Personalized medicine is a rapidly developing approach to treatment that prescribes drugs and treatment regimens based on the individual patient. This can be achieved, for example, by using their genetic profile. Such profiling may be carried out for various gene expression and mutation quantities. Individualized prescription of different treatment schemes may be performed according to two different paradigms. First, one can evaluate the abilities of a certain drug to restore the normal status of the expression/mutation-based pattern, or secondly to terminate the physiological process that is considered pathogenic for a certain disease (e.g. cell proliferation for cancer etc.). Another approach exploits machine learning based on multi-omics big data for patients with a known clinical response to certain treatment regimens, to predict the outcome for new patients. The recent sharp decrease of sequencing costs have enabled the routine use of personalized medicine today.
Personalized medicine, therefore, focuses essential efforts on machine learning and big data analysis in bioinformatics. First, we need to develop various bioinformatic algorithms for the quantitative assessment for the activation levels of cell pathways. Second, we should invent approaches to multi-omics big data-based evaluation of personalized drug action. Next, we must suggest and test machine-learning methods in multi-omics personalized medicine. Additionally, there is an urgent demand for cross-platform harmonization of multi-omics big data.
We aim to collect articles covering the following topics:
• Methods for assessment of molecular pathway activation and drug action on individual patients, based on multi-omics big data.
• Methods and applications for machine learning in personalized medicine using multi-omics big data and other clinical data.
• Case reports on patients who were treated according to recommendations of omics-based personalized medicine, clinical monitoring of such cases; clinical trials for decision support systems in omics-based personalized medicine.
• Omics-based personalized medicine for non-cancer diseases.
• Review of public repositories/databases of multi-omics big data, their content, as well as methods and software for its fast browsing and processing; methods for harmonization of multi-omics data.
• Review of repositories/collections of reference normal/disease samples, organs and tissues used for multi-omics personalized medicine.
Dr. Borisov works with Oncobox Ltd.
Personalized medicine is a rapidly developing approach to treatment that prescribes drugs and treatment regimens based on the individual patient. This can be achieved, for example, by using their genetic profile. Such profiling may be carried out for various gene expression and mutation quantities. Individualized prescription of different treatment schemes may be performed according to two different paradigms. First, one can evaluate the abilities of a certain drug to restore the normal status of the expression/mutation-based pattern, or secondly to terminate the physiological process that is considered pathogenic for a certain disease (e.g. cell proliferation for cancer etc.). Another approach exploits machine learning based on multi-omics big data for patients with a known clinical response to certain treatment regimens, to predict the outcome for new patients. The recent sharp decrease of sequencing costs have enabled the routine use of personalized medicine today.
Personalized medicine, therefore, focuses essential efforts on machine learning and big data analysis in bioinformatics. First, we need to develop various bioinformatic algorithms for the quantitative assessment for the activation levels of cell pathways. Second, we should invent approaches to multi-omics big data-based evaluation of personalized drug action. Next, we must suggest and test machine-learning methods in multi-omics personalized medicine. Additionally, there is an urgent demand for cross-platform harmonization of multi-omics big data.
We aim to collect articles covering the following topics:
• Methods for assessment of molecular pathway activation and drug action on individual patients, based on multi-omics big data.
• Methods and applications for machine learning in personalized medicine using multi-omics big data and other clinical data.
• Case reports on patients who were treated according to recommendations of omics-based personalized medicine, clinical monitoring of such cases; clinical trials for decision support systems in omics-based personalized medicine.
• Omics-based personalized medicine for non-cancer diseases.
• Review of public repositories/databases of multi-omics big data, their content, as well as methods and software for its fast browsing and processing; methods for harmonization of multi-omics data.
• Review of repositories/collections of reference normal/disease samples, organs and tissues used for multi-omics personalized medicine.
Dr. Borisov works with Oncobox Ltd.