Interactomics for modern biology.

ProPaths reads a protein's entire literature and builds its interactome the way an expert curator would. Every interaction comes with its mechanism, direction, effects, kinetics, and the pathways it belongs to.

Explore the Demo Read the methodology

Every interactome, fully curated.

Every interaction is typed by kind and placed in a pathway ontology that keeps biological systems distinct, with each partner where the literature shows it functions and has an effect.

{{ svgText }}

Every interaction, fully explained.

Most resources tell you these two proteins are associated. Here is what ProPaths holds instead.

From literature to interactome.

Five stages, run per protein, from the primary literature to a traceable graph.

01

Retrieve the literature

The primary literature on a protein, through a query built for interaction biology, taking full text wherever it exists. No later stage can recover biology that was never read.

02

Extract candidates

Every paper is read for the interactions it reports: which protein acts on which, by what mechanism, in what direction, with what measured result. This pass is deliberately generous, and is judged on how little it misses.

03

Validate against the evidence

A second pass argues against the first and rejects most of what it produced. Speculation in a discussion section is not a finding, and anything the evidence does not carry is dropped rather than kept at a low score.

04

Assemble and place

What survives becomes a graph rather than a list, placed in the pathway ontology at every level it belongs to. A partner sits in every pathway the literature puts it in, not one.

05

Enrich and reconcile

Every paper touching a pair is read together into distinct claims, each carrying its mechanism, its measurements with the assays that produced them, and the papers behind it. Papers that disagree stay distinct.

Twenty minutes of compute. A few dollars. One interactome.

Read the full method

Built for developers and agents.

The interactome is a tool, not just a view. Everything in the demo is also a clean read API and a local MCP server, so an agent works the graph the way a curator does. It gets the map first, then pulls full mechanism and papers for the one edge it needs. Sized for a model's context window, not a browser, and it speaks MCP, so it drops into Claude in one line.

The question
The call
What comes back
The questionWhat does ATXN3 interact with?
The callget_protein("ATXN3")
What comes backThe whole map, sized to skimedges · kinds · pathway placement
The questionWhat exactly happens at one edge?
The callget_interaction(id)
What comes backThat edge, in fullmechanism · kinetics · PMIDs
Quick Start

Read the full API reference, or get the MCP server on GitHub.
For write access, higher limits, or a hosted MCP, get in touch.

Our demo is live.

The public demo is free and no account is required. Click the link below to get started.

Explore the Demo

If you have a question, or want your own protein read, get in touch.