How digital container twins can improve pharma manufacturing

Manufacturing Intelligence: Digital Twins Meet Pharma Containers

Navigating FDA Shakeups and Obesity Drug Wars

Behind the Headlines Episode 28

Ask the Expert

How evolving regulatory expectations are reshaping pharma development and manufacturing.

Drug Digest April 2026

How It Helps Avoid Facility and Equipment Problems

A “Plan, Prevent, Prove” Approach

Sandra Coufal, Toragen, shares promising Phase I results showing dramatic HPV DNA reductions and tumor shrinkage, with Phase II set to confirm efficacy and safety.

TGN-S11 and Early Indicators of Drug Activity

Sandra Coufal, MD, CEO, Toragen, discusses the methods used to measure drug activity in phase I clinical trial patients and what the encouraging early results mean for the study's next stage.

Dr. Coufal explains that the research team used two approaches to track treatment response. The first was a monthly blood test measuring circulating tumor HPV DNA numbers, a tool oncologists rely on to gauge whether a patient's therapy is working. "It actually decreases and precedes a decrease in size of tumors on CAT scan," Dr. Coufal notes, highlighting its value as an early indicator of what is happening in the body. The team observed dramatic reductions in HPV DNA levels among patients, signaling meaningful drug activity.

The second measurement approach was standard-of-care CAT scans conducted every six to eight weeks, aligned with known tumor cell doubling times. Results were similarly promising, with some tumors shrinking and others remaining stable.

Looking ahead to phase II, the team aims to enroll enough patients to reach statistically significant conclusions about partial and complete response rates. "If we had had more patients like we will have in phase II, then we get into being able to determine partial response or complete response, really more efficacy parameters," Dr. Coufal said.

Safety remains a priority as researchers work to identify the highest tolerable dose for patients. Dr. Coufal expressed confidence in the drug's profile, noting that the removal of the non-preferred enantiomer makes tolerability a lesser concern than it might otherwise be.

Videos

PharmTech Weekly Roundup May 22, 2026

 focused on three industry themes: increased regulatory flexibility for rare diseases, a critical shift toward automated, data-driven manufacturing, and strategic acquisitions in genetic medicine. As the FDA experiences leadership transitions, manufacturers must stay agile, adopting “just-in-time” logistics and predictive process controls to maintain a competitive edge in a rapidly evolving landscape.

Eli Lilly’s acquisition of Engage Biologics

 adds a non-viral Tethosome platform to its portfolio, aiming to overcome traditional barriers in genetic medicine, such as nuclear localization and innate immune sensing.

 finds that persistent leadership turnover at the FDA’s Center for Drug Evaluation and Research and the Center for Biologics Evaluation and Research has created a pattern of instability that could disrupt review timelines and internal prioritization for sponsors.

, the 2026 regulatory environment is moving toward greater flexibility, utilizing the “Plausible Mechanism” framework and observational data to accelerate approvals for ultra-rare conditions.

, Susan Schniepp, distinguished fellow at Nelson Labs, and Siegfried Schmitt, PhD, vice president, Technical, at Parexel, discussed the need for a robust out-of-specification program that requires a shift from reactive troubleshooting to holistic trend analysis and process mapping that identifies recurring issues across methods, personnel, and equipment.

, explained that by leveraging decades of existing safety data and composition-of-matter patents, Toragen is streamlining the development of a liquid formulation cancer drug designed specifically for patients who cannot swallow pills.

, vice president of clinical development at Precision for Medicine, explained why radiopharmaceuticals are unique for patients with cancer and what makes them challenging to develop for those patients. The inherent nature of radioactive decay necessitates a transition from traditional inventory models to high-precision, "just-in-time" delivery networks supported by specialized radiation safety infrastructure.

Deborah Smook, co-founder and co-owner of TurboFil Packaging Machines

, explained how managing complex liquid viscosities requires tailored filling methodologies and the integration of AI for predictive maintenance to prevent out-of-specification production.

Stuart Tindal, Sartorius, and David Chau, Thermo Fisher,

 talked about how automation is no longer optional in continuous bioprocessing, as the industry shifts from reactive set-point controllers toward predictive, model-based "process steering" to maintain consistency.

 explained that in order to resolve bottlenecks caused by high upstream titers, manufacturers are adopting footprint-neutral intensification strategies, real-time analytics, and modular single-use skids to future-proof biologics production.

Staying ahead in this industry means embedding scalability and automation into early-stage design while remaining vigilant of the changing regulatory guard. Be sure to watch the various interviews and read these features on 

Increased regulatory flexibility for rare diseases, a critical shift toward automated, data-driven manufacturing, and strategic acquisitions in genetic medicine were some of the highlights this week.

PharmTech Weekly Roundup-May 22, 2026

Cheryl Barton is director of PharmaVision, 

European union DNA | Image Credit: ©Kestutis -stock.adobe.com


Europe is emerging as a key player in next-generation cell and gene therapy (CGT) production, driven by collaborative research networks, public-private partnerships, and specialized hubs of innovation that leverage artificial intelligence (AI) to streamline CGT production and automate batch recording and data analysis.

 The European CGT market may exceed US$11.8 billion by 2035, delivering a compound average growth rate of 18.2% from 2025 to 2035, fuelled by the development of novel chimeric antigen receptor (CAR-T), gene-edited medicines, and regenerative therapies (see 

Figure. European Cell and Gene Therapy Market Forecasts 2025-2025. (Figure courtesy of the author)

Europe leads in research and early innovation with more than 250 advanced therapy medicinal product (ATMP) clinical trials and a strong biotech presence in the United Kingdom, Belgium, France, Germany, and Switzerland.

 However, it still trails the United States in commercialization and manufacturing, while Asia, especially China, South Korea, and Singapore, is rapidly building low-cost biomanufacturing facilities.

 Scaling up CGT production presents technical challenges, and European manufacturers have been focusing on applying advanced manufacturing techniques to meet the growing demand for innovative CGTs.

Currently, the cost of goods (CoGs) for CGTs ranges from 55% to 70% of the total cost of a therapy, depending on material costs, consumables, capital, and labour.

 For CAR-T treatments, manufacturing costs alone can exceed €60,000 per patient, depending on the production model.

 At the same time, global manufacturing capacity has fallen dramatically short of demand.

 Bridging this gap will require creative and innovative delivery models, such as increased automation, closed processes, decentralized manufacturing, and point-of-care solutions.

Investment activity in CGTs increased following the European Medicines Agency (EMA) approval of CAR-T therapies, Kymriah (tisagenlecleucel) and Yescarta (axicabtagene ciloleucel)to treat haematological cancers in 2018. Many major pharmaceutical companies expanded their presence through acquisitions and partnerships (

). Funding has declined in recent years, and the European CGT sector has experienced significant consolidation and strategic alliances as biotech firms, contract development and manufacturing organizations (CDMOs), and pharmaceutical companies seek to secure manufacturing capacity, viral vector technologies, and scalable production platforms.

The commercialization of these life-changing medicines remains a challenge, in part due to their high production costs, regulatory complexities and limited scalability.

Table: Transactions and Strategic Collaborations in European Cell and Gene Therapy (2021–2026)

Leading European biotechnology companies are developing next-generation manufacturing. Several European biotechnology companies are at the forefront of this transition, including the following:

, develops programmable CAR-T therapies using modular engineering to enhance safety and persistence in blood cancers. Its manufacturing strategy focuses on streamlined autologous production with integrated analytics to cut turnaround times. Autolus merges clinical development with vertically integrated manufacturing, forming a hybrid biotech-commercial model. Autolus has forged numerous partnerships with industry and academic partners, including Blackstone Life Sciences (2021), Moderna (2021), Bristol Myers Squibb (2022), Cabaletta Bio (2023), BioNTech (2024), and the University College London to develop next-generation CGTs.

focuses on manufacturing technology, leveraging its closed-loop automated CGT platform to support decentralized manufacturing. In 2022, the company raised US$100 million in Series B funding to launch its CGT manufacturing platform.

is a leading European viral vector manufacturer. It provides lentiviral vector development and production to CGT developers through a CDMO model. The platform focuses on scalable, standardized vector production to maintain a reliable supply of viral vectors. In January 2024, it acquired ABL Europe to expand its viral vector footprint in Europe.

 was founded by Syncona Ltd in June 2018. It focuses on process optimization and quality-by-design manufacturing methods.

 The company is leveraging its pioneering Foxp3 Phenotype Lock technology, multi-modular platform, and integrated manufacturing capabilities to design and develop a pipeline of highly engineered regulatory T-cell (Treg) therapies to treat autoimmune and inflammatory diseases. In 2021, the company raised US$204 million in Series A and B financing and has since established partnerships with Cellistic (2022), AstraZeneca (2023), and AGC Biologics (2025).

 In March 2026, it initiated a phase 1/2 clinical trial with its autologous CAR-Treg therapy, QEL-005, in patients with rheumatoid arthritis and systemic sclerosis.

was founded in 2007 and is a market leader in cell-free enzymatic manufacturing. Ituses its synthetic DNA platform, dbDNAtechnology, to synthesise “doggybone DNA”, an alternative to plasmid DNA. This method accelerates production, reduces contamination risks, and enhances scalability for messenger RNA (mRNA) vaccines, viral vectors, and gene editing. In March 2023, it secured £14 million from the UK government to scale up its DNA manufacturing and has signed agreements with Lonza (2022), Pfizer (2022), Voyager (2022), 20Med Therapeutics (2023), Curia (2023), GlaxoSmithKline (2024), LenioBio (2024), and Ceva Animal Health (2025).

has developed the proprietary C-Stem technology for large-scale stem cell expansion in bioreactors. This could lower manufacturing costs for regenerative medicine and allogeneic therapies.

 It focuses on scalable allogeneic production, supporting the industry shift to off-the-shelf treatments for wider commercialization. In April 2024, TreeFrog signed a licensing deal with Vertex Pharmaceuticals for an exclusive licence to C-Stemfor the Type 1 Diabetes programme.

 In May 2025, TreeFrog secured €30 million in financing from the EIB to accelerate the development of its CGT platform.

During the past five years, several trends in CGT manufacturing have emerged, such as the following:

: Companies like Ori Biotech, UK, have developed closed, automated systems to cut CoGs, ensure consistency, and enable decentralised manufacturing near hospitals. Novel manufacturing technologies are pivotal in Europe’s approach to cost-effectively and sustainably produce ATMPs, especially in autologous therapies, where production is complex and has hindered commercialization to date.

. Leading pharmaceutical companies and CDMOs have forged strategic alliances and acquired companies to expand their access to scalable manufacturing, vector optimization, and decentralized production, thereby supporting the simultaneous development and commercialization of multiple therapies.

Europe is emerging as a global hub for viral vectors and DNA manufacturing. 

Many European countries have established CGT manufacturing innovation hubs, including the CGT Catapult Stevenage Manufacturing Innovation Centre in the UK, the DACH Region CGT Manufacturing Site in Germany, and NecstGen in the Netherlands, to drive precision manufacturing.

 Innovative biotechs such as Oxford Biomedica have forged strategic partnerships to leverage and advance their lentiviral vector production capabilities, while Touchlight Genetics has pioneered enzymatic DNA synthesis.

The CGT manufacturing has become more competitive.

 US firms dominate CGT manufacturing; however, China is rapidly expanding its low-cost CGT infrastructure via government-backed policies. Europe has shifted from research-focused CGT to a more integrated manufacturing and commercial ecosystem, enabling Europe to build a scalable and resilient global supply chain.

To stay competitive, Europe is advancing regulatory modernization and initiatives to enhance supply chain resilience.

 Reforms to European pharmaceutical laws and biotech policy also aim to streamline trials, facilitate the use of AI, and improve manufacturing competitiveness.

 The proposed Critical Medicines Act (CMA) aims to boost European Union pharmaceutical manufacturing capacity, diversify supply chains, and promote strategic production projects via funding incentives and streamlined administrative processes.

 Although initially focused on essential medicines, the CMA may indirectly boost CGT manufacturing by aiding domestic infrastructure, reducing reliance on external suppliers, and promoting resilient procurement.

While European companies have excelled in discovery and engineering, advances in manufacturing and commercialization are essential if Europe is to maintain its competitive edge. Europe’s CGT sector's future depends on industrialising innovation. Europe has started to centre on healthcare resilience and advanced manufacturing capabilities to reduce CoGs, expand patient access and maintain its leadership in next-generation biomedical technologies.

 During the next decade, decentralized networks, AI-driven quality systems, continuous bioprocessing, and automated platforms will help reduce costs and expand access to CGTs. With supportive regulation and coordinated industrial policy, European manufacturers could close the gap with the US and become global leaders in resilient, next-generation CGT manufacturing.

Europe Cell and Gene Therapy Market to Rise at 18.2% CAGR till 2035.

 20 April 2026. https://www.towardshealthcare.com/insights/europe-cell-and-gene-therapy-market-sizing

European CGT Commercialisation Gap: Challenges in Cell & Gene Therapy Europe.

 23 April 2026. https://www.phacilitate.com/insights-resources/european-cgt-commercialisation-gap

2025 cell and gene challenges: Scalability, supply chain and manufacturing.

 3 February 2025. https://www.cellgenetherapyreview.com/3975-Featured-Articles/617533-2025-cell-and-gene-challenges-Scalability-supply-chain-and-manufacturing/

Industrializing CAR-T cell therapy: impact of automation on cost and space efficiency of manufacturing facilities.

Frontiers in Bioengineering and Biotechnology.

Cost of Goods Sold Analysis for Manufacturing mRNA-Based Cell and Gene Therapie

https://www.medrxiv.org/content/10.64898/2026.05.04.26352406v2

22nd Annual Report and Survey of Biopharmaceutical Manufacturing Capacity and Production

. 2025. Accessed 22 May 2026. https://www.bioplanassociates.com/22nd/

Why flexibility and commercial viability must be built-in early for scaling CGTs.

https://www.biopharminternational.com/view/why-flexibility-and-commercial-viability-must-be-built-in-early-for-scaling-cgts

Cell and gene therapy manufacturing challenges to persist in 2025.

 23 December 2024. https://www.pharmamanufacturing.com/all-articles/article/55251398/cell-and-gene-therapy-manufacturing-challenges-to-persist-in-2025

First two CAR-T cell medicines recommended for approval in the European Union | European Medicines Agency

. 29 June 2018. https://www.ema.europa.eu/en/news/first-two-car-t-cell-medicines-recommended-approval-european-union

Ori Biotech, Cell Therapies and AdAlta join forces to tackle cell therapy manufacturing challenges.

 News release. 21 April 2026. https://oribiotech.com/press-releases/oribiotech-cell-therapies-and-adalta-join-forces-to-tackle-cell-therapy-manufacturing-challenges

Ori Biotech and Fresenius Kabi collaborate to advance modular, scalable manufacturing of cell and gene therapies. News release. 10 December 2024. https://oribiotech.com/press-releases/ori-biotech-and-fresenius-kabi-collaborate-to-advance-modular-scalable-manufacturing-of-cell-and-gene-therapies

WuXi AppTec completes acquisition of OXGENE to strengthen cell & gene therapy service offerings.

 News Release. 2 March 2026. https://www.wuxiapptec.com/news/wuxi-news/4493

AskBio and Touchlight restructure joint centure. News release. 8 February 2022. https://www.askbio.com/askbio-and-touchlight-restructure-joint-venture/

Vertex and TreeFrog therapeutics announce licensing agreement and collaboration to optimize production of Vertex’s cell therapies for type 1 diabetes

. News release. 23 April 2024. https://investors.vrtx.com/news-releases/news-release-details/vertex-and-treefrog-therapeutics-announce-licensing-agreement

Oxford Biomedica completes acquisition of ABL Europe.

 News release. 29 January 2024 https://oxb.com/news/oxford-biomedica-completes-acquisition-of-abl-europe/

AstraZeneca to acquire EsoBiotec to advance cell therapy ambition.

 News release. 17 Mar. 2025. https://www.astrazeneca.com/media-centre/press-releases/2025/astrazeneca-to-acquire-esobiotec.html

 Accessed May 2026. https://www.autolus.com/about-us/our-partners/

Ori Biotech raises over $100 million in Series B funding to launch innovative cell and gene therapy manufacturing platform.

 News release. 18 January 2022. https://oribiotech.com/press-releases/ori-biotech-raises-over-100-million-in-series-b-funding-to-launch-innovative-cell-and-gene-therapy-manufacturing-platform

Transforming lives in immune-mediated disease.

 Accessed May 2026. https://www.quell-tx.com/?part=manufacturing

Quell Therapeutics initiates CHILL phase 1/2 trial of novel QEL-005 CAR Treg therapy in refractory rheumatoid arthritis and systemic sclerosis following UK CTA approval. New release. 3 March 2026. 

https://www.quell-tx.com/news/quell-therapeutics-initiates-chill-phase-1-2-trial

 Accessed 22 May 2026. https://touchlight.com/news-events/

Treefrog Therapeutics secures €30 million from EIB, marking a significant milestone in the company’s journey to accelerate the field of cell therapy.

 Partnerships. 27 May 2025. https://www.eib.org/en/press/all/2025-222-treefrog-therapeutics-secures-eur30-million-from-eib-eib-marking-a-significant-milestone-in-the-company-s-journey-to-accelerate-the-field-of-cell-therapy

LinkedIn. CGT Manufacturing in DACH: Europe's Answer to the Global CGT Challenge. 4 February 2026.

https://www.linkedin.com/pulse/cgt-manufacturing-dach-europes-answer-global-challenge-imapac-grnre/

https://ct.catapult.org.uk/facilities?facility=stevenage

 Accessed 22 May 2026. https://necstgen.com/

Regulation of advanced therapies in Europe: Are we on the right track?

 Cell Stem Cell. 30, 8, 3 August 2023. 1013-1016. doi: 10.1016/j.stem.2023.07.004

 December 2025. https://health.ec.europa.eu/medicinal-products/reform-eu-pharmaceutical-legislation_en

 March 2025. https://health.ec.europa.eu/medicinal-products/critical-medicines-act_en

Europe Is Scaling Investment in Regenerative Medicine.

 12 May 2026. www.sorosgabinete.com/insights/europe-is-scaling-investment-in-regenerative-medicine

Cheryl Barton, PhD, is founder and director of PharmaVision, Pharmavision.co.uk. 

Articles

Europe is positioning itself as a next-generation CGT manufacturing center, underpinned by dense research networks, public–private partnerships, and innovation hubs deploying AI for process control and data automation. Despite strong ATMP trial activity, commercialization lags the US and faces intensifying cost competition from Asia. High CoGs—often 55%–70% of total therapy costs—and constrained capacity are driving investment toward automation, closed systems, decentralized/point-of-care models, and scalable vector/DNA platforms. Regulatory modernization and industrial policy may improve resilience and competitiveness.

European biotechnology companies are increasing patient access to innovative cell and gene therapies through decentralized next-generation manufacturing platforms. 

European Biotechs Developing Next-Generation Cell and Gene Therapy Manufacturing Technologies

Quantum chemistry and AI are converging to accelerate drug discovery with better, physics-based data.

There is a question ringing throughout the pharmaceutical industry: how far will AI take us? You can hear it in the $17 billion worth of AI partnership deals announced by pharma in the last year.

You can hear it in the almost weekly LinkedIn announcement revealing the latest AI scientist company. You can hear it in the quiet skepticism of chemists and biologists who, despite spending valuable funding on multiple approaches, still can’t find a model that works for their target.

If you’ve read a review on AI in drug discovery, you’re probably familiar with its primary challenges. Lack of quality data. Lack of explainability. And lack of generalisation.

Meanwhile, another in silico method has been advancing quietly but rapidly in mutual symbiosis with AI: quantum chemistry. For a century, it’s been theoretically possible to calculate the behaviour of all chemical systems; but computationally impossible to run those calculations ab initio at biologically relevant scales.The development of highly parallelisable algorithms and GPUs, accelerated for the purposes of AI, has helped change this. At the end of 2024, QDX’s research team demonstrated that quantum chemistry calculations can be run 3,568x faster than the previous state of the art, simulating the ab initio dynamics of a system with over 1400x more electrons than previously modelled at that level of accuracy.

The biologists in the room should be pointing out that mutual symbiosis requires a benefit to go both ways. The AI wave has catalysed rapid development of GPUs into powerful, general-purpose parallel processors, directly impacting the number of quantum chemistry calculations that can be performed at once. Incidentally, quantum chemistry at scale is able to provide an ideal data engine for many drug-discovery-focused AI models. With recent advances, data generated using quantum chemistry is cheaper and more scalable than experimental data; it’s reproducible (no random noise between experiments); it’s not limited to what has previously been discovered; it encodes the physics of the system, rather than just teaching the model statistical correlations; and it’s been found to reduce the number of data points required to train an accurate AI model.

Say we wanted to train an AI model to predict binding affinity. High-quality experimental data is scarce, expensive to produce, and notoriously inconsistent. As demonstrated in Figure 1, Landrum et al found that combining IC50 or Ki values from different assays causes significant noise in the dataset.

 Or as one computational chemist said to me in regards to an AI model: ‘rubbish in, rubbish out.’

Figure 1: Experimental binding data is noisy. Agreement between duplicate IC50 measurements on the same target shows R² of just 0.3 with only activity curation—essentially random. Heavy curation improves consistency but discards ~99% of data. Adapted from Landrum et al.

On the other hand, quantum chemistry enables physics-based calculations of binding energy with high levels of accuracy.

 These calculations are embarrassingly parallelisable and, with recent speedups in quantum chemistry software, significantly cheaper than experimental assays per compound. It’s far easier and more affordable to rent compute than to rent lab space.

Beyond economics and convenience, quantum chemistry can generate forms of data that are impossible to measure experimentally or compute classically. If you want to train a model to predict transition state geometries, quantum chemistry provides the only way to systematically generate the necessary 'ground truth' data. If you want to model charge transfer, you need quantum chemistry. If you want to model how a drug interacts with metal ions, you need quantum chemistry.

Quantum chemistry also changes the type and quality of inputs we can feed to AI models. Feature generation and selection can play key roles in improving a machine learning model’s predictive precision and generalization.

 What features of the molecule do we want to feed to the AI model? Which will be most informative for its pattern recognition? Currently, most models are trained on classical data, which doesn’t encode any actual description of the physics of the molecule. Efficient quantum data generation unlocks a new feature set for chemical AI; we move from training models on topological proxies (atoms and bonds) to training them on fundamental physical descriptors. Providing an AI with electron density maps, vibrational modes, and atomized energies allows it to learn the underlying 'energy landscape' of a molecule. This can provide an entirely different type of information.

Consider for a moment a more intuitive scenario. Say we were training an AI model to predict heart attacks:


1) Experimental data is comparable to feeding the model information about people who have had heart attacks. It may look at a million patients and learn that people who wear expensive watches and live in cold climates are likely to have heart attacks. These things aren’t actually the cause of heart attacks, but wearing expensive watches may correlate with having a stressful job, and living in a cold climate may correlate with getting less exercise. The model will work sometimes but miss anyone in a warm climate having a heart attack without an expensive watch.

2) Data computed using classical chemistry is based on a simplification of reality that changes depending on the forcefield used. In our analogy, we could compare it to feeding a model lots of textbook drawings of healthy and unhealthy hearts. It may learn how to predict which drawn hearts are unhealthy; but the style of drawing makes a difference, and the things it learns may not match what’s happening with real hearts. It’s ‘hit or miss’ how well it extends to the real world.

3) Now say we train the model on high-information descriptors that encode the actual physical causes of the heart attack: blood viscosity, arterial wall tension, and calcium density. Because these root causes are generalisable across heart attacks, it makes sense that you’d need far fewer examples for the model to get the idea. And once it learns how those features combine to cause heart attacks, it can be expected to accurately predict heart attacks in almost all hearts it may encounter.

Accordingly, quantum mechanical (QM) descriptors which encode the fundamental physics of chemical systems have been found to improve model performance in some scenarios, particularly when the dataset size is small.

 This means fewer data points are required for QM-augmented models to reach the same level of accuracy as classical models. As shown in Figure 2, they also improve generalisability; information on electronic structure is universally applicable across all of chemistry, while classical data is tethered to atom-types and empirical force-field parameters. These local shortcuts fail when the model encounters unfamiliar molecular architectures, whereas QM-trained models make accurate predictions even when encountering molecules with atoms that weren’t in their training set.

Figure 2: QM-augmented models need less data to generalize. With only 100 training points, QM-GNN models significantly outperform standard GNNs, especially on scaffold splits that test true extrapolation.

Another example of QM providing unique data is in covalent binders. By running QM/MM dynamics on entire protein-ligand systems, we can model proposed reaction mechanisms and extract data that experiments cannot provide: transition state geometries and reaction barriers. The transition state (the highest-energy configuration that determines whether a reaction proceeds) cannot be directly observed experimentally, but QM calculations can characterize it. The barrier height tells us about reactivity: a warhead that's too reactive risks hitting off-target residues, while one that's not reactive enough would fail to label the protein efficiently. When multiple mechanisms are plausible, we can compare them and identify which is most energetically favorable. This mechanistic understanding helps medicinal chemists make informed design decisions rather than iterating through a large number of designs. Classical simulations cannot provide any of this; with bonds fixed, there is no reaction to model.

Training better models on new forms of data is valuable. But in drug discovery, knowing that a molecule bind isn't enough: medicinal chemists need to know why. This is where quantum chemistry offers something AI alone cannot.

The deeper advantage separating QM from purely statistical approaches is that calculating from first principles physics gives you an explanation along with your answer. This level of interpretability is important for medicinal chemists trying to refine their molecule based on computational results, and entirely absent from AI or other methods. Take the example of binding affinity again: we can measure binding affinity experimentally, or we can train an AI model to predict binding affinity. But neither of these methods tell scientists what’s driving that binding. You get an answer, but not much insight.

Instead, if we use a physics-based approach, such as ab initio QM to calculate relative binding free energy, we can extract a more holistic view of the components that impact binding affinity. Such a calculation also gives us information about how each residue of the protein is interacting with different components of the ligand and its quantitative impact on total binding energy, whereas AI models typically only give a single consolidated binding affinity prediction for each ligand that cannot be easily dissected. By providing these quantitative measures of design changes, medicinal chemists are better empowered to make highly informed decisions during lead optimization.


These examples highlight a unique strength of quantum chemistry: not just prediction, but explanation. When it comes to training AI models, this matters too - as previously discussed, QM-derived features encode physical reality in ways that improve generalization. Of course, it’s important to note that quantum chemistry isn’t the ideal data generation engine for 

AI models. There are cases where data generated from the real world is necessary to encode statistical correlations; most obviously, there’s no way of calculating clinical outcomes or complex biological interactions from first principles alone.

But for properties that can be linked to the fundamental physics of a system, it seems almost obvious that feeding a model information about the physics is a more effective and generalizable training method than any approximation. For a long time, it’s been impossible to generate quantum chemistry data at enough scale to fully leverage this. With the progress that’s been made only in the last few years, we have reached an inflection point. For decades, quantum chemistry has been the domain of specialists running week-long calculations on single molecules. That era is ending. As QM data generation becomes fast and cheap enough to feed AI at scale, we're not just improving existing models; we're unlocking an entirely new paradigm for computational drug discovery. The companies that recognise this shift early will have a significant head start.

The question ringing through pharma—how far will AI take us?—may be missing the point. AI alone will take us as far as our data allows; no further. The more interesting question is: how far can AI take us when we finally give it data that encodes reality?

None of this is to say quantum chemistry will replace experimental data, or that AI trained on QM descriptors will solve drug discovery overnight. But for the specific, critical problem of training models that generalise beyond their training set, that understand why molecules behave the way they do: physics-based data generation may be the missing piece. The infrastructure to generate it at scale finally exists. Now it's a matter of using it.

NVIDIA; Eli Lilly and Company. NVIDIA and Lilly Announce Co-Innovation AI Lab to Reinvent Drug Discovery In the Age of AI. Indianapolis: Eli Lilly and Company; 2026 Jan 12. 

https://investor.lilly.com/news-releases/news-release-details/nvidia-and-lilly-announce-co-innovation-ai-lab-reinvent-drug

Insilico Medicine. Insilico Medicine announces US$888 million multi-year collaboration with Servier for drug discovery and development in oncology. Cambridge (MA): Insilico Medicine; c2026. 

https://insilico.com/news/u4cbsok2s1-insilico-medicine-announces-us888-millio

AstraZeneca. AstraZeneca enters into collaboration with CSPC. Cambridge (UK): AstraZeneca; c2025. 

https://www.astrazeneca.com/media-centre/press-releases/2025/astrazeneca-enters-into-collaboration-with-cspc.html

Superluminal Medicines. Superluminal Medicines announces collaboration with Eli Lilly and Company to advance small molecule therapeutics for cardiometabolic diseases and obesity. Boston: PR Newswire; 2025 Aug 14. 

https://www.prnewswire.com/news-releases/superluminal-medicines-announces-collaboration-with-eli-lilly-and-company-to-advance-small-molecule-therapeutics-for-cardiometabolic-diseases-and-obesity-302529689.html

Orionis Biosciences. Orionis Biosciences announces strategic partnership with Genentech. Boston (MA): Orionis Biosciences; 2025 May 21. 

https://orionisbio.com/2025/05/genentech-collaboration-2025/

Creyon Bio, Inc. Creyon Bio and Lilly enter into RNA-targeted oligo therapy development collaboration. San Diego (CA): Creyon Bio; 2025 Apr 29. 

https://creyon.com/news/creyon-bio-and-lilly-enter-into-rna-targeted-oligo-therapy-development-collaboration/

Nabla Bio, Inc. Nabla Bio signs second Takeda collaboration to advance AI-driven design of protein therapeutics [Internet]. Cambridge (MA): Business Wire; 2025 Oct 14. 

https://www.businesswire.com/news/home/20251014934240/en/Nabla-Bio-Signs-Second-Takeda-Collaboration-to-Advance-AI-Driven-Design-of-Protein-Therapeutics

Relation Therapeutics. Relation announces strategic collaboration with Novartis to advance therapeutics for atopic diseases. London: GlobeNewswire; 2025 Dec 9. 

https://www.globenewswire.com/news-release/2025/12/09/3202076/0/en/Relation-announces-strategic-collaboration-with-Novartis-to-advance-therapeutics-for-atopic-diseases.html

Halda Therapeutics. VantAI and Halda Therapeutics forge alliance to discover next-generation RIPTAC medicines. New Haven (CT): Halda Therapeutics; 2025 Aug 19. 

https://haldatx.com/vantai-and-halda-therapeutics-forge-alliance-to-discover-next-generation-riptac-medicines/

Earendil Labs. Earendil Labs announces worldwide exclusive license agreement with Sanofi for next-generation bispecific antibodies for autoimmune and inflammatory bowel diseases. Middletown (DE): PR Newswire; 2025 Apr 17. 

https://www.prnewswire.com/news-releases/earendil-labs-announces-worldwide-exclusive-license-agreement-with-sanofi-for-next-generation-bispecific-antibodies-for-autoimmune-and-inflammatory-bowel-diseases-302431020.html

Bhat, A. R., & Ahmed, S. (2025). Artificial intelligence (AI) in drug design and discovery: A comprehensive review. 

https://doi.org/10.1016/j.insi.2025.100049

Stocks, R., Galvez Vallejo, J. L., Yu, F. C. Y., Snowdon, C., Palethorpe, E., Kurzak, J., Bykov, D., & Barca, G. M. J. (2024). Breaking the million-electron and 1 EFLOP/s barriers: Biomolecular-scale ab initio molecular dynamics using MP2 potentials. 

SC24: International Conference for High Performance Computing, Networking, Storage and Analysis

https://doi.org/10.1109/SC41406.2024.00015

Landrum, G. A., & Riniker, S. (2024). Combining IC$_{50}$ or $K_i$ values from different sources is a source of significant noise. 

Journal of Chemical Information and Modeling

Toniato, A., Unsleber, J. P., Vaucher, A. C., Weymuth, T., Probst, D., Laino, T., & Reiher, M. (2023). Quantum chemical data generation as fill-in for reliability enhancement of machine-learning reaction and retrosynthesis planning. 

Thapa, B., Beckett, D., Erickson, J., & Raghavachari, K. (2018). Theoretical study of protein–ligand interactions using the molecules-in-molecules fragmentation-based method. 

Journal of Chemical Theory and Computation, 14

Theng, D., & Bhoyar, K. K. (2024). Feature selection techniques for machine learning: a survey of more than two decades of research. 

https://doi.org/10.1007/s10115-023-02010-5

Li, S.-C., Wu, H., Menon, A., Spiekermann, K. A., Li, Y.-P., & Green, W. H. (2024). When do quantum mechanical descriptors help graph neural networks to predict chemical properties? 

Shen, Z., Yang, Y., Sparrow, Z. M., Ernst, B. G., Quady, T. K., Kang, R., Lee, J., Yang, Y., Tu, L., & DiStasio, R. A., Jr. (2025). Learning molecular conformational energies using semilocal density fingerprints. 

The Journal of Physical Chemistry Letters

https://doi.org/10.1021/acs.jpclett.5c02222

Pecina, A., Fanfrlík, J., Lepšík, M., Řezáč, J., Hobza, P., & Bronowska, A. K. (2024). SQM2.20: Semiempirical quantum-mechanical scoring function yields DFT-quality protein–ligand binding affinity predictions in minutes. 

https://doi.org/10.1038/s41467-024-45431-8

Markovitch, S., & Rosenstein, D. (2002). Feature generation using general constructor functions. 

AI drug discovery remains constrained by sparse, noisy experimental datasets, limited explainability, and weak out-of-distribution generalization. Rapid GPU-driven advances are making biomolecular-scale quantum chemistry feasible, positioning QM as a scalable, reproducible data engine that encodes first-principles physics. QM-derived binding energies and electronic-structure descriptors can reduce training-set requirements, improve transfer to novel chemotypes, and enable tasks inaccessible to classical force fields (e.g., charge transfer, transition states, metal coordination). Physics-based simulations additionally provide mechanistic interpretability to guide medicinal chemistry decisions.

Quantum chemistry is accelerating drug discovery AI by providing physics-based, reproducible, and scalable data that encodes molecular reality.

Featured Content

Manufacturing Intelligence: Digital Twins Meet Pharma Containers

Behind the Headlines Episode 28

Ask the Expert

Drug Digest April 2026

A “Plan, Prevent, Prove” Approach