Candidates prioritized
Repurposing candidates ranked using baseline organoid proteomes and drug features. Selected candidates were tested in three TNBC patient-derived organoids.
Explore AIVC for drug research, followed by our clinical diagnostics and laboratory products.
ProteinTalks establishes a research foundation in breast-cancer systems. Use predictions to prioritize candidates and test hypotheses independently.
Explore the AIVC platformExplore biological context and connect molecular hypotheses to response evidence.
Task-specific co-development
Evaluate drug-response predictions over time in defined cell systems, then test dose–response independently.
Published oncology tasks
Investigate pathways and resistance-associated protein signatures with functional assays.
Hypotheses plus experimental testing
Prioritize combination hypotheses and evaluate response in relevant resistant states.
Published oncology combination tasks
Test whether response representations transfer to patient-relevant experimental systems.
PDX response transfer and organoid research
Develop biomarker and response hypotheses with clinical research partners.
Retrospective evidence; prospective work required
Connect cellular responses to appropriate exposure models and healthy-tissue counter-screens.
Research extension requiring new evidence
Broader exposure, safety and prospective clinical uses require their own data and evaluation.
An operational perturbation proteomics-based virtual cell model.
Proteomic profiles across 18 breast-cancer cell lines.
Temporal protein measurements capturing cellular responses.
Drugs and drug combinations in the published response dataset.
Repurposing candidates ranked using baseline organoid proteomes and drug features. Selected candidates were tested in three TNBC patient-derived organoids.
A TNBC cohort supports clinically relevant prognostic research. The reported survival-analysis subgroup includes 62 low-risk and 59 high-risk patients.
Mean AUROC in the reported study implementations. ProteinTalks used RNA adaptation and inputs following proteomic pretraining.
Research evidence does not establish prospective treatment benefit or a universal ranking of model platforms.
ProteinTalks, Nature (2026), Figure 5 · Independent in-vitro and retrospective research evidence.
Explore our diagnostic products and translational proteomics capabilities.
Insulin-like growth factor I, measured by LC–MS/MS.
A mass-spectrometry-based test kit for IGF-I quantification, supporting laboratory assessment of growth and endocrine biology.
Protein evidence for thyroid-nodule assessment.
Quantitative proteomics and AI for investigating benign and malignant thyroid nodules, including tissue and fine-needle-aspiration research.
Product-specific intended use and availability are separate from AIVC research predictions. Contact our clinical team for current product documentation.
Defined perturbations, primary donors and matched functional readouts offer a practical direction for extending response models.
Antibodies, biosynthetic pathways, agriculture and tissue engineering require task-specific data and outcomes. The virtual-yeast framework informs this longer-term research direction.
Virtual yeast · Nature 2026Contact our team for AIVC projects, research services or diagnostic-product enquiries.