High-throughput screening of drug sensitivity of cancer cell lines (CCLs) holds the potential to unlock anti-tumor therapies. In this study, we leverage such datasets to predict drug response using cell line transcriptomics, focusing on models’ interpretability and deployment on patients’ data. We use large language models (LLMs) to match drug to mechanisms of action (MOA)-related pathways. Genes crucial for prediction are enriched in drug-MOAs, suggesting that our models learn the molecular determinants of response. Furthermore, by using only LLM-curated, MOA-genes, we enhance the predictive accuracy of our models. To enhance translatability, we align RNAseq data from CCLs, used for training, to those from patient samples, used for inference. We validated our approach on TCGA samples, where patients’ best scoring drugs match those prescribed for their cancer type. We further predict and experimentally validate effective drugs for the patients of two highly lethal solid tumors, i.e., p...

Learning and actioning general principles of cancer cell drug sensitivity

Francesco Carli;Chakit Arora;Luisa Bisceglia;Francesco Pasqualetti;Paolo Aretini;Pasquale Miglionico;Fosca Giannotti;Miquel Duran-Frigola;Francesco Raimondi
2025

Abstract

High-throughput screening of drug sensitivity of cancer cell lines (CCLs) holds the potential to unlock anti-tumor therapies. In this study, we leverage such datasets to predict drug response using cell line transcriptomics, focusing on models’ interpretability and deployment on patients’ data. We use large language models (LLMs) to match drug to mechanisms of action (MOA)-related pathways. Genes crucial for prediction are enriched in drug-MOAs, suggesting that our models learn the molecular determinants of response. Furthermore, by using only LLM-curated, MOA-genes, we enhance the predictive accuracy of our models. To enhance translatability, we align RNAseq data from CCLs, used for training, to those from patient samples, used for inference. We validated our approach on TCGA samples, where patients’ best scoring drugs match those prescribed for their cancer type. We further predict and experimentally validate effective drugs for the patients of two highly lethal solid tumors, i.e., p...
2025
Settore BIOS-08/A - Biologia molecolare
   Decoding and recoding onco-GPCR signaling through integrative bioinformatics and protein engineering
   ASSOCIAZIONE ITALIANA PER LA RICERCA SUL CANCRO (AIRC)
   MFAG 2020 ID 24317
File in questo prodotto:
File Dimensione Formato  
s41467-025-56827-5 (1).pdf

accesso aperto

Tipologia: Published version
Licenza: Creative Commons
Dimensione 4.47 MB
Formato Adobe PDF
4.47 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11384/151330
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
  • OpenAlex ND
social impact