Accepted_test

SmartCrop cognitive platform: modules for automatic knowledge extraction from scientific publications, patents and factual databases for reconstruction and analysis of gene networks of stress response in rice and wheat
by Ivanisenko V.A. | Demenkov P.S. | Ivanisenko T.V. | Antropova E.A. | Volyanskaya A.R. | Zubairova U.S. | Makarova A.A. | Orlov Y.L. | Chen M. | ICG SB RAS | ICG SB RAS | ICG SB RAS | ICG SB RAS | ICG SB RAS | ICG SB RAS | ICG SB RAS | ICG SB RAS | College of Life Sciences, First Affiliated Hospital of Medical School, Zhejiang University, Hangzhou, China
Abstract ID: 307
Event: BGRS-abstracts
Sections: [Sym 12] Section “Systems theory, big biological data analysis, ontologies and artificial intelligence”

The thesis presents the development of the SmartCrop cognitive platform, focusing on the automatic knowledge extraction module for analyzing scientific publications, patents, and factual databases to reconstruct gene networks related to stress response in rice and wheat. The platform aims to provide a comprehensive knowledge engineering solution for studying the molecular genetic mechanisms connecting genotype, phenotype, and environment in these agriculturally valuable crops.

The research is a collaboration between Chinese and Russian groups, combining their expertise in data mining and knowledge extraction. The platform addresses various tasks, such as interpreting omics data, reconstructing gene networks, identifying regulatory and signaling pathways, predicting candidate genes, and finding markers for breeding and plant protection.

The knowledge extraction module utilizes semantic-linguistic patterns, neural network models, and ontologies to extract information from texts and represent it as a knowledge graph. The initial filling of the knowledge base was performed using a subset of articles, revealing a significant number of interactions for wheat and rice.

The thesis concludes with plans to integrate the knowledge extraction module with a multi-omics data analysis unit, providing a full-featured platform for understanding the molecular genetic mechanisms underlying the genotype-phenotype relationship in rice and wheat, considering environmental factors. This research contributes to the development of tools for improving crop productivity and resilience.