clustalo_msa

Name: clustalo_msa
Author: ai4protein

244stars35forks

How to install clustalo_msa?

ai4protein/venusfactory2/clustalo_msa

$npx -y skills add ai4protein/VenusFactory2 --skill clustalo_msa

Installs into the current project.

Summary

Multiple sequence alignment of proteins via EBI Clustal Omega web service. Use when you have ≥2 protein sequences in a FASTA file (≤4000 sequences, ≤4 MB) and need an alignment to assess conservation, residue importance, or domain structure. Do NOT use for: single sequences, homo

Files · 1

View on GitHub

SKILL.md

1	# Clustal Omega MSA (EBI)
2
3	## Overview
4
5	Submits a FASTA file with multiple protein sequences to the [EBI Clustal Omega REST service](https://www.ebi.ac.uk/jdispatcher/msa/clustalo), polls for completion, and downloads the resulting alignment in FASTA format. Pipeline is fully managed by the tool — the agent only provides the input FASTA and an output directory.
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| download_clustalo_msa_by_fasta \| `fasta_path` (required, path to input FASTA), `out_dir` (required), `email` (optional; falls back to env `USER_EMAIL`, then `noreply@venusfactory.cn`), `poll_interval` (default `10.0` s), `timeout_secs` (default `900` s) \| JSON: `{status, file_info {file_path, file_name, file_size, format: "fasta"}, content_preview, biological_metadata {input_sequences, aligned_sequences, job_id, email}, execution_context}` \| Submit + poll + download MSA. Writes `<input_stem>_msa.fasta` to `out_dir`. \|
12
13	## When to Use This Skill
14
15	- Compute MSA for a small/medium set of homologous proteins (UniProt search results, BLAST hits, manually curated set)
16	- Generate input for conservation scoring, phylogenetic analysis, or HMM profile training
17	- Identify conserved active-site residues from a small protein family
18
19	## When NOT to Use
20
21	- Single sequence input → use `protein_sequence_similarity_search` to first find homologs
22	- >4000 sequences or >4 MB FASTA → EBI rejects; split into chunks or run locally with `mafft --auto`
23	- DNA / RNA alignment → Clustal Omega is for proteins
24	- Structural alignment of 3D structures → use `download_foldseek_results_by_pdb_file`
25
26	## Pipeline
27
28	1. Validate input: file exists, size ≤ 4 MB, 2 ≤ sequence count ≤ 4000.
29	2. Submit: `POST https://www.ebi.ac.uk/Tools/services/rest/clustalo/run` with `email` + `title` + `sequence` form data.
30	3. Poll: `GET .../status/{job_id}` every `poll_interval` seconds until `FINISHED` (or `ERROR`/`FAILURE`/`NOT_FOUND` → fail fast).
31	4. Download: `GET .../result/{job_id}/fa` → FASTA alignment text.
32	5. Save: write to `<out_dir>/<input_stem>_msa.fasta`.
33
34	## Rate Limiting & Politeness
35
36	- The tool defaults to 10-second polls with a 15-minute wall-clock timeout.
37	- EBI requests a valid contact email — the default `noreply@venusfactory.cn` works but setting `USER_EMAIL` in your environment is preferred so EBI can contact you if your job affects service health.
38	- A single submit + many polls is the established contract; do not invoke the tool in a tight loop.
39
40	## Common Mistakes
41
42	- Passing a single sequence: the tool errors with `ValidationError: need ≥2 sequences`. Run a similarity search first.
43	- Pasting raw sequences into a tool argument: this tool only accepts a file path. Write the FASTA to disk first (use `read_fasta`, `extract_uids_from_fasta`, etc., to compose).
44	- Mixing nucleotide and protein sequences: EBI returns garbage. Filter the input FASTA before calling.
45
46	## References
47
48	- [EBI Clustal Omega REST docs](https://www.ebi.ac.uk/Tools/common/tools/help/index.html?tool=clustalo)
49	- [Terms of use](https://www.ebi.ac.uk/about/terms-of-use/)
50	- Adapted from `google-deepmind/science-skills:skills/protein_sequence_msa/scripts/msa_align.py`

People who liked this also viewed

6 picks

Type

clustalo_msa

244stars35forks

View on GitHub

How to install clustalo_msa?

ai4protein/venusfactory2/clustalo_msa

$npx -y skills add ai4protein/VenusFactory2 --skill clustalo_msa

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Clustal Omega MSA (EBI)
2
3	## Overview
4
5	Submits a FASTA file with multiple protein sequences to the [EBI Clustal Omega REST service](https://www.ebi.ac.uk/jdispatcher/msa/clustalo), polls for completion, and downloads the resulting alignment in FASTA format. Pipeline is fully managed by the tool — the agent only provides the input FASTA and an output directory.
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| download_clustalo_msa_by_fasta \| `fasta_path` (required, path to input FASTA), `out_dir` (required), `email` (optional; falls back to env `USER_EMAIL`, then `noreply@venusfactory.cn`), `poll_interval` (default `10.0` s), `timeout_secs` (default `900` s) \| JSON: `{status, file_info {file_path, file_name, file_size, format: "fasta"}, content_preview, biological_metadata {input_sequences, aligned_sequences, job_id, email}, execution_context}` \| Submit + poll + download MSA. Writes `<input_stem>_msa.fasta` to `out_dir`. \|
12
13	## When to Use This Skill
14
15	- Compute MSA for a small/medium set of homologous proteins (UniProt search results, BLAST hits, manually curated set)
16	- Generate input for conservation scoring, phylogenetic analysis, or HMM profile training
17	- Identify conserved active-site residues from a small protein family
18
19	## When NOT to Use
20
21	- Single sequence input → use `protein_sequence_similarity_search` to first find homologs
22	- >4000 sequences or >4 MB FASTA → EBI rejects; split into chunks or run locally with `mafft --auto`
23	- DNA / RNA alignment → Clustal Omega is for proteins
24	- Structural alignment of 3D structures → use `download_foldseek_results_by_pdb_file`
25
26	## Pipeline
27
28	1. Validate input: file exists, size ≤ 4 MB, 2 ≤ sequence count ≤ 4000.
29	2. Submit: `POST https://www.ebi.ac.uk/Tools/services/rest/clustalo/run` with `email` + `title` + `sequence` form data.
30	3. Poll: `GET .../status/{job_id}` every `poll_interval` seconds until `FINISHED` (or `ERROR`/`FAILURE`/`NOT_FOUND` → fail fast).
31	4. Download: `GET .../result/{job_id}/fa` → FASTA alignment text.
32	5. Save: write to `<out_dir>/<input_stem>_msa.fasta`.
33
34	## Rate Limiting & Politeness
35
36	- The tool defaults to 10-second polls with a 15-minute wall-clock timeout.
37	- EBI requests a valid contact email — the default `noreply@venusfactory.cn` works but setting `USER_EMAIL` in your environment is preferred so EBI can contact you if your job affects service health.
38	- A single submit + many polls is the established contract; do not invoke the tool in a tight loop.
39
40	## Common Mistakes
41
42	- Passing a single sequence: the tool errors with `ValidationError: need ≥2 sequences`. Run a similarity search first.
43	- Pasting raw sequences into a tool argument: this tool only accepts a file path. Write the FASTA to disk first (use `read_fasta`, `extract_uids_from_fasta`, etc., to compose).
44	- Mixing nucleotide and protein sequences: EBI returns garbage. Filter the input FASTA before calling.
45
46	## References
47
48	- [EBI Clustal Omega REST docs](https://www.ebi.ac.uk/Tools/common/tools/help/index.html?tool=clustalo)
49	- [Terms of use](https://www.ebi.ac.uk/about/terms-of-use/)
50	- Adapted from `google-deepmind/science-skills:skills/protein_sequence_msa/scripts/msa_align.py`

People who liked this also viewed

6 picks

Type