The use of program code as a data source is increasingly expanding among data scientists. The purpose of the usage varies from the semantic classification of code to the automatic generation of programs. However, the machine learning model application is somewhat limited without annotating the code snippets. To address the lack of annotated datasets, we present the Code4ML corpus. It contains code snippets, task summaries, competitions, and dataset descriptions publicly available from Kaggle—the leading platform for hosting data science competitions. The corpus consists of ~2.5 million snippets of ML code collected from ~100 thousand Jupyter notebooks. A representative fraction of the snippets is annotated by human assessors through a user-friendly interface specially designed for that purpose. Code4ML dataset can help address a number of software engineering or data science challenges through a data-driven approach. For example, it can be helpful for semantic code classification, code auto-completion, and code generation for an ML task specified in natural language.

An online meeting of experts held on November 6, 2020 describes the results of EMPA-REG OUTCOME and EMPEROR-Reduced trials on sodium-glucose co-transporter-2 (SGLT2) inhibitor empagliflozin. We analyzed cardiovascular and renal outcomes in patients with and without type 2 diabetes (T2D) receiving empagliflozin. A number of proposals and recommendations have been adopted regarding the further study of the cardiovascular and renal effects of empagliflozin and its practical use in patients with heart failure, regardless of the T2D presence.

At an online meeting of experts held on May 14, 2021 additional research results on a sodium-glucose co-transporter-2 (SGLT2) inhibitor empagliflozin in patients with heart failure with reduced ejection fraction were considered. According to the data from the EMPEROR-Reduced international study, cardiovascular and renal effects of empagliflozin therapy in patients with and without type 2 diabetes (T2D) were analyzed. A number of proposals and recommendations was accepted regarding the further study of cardiovascular and renal effects of empagliflozin and its use in clinical practice in patients with heart failure, regardless of the T2D presence.

Circulating tumor cells (CTC) and cell free circulating tumor mRNA (cctmRNA) can serve as biomarkers for prognosis and treatment response in lung and other cancers. A barrier to CTC use in some cancers is the low numbers of CTC captured, and the low percent of patients with detectable CTCs. Past comparisons of non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) patients have shown larger cohorts of patients with detectable CTCs, and higher CTC numbers, for SCLCs. We compared methods for CTC capture/identification, and profiled mRNA from both the CTCs and cell free plasma RNA (cctmRNA) for to identify tumor-associated biomarkers. Peripheral blood was collected from 10 SCLC and 10 NSCLC patients prior to therapy, and from 4 normal controls. Capture using the standard EpCAM CellSearch reagent (unicapture) was run in parallel with EpCAM plus Her2, EGFR and MUC-1 combined ferrofluid (quadcapture) plus the use of anti-cytokeratin 7 (CK7) to assist in CTC identification. Unicapture detected CTCs in 40% of NSCLC and 60% of SCLC; whereas, quadcapture/CK7 identified 20% CTCs in NSCLC and 80% in SCLC. Overall, the quadcapture did not improve CTC capture efficiency. Exploratory NanoString analysis was performed on cell-free plasma from these patients and the ferrofluid isolated CTCs. Cancer-specific biomarkers were detected in mRNA from plasma and CTCs by NanoString included CCL5, CLU and SRGN. In summary, quadcapture ferrofluid reagent did not improve the capture efficiency, although the addition of CK7 may have the potential to identify additional CTCs. Nanostring analysis of cctmRNA and CTCs mRNA suggested potential new lung cancer biomarkers that require validation in larger studies. Citation Format: Yanis Boumber, Charu Aggarwal, Catherine Thrash-Bingham, Patricia Fittipaldi, Polina Guseva, Ramillya Vlasenkova, Chandra Rao, Jianming Pei, Brian L. Egleston, Hossein Borghaei, Massimo Cristofanilli, Ranee Mehra, Ilya Serebriiskii, R. Katherine Alpaugh. Comparison of circulating tumor cell (CTC) capture/identification methods and NanoString evaluation of gene expression in CTCs and cell-free circulating tumor mRNA (cctmRNA) in patients with metastatic lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 1584.