Computationally repurposing drugs for breast cancer subtypes using a network-based approach.

'De novo' drug discovery is costly, slow, and with high risk. Repurposing known drugs for treatment of other diseases offers a fast, low-cost/risk and highly-efficient method toward development of efficacious treatments. The emergence of large-scale heterogeneous biomolecular networks, molecular, chemical and bioactivity data, and genomic and phenotypic data of pharmacological compounds is enabling the development of new area of drug repurposing called 'in silico' drug repurposing, i.e., computational drug repurposing (CDR). The aim of CDR is to discover new indications for an existing drug (drug-centric) or to identify effective drugs for a disease (disease-centric). Both drug-centric and disease-centric approaches have the common challenge of either assessing the similarity or connections between drugs and diseases. However, traditional CDR is fraught with many challenges due to the underlying complex pharmacology and biology of diseases, genes, and drugs, as well as the complexity of their associations. As such, capturing highly non-linear associations among drugs, genes, diseases by most existing CDR methods has been challenging. We propose a network-based integration approach that can best capture knowledge (and complex relationships) contained within and between drugs, genes and disease data. A network-based machine learning approach is applied thereafter by using the extracted knowledge and relationships in order to identify single and pair of approved or experimental drugs with potential therapeutic effects on different breast cancer subtypes. Indeed, further clinical analysis is needed to confirm the therapeutic effects of identified drugs on each breast cancer subtype.

A novel model used to detect differential splice junctions as biomarkers in prostate cancer from RNA-Seq data.

BACKGROUND: In cancer alternative RNA splicing represents one mechanism for flexible gene regulation, whereby protein isoforms can be created to promote cell growth, division and survival. Detecting novel splice junctions in the cancer transcriptome may reveal pathways driving tumorigenic events. In this regard, RNA-Seq, a high-throughput sequencing technology, has expanded the study of cancer transcriptomics in the areas of gene expression, chimeric events and alternative splicing in search of novel biomarkers for the disease. RESULTS: In this study, we propose a new two-dimensional peak finding method for detecting differential splice junctions in prostate cancer using RNA-Seq data. We have designed an integrative process that involves a new two-dimensional peak finding algorithm to combine junctions and then remove irrelevant introns across different samples within a population. We have also designed a scoring mechanism to select the most common junctions. CONCLUSIONS: Our computational analysis on three independent datasets collected from patients diagnosed with prostate cancer reveals a small subset of junctions that may potentially serve as biomarkers for prostate cancer. AVAILABILITY: The pipeline, along with their corresponding algorithms, are available upon request.

A modular inquiry-based semester theme that integrates data science education and bioinformatics in protein structure function courses.

BACKGROUND: With an exponential growth in biological data and computing power, familiarity with bioinformatics has become a demanding and popular skill set both in academia and industry. There is a need to increase students' competencies to be able to take on bioinformatic careers, to get them familiarized with scientific professions in data science and the academic training required to pursue them, in a field where demand outweighs the supply. METHODS: Here we implemented a set of bioinformatic activities into a protein structure and function course of a graduate program. Concisely, students were given hands-on opportunities to explore the bioinformatics-based analyses of biomolecular data and structural biology via a semester-long case study structured as inquiry-based bioinformatics exercises. Towards the end of the term, the students also designed and presented an assignment project that allowed them to document the unknown protein that they identified using bioinformatic knowledge during the term. RESULTS: The post-module survey responses and students' performances in the lab module imply that it furthered an in-depth knowledge of bioinformatics. Despite having not much prior knowledge of bioinformatics prior to taking this module students indicated positive feedback. CONCLUSION: The students got familiar with cross-indexed databases that interlink important data about proteins, enzymes as well as genes. The essential skillsets honed by this research-based bioinformatic pedagogical approach will empower students to be able to leverage this knowledge for their future endeavours in the bioinformatics field.

A fully automatic gridding method for cDNA microarray images.

BACKGROUND: Processing cDNA microarray images is a crucial step in gene expression analysis, since any errors in early stages affect subsequent steps, leading to possibly erroneous biological conclusions. When processing the underlying images, accurately separating the sub-grids and spots is extremely important for subsequent steps that include segmentation, quantification, normalization and clustering. RESULTS: We propose a parameterless and fully automatic approach that first detects the sub-grids given the entire microarray image, and then detects the locations of the spots in each sub-grid. The approach, first, detects and corrects rotations in the images by applying an affine transformation, followed by a polynomial-time optimal multi-level thresholding algorithm used to find the positions of the sub-grids in the image and the positions of the spots in each sub-grid. Additionally, a new validity index is proposed in order to find the correct number of sub-grids in the image, and the correct number of spots in each sub-grid. Moreover, a refinement procedure is used to correct possible misalignments and increase the accuracy of the method. CONCLUSIONS: Extensive experiments on real-life microarray images and a comparison to other methods show that the proposed method performs these tasks fully automatically and with a very high degree of accuracy. Moreover, unlike previous methods, the proposed approach can be used in various type of microarray images with different resolutions and spot sizes and does not need any parameter to be adjusted.

Transcriptomics Signature from Next-Generation Sequencing Data Reveals New Transcriptomic Biomarkers Related to Prostate Cancer.

Prostate cancer is one of the most common types of cancer among Canadian men. Next-generation sequencing using RNA-Seq provides large amounts of data that may reveal novel and informative biomarkers. We introduce a method that uses machine learning techniques to identify transcripts that correlate with prostate cancer development and progression. We have isolated transcripts that have the potential to serve as prognostic indicators and may have tremendous value in guiding treatment decisions. Analysis of normal versus malignant prostate cancer data sets indicates differential expression of the genes HEATR5B, DDC, and GABPB1-AS1 as potential prostate cancer biomarkers. Our study also supports PTGFR, NREP, SCARNA22, DOCK9, FLVCR2, IK2F3, USP13, and CLASP1 as potential biomarkers to predict prostate cancer progression, especially between stage II and subsequent stages of the disease.

An Integrative Approach for Identifying Network Biomarkers of Breast Cancer Subtypes Using Genomic, Interactomic, and Transcriptomic Data.

Breast cancer is a complex disease that can be classified into at least 10 different molecular subtypes. Appropriate diagnosis of specific subtypes is critical for ensuring the best possible patient treatment and response to therapy. Current computational methods for determining the subtypes are based on identifying differentially expressed genes (i.e., biomarkers) that can best discriminate the subtypes. Such approaches, however, are known to be unreliable since they yield different biomarker sets when applied to data sets from different studies. Gathering knowledge about the functional relationship among genes will identify "network biomarkers" that will enrich the criteria for biomarker selection. Cancer network biomarkers are subnetworks of functionally related genes that "work in concert" to perform functions associated with a tumorigenic. We propose a machine learning framework that can be used to identify network biomarkers and driver genes for each specific breast cancer subtype. Our results show that the resulting network biomarkers can separate one subtype from the others with very high accuracy.

Predicting Outcomes of Hormone and Chemotherapy in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) Study by Biochemically-inspired Machine Learning.

Genomic aberrations and gene expression-defined subtypes in the large METABRIC patient cohort have been used to stratify and predict survival. The present study used normalized gene expression signatures of paclitaxel drug response to predict outcome for different survival times in METABRIC patients receiving hormone (HT) and, in some cases, chemotherapy (CT) agents. This machine learning method, which distinguishes sensitivity vs. resistance in breast cancer cell lines and validates predictions in patients; was also used to derive gene signatures of other HT  (tamoxifen) and CT agents (methotrexate, epirubicin, doxorubicin, and 5-fluorouracil) used in METABRIC. Paclitaxel gene signatures exhibited the best performance, however the other agents also predicted survival with acceptable accuracies. A support vector machine (SVM) model of paclitaxel response containing genes  ABCB1, ABCB11, ABCC1, ABCC10, BAD, BBC3, BCL2, BCL2L1, BMF, CYP2C8, CYP3A4, MAP2, MAP4, MAPT, NR1I2, SLCO1B3, TUBB1, TUBB4A, and TUBB4B was 78.6% accurate in predicting survival of 84 patients treated with both HT and CT (median survival ≥ 4.4 yr). Accuracy was lower (73.4%) in 304 untreated patients. The performance of other machine learning approaches was also evaluated at different survival thresholds. Minimum redundancy maximum relevance feature selection of a paclitaxel-based SVM classifier based on expression of genes  BCL2L1, BBC3, FGF2, FN1, and  TWIST1 was 81.1% accurate in 53 CT patients. In addition, a random forest (RF) classifier using a gene signature ( ABCB1, ABCB11, ABCC1, ABCC10, BAD, BBC3, BCL2, BCL2L1, BMF, CYP2C8, CYP3A4, MAP2, MAP4, MAPT, NR1I2,SLCO1B3, TUBB1, TUBB4A, and TUBB4B) predicted >3-year survival with 85.5% accuracy in 420 HT patients. A similar RF gene signature showed 82.7% accuracy in 504 patients treated with CT and/or HT. These results suggest that tumor gene expression signatures refined by machine learning techniques can be useful for predicting survival after drug therapies.

CMT: a constrained multi-level thresholding approach for ChIP-Seq data analysis.

Genome-wide profiling of DNA-binding proteins using ChIP-Seq has emerged as an alternative to ChIP-chip methods. ChIP-Seq technology offers many advantages over ChIP-chip arrays, including but not limited to less noise, higher resolution, and more coverage. Several algorithms have been developed to take advantage of these abilities and find enriched regions by analyzing ChIP-Seq data. However, the complexity of analyzing various patterns of ChIP-Seq signals still needs the development of new algorithms. Most current algorithms use various heuristics to detect regions accurately. However, despite how many formulations are available, it is still difficult to accurately determine individual peaks corresponding to each binding event. We developed Constrained Multi-level Thresholding (CMT), an algorithm used to detect enriched regions on ChIP-Seq data. CMT employs a constraint-based module that can target regions within a specific range. We show that CMT has higher accuracy in detecting enriched regions (peaks) by objectively assessing its performance relative to other previously proposed peak finders. This is shown by testing three algorithms on the well-known FoxA1 Data set, four transcription factors (with a total of six antibodies) for Drosophila melanogaster and the H3K4ac antibody dataset.