Computational oncology · one RNA-seq profile
Provotics reads a tumor's RNA-seq profile and returns its full molecular portrait: where in the body it arose, its molecular subtype, its candidate druggable alterations, and its immune profile, with the genes behind every call.
Trained and benchmarked on 17,410 public tumor RNA-seq profiles spanning 25 anatomical sites.
Cancers are defined by where they start, but metastases and cancers of unknown primary can hide that origin, and the answer changes how a patient is treated. The signal is written in the tumor's gene expression. Reading it is the whole game.
Where a cancer began shapes the entire treatment plan, yet metastatic and unknown-primary tumors blur that answer.
Each sample carries tens of thousands of gene measurements. The biological signal is real but buried in noise and correlation.
In oncology, a prediction is only actionable with its reasoning and honest uncertainty attached. The genes behind a call are what make it reviewable.
Provotics turns one expression profile into a calibrated, explainable call, and points toward what to do next.
Reads a tumor's site of origin across 25 anatomical sites straight from its transcriptome, ~94% balanced accuracy on held-out tumors, then reads its molecular subtype, likely alterations, and immune profile.
Every call carries a calibrated probability, so a stated 80% means roughly 80% in practice. Low-confidence or out-of-distribution samples are abstained on or flagged as novel, rather than forced into a label.
Surfaces the tumor's over-expressed, druggable targets as research hypotheses, a bridge from a diagnosis toward candidate therapies.
One pipeline, four steps. Each profile is quality-checked, harmonized to a common gene space, scored by the model, and returned with its reasoning attached.
Start from a single tumor expression profile, gene-level counts or TPM.
Mapped to a common gene space, normalized, and screened for quality before any prediction.
An ensemble scores the profile and calibrates the probabilities, abstaining when confidence is low.
Site of origin, subtype, druggable targets, and immune profile, with the driver genes behind each call.
Pick an illustrative tumor profile and watch the portrait Provotics produces, the calibrated site call, its top alternatives, the molecular detail, and the driver genes behind it.
Calibrated probability. Top alternatives shown below.
Illustrative examples for demonstration. Sample profiles, probabilities, and markers are representative, not live model outputs, and no proprietary data or model weights are shipped to your browser. The real model runs server-side for approved users.
Numbers from held-out tumors and independent cohorts, not the training set. Where the model is weak, it says so rather than guessing.
From a single RNA-seq profile to a portrait you can act on, wherever expression data is generated and interpreted.
Characterize tumor samples and unknown-primary cases, and generate testable hypotheses straight from expression data.
Surface over-expressed, druggable targets across cohorts to prioritize programs and narrow the search.
A calibrated, explainable baseline with the driver genes exposed, so every call is reviewable, not a black box.
Access is invite-only and granted under a confidentiality agreement. Tell us who you are and how you plan to use the model, and review the access terms before submitting.