Machine learning and feature selection for drug response prediction in precision oncology applications

Ali, Mehreen; Aittokallio, Tero

doi:10.1007/s12551-018-0446-z

Cited by 168 publications

(121 citation statements)

References 70 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…Quantitative Structure-Activity Relationship (QSAR) models establish a mathematical relationship between the chemical structure of a molecule, encoded as a 3 set of structural and/or physico-chemical features (descriptors), and its biological activity on a target. Such methods have been successfully used in a wide variety of pharmacology and drug design projects 13 , including cancer research [14][15][16] . QSAR models are traditionally built using simple linear models [17][18][19][20] to predict the activity of individual molecules against a molecular target.…”

Section: Introductionmentioning

confidence: 99%

Predicting synergism of cancer drug combinations using NCI-ALMANAC data

Sidorov

Naulaerts

Ariey-Bonnet

et al. 2018

Preprint

View full text Add to dashboard Cite

Background. Drug combinations are of great interest for cancer treatment. Unfortunately, the discovery of synergistic combinations by purely experimental means is only feasible on small sets of drugs. In silico modeling methods can substantially widen this search by providing tools able to predict which of all possible combinations in a large compound library are synergistic.Here we investigate to which extent drug combination synergy can be predicted by exploiting the largest available dataset to date (NCI-ALMANAC, with over 290,000 synergy determinations). Methods. Each cell line is modeled using primarily two machine learning techniques, RandomForest (RF) and Extreme Gradient Boosting (XGBoost), on the datasets provided by NCI-ALMANAC. This large-scale predictive modeling study comprises more than 5000 pair-wise drug combinations, 60 cell lines, 4 types of models and 5 types of chemical features. The application of a powerful, yet uncommonly used, RF-specific technique for reliability prediction is also investigated.Results. The evaluation of these models shows that it is possible to predict the synergy of unseen drug combinations with high accuracy (Pearson correlations between 0.43 and 0.86 depending on 2 the considered cell line, with XGBoost providing slightly better predictions than RF). We have also found that restricting to the most reliable synergy predictions results in at least two-fold error decrease with respect to employing the best learning algorithm without any reliability estimation. Alkylating agents, tyrosine kinase inhibitors and topoisomerase inhibitors are the drugs whose synergy with other partner drugs are better predicted by the models.Conclusions. Despite its leading size, NCI-ALMANAC comprises an extremely small part of all conceivable combinations. Given their accuracy and reliability estimation, the developed models should drastically reduce the number of required in vitro tests by predicting in silico which of the considered combinations are likely to be synergistic.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting synergism of cancer drug combinations using NCI-ALMANAC data

Sidorov

Naulaerts

Ariey-Bonnet

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…It is worth pointing out that they used a form that is more general than Eqn. (9) so that the responses data do not necessarily involve the same set of cell lines for different drugs.…”

Section: Bayesian Inference Methodsmentioning

confidence: 99%

A Survey and Systematic Assessment of Computational Methods for Drug Response Prediction

Chen

Zhang

2019

Preprint

View full text Add to dashboard Cite

Drug response prediction arises from both basic and clinical research of personalized therapy, as well as drug discovery for cancer and other diseases. With gene expression profiles and other omics data being available for over 1000 cancer cell lines and tissues, different machine learning approaches have been applied to solve drug response prediction problems. These methods appear in a body of literature and have been evaluated on different datasets with only one or two accuracy metrics. We systematically assessed 17 representative methods for drug response prediction, which have been developed in the past five years, on four large public datasets in nine metrics. This study provides insights and lessons for future research into drug response prediction.

show abstract

“…An approach to compensate for the lack of genetic hotspots in NF1 tumors is to focus on combinations of transcriptomic signatures that may be unique to specific tumor types. In other tumor types, transcriptomic landscapes across cancer datasets [18,19] have shown that combining RNA-seq data from similar diseases can identify expression profiles that correlate with prognosis [20] , predict drug response [21,22] or identify key tumor biology [23] .…”

Section: Introductionmentioning

confidence: 99%

Integrative analysis identifies candidate tumor microenvironment and intracellular signaling pathways that define tumor heterogeneity in NF1

Banerjee

Allaway

Taroni

et al. 2020

Preprint

View full text Add to dashboard Cite

Neurofibromatosis type 1 is a monogenic syndrome that gives rise to numerous symptoms including cognitive impairment, skeletal abnormalities, and growth of benign nerve sheath tumors. Nearly all NF1 patients develop cutaneous neurofibromas (cNFs), which occur on the skin surface, while 40-60% of patients develop plexiform neurofibromas (pNFs) which are deeply embedded in the peripheral nerves. Patients with pNFs have a ~10% lifetime chance of these tumors becoming malignant peripheral nerve sheath tumors (MPNSTs). These tumors have a severe prognosis and few treatment options other than surgery. Given the lack of therapeutic options available to patients with these tumors, identification of druggable pathways or other key molecular features could aid ongoing therapeutic discovery studies. In this work, we used statistical and machine learning methods to analyze 77 NF1 tumors with genomic data to characterize key signaling pathways that distinguish these tumors and identify candidates for drug development. We identified subsets of latent gene expression variables that may be important in the identification and etiology of cNFs, pNFs, other neurofibromas, and MPNSTs. Furthermore, we characterized the association between these latent variables and genetic variants, immune deconvolution predictions, and protein activity predictions.

show abstract

Machine learning and feature selection for drug response prediction in precision oncology applications

Cited by 168 publications

References 70 publications

Predicting synergism of cancer drug combinations using NCI-ALMANAC data

Predicting synergism of cancer drug combinations using NCI-ALMANAC data

A Survey and Systematic Assessment of Computational Methods for Drug Response Prediction

Integrative analysis identifies candidate tumor microenvironment and intracellular signaling pathways that define tumor heterogeneity in NF1

Contact Info

Product

Resources

About