Search

Robustly predicting outcome for cancer patients from gene expression is an important challenge on the road to better personalized treatment. Network-based outcome predictors (NOPs), which considers the cellular wiring diagram in the classification, hold much promise to improve performance, stability and interpretability of identified marker genes. Problematically, reports on the efficacy of NOPs are conflicting and for instance suggest that utilizing random networks performs on par to networks that describe biologically relevant interactions. In this paper we turn the prediction problem around: instead of using a given biological network in the NOP, we aim to identify the network of genes that truly improves outcome prediction. To this end, we propose SyNet, a gene network constructed ab initio from synergistic gene pairs derived from survival-labelled gene expression data. To obtain SyNet, we evaluate synergy for all 69 million pairwise combinations of genes resulting in a network that is specific to the dataset and phenotype under study and can be used to in a NOP model. We evaluated SyNet and 11 other networks on a compendium dataset of >4000 survival-labelled breast cancer samples. For this purpose, we used cross-study validation which more closely emulates real world application of these outcome predictors. We find that SyNet is the only network that truly improves performance, stability and interpretability in several existing NOPs. We show that SyNet overlaps significantly with existing gene networks, and can be confidently predicted (~85% AUC) from graph-topological descriptions of these networks, in particular the breast tissue-specific network. Due to its data-driven nature, SyNet is not biased to well-studied genes and thus facilitates post-hoc interpretation. We find that SyNet is highly enriched for known breast cancer genes and genes related to e.g. histological grade and tamoxifen resistance, suggestive of a role in determining breast cancer outcome. [ABSTRACT FROM AUTHOR]

How can we predict the occurrence of acute kidney injury (AKI) in cancer patients based on machine learning with serum creatinine data? Given irregular and heterogeneous clinical data, how can we make the most of it for accurate AKI prediction? AKI is a common and significant complication in cancer patients, and correlates with substantial morbidity and mortality. Since no effective treatment for AKI still exists, it is important to take timely preventive measures. While several approaches have been proposed for predicting AKI, their scope and applicability are limited as they either assume regular data measured over a short hospital stay, or do not fully utilize heterogeneous data. In this paper, we provide an AKI prediction model with a greater applicability, which relaxes the constraints of existing approaches, and fully utilizes irregular and heterogeneous data for learning the model. In a cohort of 21,022 cancer patients who were registered into Korea Central Cancer Registry (KCCR) in Seoul National University Hospital between January 1, 2004 and December 31, 2013, our method achieves 0.7892 precision, 0.7506 recall, and 0.7576 F-measure in predicting whether a patient will develop AKI during the next 14 days. [ABSTRACT FROM AUTHOR]

Drug screening studies typically involve assaying the sensitivity of a range of cancer cell lines across an array of anti-cancer therapeutics. Alongside these sensitivity measurements high dimensional molecular characterizations of the cell lines are typically available, including gene expression, copy number variation and genomic mutations. We propose a sparse multitask regression model which learns discriminative latent characteristics that predict drug sensitivity and are associated with specific molecular features. We use ideas from Bayesian nonparametrics to automatically infer the appropriate number of these latent characteristics. The resulting analysis couples high predictive performance with interpretability since each latent characteristic involves a typically small set of drugs, cell lines and genomic features. Our model uncovers a number of drug-gene sensitivity associations missed by single gene analyses. We functionally validate one such novel association: that increased expression of the cell-cycle regulator C/EBPδ decreases sensitivity to the histone deacetylase (HDAC) inhibitor panobinostat. [ABSTRACT FROM AUTHOR]

Target-based screening is one of the major approaches in drug discovery. Besides the intended target, unexpected drug off-target interactions often occur, and many of them have not been recognized and characterized. The off-target interactions can be responsible for either therapeutic or side effects. Thus, identifying the genome-wide off-targets of lead compounds or existing drugs will be critical for designing effective and safe drugs, and providing new opportunities for drug repurposing. Although many computational methods have been developed to predict drug-target interactions, they are either less accurate than the one that we are proposing here or computationally too intensive, thereby limiting their capability for large-scale off-target identification. In addition, the performances of most machine learning based algorithms have been mainly evaluated to predict off-target interactions in the same gene family for hundreds of chemicals. It is not clear how these algorithms perform in terms of detecting off-targets across gene families on a proteome scale. Here, we are presenting a fast and accurate off-target prediction method, REMAP, which is based on a dual regularized one-class collaborative filtering algorithm, to explore continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. Furthermore, REMAP is highly scalable. It can screen a dataset of 200 thousands chemicals against 20 thousands proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and side effect prediction. The software and benchmark are available at . [ABSTRACT FROM AUTHOR]

Purpose: The objective of this study was to prospectively evaluate various quantitative metrics on FDG PET/CT for monitoring sunitinib therapy and predicting prognosis in patients with metastatic renal cell cancer (mRCC). Methods: Seventeen patients (mean age: 59.0 ± 11.6) prospectively underwent a baseline FDG PET/CT and interim PET/CT after 2 cycles (12 weeks) of sunitinib therapy. We measured the highest maximum standardized uptake value (SUVmax) of all identified lesions (highest SUVmax), sum of SUVmax with maximum six lesions (sum of SUVmax), total lesion glycolysis (TLG) and metabolic tumor volume (MTV) from baseline PET/CT and interim PET/CT, and the % decrease in highest SUVmax of lesion (%Δ highest SUVmax), the % decrease in sum of SUVmax, the % decrease in TLG (%ΔTLG) and the % decrease in MTV (%ΔMTV) between baseline and interim PET/CT, and the imaging results were validated by clinical follow-up at 12 months after completion of therapy for progression free survival (PFS). Results: At 12 month follow-up, 6/17 (35.3%) patients achieved PFS, while 11/17 (64.7%) patients were deemed to have progression of disease or recurrence within the previous 12 months. At baseline, PET/CT demonstrated metabolically active cancer in all cases. Using baseline PET/CT alone, all of the quantitative imaging metrics were predictive of PFS. Using interim PET/CT, the %Δ highest SUVmax, %Δ sum of SUVmax, and %ΔTLG were also predictive of PFS. Otherwise, interim PET/CT showed no significant difference between the two survival groups regardless of the quantitative metric utilized including MTV and TLG. Conclusions: Quantitative metabolic measurements on baseline PET/CT appears to be predictive of PFS at 12 months post-therapy in patients scheduled to undergo sunitinib therapy for mRCC. Change between baseline and interim PET/CT also appeared to have prognostic value but otherwise interim PET/CT after 12 weeks of sunitinib did not appear to be predictive of PFS. [ABSTRACT FROM AUTHOR]

Objectives: Measurement of MRP8/14 serum levels has shown potential in predicting clinical response to different biological agents in rheumatoid arthritis (RA). We aimed to develop a treatment algorithm based on a prediction score using MRP8/14 measurements and clinical parameters predictive for response to different biological agents. Methods: Baseline serum levels of MRP8/14 were measured in 170 patients starting treatment with infliximab, adalimumab or rituximab. We used logistic regression analysis to develop a predictive score for clinical response at 16 weeks. MRP8/14 levels along with clinical variables at baseline were investigated. We also investigated how the predictive effect of MRP8/14 was modified by drug type. A treatment algorithm was developed based on categorizing the expected response per drug type as high, intermediate or low for each patient and optimal treatment was defined. Finally, we present the utility of using this treatment algorithm in clinical practice. Results: The probability of response increased with higher baseline MRP8/14 complex levels (OR = 1.39), differentially between the TNF-blockers and rituximab (OR of interaction term = 0.78), and also increased with higher DAS28 at baseline (OR = 1.28). Rheumatoid factor positivity, functional disability (a higher HAQ), and previous use of a TNF-inhibitor decreased the probability of response. Based on the treatment algorithm 80 patients would have been recommended for anti-TNF treatment, 8 for rituximab, 13 for another biological treatment (other than TNFi or rituximab) and for 69 no recommendation was made. The predicted response rates matched the observed response in the cohort well. On group level the predicted response based on the algorithm resulted in a modest 10% higher response rate in our cohort with much higher differences in response probability in individual patients treated contrary to treatment recommendation. Conclusions: Prediction of response using MRP8/14 levels along with clinical predictors has potential in personalizing treatment for RA patients starting biological anti-rheumatic treatment, and might increase cost-effectiveness. [ABSTRACT FROM AUTHOR]