Application of Bioinformatics in CancersChad Brenner This collection of 25 research papers comprised of 22 original articles and 3 reviews is brought together from international leaders in bioinformatics and biostatistics. The collection highlights recent computational advances that improve the ability to analyze highly complex data sets to identify factors critical to cancer biology. Novel deep learning algorithms represent an emerging and highly valuable approach for collecting, characterizing and predicting clinical outcomes data. The collection highlights several of these approaches that are likely to become the foundation of research and clinical practice in the future. In fact, many of these technologies reveal new insights about basic cancer mechanisms by integrating data sets and structures that were previously immiscible. Accordingly, the series presented here bring forward a wide range of artificial intelligence approaches and statistical methods that can be applied to imaging and genomics data sets to identify previously unrecognized features that are critical for cancer. Our hope is that these articles will serve as a foundation for future research as the field of cancer biology transitions to integrating electronic health record, imaging, genomics and other complex datasets in order to develop new strategies that improve the overall health of individual patients. |
Common terms and phrases
according activity algorithm alterations analysis applied approach associated authors bioinformatics biological biomarkers brain breast cancer carcinoma cell classification clinical clusters cohort combined common compared computational correlation CrossRef database datasets detection diagnosis differentially disease distribution effects enrichment estimated et al evaluated extracted factors Figure function further gene expression genetic genomic Geometry groups head human identified imaging important integration interaction involved learning levels lines lung cancer mean method miRNAs molecular multiple mutations neck normal observed oral outcome overall p-value package pathway patients performed positive potential prediction present primary profiles prognosis protein PubMed regulation respectively response risk role samples score selected sequencing showed shown signaling signatures significant somatic specific stage StAR statistical surgery survival Table TCGA therapy tissue treatment tumor types validation values variables weight