Abstract 145P
Background
In this study, we use KEM® (Knowledge Extraction and Management) explainable Artificial Intelligence (xAI) platform to systematically explore association rules in a heterogeneous patient database accounting for above 30 cancer types and thus identify biomarkers characterizing patients with higher chances of survival. The list of candidates’ biomarkers included drug scores generated by OncoKEM®, an AI-transcriptional-based therapeutic recommendation-tool that computes scores for up to 205 drugs based on the drug's transcriptional signatures and the tumor transcriptional profile. The goal was to demonstrate the biological relevance of OncoKEM® by confronting its results with the findings obtained through a standard pathway analysis.
Methods
Data was retrieved from the PROFILER study (NCT01774409), a molecular screening program, and aggregated into a consolidated database totaling 247 patients and 215,670 variables that included survival, baseline descriptors, gene expression, derived REACTOME pathway dysregulations, and OncoKEM® scores. KEM® xAI platform extracted 55,335 relations associating candidate biomarkers and survival. These results were then filtered based on Support (number of examples), Lift (relative probability) and statistical significance. The remaining relations were finally split into 2 sets to study the associations between survival and respectively pathways dysregulations or OncoKEM® scores.
Results
Our analysis first identified 4 pathway dysregulations that were associated with the overall survival (hazard ratio ranged from 2.36 to 2.80). 3 of these pathways were related to tubulin. Consistently, 4 OncoKEM® scores were then identified as associated with survival (hazard ratio ranged from 2.20 to 2.52) and all 4 corresponded to microtubule inhibitor drugs: ixabepilone, cabazitaxel, vinflunine and brentuximab vedotin.
Conclusions
Our analysis enabled the identification of biomarkers of survival across cancer types. The consistency of the findings both demonstrated the biological relevance of OncoKEM® for microtubule inhibitor drugs and paved the way for the use of this tool as a prognostic marker for refractory cancers.
Clinical trial identification
NCT01774409.
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Ariana Pharma.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
144P - Artificial intelligence supported treatment decisions for precision oncology
Presenter: Damian Rieke
Session: Poster session 01
147P - Non-small cell lung cancer: Artificial intelligence enables the identification of survival signatures complementary to an Immunologically active gene expression signature involving previous therapies
Presenter: Pierre Saintigny
Session: Poster session 01
149P - Assessing the effect of single dose trastuzumab and pertuzumab (HP) on biological changes and pathological complete response (pCR) in ERBB2+ Breast Cancer: Results from the neoadjuvant BionHER study
Presenter: Nadia Gomez Serra
Session: Poster session 01
150P - Validation of a genomic assay in early-stage HER2+ breast cancer (BC) treated with trastuzumab and pertuzumab (HP): A correlative analysis from PHERGain phase II trial
Presenter: Antonio Llombart Cussac
Session: Poster session 01
152P - Efficacy of olaparib in advanced cancers with germline or somatic tumor mutations in BRCA1, BRCA2, CHEK2 and ATM: A Belgian precision tumor-agnostic phase II study
Presenter: Sofie Joris
Session: Poster session 01
153P - Descriptive analysis of the location of point mutations in BRCA and the risk of breast or ovarian cancer diagnosis
Presenter: Pablo Torres-Mozas
Session: Poster session 01
154P - Highly sensitive serum volatolomic biomarkers for pancreatic cancer diagnosis and prognosis
Presenter: Alfredo Martínez
Session: Poster session 01
155P - Exploring the utility of serum anti-tNASP antibodies as a screening biomarker in prostate, pancreatic, and ovarian cancer
Presenter: Oleg Alekseev
Session: Poster session 01