Search

Colorectal cancer (CRC) is a primary global health concern, and identifying the molecular pathways, genetic subtypes, and mutations associated with CRC is crucial for precision medicine. However, traditional measurement techniques such as gene sequencing are costly and time-consuming, while most deep learning methods proposed for this task lack interpretability. This study offers a new approach to enhance the state-of-the-art deep learning methods for molecular pathways and key mutation prediction by incorporating cell network information. We build cell graphs with nuclei as nodes and nuclei connections as edges of the network and leverage Social Network Analysis (SNA) measures to extract abstract, perceivable, and interpretable features that explicitly describe the cell network characteristics in an image. Our approach does not rely on precise nuclei segmentation or feature extraction, is computationally efficient, and is easily scalable. In this study, we utilize the TCGA-CRC-DX dataset, comprising 499 patients and 502 diagnostic slides from primary colorectal tumours, sourced from 36 distinct medical centres in the United States. By incorporating the SNA features alongside deep features in two multiple instance learning frameworks, we demonstrate improved performance for chromosomal instability (CIN), hypermutated tumour (HM), TP53 gene, BRAF gene, and Microsatellite instability (MSI) status prediction tasks (2.4%–4% and 7–8.8% improvement in AUROC and AUPRC on average). Additionally, our method achieves outstanding performance on MSI prediction in an external PAIP dataset (99% AUROC and 98% AUPRC), demonstrating its generalizability. Our findings highlight the discrimination power of SNA features and how they can be beneficial to deep learning models' performance and provide insights into the correlation of cell network profiles with molecular pathways and key mutations. [Display omitted] • A novel method to integrate deep features and cell relationship information. • Utilizing efficient social network analysis to capture cell relationship information. • High performance in predicting CIN, HM, TP53 , BRAF , and MSI status in CRC. • Give insights into the association of cellular relationships and molecular alterations. [ABSTRACT FROM AUTHOR]

Abstract: Quahog parasite unknown (QPX) is a fatal protistan parasite affecting cultured and wild hard clams Mercenaria mercenaria along the northeastern coasts of the USA and maritime Canada. Field investigations and laboratory transmission studies revealed some variations in the susceptibility of different hard clam stocks to QPX infection. In this study, we used in vitro QPX cultures to investigate the effect of plasma and tissue extracts from two different clam stocks on parasite survival and growth. Results demonstrated the presence of factors in clams that significantly modulate QPX growth. Extracts from gills and mantle tissues as well as plasma inhibited in vitro QPX growth, whereas foot and adductor muscle extracts enhanced parasite growth. Investigations of anti-QPX activities in plasma from two clam stocks displaying different susceptibility toward QPX disease in vivo demonstrated higher inhibition of QPX growth by plasma from New York (resistant) clams compared to Florida (susceptible) clams. Some clams appeared to be deficient in inhibitory factors, suggesting that such animals may become more easily infected by the parasite. [Copyright &y& Elsevier]