignoring them produces numbers that look fine and mean nothing.\n\n- **Below ~1,000 labelled examples, Waypoint underperforms a random forest on raw abundances.** The\n  paper's crossover against the RF baseline sits near **10,000** training examples. Fit the baseline\n  first; only adopt the transformer if it wins on your data.\n- **Out-of-vocabulary taxa are dropped, not flagged.** Every Compass dataset carries some. Run\n  `scripts\u002Fvocab_coverage.py` and report the coverage alongside your results.\n- **45M, not 170M, was the best benchmark model.** Pretraining loss keeps falling with scale, but\n  downstream Compass score does not — start at 6m or 45m and only scale up if it demonstrably helps.\n- **Genus-level tokenisation is the default**, so species-level distinctions are collapsed. Changing\n  `taxon_rank` requires re-pretraining, not just re-tokenising.\n- **Compositional data.** Relative abundances are constrained to sum to 1; differences in one taxon\n  induce apparent changes in others. This affects interpretation of any per-taxon attribution.\n- **Batch and study effects dominate microbiome data.** Atlas spans MGnify pipelines v1.0–v5.0 and\n  four sequencing modalities. Never let a study or run boundary coincide with your label boundary.\n- **Not a clinical or diagnostic tool.** The model cards state this explicitly.\n\n## References\n\n- `references\u002Fcli-reference.md` — every subcommand flag, every config key, the model-size table.\n- `references\u002Fcompass-benchmark.md` — the eight tasks, filters, metrics, `benchmark_results.json` schema.\n- `references\u002Fdata-preparation.md` — waypoint format, profiler conversions, taxonomy string rules.\n- `references\u002Fpython-api.md` — using the tokenizer, datasets, heads, and checkpoints from Python.\n\n## Scripts\n\n- `scripts\u002Fprofiler_to_waypoint.py` — MetaPhlAn \u002F Kraken2 \u002F QIIME 2 \u002F generic lineage tables → waypoint format.\n- `scripts\u002Fvocab_coverage.py` — tokenizer coverage report for a waypoint-format file.\n\n## Upstream\n\nCode [github.com\u002FOutpost-Bio\u002Fwaypoint](https:\u002F\u002Fgithub.com\u002FOutpost-Bio\u002Fwaypoint) ·\npackage `waypoint-bio` ·\npaper [bioRxiv 2026.05.02.722381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.05.02.722381v2) ·\ncommunity [Waypoint Slack](https:\u002F\u002Fjoin.slack.com\u002Ft\u002Foutpostbio-waypoint\u002Fshared_invite\u002Fzt-3w6ivgtba-WJOCkdxiISxQpwVq9ZZxTA) ·\ncontact `waypoint@outpost.bio`.\n\nCite Treloar, N. J., Ur-Rehman, S., Yang, J., & Outpost Bio (2026). *Learning the Language of the\nMicrobiome with Transformers.* bioRxiv. Per-artefact DOIs are listed at\n[outpost.bio\u002Fcitations](https:\u002F\u002Fwww.outpost.bio\u002Fcitations).\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm tool versions, the reference genome\u002Fannotation build and the input formats (FASTQ, BAM, VCF, h5ad).\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run the pipeline on a small subset (one sample, one chromosome, a few thousand cells) first.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Check QC metrics, sample identities, genome build consistency and batch effects before interpreting results.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Genome builds or identifiers do not match between inputs | Stop and harmonize (liftover, ID mapping) before continuing. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Do not interpret biological significance beyond what the statistics support; report multiple-testing correction.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `scikit-bio`: Python library scikit-bio for biological sequence and community-ecology analysis: DNA\u002FRNA\u002Fprotein sequences, pair_align alignment, phylogen…\n- `distributed-llm-pretraining-torchtitan`: Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).\n","# Waypoint: Outpost Bio's Open Microbiome Foundation Models\n\n## Overview\n\nOutpost Bio open-sourced three artefacts under Apache 2.0, described in\n[Treloar et al., bioRxiv 2026.05.02.722381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.05.02.722381v2):\n\n| Artefact | What it is | Hugging Face |\n| --- | --- | --- |\n| **Waypoint** | GPT-2-style causal LMs over taxonomic tokens, 6M–170M params | `outpost-bio\u002FWaypoint-6m`, `-45m`, `-170m` |\n| **Atlas** | 539,308 microbiome samples scraped from MGnify (485,377 pretrain \u002F 53,931 benchmark) | `outpost-bio\u002FAtlas` |\n| **Compass** | Eight downstream tasks over four studies | `outpost-bio\u002FCompass` |\n\nThe unifying idea: a microbiome sample is a *sentence*. Each taxon is one token, tokens are ordered\nby descending abundance z-score, and the model is trained with next-token prediction. A pretrained\ncheckpoint then supplies sample-level embeddings or a fine-tuning backbone for prediction tasks.\n\nAll of it is driven by one CLI, `waypoint`, with five subcommands: `prepare-dataset`, `embed`,\n`finetune`, `benchmark`, `pretrain`.\n\n## When to use\n\n- Embedding 16S\u002Fshotgun taxonomic profiles into fixed-size vectors for clustering, visualisation, or\n  a downstream classifier.\n- Fine-tuning a Waypoint checkpoint to predict a phenotype, treatment, or continuous readout from\n  community composition.\n- Scoring your own microbiome model against Compass so the number is comparable to the paper.\n- Pretraining a taxonomic language model on Atlas or on your own corpus.\n- Converting profiler output (MetaPhlAn, Kraken2\u002FBracken, QIIME 2, MGnify TSVs) into the input format\n  these tools expect.\n\n**Do not reach for this** when you have fewer than ~1,000 labelled samples — see\n[Scientific caveats](#scientific-caveats). A random forest on relative abundances is the better tool\nthere, and the paper says so.\n\n## Setup\n\n```bash\npip install waypoint-bio       # installs the `waypoint` command\n```\n\nAtlas, Compass, and every Waypoint checkpoint are **gated**. Access is auto-approved, but you must\nclick through once per repo and then authenticate:\n\n1. Request access on each repo page you need: [Waypoint-6m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-6m),\n   [Waypoint-45m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-45m),\n   [Waypoint-170m](https:\u002F\u002Fhuggingface.co\u002Foutpost-bio\u002FWaypoint-170m),\n   [Atlas](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Foutpost-bio\u002FAtlas),\n   [Compass](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Foutpost-bio\u002FCompass).\n2. Authenticate locally:\n\n   ```bash\n   hf auth login          # or: export HF_TOKEN=hf_...\n   ```\n\nA 401\u002F403 from any subcommand almost always means access was never requested on that specific repo —\na token alone is not enough. Use a read-scoped token. The tokenizer loads via\n`trust_remote_code=True`, so pin a `revision` if you need the remote code fixed across runs.\n\n## The waypoint data format\n\nEverything except `prepare-dataset` consumes **waypoint format**: a `.parquet` \u002F `.csv` \u002F `.tsv`\nwhose rows are samples, with two aligned list-columns plus any label columns you need.\n\n| Column | Type | Notes |\n| --- | --- | --- |\n| `Taxa` | `list[str]` | Full lineage strings, `;`-separated: `k__Bacteria; p__Firmicutes; ...; g__Lactobacillus` |\n| `Relative Abundances` | `list[float]` | Same length as `Taxa`, same order |\n| *(any)* | scalar | Targets, covariates, or a `Split` column |\n\nPrefer parquet. CSV\u002FTSV stores the lists as `repr` strings and round-trips through `ast.literal_eval`.\n\n**Give full lineages, not bare names.** The tokenizer extracts the genus segment (`g__`) from each\nlineage and falls back to the most specific higher rank when genus is missing. Bare names disable\nthat fallback entirely.\n\n## Workflow\n\n### 1. Get your data into waypoint format\n\nIf you already have a sample × taxa (or taxa × sample) abundance matrix with lineage labels:\n\n```bash\nwaypoint prepare-dataset \\\n    --input abundance_matrix.tsv \\\n    --metadata sample_labels.csv \\\n    --output dataset.parquet\n```\n\nOrientation is auto-detected from the first column header (`taxonomy`, `lineage`, `taxon`, `otu`,\n`#otu id` ⇒ taxa-as-rows); override with `--orientation`. Rows are normalised to sum to 1 unless you\npass `--no_normalize`, and zeros are dropped unless you pass `--keep_zeros`.\n\n`prepare-dataset` cannot read profiler output directly — MetaPhlAn uses `|` separators, Kraken2\nreports encode the hierarchy as indentation, and QIIME 2\u002FSILVA prefixes the domain `d__` instead of\n`k__` (which the tokenizer silently ignores). Use the bundled converter for those:\n\n```bash\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input merged_metaphlan.tsv --format metaphlan \\\n    --output dataset.parquet\n\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input reports\u002F*.kreport --format kraken \\\n    --output dataset.parquet\n\npython scripts\u002Fprofiler_to_waypoint.py \\\n    --input feature-table.tsv --format qiime2 \\\n    --output dataset.parquet\n```\n\nSee `references\u002Fdata-preparation.md` for every input layout, rank handling, and the `d__`\u002F`|` gotchas.\n\n### 2. Check vocabulary coverage before anything else\n\nWaypoint's vocabulary is fixed at pretraining time from Atlas. Taxa absent from it become `\u003Cunk>` and\nare **silently dropped** by `waypoint embed`; the paper names this as the models' main limitation. A\nsample whose taxa are all out-of-vocabulary yields a degenerate `[BOS][EOS]` embedding.\n\n```bash\npython scripts\u002Fvocab_coverage.py --model outpost-bio\u002FWaypoint-6m --data dataset.parquet\n```\n\nIt reports per-sample and abundance-weighted coverage and flags samples below a threshold. Treat\nmedian abundance-weighted coverage under ~0.8 as a reason to re-examine your taxonomy labels before\ntrusting any downstream number.\n\n### 3. Embed samples\n\n```bash\nwaypoint embed \\\n    --model outpost-bio\u002FWaypoint-6m \\\n    --data dataset.parquet \\\n    --output embeddings.parquet\n```\n\nOutput is indexed by sample ID with columns `dim_0 … dim_{H-1}` (`H` = 256 for 6m, 512 for 45m,\n768 for 170m). Defaults: `--pooling last_token`, `--batch_size 32`, `--max_length 512`, device\nauto-detected (`cuda` → `mps` → `cpu`).\n\nKeep `--pooling last_token` unless you have a reason to change it: it matches how the checkpoints\nwere pretrained and how `benchmark` and `finetune` pool. `mean` is a reasonable alternative for\nunsupervised use; `first_token`\u002F`cls_token` return the BOS position and carry little signal in a\ncausal LM.\n\n### 4. Fine-tune on your labels\n\n```bash\n# classification\nwaypoint finetune \\\n    --model outpost-bio\u002FWaypoint-45m \\\n    --data dataset.parquet \\\n    --output_dir outputs\u002Fft_disease \\\n    --task_type classification \\\n    --target \"Disease Status\" \\\n    --config configs\u002Ffinetune_classification.yaml\n\n# regression, with a categorical covariate one-hot appended to the pooled embedding\nwaypoint finetune \\\n    --model outpost-bio\u002FWaypoint-45m \\\n    --data dataset.parquet \\\n    --output_dir outputs\u002Fft_degradation \\\n    --task_type regression \\\n    --target \"Degradation Rate\" \\\n    --covariate_column Drug \\\n    --config configs\u002Ffinetune_regression.yaml\n```\n\nConfig paths resolve against the bundled `waypoint_bio\u002Fconfigs\u002F` tree, so `configs\u002F...` works from\nany directory without cloning.\n\nDefaults worth overriding for small datasets: `warmup_steps: 1000` (drop to ~50 so warmup finishes\nbefore early stopping), `num_epochs: 1` in the shipped configs (raise it — early stopping on\nvalidation loss is what actually terminates training), and `use_lora: true` when VRAM is tight\n(~1% of parameters trained; adapters are merged back before saving, so the checkpoint stays a plain\n`AutoModel`).\n\nSplits default to a random 80\u002F10\u002F10. **Set `split_column` to a `Split` column whenever samples are\ncorrelated** — repeated measures, one donor sampled over time, technical replicates — or a random\nsplit leaks and the test score is meaningless.\n\nOutputs land in `--output_dir`: `best_model\u002F` (loadable by `embed`\u002F`benchmark`),\n`test_metrics.json`, `training_log.csv` + `.html`, and `finetune_results.json`.\n\n### 5. Benchmark on Compass\n\n```bash\nwaypoint benchmark --model outpost-bio\u002FWaypoint-6m --output_dir outputs\u002Fbenchmark\nwaypoint benchmark --model outputs\u002Fpretrain\u002Fbest_model --tasks 1 6 --output_dir outputs\u002Fsmoke\n```\n\nFine-tunes a fresh head per task and writes `benchmark_results.json`. Classification tasks score\nmacro-F1; the one regression task scores R² clamped to [0, 1]; `final_score` is the unweighted mean\nacross tasks. Full task table, metric keys, and result-file schema: `references\u002Fcompass-benchmark.md`.\n\n### 6. Pretrain\n\n```bash\nwaypoint pretrain \\\n    --model_config configs\u002Fmodels\u002Fgpt2-45m.yaml \\\n    --pretrain_config configs\u002Fpretraining.yaml \\\n    --output_dir outputs\u002Fpretrain_45m\n```\n\nDownloads Atlas, builds a taxonomic tokenizer from the corpus, computes per-token abundance\nmean\u002Fstd for z-score ordering, then trains with next-token prediction and early stopping. Add\n`--data my_corpus.parquet` to pretrain on your own waypoint-format corpus instead, and\n`--max_samples N` for a smoke test.\n\nNine architectures ship, from `gpt2-6m.yaml` (8 layers, 256 hidden) to `gpt2-170m.yaml` (24 layers,\n768 hidden); per-head dimension is fixed at 64 throughout. `references\u002Fcli-reference.md` has the\nfull table and every config key.\n\n## Scientific caveats\n\nThese are load-bearing. Ignoring them produces numbers that look fine and mean nothing.\n\n- **Below ~1,000 labelled examples, Waypoint underperforms a random forest on raw abundances.** The\n  paper's crossover against the RF baseline sits near **10,000** training examples. Fit the baseline\n  first; only adopt the transformer if it wins on your data.\n- **Out-of-vocabulary taxa are dropped, not flagged.** Every Compass dataset carries some. Run\n  `scripts\u002Fvocab_coverage.py` and report the coverage alongside your results.\n- **45M, not 170M, was the best benchmark model.** Pretraining loss keeps falling with scale, but\n  downstream Compass score does not — start at 6m or 45m and only scale up if it demonstrably helps.\n- **Genus-level tokenisation is the default**, so species-level distinctions are collapsed. Changing\n  `taxon_rank` requires re-pretraining, not just re-tokenising.\n- **Compositional data.** Relative abundances are constrained to sum to 1; differences in one taxon\n  induce apparent changes in others. This affects interpretation of any per-taxon attribution.\n- **Batch and study effects dominate microbiome data.** Atlas spans MGnify pipelines v1.0–v5.0 and\n  four sequencing modalities. Never let a study or run boundary coincide with your label boundary.\n- **Not a clinical or diagnostic tool.** The model cards state this explicitly.\n\n## References\n\n- `references\u002Fcli-reference.md` — every subcommand flag, every config key, the model-size table.\n- `references\u002Fcompass-benchmark.md` — the eight tasks, filters, metrics, `benchmark_results.json` schema.\n- `references\u002Fdata-preparation.md` — waypoint format, profiler conversions, taxonomy string rules.\n- `references\u002Fpython-api.md` — using the tokenizer, datasets, heads, and checkpoints from Python.\n\n## Scripts\n\n- `scripts\u002Fprofiler_to_waypoint.py` — MetaPhlAn \u002F Kraken2 \u002F QIIME 2 \u002F generic lineage tables → waypoint format.\n- `scripts\u002Fvocab_coverage.py` — tokenizer coverage report for a waypoint-format file.\n\n## Upstream\n\nCode [github.com\u002FOutpost-Bio\u002Fwaypoint](https:\u002F\u002Fgithub.com\u002FOutpost-Bio\u002Fwaypoint) ·\npackage `waypoint-bio` ·\npaper [bioRxiv 2026.05.02.722381](https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002F10.64898\u002F2026.05.02.722381v2) ·\ncommunity [Waypoint Slack](https:\u002F\u002Fjoin.slack.com\u002Ft\u002Foutpostbio-waypoint\u002Fshared_invite\u002Fzt-3w6ivgtba-WJOCkdxiISxQpwVq9ZZxTA) ·\ncontact `waypoint@outpost.bio`.\n\nCite Treloar, N. J., Ur-Rehman, S., Yang, J., & Outpost Bio (2026). *Learning the Language of the\nMicrobiome with Transformers.* bioRxiv. Per-artefact DOIs are listed at\n[outpost.bio\u002Fcitations](https:\u002F\u002Fwww.outpost.bio\u002Fcitations).\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm tool versions, the reference genome\u002Fannotation build and the input formats (FASTQ, BAM, VCF, h5ad).\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run the pipeline on a small subset (one sample, one chromosome, a few thousand cells) first.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Check QC metrics, sample identities, genome build consistency and batch effects before interpreting results.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| Genome builds or identifiers do not match between inputs | Stop and harmonize (liftover, ID mapping) before continuing. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Do not interpret biological significance beyond what the statistics support; report multiple-testing correction.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `scikit-bio`: Python library scikit-bio for biological sequence and community-ecology analysis: DNA\u002FRNA\u002Fprotein sequences, pair_align alignment, phylogen…\n- `distributed-llm-pretraining-torchtitan`: Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).\n",{"name":5,"license":15,"metadata":44,"description":7,"compatibility":57},{"tags":45,"version":46,"category":47,"openclaw":48,"maintainer":54,"last-reviewed":55,"upstream-version":56},"microbiome, foundation models, metagenomics, benchmarks","1.1","life-sciences",{"envVars":49,"primaryEnv":51},[50],{"name":51,"required":52,"description":53},"HF_TOKEN",true,"Hugging Face read token with access to the gated outpost-bio\u002FWaypoint-*, outpost-bio\u002FAtlas, and outpost-bio\u002FCompass repos.","Kalaris Labs","2026-08-17","waypoint-bio 1.0.2 (PyPI); GitHub main 1.0.4","Requires Python 3.10+ with `waypoint-bio` (pulls torch, transformers, datasets, peft, scikit-learn). Needs network access and a Hugging Face token with access granted to the gated outpost-bio repos. A GPU is strongly recommended for pretraining and benchmarking.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-waypoint-bio","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":52},[69,72,75],{"tool":70,"command":71},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill waypoint-bio",{"tool":73,"command":74},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill waypoint-bio",{"tool":76,"command":77},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill waypoint-bio","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002FSKILL.md",[80,86,90,94,98,104],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fcli-reference.md","REFERENCE","参考文档",8988,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Freferences\u002Fcli-reference.md",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fcompass-benchmark.md",6952,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Freferences\u002Fcompass-benchmark.md",{"path":91,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fdata-preparation.md",8397,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Freferences\u002Fdata-preparation.md",{"path":95,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fpython-api.md",8440,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Freferences\u002Fpython-api.md",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fprofiler_to_waypoint.py","SCRIPT","脚本",16893,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Fscripts\u002Fprofiler_to_waypoint.py",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fvocab_coverage.py",8318,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-waypoint-bio\u002Fscripts\u002Fvocab_coverage.py",[109,140,164,190,214,238],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":120,"publishedAt":39},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[115],{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,22,137,138,139],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","browsing","request","youtube transcripts",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":39},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[147,148,149,150,125,151,152,153,154,155,156,157,158,159,21,160,161,162,163,22],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","platform","grow","posting","competitive",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":39},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000023","Skill与智能体开发",[174,158,38,175,176,177,178,179,21,180,181,58,182,183,184,185,186,187,188,189],"write a skill","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":39},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[197,198,199,200,201,202,203,204,205,21,206,132,207,208,209,210,211,23,212,213],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","directions","phase",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":39},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[220],{"categoryNo":171,"categoryName":172,"taxonomyType":118,"taxonomyTypeDesc":119},[222,223,224,225,226,175,202,227,228,229,230,231,158,232,131,233,234,235,236,237],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":244,"publishedAt":39},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[245,246,247,248,249,250,251,33,252,230,253,254,255,256,257,258,133,259,260,213],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]