What is K Pro?
K Pro is an agentic AI platform designed to explore complex biology and accelerate biomedical research. It combines unparalleled access to multimodal data, cutting-edge AI to understand biology, and pioneering agentic AI capabilities to help researchers make faster, more confident, and better-informed decisions.
Currently, K-Pro is available in two versions:
K Pro Free: The standard version for researchers and academics
K Pro: The advanced version with enhanced capabilities for pharmaceutical teams
Core capabilities
Consolidated knowledge from multiple sources:
By pulling from credible data sources (including PubMed and comprehensive biological knowledge bases), K Pro answers scientific questions with synthesized, evidence-based insights. All data and recommendations are fully traceable, allowing source verification.
Partnering with Consensus, leading AI-powered literature review service
K Pro users can access literature review content powered by Consensus. Consensus is an AI-powered academic search engine built on a database of over 220 million peer-reviewed research papers. Unlike general AI tools, every response is tied back to a real research paper and is grounded in scientific research.
Smart hypothesis testing:
You can use K Pro to validate scientific hypotheses, leveraging advanced statistical reasoning and up-to-date datasets. The system helps explore whether your ideas are supported by the current body of scientific evidence.
Scientific writing assistance:
K Pro generates high-quality, publication-ready text tailored to your research needs, including review paragraphs, scientific summaries, and manuscript sections.
Interactive data visualization:
K Pro creates interactive plots and data visualizations using resources like TCGA and MOSAIC, making it easy to summarize, analyze, and interpret complex patient datasets. You can explore data by slicing and dicing variables to uncover deeper insights.
Example: How K Pro differentiates from competition in the AI-for-target-prioritization space
Multimodal patient data at depth. Most platforms sit on top of aggregated public databases (Open Targets, GWAS Catalog, ChEMBL). K Pro is built on Owkin's data network of 164 academic medical institutions, with MOSAIC as the flagship cohort in oncology: one of the largest spatially-resolved multimodal oncology datasets, combining bulk RNA-seq, single-cell RNA-seq, spatial transcriptomics, whole-exome sequencing, H&E and IHC pathology imaging, and longitudinal clinical follow-up. For target prioritization, this enables spatial co-localization of targets with TLS structures, malignant-cell specificity at single-cell resolution, intra-tumor heterogeneity quantification.
Specialized AI models, wrapped in expert skills. K Pro orchestrates calls to specialized models like HistoPLUS (Owkin's computational pathology foundation model, Adjadj et al., 2025), which detects 13 cell types including under-studied immune populations like neutrophils and eosinophils, with 14% better F1 classification than prior SOTA at 5× fewer parameters. It can also call Owkin Zero, our proprietary biological reasoning model (32B-parameter post-trained model on ~10M curated Q&A pairs with reinforcement learning from verifiable biological rewards). These models are called by skills encoding specialized know-how — for example, how to orchestrate relevant data and tools to produce a target characterization package consistent with customer templates. Skills are provided by Owkin and can be customized per team.
For target prioritization specifically, K Pro is designed to improve several measurable outcomes:
Time to first target dossier (literature + expression + competitive landscape): 2–4 weeks of analyst time before K Pro, vs. hours with K Pro, reviewed and refined collaboratively
Number of targets evaluated in parallel for a given indication: a handful before (constrained by analyst capacity), vs. dozens in parallel and consistent campaigns with K Pro
Reproducibility of scoring across analysts and projects: same skill applied consistently with versioned cohort definitions
Evidence coverage (modalities per target): often bulk RNA-seq plus literature before, vs. bulk + single-cell + spatial RNA + pathology + clinical landscape in addition to literature with K Pro
Last updated
Was this helpful?