BACKGROUND: Machine learning has been utilized to predict cancer drug response from multi-omics data generated from sensitivities of cancer cell lines to different therapeutic compounds. Here, we build machine learning models using gene expression data from patients' primary tumor tissues to predict whether a patient will respond positively or negatively to two chemotherapeutics: 5-Fluorouracil and Gemcitabine. RESULTS: We focused on 5-Fluorouracil and Gemcitabine because based on our exclusion criteria, they provide the largest numbers of patients within TCGA. Normalized gene expression data were clustered and used as the input features for the study. We used matching clinical trial data to ascertain the response of these patients via multiple classification methods. Multiple clustering and classification methods were compared for prediction accuracy of drug response. Clara and random forest were found to be the best clustering and classification methods, respectively. The results show our models predict with up to 86% accuracy; despite the study's limitation of sample size. We also found the genes most informative for predicting drug response were enriched in well-known cancer signaling pathways and highlighted their potential significance in chemotherapy prognosis. CONCLUSIONS: Primary tumor gene expression is a good predictor of cancer drug response. Investment in larger datasets containing both patient gene expression and drug response is needed to support future work of machine learning models. Ultimately, such predictive models may aid oncologists with making critical treatment decisions.

BACKGROUND: The majority of ovarian cancer biomarker discovery efforts focus on the identification of proteins that can improve the predictive power of presently available diagnostic tests. We here show that metabolomics, the study of metabolic changes in biological systems, can also provide characteristic small molecule fingerprints related to this disease. RESULTS: In this work, new approaches to automatic classification of metabolomic data produced from sera of ovarian cancer patients and benign controls are investigated. The performance of support vector machines (SVM) for the classification of liquid chromatography/time-of-flight mass spectrometry (LC/TOF MS) metabolomic data focusing on recognizing combinations or "panels" of potential metabolic diagnostic biomarkers was evaluated. Utilizing LC/TOF MS, sera from 37 ovarian cancer patients and 35 benign controls were studied. Optimum panels of spectral features observed in positive or/and negative ion mode electrospray (ESI) MS with the ability to distinguish between control and ovarian cancer samples were selected using state-of-the-art feature selection methods such as recursive feature elimination and L1-norm SVM. CONCLUSION: Three evaluation processes (leave-one-out-cross-validation, 12-fold-cross-validation, 52-20-split-validation) were used to examine the SVM models based on the selected panels in terms of their ability for differentiating control vs. disease serum samples. The statistical significance for these feature selection results were comprehensively investigated. Classification of the serum sample test set was over 90% accurate indicating promise that the above approach may lead to the development of an accurate and reliable metabolomic-based approach for detecting ovarian cancer.

MOTIVATION: Long terminal repeat (LTR) retrotransposons constitute a substantial fraction of most eukaryotic genomes and are believed to have a significant impact on genome structure and function. Conventional methods used to search for LTR retrotransposons in genome databases are labor intensive. We present an efficient, reliable and automated method to identify and analyze members of this important class of transposable elements. RESULTS: We have developed a new data-mining program, LTR_STRUC (LTR retrotransposon structure program) which identifies and automatically analyzes LTR retrotransposons in genome databases by searching for structural features characteristic of such elements. LTR_STRUC has significant advantages over conventional search methods in the case of LTR retrotransposon families having low sequence homology to known queries or families with atypical structure (e.g. non-autonomous elements lacking canonical retroviral ORFs) and is thus a discovery tool that complements established methods. LTR_STRUC finds LTR retrotransposons using an algorithm that encompasses a number of tasks that would otherwise have to be initiated individually by the user. For each LTR retrotransposon found, LTR_STRUC automatically generates an analysis of a variety of structural features of biological interest. AVAILABILITY: The LTR_STRUC program is currently available as a console application free of charge to academic users from the authors.