Emerging Trends
Informed Insights

September 27, 2022

Living in the Golden Age of Deep Learning and Life Sciences


Joe Nipko, PhD

Dr. Joseph Nipko is Form Bio's VP of Artificial intelligence, where he focuses on applying state of the art deep learning techniques to various problems in biotech. Joe's 25 year career includes scientific leadership roles with EY, Home Depot’s BlackLocus and Cognira, among others. He holds PhD and Master's degrees in Physics from Colorado State University and a BS in Mathematics and Physics from SUNY Buffalo.

Innovation in life sciences is advancing at possibly the fastest pace among all branches of science.  The same can be said for deep learning – with the relentless advancement in computational power coupled with the continuous improvement in learning algorithms.  The confluence of these two disciplines has the potential to change the world in a dramatic way.   Today we are living in a golden age of these technologies, a renaissance where the synergy between deep learning and biology will provide the catalyst for historic advancements in life sciences.   The effects of this union have already had a substantial impact in biological research,  medical diagnosis, and precision medicine – and it's only the beginning of the realization of the potential.   

Figure. Deep Learning Adoption in the Life Sciences, Form Bio 2022.

Biological Research 

Deep learning has great potential to transform basic research in biology.   Particularly in cases where research teams produce enormous volumes of data – so much that it is difficult to analyze all of it.   One such domain is deep learning in drug discovery.  Over the past decade, there has been a remarkable increase in the amount of available compound activity and biomedical data owing to the emergence of new experimental techniques such as high throughput screening, parallel synthesis, among others   Deep learning algorithms are used to predict likely interactions between complex proteins and potential drug molecules (1,2).   The introduction of a representation of complex protein molecules into grids of 3D pixels, called voxels, has allowed data scientists to train deep learning models directly from the 3D structure of proteins and small molecules with atomic precision.  The latent representations learned from training the deep learning models from these features can be used to predict drug molecules are likely to interact with a given protein. 

Taken from Sarah Webb. Deep Learning for Biology. Nature 554, 555-557 (2018).

Another area of research that has been aided by recent developments in deep learning is in microscopy.    For example, Steve Finkbeiner’s team at the Gladstone Institute of Neurological Disease.   His team is leveraging robotic microscopy to study brain cells, and generating large image datasets that were a challenge to analyze with traditional machine learning techniques (3,4). 

His efforts in collaborating with Google in applying deep learning to this data paid off in astonishing good predictions of labeled robotic imaging data, coupled with the ability to analyze all of the data his team was generating.  

Another example is the research conducted by Alexandra Maslova et al in applying deep learning to immunology (5)..    In that study she trained a convolutional neural network model to determine cell type-specific open chromatin regions.   Their model was able to learn the sequence syntax that underlies the globality of immune cell differentiation.

Medical Diagnostics 

There are several drivers that are fueling the advancement of medical diagnostics through deep learning technology including:

  • Rising cost of health care
  • Shortage of healthcare workers
  • Growth of computing power and algorithms
  • Abundance of medical data to train models

Geoffrey Hinton,  whom many consider the Godfather of Deep Learning, famously predicted that radiologists would soon lose their jobs (6).  “People should stop training radiologists right now,” he announced, “It’s obvious that within five years deep learning is going to do better than humans.”   One of the reasons Dr Hinton said this is that diagnostic imaging is a natural fit for deep learning algorithms that excel at learning from labeled and unlabeled image data.   It has been six years since he made that claim and while deep learning has been widely used in disease detection,  the employment of radiologists has not been impacted in the way he suggested.  

One case of this accuracy improvement was recently published in The Lancet by a Korean team of researchers (7).     In their research on breast cancer detection they showed that a deep learning model alone had 88.8% sensitivity, whereas radiologists alone had 75.3% accuracy.   When radiologists were aided by the deep learning model, the accuracy increased by 9.5% to 84.8%.

Taken from M.K. Gilson, et al. BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res., 44 pp. D1045-D1053 (2016).

In just the last few years, models have been published that match or exceed the accuracy of expert humans at diagnosing many important diseases including: pneumonia , skin cancer , diabetic retinopathy , age-related macular degeneration, heart arrhythmia – just to name a few (8,9,10,11,12).  In diagnostic medicine, trained deep learning models clearly have had a profound effect in accuracy improvement.  However, even with all of the advancements provided by these models medical professionals will not be replaced anytime soon.  The models are meant to support and augment the diagnoses of the medical professional, providing them with additional data to support their decisions for care.  In the coming months and years, we are likely to see a dramatic increase in the standard of care doctors provide when aided by these models.

Precision Medicine 

The next step beyond diagnosing an illness is deciding how to treat it.    Precision medicine is an emerging approach to patient care that focuses on understanding and treating disease by integrating data from an individual to make patient-tailored decisions.  It  takes into account every patient’s unique genetics and biochemistry to select the best treatment for that individual, providing the greatest benefit with the fewest side effects.   In order to achieve this lofty goal, models must be trained on terabytes of genomic, image, and other forms of data –  deep learning excels at this kind of challenge.   

The evolution of precision medicine has been heavily influenced by the exponential increase in the amount of biologic data that can now be collected for each individual patient, in large part due to the advent of new technologies in the fields of medicine, genetics, metabolics, and imaging, among others.   Using data generated from previous patients treated for a disease, deep learning models can identify future patients who may benefit from a specific treatment.   Deep learning models can also be trained on data acquired through electronic medical records to identify patients with conditions that may benefit from participation in novel treatment studies (13).

A recent study by researchers at the University of Shanghaidemonstrated that response to cancer treatments could be predicted based on genomics (14).   If the methodology in research such as theirs is clinically applied it would help avoid unnecessary treatments for patients that are unresponsive to certain drugs in favor of the most effective treatment based on the patient’s genome.   Deep learning models can even take this one step further by helping design drugs that are tailored for the biological response of each individual.   These deep learning models have helped pave the way for pharmacogenomics – a new research field – which helps inform personalized drug design (15).

There are a multitude of areas where deep learning and biological research, medical diagnostics and precision medicine have joined forces to make significant advancements, in this insights piece, we have only highlighted a few areas that demonstrate the breadth of the problem domains addressable by deep learning.   We are at a remarkable moment in history when a set of new technologies is coming together to change the world.

Subscribe to our newsletter and get updates on emerging computational life science trends straight in your inbox.


  1. G. Papadatos, et al. Activity, assay and target data curation and quality in the ChEMBL database. J. Comput. Aided Mol. Des., 29, pp. 885-896 (2015).
  2. M.K. Gilson, et al. BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res., 44 pp. D1045-D1053 (2016).
  3. Sarah Webb. Deep Learning for Biology. Nature 554, 555-557 (2018).
  4. Yang, S.J., Berndl, M., Michael Ando, D. et al. Assessing microscope image focus quality with deep learning. BMC Bioinformatics 19, 77 (2018). 
  5. Maslova, Alexandra, Ricardo N. Ramirez, Ke Ma, Hugo Schmutz, Chendi Wang, Curtis Fox, Bernard Ng, Christophe Benoist, Sara Mostafavi, and Immunological Genome Project. Deep learning of immune cell differentiation. Proceedings of the National Academy of Sciences 117, no. 41: 25655-25666 (2020).
  6. Geoff Hinton: On Radiology
  7. Eun-Kyung Kim et al.  Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader studyThe Lancet Digital Health, Volume 2, Issue 3, E138 - E148 (March 01, 2020). 
  8. Hirani E et al. Deep Learning Approach to detect Pneumonia2020 4th International Conference On Electronics, Communication And Aerospace Technology (ICECA) (2020). 
  9. Dildar M, Akram S, Irfan M, Khan HU, Ramzan M, Mahmood AR, et al.. Skin Cancer Detection: A Review Using Deep Learning TechniquesInt J Environ Res Public Health  18:5479 (2021).
  10. Dai, L., Wu, L., Li, H. et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat Commun 12, 3242 (2021). 
  11. Yan, Q., Weeks, D.E., Xin, H. et al. Deep-learning-based prediction of late age-related macular degeneration progression. Nat Mach Intell 2, 141–150 (2020). 
  12. Ali Isin, Selen Ozdalili, Cardiac arrhythmia detection using deep learning, Procedia Computer Science, Volume 120, Pages 268-275 (2017).
  13. Rajkomar A., Dean J., and Kohane I. Machine learning in medicine. N. Eng. J. Med 380(14): 1347–1358 (2019)
  14. Dong Z., Zhang N., Li C., Wang H., Fang Y., Wang J., and Zheng X. Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection. BMC Cancer 15(1): 489 (2015).
  15. Kalinin A.A., Higgins G.A., Reamaroon N., Soroushmehr S., Allyn-Feuer A., Dinov I.D., et al.  Deep learning in pharmacogenomics: from gene regulation to patient stratificationPharmacogenomics 19(7): 629–650 (2018).

Form Bio Resources