BostonGene vs Caris Life Sciences (2026)
Both profile a tumor and they model different things about it. Caris runs comprehensive molecular profiling with an approved assay doing simultaneous whole exome and whole transcriptome sequencing, published validation and signatures that disclose their training cohorts, delivered into a molecular tumor board. BostonGene models tumor and immune biology together, integrating data types into a portrait of the microenvironment rather than a variant report, and applies the same models to clinical care and to drug development. The clinical question decides it. If you need the actionable alterations and a defensible regulatory footing for the assay, Caris. If the question is immune context, why a therapy is not working or who might respond, BostonGene is modeling the thing you are asking about. Neither publishes performance by ancestry, which is the shared blind spot of this entire category.
- The tumor and immune biology modeling is the product rather than the sequencing, integrating multiple data types into a portrait that describes the microenvironment rather than a variant list.
- It serves both clinical care and drug development from the same models, which means the platform is exercised against research grade questions as well as clinical ones.
- For a program whose question is why a patient is not responding rather than which mutation is present, immune context is where the answer usually sits.
- The approved assay is a regulatory distinction the company documents rather than blurs, and simultaneous whole exome and whole transcriptome sequencing under that approval is a genuinely different footing from laboratory developed testing.
- Clinical and analytical validation is published and the artificial intelligence signatures disclose their training cohorts and sizes.
- Scope is precisely bounded to solid tumor profiling across adult and pediatric patients, which is a clearer intended use statement than most competitors publish.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. BostonGene and Caris Life Sciences are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
| Fact | BostonGene | Caris Life Sciences |
|---|---|---|
| Primary category | Diagnostics & Genomics | Diagnostics & Genomics |
| Headquarters | Waltham, Massachusetts | Irving, Texas |
| Website | bostongene.com | carislifesciences.com |
Side by Side
Select any grade to read the note behind it.
Product updates
The latest logged changes from each vendor, newest first, each linked to its source.
Caris Life Sciences
-
Clinical evidence
Caris presented two AI models for breast cancer at ESMO 2026.
Source -
Regulatory / FDA
FDA approved a supplement to the premarket approval for MI Cancer Seek, Caris' whole exome and whole transcriptome tumor profiling assay, that moves the test's bioinformatics pipeline from Caris' own computing cluster to Amazon Web Services.
Source -
Product / capability
Caris launched an enhanced Caris Assure liquid biopsy that combines whole exome sequencing, whole transcriptome sequencing and whole blood analysis in one assay, so tumor derived alterations can be told apart from clonal hematopoiesis and incidental germline findings.
Source
Each vendor in one paragraph
Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.
Precision oncology company in Waltham, Massachusetts, combining sequencing in its own CAP accredited, CLIA certified laboratory with models of tumor and immune biology.
Source: AI Health Index, August 2026
Precision oncology company (NASDAQ: CAI) in Irving, Texas, combining whole exome and transcriptome tumor profiling in its own laboratories with AI signatures. MI Cancer Seek was approved by FDA in November 2024 (P240010) with companion diagnostic indications, and the company publishes which results fall inside and outside that label.
Source: AI Health Index, August 2026
Questions buyers ask
How do BostonGene and Caris Life Sciences handle patient data?
BostonGene's notice of health information privacy practices (effective 1 April 2021) says it never shares a patient's information for marketing or sale without written permission and may use it for research under the conditions the law sets.
Caris states in its annual notice to physicians that it is a covered entity and publishes a HIPAA notice of privacy practices, a separate privacy notice and a Washington health data notice. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified August 4, 2026. No vendor pays for placement.
Which settings and specialties do BostonGene and Caris Life Sciences cover?
In BostonGene's case, the Tumor Portrait page describes the test as for patients with advanced solid tumors, then lists cancer-specific reporting for 14 types, including two lymphomas (follicular lymphoma and diffuse large B-cell lymphoma), alongside a separate immune profiling test from blood, immunohistochemistry and an unknown primary test.
Blood-based profiling (Caris Assure) and early detection (Caris Detect) are offered separately. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified August 4, 2026. No vendor pays for placement.
How much do BostonGene and Caris Life Sciences leave to the clinician?
With BostonGene, the test is ordered by a clinician on a requisition form, run in the company's CAP and CLIA certified laboratory, and returned as a report the physician acts on.
In Caris Life Sciences' case, the label scope table tells the reader which results the FDA approval covers and which it does not, and the Molecular Tumor Board Report is labeled research use only for tumor boards and case consults. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified August 4, 2026. No vendor pays for placement.
Neither vendor publishes a governance framework, subgroup performance analysis or bias evaluation, and in precision oncology the omission is specific: signature and interpretation performance depend on the ancestral and demographic composition of the training cohorts, and a signature validated mainly in one population will perform differently in another without any signal that it has. Neither publishes a security attestation or trust center.
Both operate their own laboratories and report their own performance, so the evidence is internally generated even where it is published, and independent replication is largely absent from this category.