Abstract 388: AI/ML-driven discovery of a novel proteoglycan for precision targeting of ADCs for disruption of stromal barriers and direct anti-tumor activity
Bibliographic record
Abstract
Abstract Background: While checkpoint inhibitors (CPIs) such as anti-CTLA-4 and anti-PD-1/L1 have demonstrated efficacy in a number of solid tumor indications, those with high stromal presence have been difficult to treat with minimal response observed. We aimed to use a proprietary machine learning/artificial intelligence platform to identify novel stromal targets to relieve this immunosuppressive barrier and increase CPI responsiveness in difficult to treat indications. Methods: Based on bioinformatic analysis using our single cell RNA atlas, we assessed cancer-associated fibroblasts (CAFs)/fibroblastic cells in cancer tissue for identification of novel targets, including proteoglycans. Antibodies were generated by immunization of humanized mice, and lead antibodies were tested for activity in inhibiting cell adhesion and were further characterized for staining of both CAFs as well as tumor cells. ADCs were developed and tested in vitro for selective tumor cell killing. Results: Bioinformatic analysis identified a unique subset of cancer-associated fibroblasts, termed ecmCAFs, which demonstrated selective expression of Collagen Triple Helix Repeat Containing 1 (CTHRC1). This highly-selective expression pattern suggests it may be ideal as a target for alternative modalities, including ADC targeting or specific T cell activation. In addition, we identified that in certain tumor types, such a triple negative breast cancer and pancreatic ductal adenocarcinoma (PDAC), CTHRC1 is also highly expressed by cancer cells within the tumor and shows a more favorable expression profile for ADC targeting when compared to other stromal proteins such as FAP and LRRC15. We have confirmed surface expression and binding of CTHRC1 by our lead antibodies and have observed robust internalization on both human and mouse cancer cell lines. In vitro killing of tumor cells by ADCs and in vivo PD and efficacy will be presented on both ADCs and naked antibodies. Conclusions: We have identified CTHRC1 as a novel proteoglycan expressed by both ecmCAFs and tumor cells that appears to be an ideal target for both direct inhibition of stromal barrier function as well as targeting of cytotoxic payloads as an ADC. CTHRC1 expression is more selective than the classical markers FAP and LRRC15, both of which have been previously developed as ADCs. Citation Format: Elizabeth Koch, Max London, Amy Berkley, Allison Nixon, Sean Phippen, Kerry White, Amanda Hanson, Samuel Cooper, Christopher Harvey, Michael Briskin. AI/ML-driven discovery of a novel proteoglycan for precision targeting of ADCs for disruption of stromal barriers and direct anti-tumor activity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 388.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".