A 95-gene signature stratifies recurrence risk of invasive disease in ER-positive, HER2-negative, node-negative breast cancer with intermediate 21-gene signature recurrence scores.

PURPOSE: A subset of patients with intermediate 21-gene signature assay recurrence score may benefit from adjuvant chemoendocrine therapy, but a predictive strategy is needed to identify such patients. The 95-gene signature assay was tested to stratify patients with intermediate RS into high (95GC-H) and low (95GC-L) groups that were associated with invasive recurrence risk. METHODS: Patients with ER-positive, HER2-negative, node-negative breast cancer and RS 11-25 who underwent definitive surgery and adjuvant endocrine therapy without any cytotoxic agents were included. RNA was extracted from archived formalin-fixed, paraffin-embedded samples, and 95-gene signature was calculated. RESULTS: 206 patients had RS of 11-25 (95GC-L, N = 163; 95GC-H, N = 43). In Cox proportional hazards model, 95GC-H was significantly associated with shorter time to recurrence than was 95GC-L (HR 5.94; 95%CI 1.81-19.53; P = 0.005). The correlation between 95-gene signature and 21-gene signature assay scores was not strong (correlation coefficient r = 0.27), which might suggest that 95-gene signature reflects biological characteristics differing from what 21-gene signature shows. CONCLUSIONS: The 95-gene signature stratifies patients with ER-positive, HER2-negative, node-negative invasive breast cancer and intermediate RS of 11-25 into high and low groups that are associated with recurrence risk of invasive disease. Further retrospective analysis in the prospectively accrued TAILORx population is warranted to confirm that 95-gene signature can identify patients who would benefit from adjuvant chemoendocrine therapy.

CNVoyant: A Highly Performant and Explainable Multi-Classifier Machine Learning Approach for Determining the Clinical Significance of Copy Number Variants.

The precise classification of copy number variants (CNVs) presents a significant challenge in genomic medicine, primarily due to the complex nature of CNVs and their diverse impact on genetic disorders. This complexity is compounded by the limitations of existing methods in accurately distinguishing between benign, uncertain, and pathogenic CNVs. Addressing this gap, we introduce CNVoyant, a machine learning-based multi-class framework designed to enhance the clinical significance classification of CNVs. Trained on a comprehensive dataset of 52,176 ClinVar entries across pathogenic, uncertain, and benign classifications, CNVoyant incorporates a broad spectrum of genomic features, including genome position, disease-gene annotations, dosage sensitivity, and conservation scores. Models to predict the clinical significance of copy number gains and losses were trained independently. Final models were selected after testing 29 machine learning architectures and 10,000 hyperparameter combinations each for deletions and duplications via 5-fold cross-validation. We validate the performance of the CNVoyant by leveraging a comprehensive set of 21,574 CNVs from the DECIPHER database, a highly regarded resource known for its extensive catalog of chromosomal imbalances linked to clinical outcomes. Compared to alternative approaches, CNVoyant shows marked improvements in precision-recall and ROC AUC metrics for binary pathogenic classifications while going one step further, offering multi-classification of clinical significance and corresponding SHAP explainability plots. This large-scale validation demonstrates CNVoyant's superior accuracy and underscores its potential to aid genomic researchers and clinical geneticists in interpreting the clinical implications of real CNVs.

Systematic evaluation of objective functions for predicting intracellular fluxes in Escherichia coli.

To which extent can optimality principles describe the operation of metabolic networks? By explicitly considering experimental errors and in silico alternate optima in flux balance analysis, we systematically evaluate the capacity of 11 objective functions combined with eight adjustable constraints to predict (13)C-determined in vivo fluxes in Escherichia coli under six environmental conditions. While no single objective describes the flux states under all conditions, we identified two sets of objectives for biologically meaningful predictions without the need for further, potentially artificial constraints. Unlimited growth on glucose in oxygen or nitrate respiring batch cultures is best described by nonlinear maximization of the ATP yield per flux unit. Under nutrient scarcity in continuous cultures, in contrast, linear maximization of the overall ATP or biomass yields achieved the highest predictive accuracy. Since these particular objectives predict the system behavior without preconditioning of the network structure, the identified optimality principles reflect, to some extent, the evolutionary selection of metabolic network regulation that realizes the various flux states.

Multidimensional optimality of microbial metabolism.

Although the network topology of metabolism is well known, understanding the principles that govern the distribution of fluxes through metabolism lags behind. Experimentally, these fluxes can be measured by (13)C-flux analysis, and there has been a long-standing interest in understanding this functional network operation from an evolutionary perspective. On the basis of (13)C-determined fluxes from nine bacteria and multi-objective optimization theory, we show that metabolism operates close to the Pareto-optimal surface of a three-dimensional space defined by competing objectives. Consistent with flux data from evolved Escherichia coli, we propose that flux states evolve under the trade-off between two principles: optimality under one given condition and minimal adjustment between conditions. These principles form the forces by which evolution shapes metabolic fluxes in microorganisms' environmental context.