ToolUniverse — 1000+ Scientific Tools
You have access to ToolUniverse, a unified ecosystem of 1000+ scientific tools that covers the full spectrum of biomedical research. These tools are pre-integrated in the sandbox and ready to use through three dedicated tools.
When to Use
Use ToolUniverse tools when the user needs:
- Drug Discovery: target identification, compound screening, ADMET prediction, drug safety, drug-drug interactions, drug repurposing
- Protein Analysis: structure retrieval (PDB/AlphaFold), function lookup (UniProt), interaction networks (STRING/BioGRID), therapeutic design
- Genomics: gene expression, GWAS analysis, variant interpretation (ACMG), enrichment analysis, single-cell RNA-seq
- Literature Search: multi-source paper search (PubMed/PubTator/EuropePMC/Semantic Scholar/OpenAlex), systematic reviews
- Clinical: trial matching, guidelines, pharmacovigilance, precision oncology, rare disease diagnosis
- Molecular: docking (Boltz2), SMILES-based property prediction, compound similarity, molecular visualization
- Omics: transcriptomics, proteomics, metabolomics, multi-omics integration, spatial transcriptomics
Three-Step Workflow
Always follow this sequence: Search → Info → Run
Step 1: Search for tools
tooluniverse_search(query="protein structure prediction", limit=5)
This returns a list of matching tools with names and descriptions. Use natural language to describe what you need.
Step 2: Check tool specification
tooluniverse_info(tool_name="UniProt_get_function_by_accession")
This returns the full parameter schema (required/optional args, types, descriptions). Always check this before running a tool to ensure you provide correct arguments.
Step 3: Execute the tool
tooluniverse_run(
tool_name="UniProt_get_function_by_accession",
arguments='{"accession": "P05067"}'
)
The arguments parameter is a JSON string containing the tool's parameters.
Common Tool Examples
Protein & Gene
| Tool |
Arguments Example |
UniProt_get_function_by_accession |
{"accession": "P05067"} |
UniProt_get_entry_by_accession |
{"accession": "P05067"} |
Drug Safety
| Tool |
Arguments Example |
FAERS_count_reactions_by_drug_event |
{"medicinalproduct": "aspirin"} |
Disease-Target
| Tool |
Arguments Example |
OpenTargets_get_associated_targets_by_disease_efoId |
{"efoId": "EFO_0000685"} |
Literature
| Tool |
Arguments Example |
PubTator_search_publications |
{"query": "CRISPR cancer therapy", "limit": 10} |
ADMET Prediction
| Tool |
Arguments Example |
ADMETAI_predict_BBB_penetrance |
{"smiles": ["CCO"]} |
ADMETAI_predict_toxicity |
{"smiles": ["CCO"]} |
Molecular Docking
| Tool |
Arguments Example |
boltz2_docking |
{"protein_id": "1ABC", "ligand_smiles": "CCO"} |
Multi-Step Research Patterns
Drug Safety Profile
tooluniverse_search("drug adverse events") → find FAERS toolstooluniverse_run("FAERS_count_reactions_by_drug_event", ...) → get adverse eventstooluniverse_run("FAERS_get_drug_label_info", ...) → get drug label
Disease Target Discovery
tooluniverse_run("OpenTargets_get_associated_targets_by_disease_efoId", ...) → targetstooluniverse_run("UniProt_get_entry_by_accession", ...) → protein detailstooluniverse_run("PubTator_search_publications", ...) → supporting literature
Compound Property Analysis
tooluniverse_search("ADMET prediction") → find prediction tools- Run multiple ADMET predictions (BBB, toxicity, bioavailability, solubility)
- Synthesize results into a compound profile
Tips
- Tool names follow a pattern:
Database_action_description (e.g., UniProt_get_entry_by_accession)
- First call may be slow (~30s) as ToolUniverse initializes; subsequent calls are fast
- Results can be large: focus on the most relevant fields for the user's question
- When unsure about tool name: use
tooluniverse_search with a broad query first
- Chain multiple tools for comprehensive analysis — combine data from different sources
- API keys are optional: most tools work without keys, but some (NVIDIA, HuggingFace) may need them for specific functionality
1---2name: tooluniverse3description: Access 1000+ scientific tools through ToolUniverse for drug discovery, protein analysis, genomics, literature search, clinical data, ADMET prediction, molecular docking, and more. Use when the user needs biomedical or scientific research capabilities.4---5
6# ToolUniverse — 1000+ Scientific Tools
7
8You have access to **ToolUniverse**, a unified ecosystem of 1000+ scientific tools that covers the full spectrum of biomedical research. These tools are pre-integrated in the sandbox and ready to use through three dedicated tools.
9
10## When to Use
11
12Use ToolUniverse tools when the user needs:
13
14- **Drug Discovery**: target identification, compound screening, ADMET prediction, drug safety, drug-drug interactions, drug repurposing
15- **Protein Analysis**: structure retrieval (PDB/AlphaFold), function lookup (UniProt), interaction networks (STRING/BioGRID), therapeutic design
16- **Genomics**: gene expression, GWAS analysis, variant interpretation (ACMG), enrichment analysis, single-cell RNA-seq
17- **Literature Search**: multi-source paper search (PubMed/PubTator/EuropePMC/Semantic Scholar/OpenAlex), systematic reviews
18- **Clinical**: trial matching, guidelines, pharmacovigilance, precision oncology, rare disease diagnosis
19- **Molecular**: docking (Boltz2), SMILES-based property prediction, compound similarity, molecular visualization
20- **Omics**: transcriptomics, proteomics, metabolomics, multi-omics integration, spatial transcriptomics
21
22## Three-Step Workflow
23
24**Always follow this sequence: Search → Info → Run**
25
26### Step 1: Search for tools
27
28```
29tooluniverse_search(query="protein structure prediction", limit=5)
30```
31
32This returns a list of matching tools with names and descriptions. Use natural language to describe what you need.
33
34### Step 2: Check tool specification
35
36```
37tooluniverse_info(tool_name="UniProt_get_function_by_accession")
38```
39
40This returns the full parameter schema (required/optional args, types, descriptions). **Always check this before running a tool** to ensure you provide correct arguments.
41
42### Step 3: Execute the tool
43
44```
45tooluniverse_run(
46 tool_name="UniProt_get_function_by_accession",
47 arguments='{"accession": "P05067"}'
48)
49```
50
51The `arguments` parameter is a **JSON string** containing the tool's parameters.
52
53## Common Tool Examples
54
55### Protein & Gene
56| Tool | Arguments Example |
57|------|-------------------|
58| `UniProt_get_function_by_accession` | `{"accession": "P05067"}` |
59| `UniProt_get_entry_by_accession` | `{"accession": "P05067"}` |
60
61### Drug Safety
62| Tool | Arguments Example |
63|------|-------------------|
64| `FAERS_count_reactions_by_drug_event` | `{"medicinalproduct": "aspirin"}` |
65
66### Disease-Target
67| Tool | Arguments Example |
68|------|-------------------|
69| `OpenTargets_get_associated_targets_by_disease_efoId` | `{"efoId": "EFO_0000685"}` |
70
71### Literature
72| Tool | Arguments Example |
73|------|-------------------|
74| `PubTator_search_publications` | `{"query": "CRISPR cancer therapy", "limit": 10}` |
75
76### ADMET Prediction
77| Tool | Arguments Example |
78|------|-------------------|
79| `ADMETAI_predict_BBB_penetrance` | `{"smiles": ["CCO"]}` |
80| `ADMETAI_predict_toxicity` | `{"smiles": ["CCO"]}` |
81
82### Molecular Docking
83| Tool | Arguments Example |
84|------|-------------------|
85| `boltz2_docking` | `{"protein_id": "1ABC", "ligand_smiles": "CCO"}` |
86
87## Multi-Step Research Patterns
88
89### Drug Safety Profile
901. `tooluniverse_search("drug adverse events")` → find FAERS tools
912. `tooluniverse_run("FAERS_count_reactions_by_drug_event", ...)` → get adverse events
923. `tooluniverse_run("FAERS_get_drug_label_info", ...)` → get drug label
93
94### Disease Target Discovery
951. `tooluniverse_run("OpenTargets_get_associated_targets_by_disease_efoId", ...)` → targets
962. `tooluniverse_run("UniProt_get_entry_by_accession", ...)` → protein details
973. `tooluniverse_run("PubTator_search_publications", ...)` → supporting literature
98
99### Compound Property Analysis
1001. `tooluniverse_search("ADMET prediction")` → find prediction tools
1012. Run multiple ADMET predictions (BBB, toxicity, bioavailability, solubility)
1023. Synthesize results into a compound profile
103
104## Tips
105
106- **Tool names follow a pattern**: `Database_action_description` (e.g., `UniProt_get_entry_by_accession`)
107- **First call may be slow** (~30s) as ToolUniverse initializes; subsequent calls are fast
108- **Results can be large**: focus on the most relevant fields for the user's question
109- **When unsure about tool name**: use `tooluniverse_search` with a broad query first
110- **Chain multiple tools** for comprehensive analysis — combine data from different sources
111- **API keys are optional**: most tools work without keys, but some (NVIDIA, HuggingFace) may need them for specific functionality
gabrielmoreira