A Nested Named Entity Recognition Model Robust in Few-Shot Learning Environments Using Label Description Information by Hyunsun Hwang, Youngjun Jung, Changki Lee, Wooyoung Go

“…Nested named entity recognition (NER) is a task that identifies hierarchically structured entities, where one entity can contain other entities within its span. …”
Get full text

Can open source large language models be used for tumor documentation in Germany?—An evaluation on urological doctors’ notes by Stefan Lenz, Arsenij Ustjanzew, Marco Jeray, Meike Ressing, Torsten Panholzer

“…It involves reading the textual patient documentation and filling in forms in dedicated databases to obtain structured data. Advances in information extraction techniques that build on large language models (LLMs) could have the potential for enhancing the efficiency and reliability of this process. …”
Get full text

Investigation of the genetic diversity of gut mycobiota of the wild and laboratory mice by Ji-Xin Zhao, Hany M. Elsheikha, Kai-Meng Shang, Jin-Wen Su, Yong-Jie Wei, Ya Qin, Zi-Yu Zhao, He Ma, Xiao-Xuan Zhang

“…Here, we studied the diversities and structures of cecal fungal communities in wild (Lasiopodomys brandtii, Apodemus agrarius, and Microtus fortis) vs laboratory C57BL/6J mice to disentangle the contributions of gut fungi to the adaptation of mice to genetic diversity. …”
Get full text

Identification of Upregulating Genes, Transcription Factors, and miRNAs in Vitiligo. In silico Study by AbdElneam AI, Al-Dhubaibi MS, Bahaj SS, Mohammed GF, Atef LM

“…The functional annotation and potential pathways of differentially expressed genes (DEGs) were additionally investigated through Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. …”
Get full text

Developing an AI-powered wound assessment tool: a methodological approach to data collection and model optimization by Alessio Stefanelli, Sofia Zahia, Guillaume Chanel, Rania Niri, Swann Pichon, Sebastian Probst

“…The prospective data included high-resolution images, short videos, and 3D scans, along with structured clinical metadata. Retrospective data were anonymized and manually annotated by wound care experts. …”
Get full text

The mitigative effects of Blautia producta 1009924 on DSS-induced intestinal inflammation by Yishu Chen, Yan Ma, Yang Leng, Xiaoling Li, Sishi Qin, Xiaoyan Li, Zhao Zhang, Zhao Zhang, Huajun Yu

“…It is Gram-positive, arranged in chains, and field emission scanning electron microscopy revealed abundant surface folds and pilus structures, along with excellent acid and bile salt tolerance. …”
Get full text

Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation by Tristan Whitmarsh, Wei Cope, Julia Carmona-Bozo, Roido Manavaki, Stephen-John Sammut, Ramona Woitek, Elena Provenzano, Emma L. Brown, Sarah E. Bohndiek, Ferdia A. Gallagher, Carlos Caldas, Fiona J. Gilbert, Florian Markowetz

“…We first used a U-Net based convolutional neural network, trained and validated using 36 partially annotated whole slide images from 27 patients, to segment vessel structures and tumour regions from which the measurements are taken. …”
Get full text

A SORT1/EGFR molecular interplay as a prognostic biomarker in glioblastoma vasculogenic mimicry: implications in the transcriptional regulation of cancer stemness and drug resistan... by Marie-Eve Roy, Alain Zgheib, Nicoletta Eliopoulos, Borhane Annabi

“…Abstract Background The epidermal growth factor receptor (EGFR) plays a significant role in vasculogenic mimicry (VM), a process by which aggressive cancer cells within hypoxic solid tumors form blood vessel-like structures independent of endothelial cells. Mostly attributed to cancer stem cells (CSC), VM is strongly associated with chemoresistance and poor prognosis in glioblastomas (GBMs). …”
Get full text

Dynamic taxonomy generation for future skills identification using a named entity recognition and relation extraction pipeline by Luis Jose Gonzalez-Gomez, Sofia Margarita Hernandez-Munoz, Abiel Borja, Fernando A. Arana-Salas, Jose Daniel Azofeifa, Jose Daniel Azofeifa, Julieta Noguez, Patricia Caratozzolo, Patricia Caratozzolo

“…Visualizations of the taxonomy were created using various graph structures, demonstrating its applicability across multiple sectors. …”
Get full text

Genome-wide and transcriptome analysis of PdWRKY transcription factors in date palm (Phoenix dactylifera) revealing insights into heat and drought stress tolerance by Ibrahim Khan, Lubna, Saqib Bilal, Ashraf M. M. Abdelbacki, Sang-Mo Kang, Ahmed AL-Harrasi, Sajjad Asaf, In-Jung Lee

“…Our comprehensive analysis of gene structures, conserved motifs, and protein-protein interactions confirmed functional similarities among many PdWRKYs. …”
Get full text

Prompt-based three-dimensional tooth segmentation method based on pre-trained SAM(基于预训练SAM的提示式三维牙齿分割方法) by 刘复昌(LIU Fuchang), 蔡煜晨(CAI Yuchen), 缪永伟(MIAO Yongwei), 范然(FAN Ran)

“…Currently, most studies employ supervised learning techniques to train networks on three-dimensional tooth data to perform annotation tasks. However, these methods often perform poorly on cases of missing teeth, severe misalignments, or incomplete jaw structures, exhibiting weak generalization capabilities. …”
Get full text

Construction and application of knowledge mapping of carbon emission governance technologies for coal mining and utilization by Ying WANG, Liya WANG, Fei MA, Yang YANG, Zishuai ZU

“…Encoder Representations from Transformers & Conditional Random Fields) model to recognize the entities in this domain; third, on the basis of entity recognition, the BiLSTM–Attention model is applied to further mine the relationships between entities and realize relationship extraction; fourth, entity The fourth is to use entity disambiguation and co-reference disambiguation techniques for knowledge fusion, eliminating contradictions and redundant information in the data; the fifth is to store the entities and relationships through the Neo4j graph database, based on the above structured methods and models, thus completing the construction of the knowledge map of the field of coal mining and utilization of carbon emission management technology. …”
Get full text

THE FIRST SCREENING OF ALICE IN WONDERLAND (1903) / ПЕРВАЯ ЭКРАНИЗАЦИЯ «ПРИКЛЮЧЕНИЙ АЛИСЫ В СТРАНЕ ЧУДЕС» (ALICE IN WONDERLAND, 1903) by SALNIKOVA EKATERINA V. / САЛЬНИКОВА Е.В.

“…This suggests that some scenes were sold not separately, but as a series of scenes united by a credit. Structurally, each fragment of the film, consisting of 2–3 scenes, is similar to one episode of series. …”
Get full text

Cloning and identification of human colipase-like 3 and its homologous cDNAs by LU Yan, XUE Yong-chang, YU Peng, WANG Ping-zhang

“…According to the latest release of H-InvDB (release 6.2), 34511 protein-encoding genes were annotated and most of them were function-unknown. There is still a long road ahead to identify the whole human genes and their functions. …”
Get full text