RESUMEN
Program code has recently become a valuable active data source for training various data science models, from code classification to controlled code synthesis. Annotating code snippets play an essential role in such tasks. This article presents a novel approach that leverages CodeBERT, a powerful transformer-based model, to classify code snippets extracted from Code4ML automatically. Code4ML is a comprehensive machine learning code corpus compiled from Kaggle, a renowned data science competition platform. The corpus includes code snippets and information about the respective kernels and competitions, but it is limited in the quality of the tagged data, which is ~0.2%. Our method addresses the lack of labeled snippets for supervised model training by exploiting the internal ambiguity in particular labeled snippets where multiple class labels are combined. Using a specially designed algorithm, we effectively separate these ambiguous fragments, thereby expanding the pool of training data. This data augmentation approach greatly increases the amount of labeled data and improves the overall quality of the trained models. The experimental results demonstrate the prowess of the proposed code classifier, achieving an impressive F1 test score of ~89%. This achievement not only enhances the practicality of CodeBERT for classifying code snippets but also highlights the importance of enriching large-scale annotated machine learning code datasets such as Code4ML. With a significant increase in accurately annotated code snippets, Code4ML is becoming an even more valuable resource for learning and improving various data processing models.
RESUMEN
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.
RESUMEN
Influence of a new protein-peptide complex on promoting skin wound healing in male BALB/c mice was studied. Protein-peptide complex, extracted from Sus scrofa immune organs, was percutaneously administered using two methods: by lecithin gel-like liquid crystals and by liquid microemulsion. On the fifth day, wound closure in mice with a linear wound model become faster in group (less 2 days comparison to other ones), which was treated with lecithin liquid crystals carrying the protein-peptide complex. This promoting healing can be caused by resorption of bioactive high-molecular compounds the animal skin. In mice with the linear wound model, the tensile strength of the scars were respectively higher both in mice, treated using lecithin liquid crystals with protein-peptide complex, and in mice, treated using microemulsion containing protein-peptide complex, by 215.4% and 161.5% relative to the animals, which did not receive bioactive substances for wound treatment. It was associated with the regeneratory effects of tissue- and species-specific protein-peptide complexes, including α-thymosin Sus scrofa (C3VVV8_PIG, m/z 3802.8) and other factors, which were described as parts of the new extracted complex. This reveals that percutaneous administration of the complex reliably activates local regenerative processes in animals.
RESUMEN
The reaction of [NiBr(2)(bpy)(2)] (bpy = 2,2'-bipyridine) with organic phosphinic acids ArP(O)(OH)H [Ar = Ph, 2,4,6-trimethylphenyl (Mes), 9-anthryl (Ant)] leads to the formation of binuclear nickel(II) complexes with bridging ArP(H)O(2)(-) ligands. Crystal structures of the binuclear complexes [Ni(2)(µ-O(2)P(H)Ar)(2)(bpy)(4)]Br(2) (Ar = Ph, Mes, Ant) have been determined. In each structure, the metal ions have distorted octahedral coordination and are doubly bridged by two arylphosphinato ligands. Magnetic susceptibility measurements have shown that these complexes display strong antiferromagnetic coupling between the two nickel atoms at low temperatures, apparently similar to binuclear nickel(II) complexes with bridging carboxylato ligands. Cyclic voltammetry and in situ EPR spectroelectrochemistry show that these complexes can be electrochemically reduced and oxidized with the formation of Ni(I),Ni(0)/Ni(III) derivatives.