CancerGPT for few shot drug pair synergy prediction using large pretrained language models
Top Cited Papers
Open Access
- 19 February 2024
- journal article
- research article
- Published by Springer Nature in npj Digital Medicine
- Vol. 7 (1) , 1-10
Abstract
Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. Our experiments, which involved seven rare tissues from different cancer types, demonstrate that the LLM-based prediction model achieves significant accuracy with very few or zero samples. Our proposed model, the CancerGPT (with ~ 124M parameters), is comparable to the larger fine-tuned GPT-3 model (with ~ 175B parameters). Our research contributes to tackling drug pair synergy prediction in rare tissues with limited data, and also advancing the use of LLMs for biological and medical inference tasks.Keywords
This publication has 38 references indexed in Scilit:
- Methods for High-throughput Drug Combination Screening and Synergy Scoring2018
- DeepSynergy: predicting anti-cancer drug synergy with Deep LearningBioinformatics, 2017
- Learning from Noisy Large-Scale Datasets with Minimal Supervision2017
- SynergyFinder: a web application for analyzing drug combination dose–response matrix dataBioinformatics, 2017
- XGBoost2016
- Drug combination therapy increases successful drug repositioningDrug Discovery Today, 2016
- Searching for Drug Synergy in Complex Dose–Response Landscapes Using an Interaction Potency ModelComputational and Structural Biotechnology Journal, 2015
- Phase II study to assess the efficacy, safety and tolerability of the mitotic spindle kinesin inhibitor AZD4877 in patients with recurrent advanced urothelial cancerInvestigational New Drugs, 2013
- Similarities and Differences in the Expression of Drug-Metabolizing Enzymes between Human Hepatic Cell Lines and Primary Human HepatocytesDrug Metabolism and Disposition, 2011
- Overexpression of Pim-1 in bladder cancerJournal of Experimental & Clinical Cancer Research, 2010