MétaCan
Menu
← Back to cohort

Abstract B073: Understanding treatment response in pancreatic cancer: NetraAI provides genetic differentiation in FOLFIRINOX and gemcitabine response

2024· article· en· W4390915338 on OpenAlexaff
Bessi Qorri, Mike Tsay, Josh Spiegel, Douglas J. Cook, Joseph Geraci

Bibliographic record

VenueCancer Research · 2024
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsQueen's University
Fundersnot available
KeywordsFOLFIRINOXGemcitabinePancreatic cancerOncologyInternal medicineChemotherapyCancerBiologyMedicineCancer researchBioinformaticsIrinotecan

Abstract

fetched live from OpenAlex

Abstract Pancreatic cancer is known as a “silent killer” due to vague symptoms, late diagnosis, rapid progression, and poor response to therapy. Due to the highly malignant nature of this disease, prolonging progression-free survival (PFS) and overall survival (OS) for patients is critical. Standard of care involves combination chemotherapy using FOLFIRINOX (FFX) or Gemcitabine with nab-paclitaxel (GnP). The COMPASS trial performed whole genome sequencing (WGS) and RNA sequencing (RNASeq) on pancreatic ductal adenocarcinoma (PDAC) patients prior to FFX or GnP first-line combination therapy, finding molecular heterogeneity between patients and differing response to chemotherapy. Using the COMPASS trial dataset consisting of only 208 patients and NetraAI, a novel machine learning (ML) platform using a novel causal feature set discovery methodology, we explored generated hypotheses to differentiate causal factors that affect patient response to FFX and GnP. Differentiating FFX and GnP treatment response in stable disease patients revealed 3 distinct subpopulations with genetic differentiation related to neuron death and regulation, neurotrophin signaling, and neuron apoptotic processes. NetraAI identified genes driving patient subpopulations, such as LRRC8E, PTPRH, and UTG1A13p. Further investigation revealed that LRRC29 and CLEC19A distinguished a group of patients that responded well to FFX. LRRC29 relates to HOOK1, which negatively regulates epithelial-to-mesenchymal transition and has been reported to be decreased in PDAC. Low HOOK1 and SHP2 expression in non-small cell lung cancer is associated with a good response to GnP, suggesting that chemotherapy response depends on the interaction of the chemotherapeutic agent and genetic factors involved in disease progression as opposed to the tumor type. These results suggest that LRRC29 expression can act as a biomarker to choose between GnP and FFX treatment. In this way, NetraAI's ability to generate explainable hypotheses around patient subpopulations can help oncologists personalize treatments and better understand clinical trial patient populations. By identifying distinct genetic signatures within patient datasets. By identifying unique molecular heterogeneity that explains differing responses to therapy, NetraAI is a powerful tool that can extract insights from multi-dimensional and highly heterogenous patient population datasets that can help to inform clinical trial enrichment decisions to improve the success of pivotal trials. This work has a significant impact on precision medicine and clinical trial de-risking, while identifying specific genes and pathways involved in patient response to therapy. Citation Format: Bessi Qorri, Mike Tsay, Josh Spiegel, Douglas Cook, Joseph Geraci. Understanding treatment response in pancreatic cancer: NetraAI provides genetic differentiation in FOLFIRINOX and gemcitabine response [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Pancreatic Cancer; 2023 Sep 27-30; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(2 Suppl):Abstract nr B073.

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 imitation

Not 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.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.004
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.004
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.001

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.

Opus teacher head0.086
GPT teacher head0.422
Teacher spread0.337 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueCancer Research→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→