Digitalization and automation are revolutionizing the landscape of biopharma R&D, particularly in the realm of monoclonal antibody (mAb) drugs. From artificial intelligence (AI)-driven antibody design to high-throughput screening systems and automated bioreactor technologies, innovative tools are accelerating discovery and development processes while ensuring quality and efficiency. Additionally, emerging technologies offer exciting prospects for enhancing transparency, traceability, and computational drug discovery. Companies like Wheeler Bio are working to integrate these technologies, leveraging technology partnerships and a novel contract development and manufacturing organization (CDMO) model to streamline operations, ensure consistent manufacturing, and reduce time-to-market for antibody therapeutics. As the industry embraces Pharma 4.0TM, the convergence of digitalization, automation, and strategic collaboration promises to shape the future of biopharmaceutical innovation and manufacturing.
Introduction
The fourth industrial revolution — Industry 4.0 — is underway today and is built around connectivity and integration of new technologies, including robotics and other automation solutions, artificial intelligence (AI) and machine learning (ML), Big Data analytics, cybersecurity, cloud computing, radio frequency identification (RFID), predictive analytics, and biometrics. While it has been slower to adopt these technologies than some other manufacturing industries, the pharmaceutical industry is moving toward Pharma 4.0, with growing numbers of companies moving away from paper-based, digitally siloed, and fully manual operations and toward fully autonomous operations, with many having at least implemented islands of automation and some level of connectivity and some implementing greater levels of connectivity and predictive analytics solutions.
Introduced by the International Society for Pharmaceutical Engineering (ISPE) in 2017, the Pharma 4.0 initiative guides drug manufacturers in the holistic integration of digital technologies. This approach is designed to align digital transformations with the pharmaceutical industry’s stringent regulations and best practices. Pharma 4.0 complements the FDA’s risk-based approach to 21st-century manufacturing and enhances transparency and adaptability. Appropriate implementation facilitates real-time monitoring and control, enabling quicker and more informed decision-making. This accelerates the development of superior drug candidates, improves quality, and minimizes risk.
For monoclonal antibody (mAb) therapies, the integration of digitalization and automation is revolutionizing research, development, and manufacturing processes. By harnessing the power of AI and ML, scientists can design antibodies more effectively, drawing insights from crystal structure data and other complex data sets. Complementing these advancements, high-throughput screening systems enhanced by advanced analytics have significantly sped up the identification of lead candidates. Moreover, automated bioreactors, process analytical technologies (PATs), digital twins, and scale-down models are deployed alongside predictive algorithms to expedite process optimization. This integration adheres to quality-by-design principles and utilizes design-of-experiment methodologies for more efficient outcomes. The concerted use of these digital tools enhances the upstream and downstream facets of manufacturing, ensuring improved performance and innovation in antibody production.
The Digital Shift in Biopharma R&D
While digital transformation was occurring before the COVID-19 pandemic, the pandemic underscored the value of digital transformation, as digital technologies became essential for maintaining biopharma development and manufacturing in the face of limited in-person interactions.1 This era spotlighted the role of digital tools in enhancing R&D from initial discovery to clinical trials. With real-time data-sharing capabilities, these technologies have streamlined R&D processes globally. A suite of digital innovations, including AI, ML, data analytics, in silico and scale-down modeling, PATs, and decentralized clinical trials (DCTs), have made significant strides in advancing R&D efficiency and efficacy.
Companies that excel in digitalization treat its implementation as a journey rather than a goal.2 Adopting an appropriate digitalization strategy that addresses not only tool selection and integration, but training, education, and employee concerns is essential. Leadership plays a crucial role in championing these digital initiatives, ensuring seamless incorporation into current workflows to bolster R&D efficiency and cost-effectiveness.
One key aspect of such strategies is the full-scale adoption of automated discovery and development laboratories using miniaturized and high-throughput equipment and advanced digital technologies, including orchestration software, which allow communication between different instruments across an organization’s laboratories. According to McKinsey, such an approach could slash development timelines by over 500 days and reduce costs by 25% while also improving data reproducibility and the predictability of biological activity.3
Overcoming Antibody Development Challenges with Digital Solutions
Incorporating automation and digitalization in research and development activities provides a significant advantage across all biopharma industry segments. This is particularly true for sectors with extensive history, such as those dealing with recombinant proteins and mAbs. A critical challenge in mAb development is ensuring that they are designed with manufacturability and scalability in mind. Tackling this challenge requires a development process that considers commercial-scale production from the outset. This strategy involves the early and swift production of accurate and relevant data to assess the feasibility of candidate antibodies. Such a focused approach ensures that only the most promising candidates — those with a practical and economical pathway to production at the required scale — advance to the costlier late-stage development.
Digital technologies and automation solutions are helping to overcome the bottlenecks associated with current mAb product and process development, streamlining efforts without compromising quality by eliminating time-consuming and expensive activities from the critical development path.
Cell line engineering and development are pivotal to enhancing the manufacturability of mAbs and related therapeutic agents.4 Today, various digital technologies are being utilized to expedite these historically time-intensive processes. For instance, cutting-edge single-cell sorting and imaging technologies have significantly streamlined the process of clone selection. Additionally, the integration of high-throughput systems with advanced data analytics has hastened the exploration of codon optimization, which, along with novel transcription, secretion, and selection techniques, is critical for improving expression systems.
Comprehensive omics data offers the remarkable potential to swiftly predict cellular responses to an extensive array of drug compounds and their combinations. Complementing this, in silico analyses that exploit detailed crystal structure data are advancing our ability to predict the structural dynamics and binding interactions of peptide sequences within mAbs. Such predictive capabilities are proving to be a boon for the rapid conceptualization and refinement of mAb therapies.4
On the process optimization front, an array of modeling and simulation tools — spanning mechanistic, data-driven, and hybrid approaches — are proving to be highly effective, reducing the time required to bring antibodies to market and decreasing the cost of goods sold (COGs).6 Additionally, digital twins replicate existing production processes to rapidly simulate the manufacturability of new antibody candidates, pinpointing manufacturable options and highlighting areas that require optimization.
Accelerating Development with AI and ML
One of the foundational aspects of R&D digitalization in biopharma companies leading the transformation to Pharma 4.0 is the integration of AI, ML, and natural language processing (NLP) capabilities in R&D workflows. This begins with transforming vast arrays of legacy data — encompassing previous research, clinical trials, and real-world patient experiences — into actionable insights. Mining this data facilitates the discovery of new druggable targets and potential compounds, including antibodies that promise efficacy with fewer side effects, all while being amenable to cost-effective production.
The harvested data are then mined to uncover novel drug targets and promising molecular candidates, including antibodies poised to become effective treatments with minimal adverse effects. Such discoveries are particularly valuable when they lead to therapies that are not only potent but also suitable for efficient, cost-effective manufacturing.7 Leveraging AI, ML, and NLP significantly streamlines the discovery phase, trimming the extensive period of time typically needed to design and test new molecules from several months to mere weeks, and with continued advancements, possibly even days.8
Automated laboratory processes and the increased deployment of high-throughput screening are generating vast data sets. These data sets further refine AI and ML algorithms, enhancing the precision of predictive models. Consequently, this leads to a higher success rate and faster drug development cycles owing to improved data analytics and management solutions.9 Moreover, the synergistic use of AI, ML, and NLP with comprehensive digital management platforms facilitates sophisticated real-time data analysis. This integration is vital for informed decision-making throughout the drug development process, particularly in early phases where the cost of missteps can be profound, affecting the entire project life cycle.
Researchers at the University of California San Diego School of Medicine have pioneered an AI strategy for pinpointing high-affinity antibodies.10 This approach, utilizing repeated evolution of surface proteins (RESP) technology, successfully identified an antibody with significantly stronger binding to a cancer target compared with existing drugs. Companies, such as Natural Antibody, AbSci, Adimab, AbCellera, BigHat Biosciences, and Insilico Medicine, are leveraging AI and ML to enhance their antibody discovery and development efforts, demonstrating the potential to substantially quicken the pace of antibody research and development.11
The use of AI and ML in drug development spans enterprises of all sizes, from industry giants like Bayer, Bristol-Meyers Squibb (BMS), GlaxoSmithKline (GSK), and Eli Lilly to smaller firms.11 These examples represent only a fraction of the transformative potential offered by these technologies. Maximizing the benefits of AI, ML, and NLP hinges on improved data acquisition and storage, as well as broader digital integration within the biopharma industry.9 Cloud-based platforms are already making strides in this direction, laying the groundwork for enhanced data sharing and collaborative innovation.
Enhancing Quality and Compliance through Digitization
The successful development and manufacturing of biopharmaceutical products hinge on adhering to strict industry regulations. Digital solutions are crucial to maintaining compliance with these regulations through quality control (QC), quality assurance (QA), and regulatory compliance. These systems streamline efficiency and enhance the ability to meet regulatory demands. Quality management systems (QMS) utilize data analytics and continuous monitoring to preemptively address quality issues, while regulatory information management systems (RIMS) digitalize the full spectrum of regulatory processes, ensuring comprehensive management of regulatory submissions, including Investigational New Drug (IND) and Biologics License Application (BLA) filings.12
Success Stories of Digital Integration
The Canadian software firm Cyclica utilizes a screening process to analyze the structural and biochemical properties of millions of proteins. They aim to identify those most likely to bind to specific drug targets, considering factors such as selectivity, potential for degradation, side effects, and pharmacokinetics. Cyclica has collaborated with Merck and Bayer to repurpose FDA-approved drugs for new therapeutic uses. Additionally, the firm is employing a similar approach to identify antibodies with potential therapeutic applications.13
BenevolentAI used its AI program to repurpose baricitinib, originally an Eli Lilly rheumatoid arthritis drug, for COVID-19 treatment, leading to its approval in the United States and Japan and showcasing how drug repurposing can significantly accelerate development timelines.11,14
BMS utilized an ML program to improve the accuracy of predicting CYP450 inhibition, resulting in a sixfold reduction in candidate failure rate by eliminating compounds with toxic effects.13
Exscientia is leveraging AI to predict binding for antibodies and proteins, even with limited structural data, by comparing available data against a vast database of protein interactions.13 This method can potentially decrease the timeline for discovering drug candidates, as evidenced by their collaborations with GSK to identify a promising candidate against chronic obstructive pulmonary disease and with Evotec to find an A2a receptor antagonist for treating advanced solid tumors.13,15
Wheeler Bio’s Digital Integration Vision
Wheeler Bio is applying the Pharma 4.0 model at its phase I/II facility and a greenfield site for phase III/commercial production. Partnerships with leading vendors of next-generation data, automation, and bioprocess modeling platforms and their integration across research, pilot plant, and large-scale operations present unique opportunities to streamline biologics discovery, development, and manufacturing to reduce cost, timelines, and risk for innovators.
Wheeler Bio is outfitting its process and analytical development labs with the latest automated and high-throughput screening systems, all enhanced by sophisticated predictive modeling and data analysis tools. On the manufacturing floor, data historians are utilized for comprehensive data management of bioprocess equipment, alongside PAT for real-time monitoring and control. This technical ecosystem is designed to elevate efficiency and precision throughout development and manufacturing.
Easy movement between the development areas and production suites enables close collaboration rather than isolated operations, increasing speed and reducing the cost of goods. Having the entire team on the floor together also facilitates cross-functional learning.
Wheeler Bio is incorporating a suite of cutting-edge technologies to refine early-stage antibody development. These include ATUM Leap-In-Transposase® technology for efficient generation of stable expression cell lines; the Solentim Ecosystem for rapid cell line development; Benchling Bioprocess, a cloud-based solution that accelerates process development with centralized planning, execution, data analysis and predictive modeling capabilities; DataHow’s AI-based solution for data collection, analysis, and bioprocess modeling, which accelerates process development and optimization; Ambr®15/Ambr®250 Bioreactors (Sartorius) to increase cell productivity, improve consistency, and maximize throughput during process development; Predictum’s self-validating ensemble modeling software for accelerating formulation development; Tecan’s lab automation and liquid-handling solutions to improve the efficiency, throughput, and precision of sample handling; FactoryTalk with OSI PI historian in manufacturing for data collection, trending, and batch reporting ;and the RightSourceSM platform from Charles River Laboratories for QC testing.
Using this combination of digitalization and automation technologies in conjunction with our novel business approach involving integration with contract research organizations (CROs) upstream of Wheeler, it is possible to reduce the time to IND for customers by at least three to six months and potentially up to nine months.
Emerging Digital Technologies
Beyond AI, ML, and NLP, the digitalization landscape in biopharma R&D is being reshaped by emerging technologies like blockchain and quantum computing.16,17 These innovations promise to revolutionize drug development processes for mAbs and various drug classes, presenting groundbreaking prospects for the future of biopharma research and development.
With its ability to enable secure and rapid transactions worldwide and allow independent verification of the quality and point of origin of drug substances and drug products, blockchain technology is ideal for improving transparency, traceability, and security within the supply chain. Additionally, blockchain can ensure compliance with serialization standards, protect intellectual property, maintain patient privacy, and prevent data tampering within R&D. Crucially, it offers a secure method for managing the intricate data involved in producing personalized therapies for the future.
Quantum computing is set to revolutionize drug discovery due to its proficiency in handling complex calculations quickly. This technology could notably advance the development of new drugs, including antibodies, by simulating intricate molecular structures and interactions. The potential applications in biopharmaceuticals are vast, ranging from facilitating the initial stages of drug discovery to refining clinical trials and exploring entirely new drug synthesis pathways.
Conclusion
Digitalization within the biopharma industry remains in the early stages. It has most widely been applied to the discovery of new disease pathways, drug targets, and drug candidates but is increasingly providing benefits across all other activities, from process, formulation, and analytical method development to commercial-scale manufacturing, QC, and regulatory compliance. For mAbs, digitalization and automation are already demonstrating their power to transform discovery and development by de-risking and accelerating discovery and development activities.
However, the biopharma industry is not static, nor is technology, particularly concerning digitalization. Further advances in digital technologies will drive further advances in our understanding of biology and disease pathologies, allow identification of new drug targets and ways to target those currently thought to be undruggable, increase the efficiency of drug development, and maximize the productivity of drug manufacturing.
Today, novel modalities requiring complex manufacturing processes occupy growing space within biopharma pipelines, while pressure from governments, payers, and patients to reduce costs and increase access is rising. Digitalization and automation of all aspects of drug discovery, development, and manufacturing will be essential to remain competitive. Those companies willing to commit wholly to realizing the highest levels of Pharma 4.0 by implementing the most advanced digital and automation solutions will be differentiated in the marketplace and positioned to achieve the highest levels of success.
References
Sexton, Jennifer. “Digital transformation in pharma: Improving R&D through digital solutions.” CAS Insights. 5 Sep. 2023.
“5 Digital Strategies to Save Big on Pharmaceutical R&D Costs.” Xcelpros. 15 Jan. 2021.
Cardoso, Rita, Kristian Kinscher, Tobias Ruof, Ahsan Saeed, Ulf Schrader, and Julius Seitter. “From bench to bedside: Transforming R&D labs through automation.” McKinsey. 8 Mar. 2023.
Sifniotis, Vicki, Esteban Cruz, Barbaros Eroglu, and Veysel Kayser. “Current Advancements in Addressing Key Challenges of Therapeutic Antibody Design, Manufacture, and Formulation.” Antibodies (Basel). 8: 36 (2019).
Alvaro, David. “The Powerful Potential of Digital Twin Technology to Improve Drug Discovery, Development, Manufacturing, and More.” Pharma’s Almanac. 7 Mar. 2023.
McDonnell, Susan, Raymon Floyd Principe, Maycou Soares Zamprognio and Jessica Whelan. “Challenges and Emerging Technologies in Biomanufacturing of Monoclonal Antibodies (mAbs),” in Biotechnology – Biosensors, Biomaterials and Tissue Engineering Annual Volume 2023. Ed. Luis Jesús Villarreal-Gómez. 2023.
Kim, Jisun, Matthew McFee, Qiao Fang, Osama Abdin, and Philip M. Kim. “Computational and artificial intelligence-based methods for antibody development.” Trends in Pharmacological Sciences. 4: 175-189 (2023).
Hawkins, Leila. “Why digital transformation is essential to get value from R&D data.” Pharma IQ. 9 Nov. 2022.
Marinos, George and Mark Humphries. “Optimizing Digitalization To Accelerate Your R&D.” Drug Discovery Online. 19 May 2023.
Coulson, Annie. “No RESP for the wicked: new AI model accelerates antibody discovery.” BioTechniques. 13 Mar. 2023.
“How AI reduces the cost and time of drug discovery and development.” Natural Antibody. Accessed 19 Mar. 2024.
Olmstead, Levi. “Digital Transformation in Pharma (+Examples, Challenges).” Whatfix. 10 Oct. 2023.
Freedman, David H. “Hunting for New Drugs with AI.” Nature. 18 Dec. 2019.
Liu, Angus. “Eli Lilly, spurred by AI analysis, starts pivotal study of arthritis med Olumiant in COVID-19.” Fierce Pharma. 15 Jun. 2020.
Evotec and Exscientia announce start of human clinical trials of novel immuno-oncology drug. Evotec. 9 Apr. 2021.
Challener, Cynthia A. “Why the Industry is Moving toward Blockchain Technology.” Pharma’s Almanac. 6 Dec. 2019.
Challener, Cynthia A. “Quantum Computing will Transform Drug Discovery, Development, Manufacturing, and Supply Chain Management.” Pharma’s Almanac. 24 Jun. 2022.
