drug development Archives - European Industrial Pharmacists Group (EIPG)

The EU Parliament voted its position on the Unitary SPC


by Giuliana Miglierini The intersecting pathways of revision of the pharmaceutical and intellectual property legislations recently marked the adoption of the EU Parliament’s position on the new unitary Supplementary Protection Certificate (SPC) system, parallel to the recast of the current Read more

Reform of pharma legislation: the debate on regulatory data protection


by Giuliana Miglierini As the definition of the final contents of many new pieces of the overall revision of the pharmaceutical legislation is approaching, many voices commented the possible impact the new scheme for regulatory data protection (RDP) may have Read more

Environmental sustainability: the EIPG perspective


Piero Iamartino Although the impact of medicines on the environment has been highlighted since the 70s of the last century with the emergence of the first reports of pollution in surface waters, it is only since the beginning of the Read more

Generative AI in drug development

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

Generative AI is perhaps the more advanced form of artificial intelligence available today, as it is able to create new contents (texts, images, audio, video, objects, etc) based on data used to train it. Applications of generative AI are not limited to, for example, the famous ChatGPT chatbot used to write complex texts, or to algorithms producing incredible images.

Generative AI is becoming a new paradigm in drug discovery, as it promises to greatly reduce both time and costs to develop new molecules, or to repurpose already existing ones for new indications. A fundamental goal for pharmaceutical companies, given that the average cost of developing a new medicines is estimated at $2.6 billion.

Algorithms can be trained on chemical-physical characteristics and 3D shapes of molecules in order to generate completely new molecules of interest for a certain application, and/or to predict their behaviour in the biological context (e.g. binding to a specific receptor). We resume the current status of implementation of generative AI in the field of drug development.

Quintillions of data
It seems ages since the first full sequencing of the human genome was completed in year 2000. Since then, vast amounts of genomic and other biological data have rapidly accumulated. To give an idea, the National Human Genome Research Institute estimates between 2 and 40 exabytes (i.e. quintillions) of data available within the next decade. The number becomes even more larger when considering other domains relevant to drug development, including chemical structures and properties, complex biochemical pathways, 3D protein structures and receptors, data on the efficacy and toxicity profile of already approved medicines and candidates in the pipelines, etc.
No matter to say, the parallel growing interest in artificial intelligence that characterised the last twenty years has turned fundamental for the availability of new technologies able to digest, extract and analyse these extremely large datasets.
Machine learning and deep learning algorithms represented just the first step towards this goal. Generative AI came as a consequence, its birth is attributed to a paper by Ian Goodfellow et al., published in 2014.

Opportunities and challenges of generative AI for drug discovery
The implementation of generative AI in the pharmaceutical and medtech sectors may lead to the an estimated economic value of $60-110 billion/year, says the report by McKinsey and Co. “Generative AI in the pharmaceutical industry: Moving from hype to reality”.
More specifically, McKinsey analysed 63 generative AI use cases in life sciences, calculating the potential economic impact for different domains. The higher values ($18-30 bln) are expected for the commercial domain, followed by research and early discovery ($15-28 bln) and clinical development ($13-25 bln). Less impacted appear enterprise ($8-16 bln), operations ($4-7 bln) and medical affairs ($ 3-5 bln).
Implementation of generative AI may prove not a so easy exercise for pharma companies, as it has to fit within an already complex organisation and with the strict regulatory requirements typical of the pharmaceutical lifecycle. An important message comes from the analysis from McKinsey: it is of paramount importance to exit the hype climate surrounding generative AI and understand exactly what it can and cannot be done.
The question is highly complex to be solved, and it requires multiple skills (data scientists, researchers, medical affairs, legal, risk and business functions) jointly working to set up the solution more suited to each company. The availability of a proper data infrastructure is just the first step, the chosen generative AI model has to be adapted to the complexity of the specific case of use, focusing on key applications to avoid disruption of the business.

According to an analysis by Boston Consulting Group, generative AI may prove useful to include also unstructured data among those used as data sources by the pharmaceutical industry. Possibly a challenging goal to achieve, as data access and management must fulfil regulatory requirements, for example in relation to the possibility to use data generated in clinical trials to support regulatory approval.
Governance of generative AI must also reflect the key principles established in the EU for AI systems, i.e. they “must be ‘safe, transparent, traceable, non-discriminatory and environmentally friendly,’ as well as ‘overseen by people, rather than by automation, to prevent harmful outcomes’.”

The need to integrate generative AI with human activities would probably call companies to redesign core processes. To this instance, selection of the more suited AI infrastructure and platform may turn critical for success of the initiative. Integration with already existing AI tools and flexibility are among other main features to be kept in mind. Not less important is the choice of the right partners, that should fit with the strategic business goals.

Many algorithms already available
The first AI applications based on deep learning algorithms were used, for example, to predict the sequence and structure of complex biological molecules. It was the case of the AlphaFold Protein Structure Database, which contains over 200 million protein structure predictions freely available to the scientific community. Other algorithms of this kind are ESMFold (Evolutionary Scale Modeling) and and Microsoft’s MoLeR, specifically targeted to drug design.
A more recent generation of generative AI are IBM’s MoLFormers UI, a family of foundation models trained on chemicals which can deduce the structure of molecules from simple representations. MoLFormer-XL screening algorithm, for example, was trained on more than 1.1 billion unlabelled molecules from the PubChem and ZINC datasets, each represented according to the SMILES notation system (Simplified Molecular Input Line Entry System). As reported by IBM, MoLFormer-XL is able to predict many different physical, biophysical and physiological properties (e.g. the capacity to pass the blood-brain barrier), and even quantum properties.

Mutual Information Machine (MIM) learning is the approach used by NVIDIA to built its MolMIM algorithms, a probabilistic auto-encoder for small molecule drug discovery. The NVIDIA BioNeMo cloud service uses these models to deploy a generative AI platform to create molecules that, according to the company, should fulfil all properties and features required to exert the desired pharmacological activity.

Not only big players: many new companies were born specifically to support the creation of generative (often end-to-end) AI platforms for drug discovery. Among the main ones, Insilico Medicine’s Pharma.AI platform is being used to build a fully self-generated pipeline comprehensive of 31 programs and 29 targets. The more advance product under development targets the rare disease idiopathic pulmonary fibrosis and is currently in Phase 2 in the US and China. The company’s inClinico AI data-driven multimodal platform to calculate the probability of success of single clinical trials proved useful to predict outcomes of Phase 2 to Phase 3 trials and to recognise weak points in study design.

UK’s based Exscientia, founded in 2012, is an AI-driven precision medicine company. Among its main achievements is the creation of the first functional precision oncology platform to successfully guide treatment selection and improve patient outcomes. The more advanced product in its pipeline is GTAEXS617, an oncology product targeting CDK7 in advanced solid tumors.
These are just few main examples, you can learn more on companies focused on AI for drug discovery in these articles published on Forbes and Pharmaceutical Technologies.


Investing in formulation as success’ factor

, , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

Formulation is a critical step in the development of new medicinal products, as it directly influences the bioavailability, release profile and stability of the active ingredient, overall impacting on both the efficacy and safety of the medicine.

While in the traditional approach the definition of the final formulation was a quite late step along the development process, new models of R&D greatly focus on early formulation as a way to optimise both time and costs of drug development. It is thus important to identify the optimal formulation strategy as early as possible: a quite challenging goal in many instances, especially in the case of last generation complex biopharmaceuticals which may prove difficult to formulate. An article by Felicity Thomas, published in Pharmaceutical Technology discusses how to address early formulation strategies to maximise the chance of success.

Limits and challenges of formulation

The main objective of the drug development process remains the same, reducing as much as possible the time-to-market so to fully exploit the marketing exclusivity period granted by the patents protecting an innovative medicine.

To this instance, some key aspects should be considered in order to rapidly establish the most appropriate formulation, with a special attention to achieving an early access to first-in-human assessment and proof-of-concept studies.

Scaling-up of the formulation process is another critical issue, as it requires a careful consideration of all the steps needed to establish the final manufacturing process at the commercial scale. This exercise is fundamental in order establish the critical quality attributes and process parameters, thus reducing the risk of a change of the initial formulation to make it suitable to the final manufacturing process.

As explained by Jessica Mueller-Albers, strategic marketing director Oral Drug Delivery Solutions, Evonik, the increased pressure to speed up formulation is also connected to the fact “many new drugs target small therapeutic areas, where it is essential for pharma companies to be first in the market from an economic perspective.”

The availability of enabling technologies is fundamental to early formulate niche medicinal products, moving away from the classical mass production. The trend initiated with the development of mRNA Covid-19 vaccines may represent a change of paradigm in drug development, suggests Jessica Mueller-Albers. Lipid nanoparticles (LNPs) are an example of enabling technology that has been widely employed to formulate the mRNAs used in Covid-19 vaccines. LNPs may take many different forms, i.e. liposomes, lipoplexes, solid lipid nanoparticles, nanostructured lipid nanoparticles, microemulsions, and nanoemulsions (see more in Drug Development and Delivery).

Other types of emerging technologies are also widely investigated, such as proteolysis-targeting chimeras (PROTACS). These are heterobifunctional nanomolecules, containing one moiety recognised by the E3 ligase and chemically linked to a ligand (small molecule or protein) able to bond to the target protein. The final outcome is the formation of a trimeric complex, through which it becomes possible to transfer ubiquitin molecules to the target protein. The mechanism represents an alternative approach to “knock down”, as it enables the degradation of the target protein, offering many advantages compared to the use of classical inhibitors.

Another challenge to be faced during formulation development is the need of a broad and specialised expertise in the different domain of drug development, including also material characterisation, drug metabolism and pharmacokinetics. According to Stephen Tindal, director, Science & Technology, Europe, Catalent, this is particularly true for small companies, which are often the focus of early development activities before acquisition of the projects by larger multinationals. As explained in the Pharmaceutical Technology’s article, a possible approach is to use small teams of experts to manage the preclinical phases of development.

The many challenges of early formulation

The solubility of the active pharmaceutical ingredient (API) in aqueous media is often one of the main challenges to be faced in formulation studies, impacting also on the final bioavailability of the drug in the target body compartments and/or fluids. Estimates indicates that at least 70% of new APIs are poorly soluble.

Other challenging points to be taken into consideration include the possible presence of different polymorphic forms, each characterised by its own stability and properties, and potentially giving rise to conversion from one another during the formulation and/or manufacturing process (see more in the article by A. Siew, Pharmaceutical Technology). The often limited amount of API in the early phases of development and the difficulty to evaluate the dose range on the basis of the available data are other critical point to be considered.

The development of an appropriate bioavailable formulation is often based on preclinical data obtained from animal pharmacokinetic and GLP toxicity studies, followed by pre-formulation studies to assess API’s properties (e.g. solubility, stability, permeability, etc.) in commonly used solvents and bio-relevant media. Drug delivery systems might be used to solve solubility issues, to then scale the identified formulation on the selected technology platform to be used for manufacturing (see more in Drug Development and Delivery).

The principles of the Developability Classification System (DCS) may be also considered to better assess the physicochemical and biopharmaceutical characteristics of a new API that may impact of the formulation process.

Some possible approaches to early formulation

The experts interviewed by Felicity Thomas have indicated some possible approaches useful to addresses formulation issues. For systemic oral small-molecule drugs, for example, the use of a solution as the delivery vehicle may allow to reduce the needed amount of API, thus supporting lower costs to reach Phase I proof of concept in healthy volunteers. Various techniques are also available to favour solubilisation and bioavailability of the active ingredient, i.e. hot-melt extrusion, spray drying, coated beads, size reduction, lipid-based approaches, etc. The optimisation of particle size by mean, for example, of micronisation and nanomilling techniques is another option. Co-administration with lipids can enhance the lymphatic transport of lipophilic drugs, as it favours its incorporation into chylomicrons at the intestinal level, and the subsequent delivery to the lymphatic system in the form of chylomicron–drug complexes.

Many algorithm-based platforms and predictive models are also available to support formulators in the selection of excipients and solubilisation methods, avoiding the need of extensive testing. The implementation of real-time adaptive manufacturing is another possible tool, useful to optimise the formulation on the basis of emerging clinical data.


A new role for EMA and a pilot project for the repurposing of medicines

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

by Giuliana Miglierini

A draft agreement was reached at the end of October between the Council of the European Union and the European Parliament to reinforce the mandate of the European Medicines Agency (EMA) with reference to crisis preparedness and management for medicinal products and medical devices. “EU-level preparation and coordination are two essential ingredients to fight future health crises. Thanks to this deal we are adding an essential new building block to upgrade the EU’s health architecture. It will allow the EU’s Medicines Agency to make sure we have the medicines needed to deal with public health emergencies”, said Janez Poklukar, the Slovenian minister for health.

The revision of EMA mandate is part of the broader activities announced by the EU Commission in November 2020 to achieve the European Health Union; these also include the reinforcement of the European Centre for Disease Prevention and Control and a draft law on cross-border health threats. The establishment of the new Health Emergency Preparedness and Response Authority (HERA), announced in September 2021, is also part of the package. The draft agreement shall now be endorsed both by the Council and the Parliament before entering into force.

Three new key targets for EMA

The draft agreement reached by the Council and Parliament negotiators focuses on three main areas. The first one refers to the definition of a major event and how to recognise it: these shall be events likely to pose a serious risk to public health in relation to medicinal products, as acknowledged by a positive opinion from the Medicines Shortages Steering Group, and which may trigger specific actions such as the adoption of a list of critical medicinal products to fight the health threat.

Solid funding from the Union budget shall be also provided to EMA in order to support the work of the new steering groups, task force, working parties and expert panels. The availability of provisions for adequate data protection is important to guarantee the full compliance to the GDPR regulation and other EU data protection rules, and the safe transfer of personal data relevant to EMA’s activities (e.g. data from clinical trials).

EMA shall play an improved role in the monitoring and management of shortages of medicines and medical devices, a critical activity for the availability of the products needed during public health emergencies. Other points of the agreement include the timely development of high-quality, safe and efficacious medicinal products, and the creation of a new EMA’s structure specific for expert panels in charge of the assessment of high-risk medical devices and of essential advice on crisis preparedness and management.

How to tackle shortages of medicines

According to the EU Parliament, two “shortages steering groups” (for medicines and medical devices, respectively) shall be created by EMA; if needed, these groups may also include expert advice from relevant stakeholders (e.g. patients and medical professionals, marketing authorization holders, wholesale distributors, etc.).

Parliament negotiators highlighted the importance to achieve a high transparency of the process, including avoidance of interests related to industry sectors for members of the two groups; summaries of the proceedings and recommendations shall be also made publicly available.

A European Shortages Monitoring Platform shall be created by EMA to facilitate the collection of information on shortages, supply and demand of medicinal products; a public webpage with information on shortages of critical medicines and medical devices shall be also made available.

As already occurred during the Covid pandemic, future public health emergencies may boost the development of new medicines and medical devices. Sponsors of clinical trials conducted during health emergencies will be required to make the study protocol publicly available in the EU clinical trials register at the start of the trial, as well as a summary of the results. Following the granting of the marketing authorisation, EMA will also publish product information with details of the conditions of use and clinical data received (e.g. anonymised personal data and no commercially confidential information).

With this agreement, Parliament makes both the Agency and all actors in the supply chain more transparent, involving them more in the process and fostering synergies between EU agencies. Moreover, we pave the way to promoting clinical trials for the development of vaccines and treatments, boosting transparency on those issues. In short, more transparency, more participation, more coordination, more effective monitoring and more prevention”, said Rapporteur Nicolás González Casares (S&D, ES).

EMA’s pilot project for the repurposing of medicines

The repurposing of already approved and marketed medicines is another key action put in place to ensure improved response capacity in case of future health emergencies.

A new pilot project to support the repurposing of off-patent medicines has been launched by EMA and the Heads of Medicines Agencies (HMA), with special focus on not-for-profit organisations and the academia as the main actors to carry out research activities needed to support the regulatory submission for the new indication. The initiative follows the outcomes reached by the European Commission’s Expert Group on Safe and Timely Access to Medicines for Patients (STAMP).

Interested sponsors may access EMA’s specific scientific advice upon submission of the drug repurposing submission form to the e-mail address [email protected] by 28 February 2022. More information is available in a Question-and-Answer document. The pilot will last until scientific advice for the selected repurposing candidate projects; filing of an application by a pharmaceutical company for the new indication is another target. Final results of the project will be published by EMA.

Comments from the industry

The European Federation of Pharmaceutical Industry Associations (EFPIA) welcomed the proposed framework for the repurposing of authorised medicines. “This pilot launch comes at a timely moment to test whether a streamlined and more transparent regulatory pathway for repurposing of off-patent established products increases the chances of including existing scientific evidence into regulatory assessment. One of the goals of the pilot is to raise awareness regarding the standards required for regulatory-ready evidence on the road to further increase availability of authorised therapeutic use”, said the chair of EFPIA’s Regulatory Strategy Committee Alan Morrison.

Innovation on existing, well-known molecules through repurposing can deliver huge benefits for patients, according to Medicines for Europe. The Association of the generic and biosimilar industry supports the pilot project as a way to generate robust data packages and to translate research into access for patients. A sustainable innovation ecosystem for off-patent medicine is the expected final outcome, possibly including also reformulation of existing medicines, new strengths or adaptation for specific patient groups (i.e. paediatric populations). “These investments must also be recognised in pricing and reimbursement policies to make access a reality for all patients”, writes Medicines for Europe.