Oncera looks for tumour-selective surface targets in tumouroids grown from patient material and designs VHH binders against them with the BEAM AI stack.
VHH, also known as a nanobody: the variable domain of a camelid heavy-chain antibody, about a tenth the size of an antibody.
Three failures compound. Together they stop promising surface programmes between discovery and lead optimisation.
Therapeutically relevant surface epitopes, particularly those at low to medium abundance, stay invisible to classical proteomics and screening pipelines.
Older generative approaches are frequently polyreactive, and the sequences they produce enter years-long loops optimising affinity, specificity and developability. Human-relevant validation is rarely brought in early enough to stop that.
Hepatocellular carcinoma and cholangiocarcinoma have poor prognoses and few treatment options. The first bispecific HER2 antibody for pre-treated HER2-positive biliary tumours was approved only in 2024.
Most pipelines run target discovery, binder design and validation as separate workstreams, and only find out at the end whether they agreed. Oncera sets them up as one loop, so that every experiment feeds the next design round. The first round with laboratory data on binders is still ahead.
Patient-derived tumouroids
Feeds the loop
Surface target prioritisation
Feeds the loop
BEAM binder generation
Binding assays
Validation in tumouroids
Each round is meant to improve the next design
Feeds the loop
MicroOrganoPits grow tumour avatars from patient material and hold the transcriptional fidelity that 2D cell lines lose.
Feeds the loop
Tumouroid proteomes and transcriptomes are read against hepatocyte reference organoids and public tumour-normal datasets, surfacing epitopes that abundance-driven screens miss.
The BEAM stack generates candidate binders against the prioritised epitopes and scores them for affinity, off-target risk and developability before anything reaches a bench.
The most promising designs are to be synthesised and measured against the target protein by SPR and BLI. Affinity and kinetics are to decide which candidate goes into a cell system.
Candidates are to be tested against the same patient-derived systems they were designed for, and against healthy comparators. The comparison is meant to show whether a candidate is selective.
Tumouroids and prioritisation run once per patient line, and the loop is meant to run as often after that as it takes. The tumouroid lines are the basis it runs on: they supply the surface proteome that prioritisation reads, and they are the system a candidate is to be tested in.
The two arms are linked: our own programmes are meant to test the platform prospectively and to produce the starting points that co-development partnerships build on.
A pharma or biotech partner brings an oncology target question that has been hard to answer. By target, Oncera means the docking site: the surface protein through which a binder reaches the tumour cell. It does not mean the mechanism of action. Oncera delivers prioritised surface targets, binder candidates and validation data from patient-derived tumouroids.
Status: the offer is being built. Validation data from tumouroids is still to come.
How a co-development project runsA small, deliberately focused pipeline in three gastrointestinal tumours: hepatocellular carcinoma, cholangiocarcinoma and pancreatic cancer. Each programme tests the platform on a different question of selectivity and format.
Status: preclinical. Laboratory data on the binders is still to come.
The three programmesOncera develops VHH binders and antibody formats for solid tumours. The binder can be the drug itself or take a payload to the tumour cell, such as a small-molecule drug, an oligonucleotide or a radionuclide.
Antibody-drug conjugate (ADC)
Antibody-oligonucleotide conjugate (AOC)
Antibody-radionuclide conjugate (ARC)
For ADCs, the next project phase already tests internalisation, trafficking and in vitro toxicity (WP5.3). AOC and ARC are options for the future. Each payload has to be tested separately.
Benchmark and laboratory figures go on this page once they have been re-run and cleared. Until then, this is what is measured, and against which baseline.
Sequence recovery of the BEAM model
against ProteinMPNN and AbMPNN on the same test set
CDR-H3 retrieval rate
against the published baseline for the same task
Tumouroid take rate for HCC and CCC
against conventional organoid culture
One piece of evidence is still open: that generated binders bind on patient-derived tumouroids and distinguish them from healthy comparators. The next project phase is meant to deliver it.
BEAM runs on a local GPU workstation and is not run as a network service. For a co-development project it is meant to be installed at the partner, so that sequences and structures stay on the partner's premises. The page on security and compliance lists the other tools Oncera uses and where they run.
Security and complianceThe team’s research institutions, our base at BioM, the programmes that admitted Oncera, and what the project has reached so far, with dates.
DATIpilot
Funding from the federal DATIpilot programme. The tumouroid biobank grew with it.
Nucleate
Winner of the Nucleate pitch competition.
BioLabs
A BioLabs Golden Ticket: an incubation place and the network.
AI NATION MUNICH
Admitted to the AI NATION MUNICH programme, co-financed by the European Union.
The best fit is a surface target that abundance-driven screening keeps missing, early enough in a programme to still de-risk it.