Bioinformatics and medical informatics encompass many different fields of application and underline technologies that are equally diverse. However, many of these will have aspects in common, whether in terms of the data that they are using (e.g. data from genomics, proteomics, transcriptomics, metabolomics, imaging (medical, or from lab assays), biological or physiological sensors, etc.), or in terms of the approach to exploiting the data (e.g. machine learning, AI, mathematical simulations, statistical modelling, etc.).
AI and machine learning powered medicine
Healthcare is changing beyond recognition, in part driven by the fact most of us have powerful computers in our pockets, on our wrists, and in our homes. Digital health apps are being developed to leverage this capacity, to make patient monitoring, assessment, etc. cheaper, more efficient and less time consuming.
Modern AI is very good at picking out patterns in images, some of which even escape the human eye. One of the many areas where this has shown promise is in image analysis (PET, radio, MRI, ) for diagnostics and prognostics purposes, e.g. to identify and monitor the growth of tumours from scans, to identify signs of diseases (e.g. nodules caused by diseases such as pneumonia in chest x-rays), etc.
The availability of large amounts of omics data (typically along the central dogma, i.e. genomics, transcriptomics, proteomics and combinations thereof) has opened new possibilities for diagnostics and prognostics, enabling patient stratification (the identification of subgroups of patients, such as subgroups that are likely or unlikely to benefit from specific therapies or subgroups with different prognosis, etc.), increasing diagnostic accuracy, reducing the need for invasive tests for e.g. cancer and pre-natal tests, etc. This underlines much of the precision medicine revolution.
Computational approaches to drug discovery
Successfully getting a new drug to market is becoming increasingly expensive, and increasingly infrequent. Data driven approaches including AI, machine learning, modelling, in silico optimisation etc. are offering new hope in tackling this problem.
One promising area of application of bioinformatics approaches is in drug repurposing (identifying new therapeutic applications for existing drugs) and drug efficacy screening (predicting targets and efficacy for candidate drugs). AI, machine learning and network medicine approaches, for example using comorbidity maps, pharmacogenomics, combined drug targets and interactome networks analysis etc. have the potential to make the drug discovery process cheaper, safer and faster.
Another potentially promising area is in AI powered drugs and a biologics design. Technologies such as in silico evolution of proteins with a desired function, in silico identification of drug candidates with desired targets or properties, simulation of target protein molecular dynamics to understand drug-able features of the target, etc. can help us guide the traditional drug candidate screening process. These process can essentially act like the light strip in a dark airplane aisle, guiding us towards where we need to go so we no longer have to bump into every single obstacle on a random walk that may or may not lead to the destination.
Bioprocess automation and optimisation
The control, monitoring and optimisation of processes involving biological material (such as e.g. production of biologics from cells in culture) used to be highly experience and trial-and-error based. Computational tools using design of experiments approaches, multivariate analysis, automated monitoring and interpretation of process and biological parameters for in-line, etc. are making this process more reproducible and more efficient, ultimately leading to the reliable production of high quality biological products.
Laboratory automation is becoming an increasingly important part of life in labs whether in research, development, or quality control, in an effort to increase reproducibility and efficiency of bioprocesses. This involves software and hardware improvements that come out of multidisciplinary teams involving engineers, life scientists, computer scientists, physicists, etc.
Multi-omics in food, crop science, environmental science, personal care and hygiene
Our understanding of how food impacts our health has greatly benefited from the availability of omics data, from genomics to metabolomics and microbiomics. The relatively young sciences of foodomics and nutrigenomics have helped us understand the relationship between dietary patterns and genetic factors in obesity, how food bioactives can have an effect on cancer, and how genetic engineering of crops can help us tackle malnutrition.
In agriculture, omics data is being used to design crops that have traits of interest such as drought or pest resistance, increased yield or modified composition for the production of biofuels or biopolymers, etc.
In personal care and hygiene, microbiomics approaches are helping us understand the human and animal microbiota, their impact on health, and how they can be influenced to tackle acne, skin aging, etc.
In environmental sciences, omics data is being used to help us design solutions for water purification, recycling, and bioremediation (the use of microorganisms to clean a contaminated site).