YBL-013 / Y-Biologics, 3DMed - LARVOL DELTA

Optimizing boundary dynamics for nested named entity recognition via semantic refinement and trimming. (PubMed, Neural Netw) - "Moreover, we introduce a Boundary Trimming Module (BTM), which effectively reduces irrelevant span noise through a dual-pathway architecture, simultaneously facilitating top-down semantic refinement and bottom-up semantic restoration. Extensive experiments conducted on established nested (ACE04, ACE05, GENIA) and flat (CoNLL03) NER benchmarks demonstrate that our proposed SRT method achieves state-of-the-art performance."

Journal

Transformer-based prototype network for Chinese nested named entity recognition. (PubMed, Sci Rep) - "A distance-based multi-bounding box cross-entropy loss method is introduced to optimize MSTPN, ensuring the coordinated optimization of transformer and prototype parameters. Experiments using the ACE05, ChiNesE, and RENMIN datasets demonstrate that MSTPN outperforms state-of-the-art methods, highlighting the effectiveness of prototype networks in natural language processing tasks involving long sequences."

Journal • CNS Disorders • Cognitive Disorders

PRTA:Joint extraction of medical nested entities and overlapping relation via parameter sharing progressive recognition and targeted assignment decoding scheme. (PubMed, Comput Biol Med) - "Extensive experiments were conducted on the Private Liver Disease Dataset (PLDD) provided by Beijing Friendship Hospital of Capital Medical University and public datasets (NYT, ACE04 and ACE05). The results show that our method outperforms existing SOTA methods in most indicators, and effectively handles nested entities and overlapping relationships."

Journal • Hepatology

Relation extraction: advancements through deep learning and entity-related features. (PubMed, Soc Netw Anal Min) - "Experimental results from three public datasets (ACE05 English, ACE05 Chinese, and SanWen) indicate that the proposed approach achieves F1-scores of 77.70%, 90.12%, and 68.84%, respectively, highlighting its effectiveness and robustness. This paper provides a comprehensive description of the approach and experimental results."

Journal

Development of an antibody-like T-cell engager based on VH-VL heterodimer formation and its application in cancer therapy. (PubMed, Biomaterials) - "The dual roles of ACE-05 in immune checkpoint inhibition and T-cell redirection, coupled with reduced off-target toxicity, suggest that ACE-05 may be a promising anti-cancer therapeutic agent. Moreover, the bispecific ALiCE platform can be further used for tumor-targeted or multiple immunomodulation applications."

Journal • Immune Modulation • Immunology • Inflammation • Lung Cancer • Non Small Cell Lung Cancer • Oncology • Solid Tumor

Y-Biologics signed License Agreement with 3D Medicines for T cell bispecific engager in Greater China territory (PRNewswire) - "...Y-Biologics and...3D Medicines have entered into a License Agreement granting exclusive rights to develop, manufacture, and commercialize YBL-013, a T cell bi-specific engager based on ALiCE platform technology, in the Territory of Greater China (mainland China, Hong Kong, Macau and Taiwan)...Under the terms of this Agreement, Y-Biologics will receive an upfront fee of $2 million and is eligible to receive up to $85 million in additional development, regulatory, commercialization and sales milestone payments..."

Licensing / partnership • Oncology