Top five trends in pharmaceutical and biotech research of 2021

scientific informatics

A blog article by Ashlie Reker Ph.D.

Thanks to the rapidly advancing technology of the recent decades (our previous blog highlighting some groundbreaking techniques), the biotechnology and biopharmaceutical fields have innovated at a rapid pace. Here we look at the top 5 trends pushing the boundaries of discovery.

Big Data

Big data is big business in research and development. Large data sets reveal patterns that can be used to assess risk, efficacy, develop personalized medicine, engage patients, and reduce time and cost to market. The “-omics” – genomics, metabolomics, proteomics, transcriptomics- in combination with clinical, and remote data from the “Internet of Medical Things” provide enormous amounts of data that will be generated at an ever more astounding rate with enhanced technologies such as Next Gen Sequencing. These data come in various forms, can be quite noisy and are often incomplete. Parsing out and co-analyzing such seemingly disparate data sets to attain an evidence-based and actionable conclusion is the formidable task handled by the multidisciplinary field of bioinformatics and the burgeoning technology of artificial intelligence.

Artificial Intelligence and NextGen Computing Technology

Artificial intelligence (AI) has revolutionized the data processing capabilities of the biotech, pharma and basic research sectors. Recent breakthroughs in techniques and methodologies have produced phenotypically relevant in vivo models, high-throughput processes, and data intensive results. The Science Snippets Blog from Sartorius outlines 3 principle types of AI employed in the pharma industry: data science algorithms, machine learning, and deep learning

Data scientists use human-created algorithms to perform multivariate analysis – analyzing multiple data points and determining the relationships between them to predict an outcome. Such AI used to analyze several data types that may influence an individual’s response to a treatment and predict best clinical practice.

Machine learning uses “neural network” algorithms to provide predictive outcomes with accuracy and speed based on previously learned information. Machine learning requires some assistance to correctly predict outcomes.

Deep learning, a type of machine learning, structures algorithms in layers to create a logic structure termed “artificial neural networks.” This allows error recognition, correction, and model improvement from diverse but inter-connected data sets without (or with very little) intervention. Deep learning could potentially take thousands of images used for diagnostics, and continually improve accuracy, increasing the percentage of correct diagnosis with little human intervention.

On the advent of quantum computing, AI will revolutionize the impact of big data, and potentially conduct virtual clinical trials.

Cross Company Collaboration

“All the world’s a stage, and all the men and women merely players…”. The COVID-19 pandemic saw the world stage transformed into a chaos of severe illness, death, and incredible emotional turmoil. The men and women who came together, racing for a vaccine, set an unprecedented standard for the pharmaceutical industry: cross company collaboration.

Admittedly the industry has seen increased use of a “virtually integrated pharmaceutical company” design where research is distributed across partners, but never before has such a star-studded cast – Pfizer, BioNTech, Sanofi & GSK, AstraZeneca, Oxford University, Janssen and the U.S. department of Health and Human Services – come together to develop a groundbreaking vaccine in record time (see Kini, A., 2021 for more information).

This process required tremendous data flow, storage, and intra- and inter-facility access and sharing that could only be achieved with a cloud-based digitalized approach to support such a large-scale effort.

Around the Pill

“Around the Pill” or “Beyond the Pill” refers to a movement by pharmaceutical industries to provide holistic patient-centric care. One aspect of this trend is integrating technology to achieve “connected health”, through the use of patient portals, tele- services, wearable technologies, often providing feedback data to the Internet of Medical Things, smart devices, and apps. In effect, medicine now includes a platform, where data is collected, stored, accessed, and analyzed to make evidence-based decisions for better individual health. If you would like to learn more about this topic, please refer to the references.

Cloud-Based Digital Transformation with Climb 2.0

As scientists, the most significant advantage of cloud-based transformation lies in master data management. Climb 2.0 is a comprehensive in vivo cloud-based research software that aggregates experimental data, as well as metadata capture around animal models, materials and methods, and samples. Data silos are reduced, leading to improved data management and accessibility. Climb enables you to get the most out of big data in today’s fast-paced, high through-put, evolving pharmaceutical and biotech landscape. Climb makes data securely accessible by anyone who has appropriate authorization, from anywhere, and allows them to move seamlessly throughout the drug development process, getting to cures to market faster and at lower costs.


Artificial Intelligence and NextGen Computing Technology

 Emily Uwemedimo. (2021). Three biotech trends shaping pharma’s digital economy. Pharma iQ. (Read the article here)

Science Snippets Blog. (2020). The Trending Role of Artificial Intelligence in the Pharmaceutical Industry. Satorius. (Read the article here)

Shaffer, C. (2021). Artificial Intelligence Is Helping Biotech Get Real. Genetic Engineering & Biotechnology News. (Read the article here)

Cross Company Collaboration

Kini, A. (2021) Collaboration Is the Future of Science= Technology Will Make That Happen. Technology Networks Biopharma. (Read the article here)

Around the Pill

Robinson, R. (2018). Moving Beyond the “Beyond the Pill” Conversation. PharmaVOICE. (Read the article here)

Kvedar, J., Coye, M.J., Everett, W. (2014). Technologies and Strategies to Improve Patient Care with Telemedicine and Telehealth. Health Affairs. (Read the article here)

PAttichic, C.S. & Panayides, A.S. (2019). Connected Health. Frontiers in Digital Health. (Read the article here)