Getting started

Introduction

ProteinIQ is a platform for running bioinformatics tools without writing code or managing infrastructure. You provide input data, choose a tool, and get results — all from the browser.

What ProteinIQ does

ProteinIQ wraps established open-source scientific tools — molecular docking engines, structure predictors, sequence analyzers, format converters — and makes them accessible through a web interface. The tools themselves are unchanged. ProteinIQ handles the compute, file handling, and result storage so you don't have to.

The platform is built for researchers who need reliable scientific outputs, not a simplified approximation of them. Results match what you would get running the same tool locally.

Core concepts

Tools

A tool is a single scientific program you can run on ProteinIQ. Each tool has:

  • Required inputs: sequences, structure files, SMILES strings, or other data the tool expects
  • Parameters: configuration options, most with sensible defaults
  • Outputs: result files, ranked tables, scores, or visualizations

Browse all available tools at /app/tools. Tools are grouped by category: protein folding, molecular docking, sequence analysis, format conversion, and more.

Jobs

Every time you run a tool, a job is created. A job tracks your input, the tool settings you used, and the results. Jobs persist in your history so you can revisit, compare, and download results later.

Jobs move through several states as they are processed. The most common are:

  • Pending: queued, waiting to start
  • Processing: actively running
  • Completed: finished, results available
  • Failed: something went wrong; credits are refunded automatically for platform errors

Read more about managing jobs.

Files

Every input you upload and every result file a tool produces is stored in your Files library. You can search, filter, preview, and download files across all your jobs from one place, without reopening each job individually.

Read more about the Files library.

Credits

Credits are the currency for running tools on ProteinIQ. Each tool has a credit cost based on the compute it requires. Simple analysis tools cost less; ML-powered tools like structure predictors cost more.

Credits are deducted when a job starts processing. If a job fails due to a platform error, credits are refunded. See credit costs and plans.

Workspaces

A workspace is a shared environment for a team. Members of the same workspace share a credit balance and can see each other's jobs. Each workspace has its own billing.

Personal accounts have a single default workspace. You can create additional workspaces to organize work across different projects or groups.

Read about workspaces and seats.

Input formats

Most tools accept data in multiple ways:

  • Paste text: sequences in FASTA format, SMILES strings, or raw structure data
  • Upload files: .pdb, .cif, .fasta, .sdf, and other standard formats
  • Database IDs: fetch structures directly from RCSB PDB (e.g., 1ABC) or PubChem

The tool page shows exactly what inputs it accepts.

Data privacy

Your research data is never sold or shared. Jobs and result files are stored only for your history and retrieval.

Next steps

  • Quickstart: Run your first tool in minutes
  • Jobs: Understand job management and history
  • Files: Browse and download files across all your jobs
  • Credits: How credits work and what tools cost