Genomic Machine Learning Model Predicts Radiation Therapy Benefit in Early-Stage Breast Cancer Patients with High Accuracy

BackgroundRadiation therapy (RT) is frequently recommended for post-surgery treatment of early-stage breast cancer (BC) patients, though not all benefit. Clinical factors currently guide RT treatment decisions. At present, models to predict RT-benefit predominantly use statistical methods with modest performance. In this paper we present a high-accuracy genomic Machine Learning (ML) model to predict RT-benefit in early-stage BC patients. We also present a novel method for selecting genomic features for training ML algorithms. MethodsGene expression data from 463 early-stage BC patients treated with surgery and RT from the METABRIC cohort were obtained. Wilcoxon Rank Sum (Wilcoxon RS) test and Cox Proportional Hazards (Cox PH) were used to reduce the number of genes used to train eight ML algorithms. ML algorithms were trained on 80% of data using 10-fold cross validation and tested on 20% of data to assess performance in predicting relapse status. Results Genome-wide gene expression data was reduced by 96% using Wilcoxon RS and Cox PH to a 1,596 gene set and a 977 gene set. These gene sets were used to train eight ML algorithms resulting in models that ranged in performance accuracies from 54.01% to 95.6%. Highest accuracies were obtained using Support Vector Machine (SVM977–93.41%, SVM1596–95.6%) and Neural Networks algorithms (NN977 – 92.31%, NN1596 – 93.41%). In RT-untreated patients, accuracies of all models were 30% to 40% lower compared to RT-treated patients. SVM977 had the highest sensitivity of 91.09%. Members of the 977 set were enriched with genes involved in cell cycle and differentiation as well as genes associated with radiosensitivity and radioresistance. Conclusion This study presents a novel genomic feature selection approach that used Wilcoxon RS followed by Cox PH to reduce the number of genes from genome-wide gene expression data used for training ML algorithms by 96%. This approach led to an SVM model that used the expression values of 977 genes to predict RT-benefit in early-stage BC patients with 93.41% accuracy. This work demonstrates that ML models can be clinically useful for predicting cancer patient outcomes.

Cold Shock Induced Oxidative Stress, Apoptosis and Genome-wide Gene Expression Perturbation in the Eyes of Zebrafish and the Mitigation of Blue Wavelength Light

As global climate changes, severely temperature variations have significant impacts on survival and development of fish. While the potential effects of light wavelength on cold shock and associated mechanisms remain largely unknown in fish. Here, zebrafish were pre-exposed to white LEDs (an irradiance of 0.9 W/m2) and blue LEDs (LDB, peak at 450 nm, 0.9 W/m2) for 2 weeks, and then exposed to 26℃ or 11℃ for 48 hours, respectively. Cold shock led to low survival rate. Cold shock altered retinal structure, increased the number of apoptotic cells and Caspase-3 activity, inhibited superoxide dismutase (SOD) and catalase (CAT) activities, up-regulated mRNA expression of (NF-E2-related factor 2) nrf2, p53, casp3 and casp9, and down-regulated cat expression in fish eyes. These results demonstrated that acute cold exposure induced oxidative stress and apoptosis in zebrafish eyes, which may lead to mortality. However, cold shock in combination with LDB apparently mitigated these negative effects, which might be involved in the up-regulation of antioxidant response and down-regulation of apoptotic responses at transcriptional and translational levels. Furthermore, cold shock also caused dysregulation of genome-wide gene expression involved in circadian rhythm, phototransduction and il-17 signaling pathway, indicating that cold shock disturbed phototransduction cascade and circadian rhythm signals and caused inflammatory responses. Ten key genes involved in circadian rhythm, phototransduction, cell cycle arrest, RNA processing or inflammatory responses were identified, including muc5d, rnps1, si:dkey-243i1.1, opn1mw1, gadd45ba, cebpd, btg2, si:dkey-242g16.2, nr1d1 and zgc:122979, which may play an important role in the protection of LDB against cold shock. Finally, our study suggested the relationship between spectrum and cold stress and demonstrated LDB could protect fish against the negative effect of cold stress in the eyes.

Comparative impact of dietary carbohydrates on the liver transcriptome in two strains of mice

Excessive long-term consumption of dietary carbohydrates, including glucose, sucrose or fructose, has been shown to have significant impact on genome-wide gene expression, which likely results from changes in metabolic substrate flux. However, there has been no comprehensive study on the acute effects of individual sugars on the genome wide gene expression that may reveal the genetic changes altering signaling pathways, subsequent metabolic processes and ultimately physiological/pathological responses. Considering that gene expressions in response to acute carbohydrate ingestion might be different in nutrient sensitive and insensitive mammals, we conducted comparative studies of genome wide gene expression by deep mRNA sequencing of the liver in nutrient sensitive C57BL/6J and nutrient insensitive BALB/cJ mice. Further to determine the temporal responses, we compared livers from mice in the fasted state and following ingestion of standard laboratory mouse chow supplemented with plain drinking water or water containing 20% glucose, sucrose or fructose. Supplementation with these carbohydrates induced unique extents and temporal changes in gene expressions in a strain specific manner. Fructose and sucrose stimulated gene changes peaked at 3 h postprandial, whereas glucose effects peaked at 12 h and 6 h postprandial in C57BL/6J and BABL/cJ mice, respectively. Network analyses revealed that fructose changed genes were primarily involved in lipid metabolism and were more complex in C57BL/6J than in BALB/cJ mice. These data demonstrate that there are qualitative and quantitative differences in the normal physiological responses of the liver between these two strains of mice and C57BL/6J is more sensitive to sugar intake than BALB/cJ.

A Comparative Genome-wide Transcriptome Analysis of Glucocorticoid Responder and Non-Responder Primary Human Trabecular Meshwork Cells

The genome-wide gene expression analysis of primary human trabecular meshwork (HTM) cells with known glucocorticoid (GC) responsiveness was not reported earlier. Therefore, the purpose of this study was to investigate genes and pathways involved in the GC responsiveness in human trabecular meshwork (HTM) cells using RNA sequencing. A perfusion cultured human anterior segment ex vivo model was utilized to identify the induction of GC-induced ocular hypertension in one eye of a paired eyes after dexamethasone treatment based on the maximum intraocular pressure response and in the contralateral eye, HTM cells were isolated to classify GC-responder and non-responder cells. Some previously reported and unique genes and their associated pathways were identified in HTM cells in response to dexamethasone treatment versus vehicle control and more significantly in GC-responder and non-responder cells. This study will open up the possibility of identifying suitable molecular targets which have the potential to treat GC-induced ocular hypertension/glaucoma.

The Marine Gastropod Crepidula fornicata Remains Resilient to Ocean Acidification Across Two Life History Stages

Rising atmospheric CO2 reduces seawater pH causing ocean acidification (OA). Understanding how resilient marine organisms respond to OA may help predict how community dynamics will shift as CO2 continues rising. The common slipper shell snail Crepidula fornicata is a marine gastropod native to eastern North America that has been a successful invader along the western European coastline and elsewhere. It has also been previously shown to be resilient to global change stressors. To examine the mechanisms underlying C. fornicata’s resilience to OA, we conducted two controlled laboratory experiments. First, we examined several phenotypes and genome-wide gene expression of C. fornicata in response to pH treatments (7.5, 7.6, and 8.0) throughout the larval stage and then tested how conditions experienced as larvae influenced juvenile stages (i.e., carry-over effects). Second, we examined genome-wide gene expression patterns of C. fornicata larvae in response to acute (4, 10, 24, and 48 h) pH treatment (7.5 and 8.0). Both C. fornicata larvae and juveniles exhibited resilience to OA and their gene expression responses highlight the role of transcriptome plasticity in this resilience. Larvae did not exhibit reduced growth under OA until they were at least 8 days old. These phenotypic effects were preceded by broad transcriptomic changes, which likely served as an acclimation mechanism for combating reduced pH conditions frequently experienced in littoral zones. Larvae reared in reduced pH conditions also took longer to become competent to metamorphose. In addition, while juvenile sizes at metamorphosis reflected larval rearing pH conditions, no carry-over effects on juvenile growth rates were observed. Transcriptomic analyses suggest increased metabolism under OA, which may indicate compensation in reduced pH environments. Transcriptomic analyses through time suggest that these energetic burdens experienced under OA eventually dissipate, allowing C. fornicata to reduce metabolic demands and acclimate to reduced pH. Carry-over effects from larval OA conditions were observed in juveniles; however, these effects were larger for more severe OA conditions and larvae reared in those conditions also demonstrated less transcriptome elasticity. This study highlights the importance of assessing the effects of OA across life history stages and demonstrates how transcriptomic plasticity may allow highly resilient organisms, like C. fornicata, to acclimate to reduced pH environments.

Genome-Wide Differences in Gene Expression and Alternative Splicing in Developing Embryo and Endosperm, and Between F1 Hybrids and Their Parental Pure Lines in Sorghum

Differential regulation of gene expression and alternative splicing (AS) are major molecular mechanisms dictating plant growth and development, as well as underpinning heterosis in F1 hybrids. Here, using deep RNA-sequencing we analyzed differences in genome-wide gene expression and AS between developing embryo and endosperm, and between F1 hybrids and their pure-line parents in sorghum. We uncover dramatic differences in both gene expression and AS between embryo and endosperm with respect to gene features and functions, which are consistent with the fundamentally different biological roles of the two tissues. Accordingly, F1 hybrids showed substantial and multifaceted differences in gene expression and AS compared with their pure-line parents, again with clear tissue specificities including extents of difference, genes involved and functional enrichments. Our results provide useful transcriptome resources as well as novel insights for further elucidation of seed yield heterosis in sorghum and related crops.