Bioinformatics and Machine Learning for Cancer Biology

• Other Authors: Wan, Shibiao (Editor), Fan, Yiping (Editor), Jiang, Chunjie (Editor), Li, Shengli (Editor)
• Format: Electronic Book Chapter
• Language: English
• Published: Basel MDPI - Multidisciplinary Digital Publishing Institute 2022
• Subjects: Research & information: general; Biology, life sciences; tumor mutational burden; DNA damage repair genes; immunotherapy; biomarker; biomedical informatics; breast cancer; estrogen receptor alpha; persistent organic pollutants; drug-drug interaction networks; molecular docking; NGS; ctDNA; VAF; liquid biopsy; filtering; variant calling; DEGs; diagnosis; ovarian cancer; PUS7; RMGs; CPA4; bladder urothelial carcinoma; immune cells; T cell exhaustion; checkpoint; architectural distortion; image processing; depth-wise convolutional neural network; mammography; bladder cancer; Annexin family; survival analysis; prognostic signature; therapeutic target; R Shiny application; RNA-seq; proteomics; multi-omics analysis; T-cell acute lymphoblastic leukemia; CCLE; sitagliptin; thyroid cancer (THCA); papillary thyroid cancer (PTCa); thyroidectomy; metastasis; drug resistance; n/a; biomarker identification; transcriptomics; machine learning; prediction; variable selection; major histocompatibility complex; bidirectional long short-term memory neural network; deep learning; cancer; incidence; mortality; modeling; forecasting; Google Trends; Romania; ARIMA; TBATS; NNAR
• Online Access: DOAB: download the publication; DOAB: description of the publication

Cancer is a leading cause of death worldwide, claiming millions of lives each year. Cancer biology is an essential research field to understand how cancer develops, evolves, and responds to therapy. By taking advantage of a series of "omics" technologies (e.g., genomics, transcriptomics, and epigenomics), computational methods in bioinformatics and machine learning can help scientists and researchers to decipher the complexity of cancer heterogeneity, tumorigenesis, and anticancer drug discovery. Particularly, bioinformatics enables the systematic interrogation and analysis of cancer from various perspectives, including genetics, epigenetics, signaling networks, cellular behavior, clinical manifestation, and epidemiology. Moreover, thanks to the influx of next-generation sequencing (NGS) data in the postgenomic era and multiple landmark cancer-focused projects, such as The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC), machine learning has a uniquely advantageous role in boosting data-driven cancer research and unraveling novel methods for the prognosis, prediction, and treatment of cancer.