Article | April 3, 2020
The integration of artificial intelligence within life sciences is making drug discovery and development more innovative, less labor intensive and more cost-effective, says Deloitte’s annual global outlook. According to Deloitte’s 2020 Global Life Sciences Outlook, the biotech sector is at an inflection point. To prepare for the future and remain relevant in the ever-evolving business landscape, biopharma and medtech organizations will be looking for new ways to create value and new metrics to make sense of today’s wealth of data, the report overview says. As data-driven technologies provide biopharma and medtech organizations with treasure troves of information, and automation takes over some mundane tasks, new talent models are emerging based on purpose and meaning. The integration of artificial intelligence (AI) and machine learning approaches within life sciences is making drug discovery and development more innovative, time-effective and cost-effective, the Deloitte report states.
Article | August 2, 2021
In the downstream portion of any bioprocess, one must pick through the dross before one can seize the gold the biotherapeutic that the bioprocess was always meant to generate. Unfortunately, the dross is both voluminous and various. And the biotherapeutic gold, unlike real gold, is corruptible. That is, it can suffer structural damage and activity loss. When discarding the dross and collecting the gold, bioprocessors must be efficient and gentle. They must, to the extent possible, eliminate contaminants and organic debris while ensuring that biotherapeutics avoid aggregation-inducing stresses and retain their integrity during purification and recovery. Anything less compromises purity and reduces yield.
To purify and recover biotherapeutics efficiently and gently, bioprocessors must avail themselves of the most appropriate tools and techniques. Here, we talk with several experts about which tools and techniques can help bioprocessors overcome persistent challenges. Some of these experts also touch on new approaches that can help bioprocessors address emerging challenges.
Article | April 20, 2021
With advances in data analytics and machine learning, the move from descriptive and diagnostic analytics to predictive and prescriptive analytics and controls—allowing us to better forecast and understand what will happen and thus optimize process outcomes—is not only feasible but inevitable, according to Bonnie Shum, principal engineer, pharma technical innovation, technology & manufacturing sciences and technology at Genentech.
“Well-trained artificial intelligence systems can help drive better decision making and how data is analyzed from drug discovery to process development and to manufacturing processes,” she says.
Those advances, though, only really matter when they improve the lives of patients. That’s exactly what Shum expects.
“The convergence of digital transformation and operational/processing changes will be critical for the facilities of the future and meeting the needs of our patients,” she continues. “Digital solutions may one day provide fully automated bioprocessing, eliminating manual intervention and enabling us to anticipate potential process deviations to prevent process failures, leading to real-time release and thus faster access for patients.”
To turn Bioprocessing 4.0 into a production line for precision healthcare, real-time release and quickly manufacturing personalized medicines will be critical. Adding digitization and advanced analytics wherever possible will drive those improvements. In fact, many of these improvements, especially moving from descriptive to predictive bioprocessing, depend on more digitization.
Article | February 12, 2020
In our lab, we focus on the impact of the gut microbiome on human health and disease. To evaluate this relationship, it’s important to understand the particular functions that different bacteria have. As bacteria are able to exchange, duplicate, and rearrange their genes in ways that directly affect their phenotypes, complete bacterial genomes assembled directly from human samples are essential to understand the strain variation and potential functions of the bacteria we host. Advances in the microbiome space have allowed for the de novo assembly of microbial genomes directly from metagenomes via short-read sequencing, assembly of reads into contigs, and binning of contigs into putative genome drafts. This is advantageous because it allows us to discover microbes without culturing them, directly from human samples and without reference databases. In the past year, there have been a number of tour de force efforts to broadly characterize the human gut microbiota through the creation of such metagenome-assembled genomes (MAGs)[1–4]. These works have produced hundreds of thousands of microbial genomes that vastly increase our understanding of the human gut. However, challenges in the assembly of short reads has limited our ability to correctly assemble repeated genomic elements and place them into genomic context. Thus, existing MAGs are often fragmented and do not include mobile genetic elements, 16S rRNA sequences, and other elements that are repeated or have high identity within and across bacterial genomes.