About this Research Topic
Precision medicine aims to combat complex human diseases by providing preventative, diagnostic, and treatment tools for each patient rather than each cohort. Along with the development of precision medicine (formerly called personalized medicine), the recent “All of Us” initiative seeks to gather data related to “lifestyle, environment, and biology” (according to the National Institute of Health) from a wide range of people in order to better understand individual differences and improve precision medicine.
“All of Us” precision medicine is seeking easy, low-cost, non-invasive, and effective early clinical detection approaches, which include novel experimental and computational approaches in precision healthcare research. Importantly, many types/domains of data from new technologies can be utilized, such as voice/text recording, image scanning, behavioral monitoring, and feature phenotyping, in addition to omics data from high-throughput technologies. These consist of cross-domain data, where the micro cross-domain can cover conventional omics data and the macro cross-domain can bridge the omics with other data types. Thus, the corresponding cross-domain analysis is a key to understanding “All of Us” precision medicine.
In particular, the artificial intelligence (AI) model and method (e.g., deep learning) has achieved great success in analyzing image data in many fields and is bringing new opportunities to clinical research. However, for cross-domain analysis in “All of Us” precision medicine, several challenges still exist: the numbers of variables in different domains are unbalanced, and the bias caused from the dominant domain should be removed; the number of observations is small or not large enough in clinical or biological fields, thus small-sample modeling is required; the samples in different domains may be not matched, so that heterogeneous integration is considered; and many data organizations exist, so data without a vector or matrix form needs a reasonable and powerful transformation/representation.
This Research Topic will serve as an update of our previous topic, “Machine Learning Advanced Dynamic Omics Data Analysis for Precision Medicine,” with a focus on the application of artificial intelligence with cross-domain data for further developing “All of Us” precision medicine. Several study designs are especially welcome:
• Studies on micro cross-domain, which is on the basis of omics data on different levels (e.g., the bulk or single-cell data of genomic, transcriptomic, epigenomic, proteomic, or metagenomic samples from matched or unmatched samples);
• Studies on macro cross-domain, which is collecting the molecular, voice, text, image, behavior, and phenotyping-feature data from sick or healthy patients;
• Studies on high-order cross-domain, which can be either micro cross-domain or macro cross-domain in a longitudinal manner.
We encourage submissions of both Original Research and Review articles of artificial intelligence research and applications that address these existing challenges in the diverse interdisciplinary fields for “All of Us” precision medicine, which include but are not limited to adaptive learning, small-number learning, nonlinear integration, embedding representation, deep learning, and transfer leaning; integrative disease subtyping, network biomarker detection, disease drivers recognition, and drug target prediction; and novel machine learning models and AI system development.
“All of Us” precision medicine is seeking easy, low-cost, non-invasive, and effective early clinical detection approaches, which include novel experimental and computational approaches in precision healthcare research. Importantly, many types/domains of data from new technologies can be utilized, such as voice/text recording, image scanning, behavioral monitoring, and feature phenotyping, in addition to omics data from high-throughput technologies. These consist of cross-domain data, where the micro cross-domain can cover conventional omics data and the macro cross-domain can bridge the omics with other data types. Thus, the corresponding cross-domain analysis is a key to understanding “All of Us” precision medicine.
In particular, the artificial intelligence (AI) model and method (e.g., deep learning) has achieved great success in analyzing image data in many fields and is bringing new opportunities to clinical research. However, for cross-domain analysis in “All of Us” precision medicine, several challenges still exist: the numbers of variables in different domains are unbalanced, and the bias caused from the dominant domain should be removed; the number of observations is small or not large enough in clinical or biological fields, thus small-sample modeling is required; the samples in different domains may be not matched, so that heterogeneous integration is considered; and many data organizations exist, so data without a vector or matrix form needs a reasonable and powerful transformation/representation.
This Research Topic will serve as an update of our previous topic, “Machine Learning Advanced Dynamic Omics Data Analysis for Precision Medicine,” with a focus on the application of artificial intelligence with cross-domain data for further developing “All of Us” precision medicine. Several study designs are especially welcome:
• Studies on micro cross-domain, which is on the basis of omics data on different levels (e.g., the bulk or single-cell data of genomic, transcriptomic, epigenomic, proteomic, or metagenomic samples from matched or unmatched samples);
• Studies on macro cross-domain, which is collecting the molecular, voice, text, image, behavior, and phenotyping-feature data from sick or healthy patients;
• Studies on high-order cross-domain, which can be either micro cross-domain or macro cross-domain in a longitudinal manner.
We encourage submissions of both Original Research and Review articles of artificial intelligence research and applications that address these existing challenges in the diverse interdisciplinary fields for “All of Us” precision medicine, which include but are not limited to adaptive learning, small-number learning, nonlinear integration, embedding representation, deep learning, and transfer leaning; integrative disease subtyping, network biomarker detection, disease drivers recognition, and drug target prediction; and novel machine learning models and AI system development.
Keywords: Artificial Intelligence, Cross-Domain, Precision Medicine, Machine learning
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
