BackgroundSince their introduction in 2009, the BioNLP Shared Task events have been instrumental in advancing the development of methods and resources for the automatic extraction of information from the biomedical literature. In this paper, we present the Cancer Genetics (CG) and Pathway Curation (PC) tasks, two event extraction tasks introduced in the BioNLP Shared Task 2013. The CG task focuses on cancer, emphasizing the extraction of physiological and pathological processes at various levels of biological organization, and the PC task targets reactions relevant to the development of biomolecular pathway models, defining its extraction targets on the basis of established pathway representations and ontologies.ResultsSix groups participated in the CG task and two groups in the PC task, together applying a wide range of extraction approaches including both established state-of-the-art systems and newly introduced extraction methods. The best-performing systems achieved F-scores of 55% on the CG task and 53% on the PC task, demonstrating a level of performance comparable to the best results achieved in similar previously proposed tasks.ConclusionsThe results indicate that existing event extraction technology can generalize to meet the novel challenges represented by the CG and PC task settings, suggesting that extraction methods are capable of supporting the construction of knowledge bases on the molecular mechanisms of cancer and the curation of biomolecular pathway models. The CG and PC tasks continue as open challenges for all interested parties, with data, tools and resources available from the shared task homepage.

No abstract

Terminology recognition system which is a preceding research for text mining, information extraction, information retrieval, semantic web, and question-answering has been intensively studied in limited range of domains, especially in bio-medical domain. We propose a domain independent terminology recognition system based on machine learning method using dictionary, syntactic features, and Web search results, since the previous works revealed limitation on applying their approaches to general domain because their resources were domain specific. We achieved F-score 80.8 and 6.5% improvement after comparing the proposed approach with the related approach, C-value, which has been widely used and is based on local domain frequencies. In the second experiment with various combinations of unithood features, the method combined with NGD(Normalized Google Distance) showed the best performance of 81.8 on F-score. We applied three machine learning methods such as Logistic regression, C4.5, and SVMs, and got the best score from the decision tree method, C4.5.

In this paper, we introduce a domain-independent classification framework based on both k-nearest neighbor and Naïve Bayesian classification algorithms. The architecture of our system is simple and modularized in that each sub-module of the system could be changed or improved efficiently. Moreover, it provides various feature selection mechanisms to be applied to optimize the general-purpose classifiers for a specific domain. As for the enhanced classification performance, our system provides conditional probability boosting (CPB) mechanism which could be used in various domains. In the mood classification domain, our optimized framework using the CPB algorithm showed 1% of improvement in precision and 2% in recall compared with the baseline.

EGFR is a transmembrane protein that functions as a receptor tyrosine kinase (RTK). Upon ligand binding or by activating mutations (Exon19 deletion, L858R mutation, and others), EGFR turns on the downstream signals that include oncogenic RAS/MEK/ERK, PI3K/AKT/mTOR, and JAK/STAT pathways. EGFR gene mutations and amplifications are frequently found in various human cancers and, in non-small cell lung cancer (NSCLC), the EGFR gene is mutated with 10-15% frequency (about 50% in Asian patients). While the 1st and 2nd generation EGFR inhibitors are effective in targeting EGFR mutants with Exon19 deletion and L858R mutation, additional T790M mutation in the EGFR gene causes resistance. The 3rd generation EGFR inhibitor (Osimertinib) works against EGFR mutants with T790M mutation; however, another EGFR mutation occurs at the amino acid 797 position (C797S), which makes Osimertinib ineffective. This is one of the major resistance mechanisms in Osimertinib-treated patients, and the 4th generation EGFR inhibitor that can target the C797S mutant is needed. We developed a compound that effectively disables various EGFR mutations, including Del19/T790M/C797S, L858R/T790/C797S, Del19/C797S, and L858R/C797S. In vitro kinase assay and cellular assays showed high potency and selectivity. In vivo PK/PD and efficacy tests confirmed the great therapeutic potential of this inhibitor for patients with EGFR mutations. Citation Format: Dongsu Kim, Woo Seung Son, Anna Jang, Yeri Lee, Donggeon Kim, Changyu Choi, Kyung Hoon Min, Sung Pil Choi, Sang Kyun Lim. Discovery of a small-molecule inhibitor that can target EGFR with C797S mutation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 3323.