We present a machine learning (ML) pipeline to identify star clusters in the multicolor images of nearby galaxies, from observations obtained with the Hubble Space Telescope as part of the Treasury Project LEGUS (Legacy ExtraGalactic Ultraviolet Survey). StarcNet (STAR Cluster classification NETwork) is a multiscale convolutional neural network (CNN) that achieves an accuracy of 68.6% (four classes)/86.0% (two classes: cluster/noncluster) for star cluster classification in the images of the LEGUS galaxies, nearly matching human expert performance. We test the performance of StarcNet by applying a pre-trained CNN model to galaxies not included in the training set, finding accuracies similar to the reference one. We test the effect of StarcNet predictions on the inferred cluster properties by comparing multicolor luminosity functions and mass–age plots from catalogs produced by StarcNet and by human labeling; distributions in luminosity, color, and physical characteristics of star clusters are similar for the human and ML classified samples. There are two advantages to the ML approach: (1) reproducibility of the classifications: the ML algorithm’s biases are fixed and can be measured for subsequent analysis; and (2) speed of classification: the algorithm requires minutes for tasks that humans require weeks to months to perform. By achieving comparable accuracy to human classifiers, StarcNet will enable extending classifications to a larger number of candidate samples than currently available, thus increasing significantly the statistics for cluster studies.

No abstract

No abstract

Low-dose computed tomography (LDCT) Non-Small Cell Lung (NSCLC) screening is associated with high false-positive rates, leading to unnecessary expensive and invasive follow ups. There is a need for minimally invasive approaches to improve the accuracy of NSCLC diagnosis. In addition, NSCLC patients harboring sensitizing mutations in epidermal growth factor receptor EGFR (T790M, L578R) are treated with Osimertinib, a potent tyrosine kinase inhibitor (TKI). However, nearly all patients develop TKI resistance. The underlying mechanisms are not fully understood. Plasma extracellular vesicle (EV) and circulating microRNA (miRNA) have been proposed as biomarkers for cancer screening and to inform treatment decisions. However, the identification of highly sensitive and broadly predictive core miRNA signatures remains a challenge. Also, how these systemic and diverse miRNAs impact cancer drug response is not well understood. Using an integrative approach, we examined plasma EV and circulating miRNA isolated from NSCLC patients versus screening controls with a similar risk profile. We found that combining EV (Hsa-miR-184, Let-7b-5p) and circulating (Hsa-miR-22-3p) miRNAs abundance robustly discriminates between NSCLC patients and high-risk cancer-free controls. Further, we found that Hsa-miR-22-3p, Hsa-miR-184, and Let-7b-5p functionally converge on WNT/βcatenin and mTOR/AKT signaling axes, known cancer therapy resistance signals. Targeting Hsa-miR-22-3p and Hsa-miR-184 desensitized EGFR-mutated (T790M, L578R) NSCLC cells to Osimertinib. These findings suggest that the expression levels of circulating hsa-miR-22-3p combined with EV hsa-miR-184 and Let-7b-5p levels potentially define a core biomarker signature for improving the accuracy of NSCLC diagnosis. Importantly, these biomarkers have the potential to enable prospective identification of patients who are at risk of responding poorly to Osimertinib alone but likely to benefit from Osimertinib/AKT blockade combination treatments.

Organisms have been shifting their timing of life history events (phenology) in response to changes in the emergence of resources induced by climate change. Yet understanding these patterns at large scales and across long time series is often challenging. Here we used the US weather surveillance radar network to collect data on the timing of communal swallow and martin roosts and evaluate the scale of phenological shifts and its potential association with temperature. The discrete morning departures of these aggregated aerial insectivores from ground-based roosting locations are detected by radars around sunrise. For the first time, we applied a machine learning algorithm to automatically detect and track these largescale behaviors. We used 21 years of data from 12 weather surveillance radar stations in the Great Lakes region to quantify the phenology in roosting behavior of aerial insectivores at three spatial levels: local roost cluster, radar station, and across the Great Lakes region. We show that their peak roosting activity timing has advanced by 2.26 days per decade at the regional scale. Similar signals of advancement were found at the station scale, but not at the local roost cluster scale. Air temperature trends in the Great Lakes region during the active roosting period were predictive of later stages of roosting phenology trends (75% and 90% passage dates). Our study represents one of the longest-term broad-scale phenology examinations of avian aerial insectivore species responding to environmental change and provides a stepping stone for examining potential phenological mismatches across trophic levels at broad spatial scales.