One patient is a dataset
single-patient target discovery with PortraiTARGET
Portrai is building PortraiTARGET, a platform designed to identify the best targets for cancerdrugs by analyzing large-scale, human-derived biological data.
Our belief is straightforward. The best cancer drugs should begin with human data. As biologicaldatasets continue to grow in both size and resolution, we see an opportunity to rethink howdrugs are discovered and developed. Instead of relying primarily on preclinical models,researchers can first test ideas in silico using comprehensive human molecular data, and thenmove the most promising candidates into experimental validation and clinical development.
To make this possible, we built the PortraiATLAS, a growing collection of tens of thousands ofhuman tissue samples and millions of individual cells. This resource captures the molecularlandscape of human cancers at an unprecedented scale and serves as the foundation ofPortraiTARGET.
Our long-term vision is to enable human data-driven simulation before the first patient enters aclinical trial, helping researchers identify better drug targets, reduce uncertainty, and acceleratethe development of more effective cancer therapies.
Beyond drug discovery, PortraiTARGET can also support treatment decisions for individualpatients.
A great example is the case of Sid, whose story is shared here: Cancer. Sid was diagnosedwith osteosarcoma, a rare cancer of the bone. These data include various types of biomedicaldata, from single cell RNA-seq to whole body image data. Amongst them, ‘holistic molecularmap’data by spatial transcriptomics are great resources for PortraiTARGET. Two tumor cores
placed on glass slides and analyzed using two different spatial profiling technologies. There wasno large patient cohort, no matched controls, and no similar cases to compare against.
Despite its size, this dataset represents exactly the kind of challenge where a human data-driven approach can make a difference. Instead of asking what works on average acrossthousands of patients, we can ask a much more personal question: what drug is most likely towork for this specific patient?
This is particularly relevant for antibody-drug conjugates (ADCs) and radiopharmaceuticaltherapies (RPTs). Both treatment modalities depend on finding molecules that are present on thesurface of cancer cells but absent from healthy tissues. These surface molecules serve as entrypoints, allowing highly potent drugs or radioactive isotopes to be delivered directly to tumorswhile minimizing damage to normal cells.
The central question is simple but critical. Is there a molecule on the surface of this patient'scancer cells that a drug can target without affecting healthy tissue?
Using PortraiTARGET, we ranked data-driven potential targets across multiple biological andtherapeutic criteria. We then compared these candidates with targets that are already beingpursued by pharmaceutical companies and simulated how much therapeutic radiation eachtarget could deliver to this patient's tumor.
The results were encouraging. A few well-established targets performed well, many widelystudied targets did not, and several overlooked candidates showed even stronger potential. Thisillustrates how human molecular data can uncover opportunities that might be missed byconventional approaches and, ultimately, support more personalized cancer treatment.
What we had to work with
Two things about that table are worth pausing on.
The first three rows are time. Cancer changes under treatment. A target that is present in Juneand gone by January is a target that will fail in the clinic, and you cannot see that in a singlebiopsy.
The last four rows are place. A tumor is not a bag of identical cells. It is a structure, with denseregions and sparse ones, with blood vessels and immune cells and scaffolding woven through it.A drug has to physically reach the cancer cells, which means it matters not just whether a targetis present but where. The two cores were read twice on purpose: VisiumHD reads every genebut pools four to eight cells into each square, while Xenium reads only 393 genes but readseach cell separately. Neither alone answers the question. Together they do.
What a target actually is
A cell is wrapped in a membrane, and studded through that membrane are proteins. Some pokeout into the space around the cell. Those are the only proteins a large drug can reach, becauseantibodies are far too big to get inside a living cell.
That gives you the shape of modern targeted cancer therapy. You take an antibody that sticks toone specific protein, and you attach something destructive to it: a chemical poison, in whichcase the result is called an antibody drug conjugate, or a radioactive atom, in which case it iscalled a radioligand. The antibody finds the protein, the payload does the damage.
The whole design rests on one assumption: that the protein is on the cancer and not on anythingelse. If it is also on your bone marrow, the drug destroys your bone marrow.
So a good target has to clear several bars.
Is it absent from healthy tissue? We answer this by comparing the patient's cancer cells against healthy cells drawn from 28 different tissues of the human body.
Is it on most of the cancer cells, or only some? A drug that reaches 20% of a tumor leaves 80% behind to regrow. This turns out to be the axis that separates the candidates most sharply.
Is it spread through the tissue, or clumped in a corner? Radiation travels a couple of hundred micrometres from where it lands, so a target that sits in scattered islands irradiates the gaps between them and not much else.
Two names to keep in mind
Throughout the series we compare everything against two reference points.
FAP is fibroblast activation protein. It is not on cancer cells at all in most tumor. It is on thefibroblasts that cancer recruits to build its scaffolding, and the idea behind targeting it is that youattack the support structure instead of the tumor. But Osteosarcoma originated frommesenchymal cells, usually show cancer cell expression of FAP. Several radioligands againstFAP are in clinical trials. Sid also underwent FAP targeting radiopharmaceutical treatment.
B7-H3, also called CD276, is a protein that appears across many solid tumours includingosteosarcoma. There are antibody drug conjugates and radioligands in clinical trials. If any wellknown target should work in this patient, it is this one.
A note on how the work was done
Some of the figures were not made by us. They were made by an AI agent (PortrAIgent) thatlives inside this project, was handed the patient's data, proposed its own simulation parameters,waited for a human to approve them, ran the simulation and saved the result. Its working notesare still in the project database. This paper includes also about that, because the interestingclaim is not that a model can run a script. It is that the reasoning is written down and can bechecked.
Mapping a patient in single cells
Before we can ask what is on the cancer cells, we have to know which cells are the cancer. Thatsounds trivial. It was the hardest part of this study.
The result first
The three biopsies contain 26,146 cells. After harmonizing them we can place each one and saywhat it is.
Each point is a cell. Cells that behave similarly land near each other. The three colors are thethree biopsies, spread over ten months.
The same map, colored by what each cell turned out to be. The cancer cells form the compactred island at the top. Everything else is the patient's own body: T cells and natural killer cells inblue, macrophages and other myeloid cells in orange, plasma cells in purple, blood vessel cellsin green.
3,299 of the 26,146 cells are cancer. That is the population every later measurement is about.
The whole body as a control
A drug target (Particularly, ADC, RPT and TCE) has to be absent from healthy tissue. Absent, orclose enough that the dose that kills the tumor does not kill the patient.
To test that for one patient you need a picture of the healthy human body at the same resolutionas your tumor. That picture exists. It is called Tabula Sapiens, and the version we used(subsampled for easier analysis, contains 113,621 individual cells drawn from 28 tissues: bonemarrow, blood, heart, kidney, liver, lung, skin, both intestines, salivary gland, eye, and eighteenmore.
We put the patient's 26,146 cells into the same space as those 113,621 healthy cells and askedwhat stands out.
The result first
Grey is a healthy human body. Blue is the patient's own immune and vascular cells. Red is thepatient's cancer.
The blue lands on top of the grey. The patient's T cells look like healthy T cells, because theyare healthy T cells. That overlap is the control experiment: it shows the integration is working,that we have not simply drawn a circle around one sample.
The red does not land on anything.
The funnel
Starting from 8,000 genes, six filters in sequence.
One of those stages deserve explanation.
Quiet in 11 critical organs. The organ list is not arbitrary. These are the tissues that kill you firstif a drug lands there. Bone marrow leads the list, and for this patient it matters twice: it is thedose-limiting organ for any radioactive drug. A gene is treated as present in an organ if itsaverage level clears a threshold and more than 5% of that organ's cells carry it. This stageremoved more than half of what reached it.
The standard surface filters are written to exclude: they drop a gene if a database records it asnot being a surface protein. Of the 241 genes that reached this stage, 212 had no positivesurface evidence. Requiring positive evidence takes 241 to 29.
What survived
Every surface gene, ranked by how specific it is to the cancer. The blue points are the 29 thatcleared every filter. The two diamonds are our reference targets.
The list: ITGA10, ITGA11, GPR158, GPC1, SEMA7A, S1PR3, ADGRA2, NPFFR2, GRM7, NPR2,TBXA2R, GPR173, ASIC1, GABRA3, CDH8, CDH18, SLC24A2, SLCO1A2, SLCO6A1, OR56A1, andnine members of the clustered protocadherin family.
Two of those are worth naming now.
ITGA10 is integrin alpha-10, a collagen receptor found on mesenchymal cells. It is 13-foldhigher in this patient's cancer than in the healthy body, and it has almost no signal in any ofthe 11 critical organs. Looking it up afterwards, there is a published body of work arguing thatintegrin alpha-10 drives sarcoma growth and is a therapeutic target with narrow normal-tissuedistribution, and binders against it have been made and tested in animals. As far as we can find,nothing against it has reached a clinical trial. So this is a preclinical target that somebody elseindependently arrived at, which our pipeline surfaced from one patient's data without being toldto look for it. That is the method doing its job, and it is not the same as a validated drug.
GPC1 is glypican-1, a surface proteoglycan. Antibody drug conjugates against it have shownactivity in animal models of pancreatic, oesophageal and lung cancer. Also preclinical, as far aswe can tell.
Where the well known targets land
The safety measure is a single number per gene: the average level across the 11 critical organs,on a log scale. Lower is safer.
FAP and B7-H3 are both genuinely safe by this measure. TROP2, the target of two approveddrugs, is 22 times worse than FAP here, mostly because it is abundant in eye, bladder andsalivary gland. That is not news to the people who develop TROP2 drugs, who manage it withdosing, but it tells you the number is measuring something real.
The bottom of that table is the interesting part. CD44, CXCR4, and IGF1R are all things peoplehave proposed as targets, and all four are broadly expressed in the healthy body. Whatever theirmerit elsewhere, a whole-body reference rules them out for this patient before any tumormeasurement is taken.
What this stage does not tell you
Safety is a veto, not a recommendation. Every one of the survived targets passed because it isabsent from healthy tissue, and a gene can be absent from healthy tissue and also nearly absentfrom the tumour.
Three of the 29 are on fewer than 2% of the patient's cancer cells. They cleared every filter inthis post and they are useless.
Sources for the claims about other people's work
Anti-glypican-1 antibody drug conjugate against pancreatic cancer
Glypican-1-targeted antibody drug conjugate in pancreatic and oesophageal cancer
This case study is for research and exploratory purposes only. The results have not been clinically validated and should not be used to guide patient care.
