Pharmaceutical Technology Is Now PharmTech: A Sharper Name for a Smarter Industry

Navigating FDA Shakeups and Obesity Drug Wars

Behind the Headlines Episode 28

Ask the Expert

Closing the Gap in Modern Process Control and Automation for QC/QA

Drug Digest December 2025

How It Helps Avoid Facility and Equipment Problems

A “Plan, Prevent, Prove” Approach

Feliza Mirasol is the science editor for 

On Oct. 30, 2024, Lonza's Synaffix announced that it has licensed its antibody-drug conjugate (ADC) technology to BigHat Biosciences (BigHat), a US-based biotech company. BigHat will combine the Synaffix technology with its machine learning (ML) antibody design platform to develop a new ADC pipeline program.

Under the agreement, BigHat will receive target-specific access to Synaffix’s late clinical-stage, site-specific ADC technology platform. This platform enables transformation of antibodies into proprietary, best-in-class ADC products. Lonza’s acquisition of Synaffix in June 2023 (1) means that BigHat also gains access to Lonza’s DNA-to-investigational new drug (IND) ADC offering. This DNA-to-IND offering enables drug developers to receive all necessary current good manufacturing practice (CGMP)/non-CGMP ADC batches leading up to the first clinical trial. The service is housed under a single quality system that encompasses all critical development and manufacturing activities, including antibody production, bioconjugation, and drug product filling.

“The ADC space continues to develop and evolve, and our collaboration with BigHat exemplifies the continued strength and appeal of our best-in-class ADC technology. We are excited to be at the forefront of next-generation ADC R&D by joining forces with BigHat and its AI [artificial intelligence]/ML-enabled antibody discovery and development platform. BigHat is the ideal partner for Synaffix to collaborate with. We look forward to supporting BigHat with every step in the ADC development and manufacturing process under the Lonza umbrella,” said Peter van de Sande, head of Synaffix, in a company press release.

Milliner, which is BigHat’s AI/ML-powered antibody design platform, works by integrating a synthetic biology-based high-speed wet lab with state-of-the-art ML technologies into a full-stack antibody discovery and engineering platform. This platform is used to engineer antibodies with more complex functions and better biophysical properties. Using this approach reduces the difficulty of designing antibodies and other therapeutic proteins when developers look to tackle conditions ranging from chronic illness to life-threatening disease. The platform also offers significant speed to reaching candidate discovery and validation.

“We are pleased to announce this collaboration with BigHat for its next-gen ADC molecule, which shows how drug developers can benefit from a fully integrated suite of services across our Biologics division. The Lonza network has continued to adapt to the evolving ADC landscape, including the recent addition of a highly potent vial fill capability at our Stein (CH) [Switzerland] facility. This dedicated ADC drug product capacity expansion completes our offer for comprehensive, end-to-end development and manufacturing services for ADCs, simplifying the path from DNA-to-IND and beyond for our customers,” Jean-Christophe Hyvert, president, Biologics, Lonza, said in the release.

Through this collaboration with Synaffix/Lonza, BigHat intends to advance its next-gen ADC program. BigHat’s ADC program is at the IND-enabling stage and is on track to be the company’s first clinical-stage program. According to the press release, BigHat’s next-gen ADC was optimized using the Milliner platform. It is designed for maximum payload delivery to tumor cells and with optimal drug-like-properties. Incorporating Synaffix's ADC technologies, such as GlycoConnect, HydraSpace, and toxSYN, BigHat expects to further improve the safety and efficacy of its next-gen ADC.

"BigHat is leveraging our AI-driven antibody design platform, Milliner, to develop advanced biologics that provide safer and more effective treatments for difficult-to-treat cancers. We are excited to combine Synaffix’s conjugation and linker-payload technologies with our custom-designed antibody to create a next-generation ADC for patients with high unmet medical need," said Mark DePristo, CEO, BigHat Biosciences, in the release.

1. Lonza. Lonza to Acquire Synaffix and Strengthen Antibody-Drug Conjugates Offering. Press Release. June 1, 2023.

Articles

Synaffix, a Lonza company, has licensed its ADC technology to BigHat Biosciences to be combined with the latter's ML design platform to develop new ADCs

Synaffix, a Lonza Company, Collaborates with BigHat Biosciences on ADCs Designed Using Machine Learning

Chris Burgess, PhD, is an analytical scientist at Burgess Analytical Consultancy Limited, ‘Rose Rae,’ The Lendings, Startforth, Barnard Castle, Co Durham, DL12 9AB, UK; Tel: +44 1833 637 446; chris@burgessconsultancy.com; www.burgessconsultancy.co

Financial data document graph chart report statistic marketing research development planning management strategy analysis accounting. Financial business technology hologram concept. 3d rendering. | Image Credit: © Chaosamran_Studio - stock.adobe.com

Nomenclature is important. Data governance, data integrity, and data quality are all widely used terms, but what do they actually mean and how are they connected? The purpose of this article is to provide a structured model for these terms with their definitions and their relationships in the context of analysis and testing within a pharmaceutical quality system.

The crucial concept is that data quality, including data integrity, is only attainable via data governance, as will be illustrated in the proposed model.

In a regulatory context, the establishment of measured values and subsequent reportable results of a predefined quality is an essential activity. Reportable results are then compared with predetermined acceptance criteria and/or standards and specifications. The processes, mechanisms, and control systems necessary to establish measurement values and reportable results of a defined quality are interlinked. These interlinkages may include metrological, procedural, or organizational elements.

The overall proposed model is built up using building blocks akin to the construction of Lego brick models. This approach has been used in previous papers concerning error budgets in measurement uncertainty and Monte Carlo Simulation, and data quality within a lifecycle approach (1–2).

An analytical testing flow diagram, shown in 

, gives a high-level idea of the traceability and subsequent interactions from the marketing authorization (new drug application, NDA, or abbreviated new drug application, ANDA) to the reportable result and data quality.

 A high-level process flow indicating some of the elements of data governance, data quality, and data integrity, as well as the quality management system (QMS).

This process flow has been translated into the Lego brick model shown in 

. This model is based upon a data quality within a lifecycle approach model which has been modified and extended, as will be described in some detail (2).

 Data governance model modified and extended from the data quality within a lifecycle approach model (taken from reference 2, Figure 15).

The crucial concept is that data quality is only attainable via data governance.

The data governance and data quality Lego brick model

Data quality is not an accident but a product of design. It is a combination of data integrity and the functionality and control under the Pharmaceutical Quality System, usually termed the quality management system (QMS). These aspects are underpinned by data governance and qualified information technology (IT) infrastructure services. This is essentially a sandwich structure in which the “filling” is provided by metrological integrity, analytical procedure integrity, and quality oversight. These “fillings” are described below.

 are subject to risk assessments and risk management (3), which will not be discussed here.

The qualified IT infrastructure services with cybersecurity and access control, as seen above, also will not be covered further in this article.

It is, however, necessary to discuss the key elements of data integrity and the Pharmaceutical Quality System which, when combined, generate data quality on the foundation of data governance.

Data governance is the totality of arrangements to ensure that data, irrespective of the format in which they are generated, are recorded, processed, retained, and used to ensure a complete, consistent, and accurate record throughout the data lifecycle (4).

The purpose of an analytical procedure is to provide a reportable result of the analytical characteristic or quality attribute being determined. Analysis and testing require a measurement system, and a procedure for its application to a sample.

Data integrity is underpinned by the first brick, the metrological integrity of the instrument or system’s operational performance, with demonstrable assurance that it is “fit for intended use” within a specific analytical procedure, which is “fit for intended purpose” over the data lifecycle.

Analysis and testing usually involve the use of an apparatus, analytical instrument, or system to make a measurement. Therefore, establishment of “fitness for intended use” for any apparatus, analytical instruments, or systems used in analysis and testing is necessary to ensure metrological integrity over the operational ranges required.

Therefore, it is essential to establish “fitness for intended use” before the analytical procedure is performed. The main resource for instrument and system requirements are the specific monographs and general chapters in the pharmacopeias. In particular, United States Pharmacopeia (USP) has a unique general chapter on the lifecycle processes and requirements for ensuring that any apparatus, analytical instrument, or system is “fit for intended use,” as seen in 

 Data quality outline for an analysis and testing quality control (QC) model using USP references.

analytical instrument and system qualification

calibration over the operational ranges of critical measurement functions

trend analysis to monitor an ongoing state of control.

The second component of data integrity is a validated or verified analytical procedure performed by a trained analyst.

It has been a requirement for more than 20 years that analytical methods and procedures need to be validated or verified (6–7). Recently, these requirements have been updated by the International Council for Harmonisation (ICH) and a new guideline on analytical procedure development issued (8–9). 

 General Chapter <1220> on Analytical Procedure Lifecycle should be consulted (10).

analytical target profile and development

trained analysts and second person review

Particular attention should be taken regarding analyst training and second person review within the laboratory.

Second person review is essential in ensuring data quality.

Quality control is the guardian of scientific soundness, whereas the quality assurance function is the guardian of compliance. To perform this duty of care, the quality assurance function requires a robust and comprehensive quality management system that enshrines the elements to provide and perform the necessary quality oversight over the data lifecycle.

Quality oversight involves both reviewing and auditing activities of QC but also includes the Pharmaceutical Quality System implementation itself to ensure that it is up to date (11).

Quality oversight covers key areas such as:

Much has been written on this topic, particularly regarding the three ALCOA models and the meanings of their acronyms (4). These acronyms are summarized below and illustrated in 

 Pictorial representation of the three ALCOA models.

It must be possible to identify the individual or computerized system that performed a recorded task, and when the task was performed. This also applies to any changes made to records, such as corrections, deletions, and changes, where it is important to know who made a change, when, and why.

All data, including any associated metadata, should be unambiguously readable throughout the lifecycle. Legibility also extends to any changes or modification to the original data made by an authorized individual so that the original entry is not obscured.

Data should be recorded on paper or electronically at the time the observation is made. All data entries must be dated and signed by the person entering the data.

The original record is the first capture of information, whether recorded on paper (static) or electronically (usually dynamic, depending on the complexity of the system). Data or information originally captured in a dynamic state remain in that state.

Records need to be a truthful representation of facts to be accurate. No errors in the original observation(s) and no editing are allowed without documented amendments or audit trail entries by authorized personnel. Accuracy is assured and verified by a documented review including review of audit trails.

All data from an analysis, including any data generated including original data, data before and after repeat testing, reanalysis, modification, recalculation, reintegration, and deletion. For hybrid systems, the paper output must be linked to the underlying electronic records used to produce it. A complete record of data generated electronically includes relevant metadata.

Data and information records should be created, processed, and stored in a logical manner that has a defined consistency. This includes policies or procedures that help control or standardize data (such as chronological sequencing, date formats, units of measurement, approaches to rounding, significant digits, etc.).

Data are recorded in a permanent, maintainable, authorized media form during the retention period. Records should be kept in a manner such that they continue to exist and are accessible for the entire period during which they are needed. They need to remain intact as an indelible and durable record throughout the record retention period.

Records should be available for review at any time during the required retention period, accessible in a readable format to all applicable personnel who are responsible for their review, whether for routine release decisions, investigations, trending, annual reports, audits, or inspections.

Data should be traceable though the lifecycle. Any changes to data or metadata should be explained and should be traceable without obscuring the original information. Timestamps should be traceable to a trusted time source. Metrological standards and instrument or system qualification should be traceable to international standards wherever possible.

Data quality is a combination of data integrity and overall control as part of the pharmaceutical quality system.

An example of a quality control data quality outline for analysis and testing, using examples from USP, is illustrated in 

Data quality cannot be assured without a data governance structure supported by a qualified IT infrastructure services with cybersecurity and access control.

The proposed Lego brick model provides a structural framework for assuring data quality over the lifecycle.

A short glossary of definitions of key terms is appended.

I wish to thank Bob McDowall and Oscar Quatrocchi for their review and helpful comments.

The totality of arrangements to ensure that data, irrespective of the format in which they are generated, are recorded, processed, retained, and used to ensure a complete, consistent, and accurate record throughout the data lifecycle (16).

Data integrity is the degree to which data are complete, consistent, accurate, trustworthy, reliable, and that these characteristics of the data are maintained throughout the data lifecycle. The data should be collected and maintained in a secure manner, so that they are attributable, legible, contemporaneously recorded, original (or a true copy), and accurate. Assuring data integrity requires appropriate quality and risk management systems, including adherence to sound scientific principles and good documentation practices (16).

All phases in the life of the data (including raw data), from initial generation and recording through processing (including transformation or migration), use, data retention, archive and retrieval, and destruction (17).

The assurance that data produced is exactly what was intended to be produced and fit for its intended purpose (17).

Data governance, data integrity, and data quality are all widely used terms, but what do they actually mean and how are they connected?

Data Governance, Data Integrity, and Data Quality: What’s the Connection?

Jonathan Haider, j.haider@susupport.com, is product line manager at Single Use Support.

In the course of the significant transformation of the biopharmaceutical industry, modular manufacturing emerges as a game-changing approach to fluid management. This innovative methodology is reshaping how pharmaceutical companies and contract development and manufacturing organizations (CDMOs) produce and handle biopharmaceuticals, offering unprecedented flexibility, efficiency, and scalability.

Modular manufacturing in biopharmaceutical fluid management (

It allows for rapid adaptation that is due to either changing market demands or product specifications.

It enables manufacturers to optimize their production processes, reducing costs and improving product quality.

It facilitates easier compliance with regulatory requirements.

The latter is true when technologies provide better control and traceability throughout the manufacturing process. The integration of modular systems with manufacturing execution systems (MES) helps ensure seamless operations, real-time monitoring, and data-driven decision-making.

Overall, the approach to add modularity is particularly valuable when dealing with diverse product portfolios, varying batch sizes, and the potential need for quick scale-up or scale-out capabilities.

Process flexibility: a necessity in modern biomanufacturing

In today’s dynamic biopharmaceutical landscape, process flexibility is not just an advantage—it’s a necessity. CDMOs, in particular, face the challenge of producing a wide array of products with different specifications, volumes, and handling requirements.

One of the primary drivers for process flexibility is the diverse nature of biopharmaceutical products. From monoclonal antibodies (mAbs) to cell and gene therapies, each product may require unique processing conditions, volumes, and handling protocols. Such a volatile demand necessitates rapid scalability.

Will the COVID-19 pandemic remain unique? Uncertain. However, it has prompted manufacturers to be more prepared for potential further outbreaks, such as monkeypox. With pandemic preparedness comes the importance of being able to scale up production swiftly. Modular manufacturing systems provide the agility needed to respond to such sudden surges in demand. They also allow CDMOs to quickly reconfigure their production lines to accommodate these varying needs without significant downtime or retooling or alternatively piling equipment for all possible events and scales.

Why would CDMOs invest in a full set of multiple technologies when they can have one modular system for many scenarios?

Fluid management in manufacturing: the shift to automated closed systems

Fluid management is all about transferring liquids in biopharmaceutical manufacturing between different process steps. This can be the case in upstream, downstream, fill/finish, or in between. The industry is witnessing a transition from manual, open handling to automated closed systems, in large part due to Annex 1 of the European Commission’s guidelines, which favors closed systems. This regulatory requirement has been effective in shifting the interest of manufacturers and CDMOs to automated closed systems (1). The shift in attitude is primarily driven by the need for increased sterility, reduced contamination risks, and improved process control. Even for aliquoting small volumes into single-use bags, closed systems are increasingly being used (see 

 Aliquotation of biopharmaceuticals into small single-use bags.

Why would a manufacturer or CDMO want to close the fluid path system? Responses to this question include the following:

Enhanced sterility: by minimizing human intervention and exposure to the environment, closed systems significantly reduce the risk of contamination.

Improved process control: automated systems allow for precise control over filling parameters, ensuring consistency across batches.

Increased efficiency: automation reduces manual handling, leading to faster processing times and reduced labor costs.

Better traceability: closed systems integrated with MES provide comprehensive data logging, facilitating easier compliance with regulatory requirements.

Six most current pain points and challenges in fluid management

Despite the advancements in fluid management processes, several challenges persist in the biopharmaceutical industry.

 Many current systems struggle to accommodate varying production volumes efficiently. So many aspects can change, be it the batch volume or the size of the primary packaging. Does the manufacturer fill 100 L of antibody-drug conjugates into five single-use bags of 20 L? Or does the manufacturer dispense 20 L of viral vectors into 40 single-use bags of 500 mL? Do mAbs even need to be filled into 20 1-L bottles?Scaling up, down, or out often requires significant changes to equipment or processes, leading to increased costs and downtime.

 There is one closed system that CDMOs do not like—the closed ecosystem of technologies. A vendor lock-in and the resulting incompatibilities can restrict flexibility and increase costs for manufacturers. If Solution Provider A only accepts its own single-use assemblies, single-use bags, and sometimes even platform systems and not those of Vendor B or C, it limits both the drive for optimization and productivity and simply prevents CDMOs from following suit with their customers’ mandatory equipment.

 The need for different systems to handle various scales of production leads to increased capital expenditure, larger footprints, and more complex training requirements for operators, even more when platform systems are not modular. Adding a number of technologies does not necessarily equal scalability. More equipment is just a problem with regards to footprint in manufacturing suites.

 As the industry moves toward advanced therapy medicinal products (ATMPs) and personalized medicines, the need for precise handling of small volumes becomes critical. Many existing systems lack the required accuracy for these applications into single-use bags. In most cases, scales are integrated to measure larger filling quantities, while flow sensors are used to aliquot smaller volumes.

 Some biopharmaceuticals, particularly cell-based products, always require precise temperature control. Otherwise, inaccurate temperatures reduce cell viability, such as when cells are held too warm for too long. Most current systems struggle to maintain optimal temperatures in process steps before the cooling process.

 Most existing systems often leave significant residual volumes in tubing and containers, leading to product waste and reduced yield. This waste can be limited by draining single-use assemblies post filling with negative pressure.

Streamlining requirements: a (liquid) path forward

All of the mentioned pain points are issues that every manufacturer would want to be solved. But do all these pain points make sense for a specific manufacturer’s production? These points are of importance when biopharmaceutical manufacturers and CDMOs carefully consider their project criteria and priorities when selecting or designing fluid management systems.

What are the key project criteria, and in what order should these criteria be prioritized?

 Answering these questions helps a manufacturer find the most suitable filling platform and allows them to make trade-offs between some options. Examples are illustrated in 

; if it is important to fill small volumes (e.g., ATMPs) as accurately as possible, then speed of filling might not be the biggest priority. If it is the speed that counts, then the speed may reduce the accuracy and the option to homogenize drugs before the filling process to ensure aliquot-to-aliquot consistent product quality throughout.

 Examples of project priorities for aseptic filling.

Advanced filling platform systems adapting to criteria.

 Modular, adaptable platform systems are more likely to meet manufacturers’ defined criteria and priorities. Most innovative automated aseptic filling platforms offer several key features, such as:

Unified platform communication: implementing a standardized communication protocol across different scales enables seamless changes in production capacity without major system overhauls. Whatever MES is used, the platform systems require an interface to seamlessly be integrated into the current system, such as withOpen Platform Communication Unified Architecture (OPC UA).

Plug-and-play architecture: a single control unit that can accommodate different racks or modules, allowing for easy reconfiguration based on production needs. Even multiple racks can be attached to the control unit for large-scale operations.

Flexible pumping systems: incorporating pumps that can accurately handle a wide range of volumes, from microliters to liters. Large peristaltic pumps can be as accurate as +/-2 g filling accuracy, for example, but may not be fully suitable for certain drug substances. Depending on the product characteristics, different pump setups can be considered.

Advanced sealing technologies: predominantly performed manually, there is also a possibility to implement an automated sealing mechanisms to maintain system closure and sterility. Certain pinch valves can automatically seal the tubing right after the filling process, as shown in 

, which helps skip one process step of aseptically decoupling fully.

Cooling liquids for aliquotation process: connecting cooling functions directly to the filling platform helps to maintain product integrity for temperature-sensitive biopharmaceuticals. For example, cell-based products are cooled prior to the filling process during homogenization and mixing to maximize cell viability (2).

Optimized tubing design: enlarging the inner and outer diameters of tubing where appropriate to accommodate higher flow rates and reduce flow rates for low amounts of residual volumes. Integrated pinch valves need to be compatible to tubing of different sizes and characteristics. This allows a wider spectrum of scales and filling accuracy for manufacturers.

 Sealing pinch valves for aseptic decoupling.

Why modular filling platforms can no longer be overlooked by CDMOs

Modular manufacturing in biopharmaceutical fluid management marks a significant advancement in the industry, offering a multitude of benefits that are essential for modern production demands. One of the most compelling advantages is increased flexibility, which allows manufacturers and CDMOs to swiftly adapt to varying product requirements and batch sizes. This adaptability is crucial in a landscape where market needs can change rapidly.

Moreover, these modular systems contribute to improved efficiency by reducing setup times and facilitating easier changeovers between products, ultimately leading to higher overall equipment effectiveness. The cost-effectiveness of modular platforms cannot be overstated; by consolidating multiple dedicated systems into a single, versatile platform, companies can significantly lower capital expenditures and optimize their manufacturing footprint.

Quality control is enhanced through the implementation of closed, automated systems that minimize human error and contamination risks, ensuring consistent product quality. Additionally, the integrated data management and traceability features simplify regulatory compliance, making it easier for manufacturers to meet stringent industry standards.

As the biopharmaceutical landscape evolves, the adaptability of modular systems provides a vital degree of future proofing, allowing facilities to upgrade or expand as new technologies and regulations emerge. Furthermore, the ability to quickly scale up production can substantially shorten the time required to bring new products to market, giving companies a competitive edge.

In fact, those who embrace modular manufacturing will be well positioned to navigate the complexities of the biopharmaceutical industry, respond to changing demands, and thrive in an increasingly competitive environment. The future of biopharmaceutical manufacturing lies in modularity.

The Rules Governing Medicinal Products in the European Union Volume 4 EU Guidelines for Good Manufacturing Practice for Medicinal Products for Human and Veterinary Use

. 8.127 of Annex 1 (2022).
2. Moloney, B. Homogenization of Cells & Aliquotation in Single-use Bags. 

®
Vol. 48, No. 11
November 2024
Pages: 17–19, 30

When referring to this article, please cite it as Haider, J. Automate Aseptic Filling: Closing the System at Full Modularity. 

Shifting to automated, closed modular manufacturing systems is growing increasingly crucial for biopharmaceutical production.

Automate Aseptic Filling: Closing the System at Full Modularity

Chris Stumpf is director of Drug Discovery Informatics Solutions, Revvity Signals.

Many pharmaceutical and biotechnology organizations are rich in data but need more insights. Scientific data are often siloed, lacking context, and, therefore, inaccessible. Artificial intelligence (AI) and machine learning (ML) are promising tools for enhancing R&D. In drug discovery, AI can perform a variety of tasks, from identifying potential drug targets to predicting drug efficacy and optimizing treatment strategies. However, there is often a missing link between drug discovery data and AI outcomes. The integration of AI in drug discovery hinges on a crucial need for robust data management.

Why proper data management is essential for evolving research needs

Demand for traditional drugs and new modalities has increased data digitization across the pharmaceutical industry (1). Meanwhile, the latest AI and ML methods are transforming the R&D process within drug discovery, delivering on the promise to accelerate the journey from laboratory insights to lifesaving therapies. This transformative power of AI inspires optimism for the future of drug discovery, but much of the potential is trapped in isolated and undefined data.

AI is only as powerful as the data it consumes, and it works best with data that have the proper quality, detail, and context. While there are abundant scientific data in pharmaceuticals and biotechnology, the data are often siloed, poorly modeled, and ultimately inaccessible. A meticulous approach to capturing and curating R&D data is indispensable to unlock the full potential of novel AI methodologies. Examining how data are ingested, stored, organized, and maintained is crucial. A strong AI-ready data management strategy can help drug discovery leaders leverage AI to deliver innovative drugs to patients faster.

As AI has matured, many industries have experienced the benefits of automating tedious, data-heavy tasks. Now, the drug discovery industry is facing a high demand for finding insights from high volumes of data, while cutting-edge AI technology is becoming more widely available just in time.

 Pharmaceutical R&D has always been data-intensive, involving many data types from various sources, including laboratory instruments, clinical trials, and real-world evidence.

These data are often stored in disparate systems, leading to silos that make it difficult for both humans and machines to access and utilize the data. What’s more, modern drug therapies are increasingly complex. Drug modalities such as antibodies and cell and gene therapies comprise large, intricate molecular entities, and developing these complicated solutions requires large amounts of data. This complexity is an opportunity for innovation, but it also underscores the need for AI’s interpretive capabilities in drug discovery (see 

 Newer drug modalities comprise large, intricate molecular entities, and potentially terabytes and petabytes of data, that artificial intelligence can interpret.

As science grows in complexity, researchers need new tools and different approaches to curating data to ensure quality and consistency. Simple tools for storing and organizing data were adequate for managing the work that previous generations performed, but they lacked the capabilities required for today’s complex research needs. Fortunately, AI can reduce human workload and quickly achieve targets (2). When paired with proper data management, it can rapidly find patterns and discover hidden insights that humans would otherwise miss.

 AI can consume and analyze complex datasets, and ML can identify valuable patterns within the data. Much like how the manufacturing industry has outsourced heavy lifting and repetitive tasks to robots, the pharmaceutical industry can delegate complex computing tasks to AI systems, enabling humans to find insights, make decisions, and explore new capabilities. Tools such as generative AI and ML algorithms give back quality time to scientists and fuel what scientists do best: think, experiment, and discover new therapies faster.

There are already many use cases for AI in drug discovery. In drug design and molecule generation, generative AI models can analyze existing databases of chemical compounds and learn how to generate novel molecules that are likely to have the desired efficacy and safety profile. In this way, researchers can employ AI to design new molecular structures with desired properties for treating specific diseases. Additionally, AI models can analyze biological data to understand the complex interactions within biological systems and identify points where therapeutic intervention could be beneficial.

Generative AI can also aid in discovering new biomarkers for diseases, which can lead to the development of more precise and targeted therapies. By analyzing patient data, including genetic information, AI models can predict how individual patients might respond to certain treatments, leading to more personalized and effective therapy plans.

Furthermore, AI models can simulate the interaction between drugs and biological systems, predicting drugs’ efficacy and potential side effects before real-world testing. Researchers can also use AI to design clinical trials, identify suitable participants, and predict outcomes, thus speeding up the development process and reducing costs. Another benefit of AI is its speed in finding, analyzing, and summarizing large volumes of external literature. For example, researchers can employ techniques such as natural language processing (NLP) and semantic search to quickly find and understand relevant issues from large bodies of work.

AI is clearly making a tremendous impact on the pharma industry, and the future holds even more promise. However, as the volume and complexity of research data grow, AI’s success depends on data management. Take ML, for example. An ML algorithm’s effectiveness depends on the quality of the training dataset. As AI capabilities continue to advance, there will be even more opportunities to streamline the scientific process and unite disparate sources of information—as long as organizations practice strategic data management.

 As technology advances and labs continue introducing more automation to their processes, the volume of data will increase, thus underscoring the need for proactive data management. Traditional on-premises infrastructure struggles to keep pace with the demands of modern labs, often leading to inefficiencies and increased costs. As a result, many research organizations have embraced cloud computing, which provides data storage and computational power for processing it. But simply storing data in the cloud is not enough. No matter where the data are stored, it needs context in order to be useful. Metadata—or in other words, data about data—are essential. Without metadata, data are like a cabinet full of unlabeled chemicals. In order to utilize AI, researchers must label data with information about the experiment, such as experimental methods, conditions, and the nature of the data.

By moving data management to the cloud, pharmaceutical companies can leverage the extensive infrastructure, security, and scalability that cloud service providers offer. This shift allows organizations to focus on their core expertise—drug discovery and development—instead of troubleshooting technical problems.

While simply moving existing applications to the cloud (a process known as “lift-and-shift”) can offer some benefits, it often fails to unlock cloud computing’s full potential. The real advantages are realized through the adoption of cloud-native applications—those specifically designed to exploit cloud computing principles and technologies from the ground up.

Cloud-native solutions provide a rich ecosystem of services and connected capabilities that are indispensable for modern pharmaceutical R&D. They facilitate seamless integration of data from multiple devices, enable the application of advanced analytics and AI, and support real-time collaboration across geographically dispersed teams.

Cloud-based Software as a Service (SaaS) platforms seamlessly integrate with existing information technology (IT) ecosystems, providing a unified and flexible approach to data management. These integration-ready SaaS applications enable pharmaceutical companies to streamline their R&D workflows, reduce manual processes, and enhance collaboration across global teams. Plus, the cloud-based approach allows for frequently updating software with new releases and capabilities. The ability to update is essential as research needs change, AI capabilities advance, and new security vulnerabilities develop.

Electronic lab notebooks (ELNs) provide a central tool for data capture, analysis, and reporting. Cloud-based ELNs offer robust integration capabilities, allowing data from various sources to exist in a single, accessible platform. This centralization not only simplifies data management but also breaks down silos, fostering a collaborative environment where researchers can share insights and work together more effectively.

They also enable the creation of seamless workflows that connect different stages of the drug development process. For instance, integration between an ELN and a sample management system can automate the flow of substance registration data, minimizing the need for manual data entry. This approach saves time and reduces the chance of human error, ensuring that ML algorithms are working with accurate data.

 Like many technological advances, AI will only be effective if users embrace it. Data entry must be simple enough to encourage researchers to adopt AI-based research methods. User-friendly interfaces can help scientists quickly learn to navigate these platforms, manipulate data, and customize workflows to suit their needs. Features such as inventory tracking and integration with familiar tools make it easier for researchers to embrace new technologies and drive innovation.

As pharmaceutical R&D evolves, security and compliance are critical aspects of data management. Ensuring robust data security and compliance is crucial for safeguarding sensitive research information, especially as AI becomes integral to the industry.

While scientists leverage AI to accelerate discoveries, cybercriminals are also using AI to develop sophisticated attack methods. The benefits of using AI far outweigh the risks, but organizations must take proactive measures to prevent attacks. A layered approach to security includes data encryption and rigorous access controls, continuous monitoring and proactive threat intelligence, and regular vulnerability scans and risk assessments.

 The Findability, Accessibility, Interoperability, and Reuse (FAIR) principle, defined in a March 2016 paper in the journal Scientific Data by a consortium of scientists and organizations, states that data should be findable, accessible, interoperable, and reusable. A given data point must have metadata and a unique identifier. Furthermore, humans and machines should be able to read the data, which must be registered or indexed in a searchable resource (2) (see 

 Findability, Accessibility, Interoperability, and Reuse (FAIR) data principles describe the concept that data should be findable, accessible, interoperable, and reusable.

Evolving data frameworks: adapting to future research needs

Scientific inquiry is unpredictable, and the data collected today might need to answer unforeseen questions tomorrow. Rigid data schemas risk losing valuable context and potential insights. A different methodology called “late binding of schema” offers the flexibility that scientific discovery requires.

This methodology involves capturing data in a way that allows for its structure to be defined and modified closer to the time of analysis. By enabling data to be restructured as new hypotheses and analytical needs emerge, late binding of schema preserves the data’s full informational content and contextual richness. This flexibility is especially critical in the context of AI and ML, where the quality of training datasets directly influences model performance.

It is not only the output of today’s research that has changed, but also the way research is conducted. Collaborating with outsourced partners and colleagues in different locations is not only possible, but common. The modern way of working requires seamless, secure data sharing across teams and scientific disciplines. As teams become more distributed, there is a need for continuous integration with a globalized scientific community.

Ushering in the next era of drug discovery with AI

As AI progresses, so will the way researchers capture, integrate, and analyze data. Gathering data and transferring these data into programs for analysis and review will continue to become more streamlined and automated so that, eventually, data could automatically flow from across systems and algorithms and onto predictive models.

In the drug development industry, unifying data and contextualizing data are paramount for advancing scientific research and innovation. By annotating data with rich metadata and employing flexible data modeling, researchers can transform overwhelming volumes of information into structured, navigable resources ready for complex analysis by today’s AI tools and new tools that will become available in the future.

The collaborative nature of scientific research necessitates a data management system that facilitates seamless and secure data sharing across teams and disciplines. This approach prevents data silos and allows for the collective expertise of the scientific community to enrich and expand upon the available data. Integrating diverse data types—such as medicinal chemistry and biochemical data, screening data, and pre-clinical observations—becomes increasingly critical for a holistic understanding of therapeutic outcomes as research becomes a global endeavor.

Flexibility in data management is also crucial, particularly in the context of AI and ML. Adopting methodologies such as late binding of schema allows for the data structure to be defined and refined as close as possible to the analysis time. This ensures that data remain agile and adaptable enough for modern scientific discovery. By enabling the reorganization of data and correction of errors without restarting the process, researchers save time and maintain the integrity and utility of their data, ultimately accelerating R&D progress and driving breakthroughs in the pharmaceutical industry.

Effective data management may have previously been considered an operational decision, but it is now a strategic decision. When data are contextualized, centralized, and accessible, AI can enable pharmaceutical companies to accelerate innovation and improve patient outcomes.

1. Paul, D.; Sanap, G.; Shenoy, S.; et al. Artificial Intelligence in Drug Discovery and Development. 

 (1), 80–93. DOI: 10.1016/j.drudis.2020.10.010
2. Wilkinson, M. D.; Dumontier, M.; Aalbersberg, I. J.; et al. The FAIR Guiding Principles for Scientific Data Management and Stewardship. 

®
Vol. 48, No. 11
November 2024
Pages: 27–30

When referring to this article, please cite it Stumpf, C. Untethered Data: Unifying and Contextualizing Drug Discovery Data. 

Capturing and curating R&D data are crucial to realizing the full value of advanced analytics.

Untethered Data: Unifying and Contextualizing Drug Discovery Data

Radoslaw Kaczanowski is head of Global Project Management at Recipharm.

Outsourcing in the biopharma and pharma industries is on the rise, driven by increasing competition, the rising number of emerging start-ups, and the demand for affordable medicines. While outsourcing offers numerous advantages, including access to specialized facilities and expertise, technology transfer remains a critical challenge.

Common hurdles in the complex nature of tech transfer may be overcome by data-driven approaches, digital tools, and effective communication.By embracing these strategies and collaborating with experienced contract development and manufacturing organizations (CDMOs), companies can navigate the complexities of tech transfer and bring innovative therapies to market faster.

The increasing complexity and cost of drug development, coupled with intensifying market competition and the demand for faster time-to-market, have driven a significant rise in outsourcing within the biopharmaceutical industry during the past 10 to 15 years (1).

As of 2023, over 60% of biopharma companies outsource at least some activities, contributing to the remarkable growth of the CDMO market, which is projected to outpace overall pharmaceutical industry growth through 2028 (2,3). This surge in outsourcing is fueled by factors such as the need for specialized expertise and infrastructure, the rise of resource-constrained start-ups, and the pressure to deliver affordable therapies.

While outsourcing to CDMO partners provides many advantages for pharma and biopharma companies, such as helping to mitigate risks and accelerate development timelines, a critical phase in the process can pose significant challenges: technology transfer. Seamless tech transfer ensures that the manufacturing process is faithfully replicated at the receiving site, safeguarding product quality, maintaining regulatory compliance, and minimizing the risk of costly delays or disruptions. However, this process is far from a simple exchange of physical assets; it involves the intricate transmission of knowledge and expertise required to replicate a complex manufacturing process.

Common tech transfer challenges include the following:

Misaligned expectations and project scope definitions.

 The drug developer or marketing authorization holder (MAH) may have preconceptions about their product based on initial information. These assumptions can influence the project plan and the tech transfer process itself. If these initial assumptions prove inaccurate, it can lead to costly delays and rework. Common examples of such discrepancies include unexpected product stability issues arising from changes in analytical methods, necessary product modifications to comply with evolving regulations (e.g., nitrosamine or elemental impurities guidelines), or misinterpretations of regulatory requirements at the project’s outset.

 Effective technology transfer hinges on a comprehensive understanding of the product and its manufacturing process. However, there can be gaps in technical knowledge that may hinder the creation of a robust transfer process, particularly with legacy products or those in early development stages. Some originating sites may lack experience in tech transfer, leading to uncertainties about the necessary information or its sources. Additionally, inadequate documentation practices can result in the loss of valuable technical knowledge, potentially leading to repeated challenges and delays during the transfer, impacting project timelines.

A lack of standardization at the receiving site.

 Challenges can arise during tech transfer without standardized internal processes and documentation at the receiving CDMO site. Multiple tech transfers from diverse clients with varying requirements can lead to inconsistencies, potentially impacting project timelines and efficiency. Implementing standardized procedures and documentation across projects streamlines the tech transfer process, enhancing productivity and fostering operational excellence. This ensures a smoother transition, regardless of the client or project complexity, and ultimately benefits both the CDMO and its partners.

 Effective tech transfer management and coordination rely on assembling dedicated teams at both the originating and receiving sites. However, this can be challenging, especially for smaller organizations or those with limited experience in tech transfer. The originating site may lack personnel with specialized knowledge in handling the transfer process, requiring additional support in gathering and organizing the necessary information for handover. Similarly, the receiving site may need to tap into expertise beyond its core tech transfer team for complex or novel projects. This ensures the development of a comprehensive and tailored plan that addresses the unique challenges of the specific technology being transferred.

Failure to address these challenges and navigate tech transfer effectively can have far-reaching consequences, impacting the overall success of the end product and potentially hindering its timely delivery to patients. Pharma and biopharma companies should always look closely at the tech transfer processes and capabilities of a potential partner when selecting a CDMO, ensuring that the right strategies are employed to successfully develop and manufacture their therapy.

Strategies for an efficient and effective tech transfer

Experienced CDMOs will employ a range of proactive strategies to ensure a seamless and successful tech transfer process while simultaneously mitigating risks to streamline timelines.

 A dedicated team of data scientists and statisticians equipped with advanced modeling and statistical tools can significantly enhance the tech transfer process. By harnessing the power of data-driven insights, development timelines can be accelerated, API consumption optimized, and tech transfers de-risked, leading to consistent, high-quality results throughout the manufacturing process.

Statistical modeling has emerged as a powerful tool for mitigating risks and ensuring a seamless transition throughout tech transfer. Harnessing a holistic, integrated approach to modeling across the drug development lifecycle, unlike standard processes which often focus on isolated aspects, drug developers can gain a comprehensive understanding of the product and its manufacturing process, allowing for confident decision-making and proactive risk mitigation.

Through the creation of sophisticated predictive models, developers and manufacturers can establish clear connections between material attributes, process parameters, and critical quality attributes (CQAs) of the drug product. Using a broad range of data sources information, including data from specialized equipment such as those used for powder characterization and simulation, historical data from previous projects, literature data, and real-time process data, developers can generate more robust and comprehensive models with enhanced predictive accuracy. This enables the identification of key process parameters that significantly impact product quality, empowering targeted optimization and control during tech transfer.

The complexities of tech transfer may be overcome by data-driven approaches, digital tools, and effective communication.

Featured Content

Pharmaceutical Technology Is Now PharmTech: A Sharper Name for a Smarter Industry

Behind the Headlines Episode 28

Ask the Expert

Drug Digest December 2025

A “Plan, Prevent, Prove” Approach