Learning approaches to improve prediction of drug sensitivity in breast cancer patients

Machine Learning Applicability for Classification of PAD/VCD Chemotherapy Response Using 53 Multiple Myeloma RNA Sequencing Profiles

Multiple myeloma (MM) affects ~500,000 people and results in ~100,000 deaths annually, being currently considered treatable but incurable. There are several MM chemotherapy treatment regimens, among which eleven include bortezomib, a proteasome-targeted drug. MM patients respond differently to bortezomib, and new prognostic biomarkers are needed to personalize treatments. However, there is a shortage of clinically annotated MM molecular data that could be used to establish novel molecular diagnostics. We report new RNA sequencing profiles for 53 MM patients annotated with responses on two similar chemotherapy regimens: bortezomib, doxorubicin, dexamethasone (PAD), and bortezomib, cyclophosphamide, dexamethasone (VCD), or with responses to their combinations. Fourteen patients received both PAD and VCD; six received only PAD, and 33 received only VCD. We compared profiles for the good and poor responders and found five genes commonly regulated here and in the previous datasets for other bortezomib regimens (all upregulated in the good responders): FGFR3, MAF, IGHA2, IGHV1-69, and GRB14. Four of these genes are linked with known immunoglobulin locus rearrangements. We then used five machine learning (ML) methods to build a classifier distinguishing good and poor responders for two cohorts: PAD + VCD (53 patients), and separately VCD (47 patients). We showed that the application of FloWPS dynamic data trimming was beneficial for all ML methods tested in both cohorts, and also in the previous MM bortezomib datasets. However, the ML models build for the different datasets did not allow cross-transferring, which can be due to different treatment regimens, experimental profiling methods, and MM heterogeneity.

Cancer gene expression profiles associated with clinical outcomes to chemotherapy treatments

Background

Machine learning (ML) methods still have limited applicability in personalized oncology due to low numbers of available clinically annotated molecular profiles. This doesn’t allow sufficient training of ML classifiers that could be used for improving molecular diagnostics.

Methods

We reviewed published datasets of high throughput gene expression profiles corresponding to cancer patients with known responses on chemotherapy treatments. We browsed Gene Expression Omnibus (GEO), The Cancer Genome Atlas (TCGA) and Tumor Alterations Relevant for GEnomics-driven Therapy (TARGET) repositories.

Results

We identified data collections suitable to build ML models for predicting responses on certain chemotherapeutic schemes. We identified 26 datasets, ranging from 41 till 508 cases per dataset. All the datasets identified were checked for ML applicability and robustness with leave-one-out cross validation. Twenty-three datasets were found suitable for using ML that had balanced numbers of treatment responder and non-responder cases.

Conclusions

We collected a database of gene expression profiles associated with clinical responses on chemotherapy for 2786 individual cancer cases. Among them seven datasets included RNA sequencing data (for 645 cases) and the others – microarray expression profiles. The cases represented breast cancer, lung cancer, low-grade glioma, endothelial carcinoma, multiple myeloma, adult leukemia, pediatric leukemia and kidney tumors. Chemotherapeutics included taxanes, bortezomib, vincristine, trastuzumab, letrozole, tipifarnib, temozolomide, busulfan and cyclophosphamide.

FLOating-Window Projective Separator (FloWPS): A Data Trimming Tool for Support Vector Machines (SVM) to Improve Robustness of the Classifier

Here, we propose a heuristic technique of data trimming for SVM termed FLOating Window Projective Separator (FloWPS), tailored for personalized predictions based on molecular data. This procedure can operate with high throughput genetic datasets like gene expression or mutation profiles. Its application prevents SVM from extrapolation by excluding non-informative features. FloWPS requires training on the data for the individuals with known clinical outcomes to create a clinically relevant classifier. The genetic profiles linked with the outcomes are broken as usual into the training and validation datasets. The unique property of FloWPS is that irrelevant features in validation dataset that don’t have significant number of neighboring hits in the training dataset are removed from further analyses. Next, similarly to the k nearest neighbors (kNN) method, for each point of a validation dataset, FloWPS takes into account only the proximal points of the training dataset. Thus, for every point of a validation dataset, the training dataset is adjusted to form a floating window. FloWPS performance was tested on ten gene expression datasets for 992 cancer patients either responding or not on the different types of chemotherapy. We experimentally confirmed by leave-one-out cross-validation that FloWPS enables to significantly increase quality of a classifier built based on the classical SVM in most of the applications, particularly for polynomial kernels.