About half of all proteins in our cells don't hold a fixed shape — they're floppy, constantly changing form, and that's actually how they do their jobs. The problem is, because they don't sit still, scientists have had a very hard time understanding what they do and how they go wrong in diseases like cancer or Alzheimer's. IDPfun built a suite of software tools and databases that automatically detect, classify, and catalog these shapeless proteins, making it much easier for researchers and drug developers to figure out which ones matter and why. Think of it like creating the first proper map for a territory that was previously just labeled "here be dragons."
By the numbers
~50%
Share of eukaryotic protein residues that are intrinsically disordered
8
Consortium partners
6
Countries represented
11
Total deliverables produced
EUR 1,291,500
EU contribution
8
Software tools and packages delivered
The business problem
What needed solving
Drug developers and biotech companies face a massive blind spot: roughly half of all protein residues in human cells are intrinsically disordered, meaning they don't hold a fixed shape. Standard protein analysis tools can't properly detect or classify these regions, leaving companies guessing about targets linked to cancer, neurodegeneration, and other diseases. Without proper tools to identify and understand disordered proteins, drug discovery pipelines waste time and money pursuing targets they don't fully understand.
The solution
What was built
IDPfun delivered 8 distinct software tools including: a pipeline for automatic detection of disordered regions from protein crystal structures, a literature-mining tool for extracting disorder information from scientific papers, software for identifying homologous disorder clusters in sequence databases, a disorder-type classification tool, a new version of the Mobi analysis software, and a package for extracting protein ensemble data. All results were integrated into MobiDB and cross-linked to UniProt and InterPro.
Audience
Who needs this
Pharma companies with disordered protein drug targets (e.g. targeting p53, alpha-synuclein, tau)Bioinformatics CROs offering computational protein analysis servicesBiotech startups developing protein-based therapeutics or diagnosticsAcademic spin-offs commercializing structural biology toolsProteomics platform companies integrating disorder prediction into their workflows
Business applications
Who can put this to work
Pharmaceutical / Drug Discovery
enterprise
Target: Pharma or biotech companies targeting intrinsically disordered proteins for drug development
If you are a pharma company struggling to develop drugs against disordered protein targets — this project built software tools that automatically detect and classify intrinsically disordered regions, integrated into major databases like UniProt and InterPro. These tools help you identify which disordered protein segments are druggable and understand their functional mechanisms, potentially cutting early-stage target validation time. The consortium of 8 partners across 6 countries produced 11 deliverables including structure-detection pipelines and literature-mining tools.
Bioinformatics / Computational Biology Services
SME
Target: CROs or bioinformatics service companies offering protein analysis
If you are a bioinformatics service provider looking to expand your protein analysis capabilities — IDPfun developed multiple open software packages including tools for automatic detection of disordered regions from protein structures, literature mining for disorder-related data, and classification of different disorder types. These can be integrated into your computational pipelines to offer clients a more complete picture of protein behavior, covering the roughly half of eukaryotic protein residues that are intrinsically disordered.
If you are a diagnostics company working on protein biomarkers and struggling with targets that don't behave like textbook proteins — IDPfun created tools that identify homologous disordered protein clusters and extract ensemble data, helping you understand which disordered protein signatures are conserved and functionally relevant. The project's MobiDB database integration means your team can cross-reference disorder data with major protein resources like InterPro and UniProt for biomarker validation.
Frequently asked
Quick answers
What would it cost to access or license these tools?+
Based on available project data, the software tools and database integrations (MobiDB, cross-links to UniProt/InterPro) were developed under an MSCA-RISE academic exchange program with EUR 1,291,500 EU funding. The tools appear to be research outputs likely available through academic licensing. Commercial licensing terms would need to be negotiated directly with the University of Padova as coordinator.
Can these tools handle industrial-scale protein datasets?+
The project produced software pipelines for automatic detection of disordered regions from protein structures and sequence databases, plus integration into major databases like UniProt and InterPro that already operate at proteome scale. The tools were designed to process large datasets, as indicated by deliverables covering automated extraction from both structural data and literature. However, no industrial-scale deployment or benchmarking data is documented.
Who owns the IP and can we license it?+
The project was coordinated by Universita degli Studi di Padova (Italy) under an MSCA-RISE grant. IP rights are typically shared among the 8 consortium partners across 6 countries according to their consortium agreement. Any licensing would likely require negotiation with the coordinator and potentially multiple academic partners.
Are these tools validated against known disease targets?+
The project objective states that intrinsically disordered proteins are 'involved in numerous human diseases' and are 'major players in cellular regulation.' The deliverables focus on detection and classification software rather than specific disease validation studies. Based on available project data, clinical or disease-specific validation would need to be confirmed with the consortium.
How do these tools integrate with existing bioinformatics infrastructure?+
Integration was a core deliverable: the project cross-linked its disorder data into UniProt and InterPro (two of the most widely used protein databases globally) and integrated new data into MobiDB. This means the tools connect directly with infrastructure most bioinformatics teams already use, reducing adoption friction significantly.
What is the timeline from accessing these tools to generating useful results?+
The project ran from 2018 to 2023 and produced 11 deliverables including ready-to-use software packages for disorder detection, literature mining, and ensemble data extraction. Since the tools are already built and integrated into existing databases, a bioinformatics team could begin using the database integrations immediately. Deploying the standalone software packages would depend on your computational infrastructure.
Consortium
Who built it
The IDPfun consortium is purely academic — 6 universities and 2 research organizations across 6 countries (Argentina, Belgium, Germany, Hungary, Ireland, Italy), with zero industrial partners and zero SMEs. This is a 0% industry ratio, which is very low even for fundamental research. The coordinator, University of Padova, is a well-established bioinformatics hub. The EUR 1,291,500 MSCA-RISE funding was designed for researcher exchange, not product development. For a business looking to commercialize these tools, the absence of any industry validation or commercial partner means you would be the first to attempt market translation — which carries both risk and first-mover opportunity.
Want to explore licensing IDPfun's protein analysis tools for your drug discovery or bioinformatics pipeline? SciTransfer can connect you with the right people at the University of Padova. Contact us for a matchmaking consultation.
