Morphological screening of mesenchymal mammary tumor organoids to identify drugs that reverse epithelial-mesenchymal transition

The epithelial-mesenchymal transition (EMT) has been implicated in conferring stem cell properties and therapeutic resistance to cancer cells. Therefore, identification of drugs that can reprogram EMT may provide new therapeutic strategies. Here, we report that cells derived from claudin-low mammary tumors, a mesenchymal subtype of triple-negative breast cancer, exhibit a distinctive organoid structure with extended “spikes” in 3D matrices. Upon a miR-200 induced mesenchymal-epithelial transition (MET), the organoids switch to a smoother round morphology. Based on these observations, we developed a morphological screening method with accompanying analytical pipelines that leverage deep neural networks and nearest neighborhood classification to screen for EMT-reversing drugs. Through screening of a targeted epigenetic drug library, we identified multiple class I HDAC inhibitors and Bromodomain inhibitors that reverse EMT. These data support the use of morphological screening of mesenchymal mammary tumor organoids as a platform to identify drugs that reverse EMT.

Rational Mobile Application to Detect Language and Compose Annotations: Notespeak App

Students in international classroom settings face difficulties comprehending and writing down data shared with them, which causes unnecessary frustration and misunderstanding. However, utilizing digital aids to record and store data can alleviate these issues and ensure comprehension by providing other means of studying/reinforcement. This paper presents an application to actively listen and write down notes for students as teachers instruct class. We applied our application to multiple class settings and company meetings, and conducted a qualitative evaluation of the approach.

Which Class Matters? Juxtaposing Multiple Class Environments as Frames-of-Reference for Academic Self-Concept Formation

Equally able students have lower academic self-concept in high achieving schools or classes, a phenomenon known as the big fish little pond effect (BFLPE). The class (more so than the school) has been shown to be the pivotal frame-of-reference for academic self-concept formation—a local dominance effect. However, many school systems worldwide employ forms of course-by-course tracking, thus exposing students to multiple class environments. Due to the high correlation between multiple student environments, the frame-of-reference used for academic self-concept formation in course-by-course tracked systems is unclear to date. We addressed this unresolved issue by using data from a comprehensive survey that measured the entire population of Austrian eighth-grade students in the domain of mathematics in 2012. General secondary school students were in the core subjects (i.e., mathematics, German, and English) grouped according to ability, whereas regular class composition was the same in all other subjects. Using cross-classified multilevel models, we regressed math self-concept on average math achievement of students’ school, math class, and regular class. Consistent with the local dominance effect, we found the BFLPE on the school level to be weak after controlling for the class levels. We found a stronger BFLPE on the regular class level and the strongest BFLPE on the math class level. Our study demonstrates the importance of multiple class environments as frames-of-reference for academic self-concept formation.

Multi-label learning with missing and completely unobserved labels

Multi-label learning deals with data examples which are associated with multiple class labels simultaneously. Despite the success of existing approaches to multi-label learning, there is still a problem neglected by researchers, i.e., not only are some of the values of observed labels missing, but also some of the labels are completely unobserved for the training data. We refer to the problem as multi-label learning with missing and completely unobserved labels, and argue that it is necessary to discover these completely unobserved labels in order to mine useful knowledge and make a deeper understanding of what is behind the data. In this paper, we propose a new approach named MCUL to solve multi-label learning with Missing and Completely Unobserved Labels. We try to discover the unobserved labels of a multi-label data set with a clustering based regularization term and describe the semantic meanings of them based on the label-specific features learned by MCUL, and overcome the problem of missing labels by exploiting label correlations. The proposed method MCUL can predict both the observed and newly discovered labels simultaneously for unseen data examples. Experimental results validated over ten benchmark datasets demonstrate that the proposed method can outperform other state-of-the-art approaches on observed labels and obtain an acceptable performance on the new discovered labels as well.