MindRank and Borui Cuanghe team up on cyclic-peptide RDCs: InteraFold-PEP predicts binding modes before any candidate exists
Synopsis
MindRank and Borui Cuanghe have announced a strategic collaboration to advance AI-driven radionuclide drug conjugates (RDCs) that use cyclic peptides as targeting ligands, aimed at unmet needs in precision oncology. MindRank contributes its Intera life-science foundation model system, with InteraFold-PEP predicting how cyclic peptides bind target proteins to guide design, screening and optimization; Borui Cuanghe contributes radiopharmaceutical development, radiolabeling and clinical translation, and the two sides iterate AI design against experimental validation. The target ligands must combine high affinity, high selectivity and good developability, and the work is at the collaboration-launch stage.
Interpretation
The two companies place AI cyclic-peptide design and radionuclide drug conjugate development on one R&D chain, pursuing first-in-class drug candidates for unmet needs in precision oncology. MindRank's AI design capability had been demonstrated mainly in small molecules and peptide algorithms: its AI-designed oral small-molecule GLP-1 receptor agonist MDR-001 has entered Phase III in China, and its peptide design algorithm PepFGLD was published at ICML 2026. This collaboration extends the design object to cyclic peptides serving as RDC targeting ligands. The collaboration rests on each side's disclosed capabilities: MindRank brings the Intera foundation model system and InteraFold-PEP binding-mode prediction, while Borui Cuanghe brings end-to-end radiopharmaceutical discovery, radiochemistry and clinical translation, with its PET tracer BR-02 in Phase IIb, its FAP-targeting BRP-010 holding a Chinese IND approval, and its cyclic-peptide Nectin-4 program BRP-020 at investigator-initiated study stage.
Cyclic-peptide candidates are designed from sequence and three-dimensional structure, then revised against experimental feedback. InteraFold-PEP predicts cyclic-peptide binding modes against target proteins, giving structural reference for design, screening and optimization rather than relying only on existing binding data. Iteration covers affinity, selectivity, stability and suitability for radionuclide conjugation, pairing MindRank's AI design with Borui Cuanghe's radiolabeling and clinical translation in a loop of design and experimental validation.
Perspective
The report covers what the two companies announced: RDCs using cyclic peptides as targeting ligands for precision oncology, with MindRank providing the Intera system and InteraFold-PEP and Borui Cuanghe providing radiopharmaceutical development, radiolabeling and clinical translation. No deal value, timeline or specific target is given, and no candidate molecule or experimental data is reported.
The collaboration is at launch stage; the announcement discloses no specific target, molecule count, milestone schedule or timeline, and does not state InteraFold-PEP's accuracy in predicting cyclic-peptide binding modes. Both sides describe the collaboration as expected to accelerate drug discovery and clinical application, which is an expectation rather than a realized result.