API Documentation

The GET API endpoint /tools allows users to see all available tools and their configurations. This returns an array of all tools you have access to along with their display names and configuration details.

The settings array in the output contains the configuration parameters that can be used with the /submit-job endpoint. Each tool also reports how it fits into a pipeline (taskType, outputTypes, outputs, filterMetrics) — see Pipelines → Concepts for how to chain tools.

HTTP Response Status Codes

Status code	Description
200	Successfully retrieved tools list
400	Bad request
405	Method not allowed
500	Internal server error

View all available tools and their configurations.

1import requests
2
3api_key = "***************"
4headers = {'x-api-key': api_key}
5base_url = "https://app.tamarind.bio/api/"
6
7response = requests.get(base_url + "tools", headers=headers)
8tools_data = response.json()
9print("Available tools:", tools_data)

Response Format

1[
2  {
3    "name": "abodybuilder",
4    "displayName": "ABodyBuilder3",
5    "github": "https://github.com/Exscientia/abodybuilder3",
6    "paper": "https://arxiv.org/abs/2405.20863",
7    "settings": [
8      {
9        "name": "heavy",
10        "type": "sequence",
11        "required": true,
12        "description": "Antibody heavy chain sequence"
13      },
14      {
15        "name": "light",
16        "type": "sequence",
17        "required": true,
18        "description": "Antibody light chain sequence"
19      }
20    ],
21    "description": "Antibody structure prediction",
22    "outputTypes": [
23      "pdb"
24    ],
25    "taskType": "structure-prediction",
26    "outputs": {
27      "produces": [
28        "pdb"
29      ],
30      "mainCSV": "chain_plddt.csv",
31      "columns": [
32        {
33          "name": "pdb_filepath",
34          "type": "pdb",
35          "displayName": "Structure",
36          "description": "Predicted antibody structure (output.pdb, single model across all chains)."
37        },
38        {
39          "name": "mean_plddt",
40          "type": "number",
41          "displayName": "Mean pLDDT",
42          "description": "Mean per-residue pLDDT confidence over the chain (0-100); higher is more confident."
43        }
44      ]
45    }
46  },
47  {
48    "name": "admet",
49    "displayName": "ADMET",
50    "github": "https://github.com/swansonk14/admet_ai",
51    "paper": "https://academic.oup.com/bioinformatics/article/40/7/btae416/7698030",
52    "settings": [
53      {
54        "name": "smilesStrings",
55        "required": true,
56        "type": "smiles",
57        "list": true,
58        "description": "List of SMILES strings to predict properties for"
59      }
60    ],
61    "description": "Quickly predict drug properties",
62    "outputTypes": [],
63    "taskType": "score",
64    "outputs": {
65      "produces": [
66        "smiles"
67      ],
68      "mainCSV": "pred.csv",
69      "columns": [
70        {
71          "name": "smiles",
72          "type": "smiles",
73          "displayName": "SMILES",
74          "description": "Input molecule as a canonical SMILES string."
75        },
76        {
77          "name": "logP",
78          "type": "number",
79          "displayName": "LogP",
80          "description": "Calculated octanol-water partition coefficient (lipophilicity)."
81        }
82      ]
83    }
84  }
85]