A Deep Learning Framework for Predicting Response to Therapy in Cancer

Sakellaropoulos, Theodore; Vougas, Konstantinos; Narang, Sonali; Koinis, Filippos; Kotsinas, Athanassios; Polyzos, Alexander; Moss, Tyler J.; Piha-Paul, Sarina A.; Zhou, Hua; Kardala, Eleni; Damianidou, Eleni; Alexopoulos, Leonidas G.; Aifantis, Iannis; Townsend, Paul A.; Panayiotidis, Mihalis Ι.; Sfikakis, Petros P.; Bártek, Jiří; Fitzgerald, Rebecca C.; Thanos, Dimitris; Shaw, Kenna; Petty, Russell; Tsirigos, Aristotelis; Gorgoulis, Vassilis G.

doi:10.1016/j.celrep.2019.11.017

Cited by 150 publications

(117 citation statements)

References 35 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Using the same dataset, Corté s-Ciriano et al (2016) showed that predictive performance could in some cases be improved using a random forest model linked to a measure of statistical confidence in each prediction. Deep neural networks (Baptista et al, 2020;Chiu et al, 2019;Menden et al, 2013;Sakellaropoulos et al, 2019) and variational autoencoders (Rampá sek et al, 2019) have also been applied to drug response prediction, with significant performance gains noted depending on the drug and disease context.…”

Section: Introductionmentioning

confidence: 99%

Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer Cells

et al. 2020

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer Cells

et al. 2020

View full text Add to dashboard Cite

“…Furthermore, while novel experimental models are generating more accurate data, advanced computational methods are under development to enhance the analytical potential of existing algorithms. As recently discussed (43)(44)(45), artificial intelligence approaches as network-based models, deep-learning frameworks, and machine-learning techniques are increasingly applied to investigate pharmacogenomics connections and drug repositioning. These methods can be effective not only for data integration but also to predict new interactions and applications of already approved drugs (46)(47)(48).…”

Section: Discussionmentioning

confidence: 99%

Computational Methods for the Integrative Analysis of Genomics and Pharmacological Data

2020

View full text Add to dashboard Cite

Since the pioneering NCI-60 panel of the late'80's, several major screenings of genetic profiling and drug testing in cancer cell lines have been conducted to investigate how genetic backgrounds and transcriptional patterns shape cancer's response to therapy and to identify disease-specific genes associated with drug response. Historically, pharmacogenomics screenings have been largely heterogeneous in terms of investigated cell lines, assay technologies, number of compounds, type and quality of genomic data, and methods for their computational analysis. The analysis of this enormous and heterogeneous amount of data required the development of computational methods for the integration of genomic profiles with drug responses across multiple screenings. Here, we will review the computational tools that have been developed to integrate cancer cell lines' genomic profiles and sensitivity to small molecule perturbations obtained from different screenings.

show abstract

“…DNN can represent functions with higher complexity if the numbers of layers and units in a single layer are increased [9], [14]. Nowadays, DNN is a trending technique and is employed in many areas such as drug-drug interaction [15] [16], medical predictions [17] or pharmaceutical sales forecasting [18].…”

Section: A Machine Learning Classifiersmentioning

confidence: 99%

Automatic Learning Framework for Pharmaceutical Record Matching

et al. 2020

View full text Add to dashboard Cite

Pharmaceutical manufacturers need to analyse a vast number of products in their daily activities. Many times, the same product can be registered several times by different systems using different attributes, and these companies require accurate and quality information regarding their products since these products are drugs. The central hypothesis of this research work is that machine learning can be applied to this domain to efficiently merge different data sources and match the records related to the same product. No human is able to do this in a reasonable way because the number of records to be matched is extremely high. This paper presents a framework for pharmaceutical record matching based on machine learning techniques in a big data environment. The proposed framework aims to explode the well-known rules for the matching of records from different databases for training machine learning models. Then the trained models are evaluated by predicting matches with records that do not follow these known rules. Finally, the production environment is simulated by generating a huge amount of combinations of records and predicting the matches. The obtained results show that, despite the good results obtained with the training datasets, in the production environment, the average accuracy of the best model is around 85%. That shows that matches which do not follow the known rules can be predicted and, considering that there is not a human way to process this amount of data, the results are promising.

show abstract

A Deep Learning Framework for Predicting Response to Therapy in Cancer

Cited by 150 publications

References 35 publications

Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer Cells

Predicting Drug Response and Synergy Using a Deep Learning Model of Human Cancer Cells

Computational Methods for the Integrative Analysis of Genomics and Pharmacological Data

Automatic Learning Framework for Pharmaceutical Record Matching

Contact Info

Product

Resources

About