Center for Development of Advanced Computing

This paper proposed the Agentic Computer Vision (AgCV) framework designed to automate complex computer vision (CV) tasks through autonomous agents that communicate through Graphical User Interface (GUI). The AgCV framework leverages LangGraph, natural language processing, deep learning, and data science to build adaptive, user-driven CV pipelines. In the proposed AgCV each Agent works on a particular task ranging from object identification and classification to image segmentation. By incorporating Retrieval-Augmented Generation (RAG) and LangGraph, the AgCV enable fully automated pipelining through user interactions. The proposed Framework strategy reduces the need for technical expertise, allowing end-users to generate and configure CV operations using intuitive language commands. AgCV promotes accessibility, scalability, and flexibility of CV applications in different domains. The AgCV not only simplifies user interaction but also ensures that the system aligns with user expectations and needs.•The proposed system allows users to create and configure CV operations using simple natural language, making it accessible even to those with limited technical expertise.•The AgCV framework supports a wide range of CV tasks and can be easily adapted to different user needs and applications.

Bamboo shoots, a staple in Asian diets, particularly in India, China, Japan, and Southeast Asia, are valued for their rich nutrients and health benefits. However, they contain cyanogenic glycosides, primarily Taxiphyllin, posing toxicity risks if improperly consumed. This review examines bamboo shoots' nutritional profile, geographical consumption patterns, and the role of Taxiphyllin. It explores the impact of traditional and industrial processing methods, such as boiling, fermentation, and steaming, in reducing Taxiphyllin levels to ensure food safety. Additionally, the paper highlights bamboo shoots' applications in pharmaceuticals, bioethanol production, therapeutics, and cosmetics. Emphasis is placed on the significance of detection technologies in food processing to prevent cyanide poisoning. The findings underscore the need for effective processing and detection techniques to balance bamboo shoots' nutritional and medicinal benefits while mitigating health risks. The review also identifies future research opportunities to maximize their potential in sustainable food and industrial applications.

Mycobacterium tuberculosis (Mtb) is one of the world's successful pathogens that flexibly adapts its metabolic nature during infection of the host, and in response to drugs. Here we used genome scale metabolic modelling coupled with differential producibility analysis (DPA) to translate RNA-seq datasets into metabolite signals and identified drug-associated metabolic response profiles. We tested four tuberculosis (TB) drugs bedaquiline (BDQ), isoniazid (INH), rifampicin (RIF), and clarithromycin (CLA); conducted RNA-seq experiments of Mtb exposed to the individual drugs at subinhibitory concentrations, followed by DPA of gene expression data to map up and downregulated metabolites. Here we highlight those metabolic pathways that were flexibly used by Mtb to tolerate stress generated upon drug exposure. BDQ and INH upregulated maximum number of central carbon metabolites in glycolysis, pentose phosphate pathway and tri-carboxylic acid cycle with concomitant downregulation of lipid and amino acid metabolite classes. Oxaloacetate was significantly upregulated in all four drug-treated Mtb cells highlighting it as an important metabolite in Mtb's metabolism. Amino acid metabolism was selectively induced by different drugs. We have enhanced our knowledge on Mtb's carbon and nitrogen metabolic adaptations in the presence of drugs and identify metabolic nodes for therapeutic development against TB. Our work also provides DPA omics platform to interrogate RNA-seq datasets of any organism that can be reconstructed as a genome scale metabolic network.