AseBio analyzes the use and barriers of digital tools in the Drug Discovery process
The Drug Discovery Working Group of AseBio has developed the document "New Technologies in the Drug Discovery Process," addressing trends and barriers in the biotech sector regarding the use of digital tools for discovering new drugs.

AseBio presents the document "New Technologies in the Drug Discovery Process", developed through its Drug Discovery Working Group. The discovery of new drugs plays a fundamental role in providing solutions to diseases without therapeutic options, such as the nearly 7,000 rare diseases identified by the World Health Organization (WHO).
This global issue will be addressed in the upcoming edition of BIOSPAIN, a leading international biotechnology sector event organized by AseBio in collaboration with Biocat, the Ajuntament de Barcelona, and the Generalitat de Catalunya, from September 26 to 28 in Barcelona.
The current economic model and the development of new technologies have resulted in an increasingly widespread use of digital tools. Big Data, Machine Learning, Internet of Things (IoT), or Artificial Intelligence (AI), among others, are tools becoming more necessary for business development, and biotechnology is not exempt from this change. The document aims to identify trends in the use of these digital tools among AseBio member companies and highlight the current barriers hindering their implementation.
There are thousands of diseases, but only 50 drugs are approved each year.
"There are thousands of diseases, but only 50 drugs are approved each year. The use of artificial intelligence is demonstrating a significant increase in pharmaceutical productivity. This paradigm shift will soon translate into more approved drugs and, therefore, access to new treatments for patients in need," states Javier Terriente, Vice President and Coordinator of the Drug Discovery Working Group at AseBio and founder of ZeClinics and ZeCardio Therapeutics.
The adoption of these digital tools by biotechnology companies has generated a significant impact, such as the creation of new departments focused on ensuring data quality and management or the diversification of teams, which are no longer composed solely of researchers but also include computer scientists. Additionally, the implementation of these tools in biotechnology companies involves modifying and standardizing their processes to ensure, among other tasks, the proper treatment of data.
“Digital tools (including AI/Machine learning methods) are having a considerable impact throughout the drug development value chain in the pharmaceutical industry (R&D)”, emphasizes Francesc Fernández Albert, Data Science Director at Almirall. “At Almirall, we have established a data science department in R&D with the goal of using these technologies in two critical aspects: accelerating informed decision-making and improving the ability to generate key information at different stages of our projects. For example, by integrating large amounts of high-quality data, we can identify therapeutic targets more reliably. We also use artificial intelligence tools to design new drugs.”
Big Data and Artificial Intelligence, the most widely used technologies.
According to the document, Big Data (79%) and Artificial Intelligence (68%) are the most widely used digital technologies among the member entities that have participated in the development of "Las nuevas tech en el proceso de Drug Discovery" (New Technologies in the Drug Discovery Process).
In the field of biotechnology, and particularly in Drug Discovery, Big Data is primarily used for analyzing information from molecular structures (proteins, RNA, chemical molecules, etc.) (53%), transcriptomic information (37%), genomic (32%), or proteomic (32%) data, among others. Through the use of this technology, knowledge can be extracted from data, and patterns and trends can be identified, enabling the research and development of innovative biotechnological solutions in areas such as precision medicine, gene therapy, pharmacogenomics, and systems biology.
Within the group of Artificial Intelligence-based digital tools, the use of Machine Learning (58%) and advanced statistical methods for drug discovery (42%) stands out. In this regard, it is worth noting the growth in the use of virtual reality (21%) for data storage and visualization, although it is not yet intensively used in Drug Discovery processes.
Digital tools are constantly evolving, and currently, there is a wide range of them. The Internet of Things (IoT) and Computer Science, although used to a lesser extent, are also employed in Drug Discovery processes for data storage, visualization, and certification.
The document's overview reveals that the application of digital tools in the discovery of new drugs occurs primarily in the phase of discovering new chemical therapeutic molecules (60%), new biomarkers (52%), or for virtual screening (44%).
The lack of professionals with knowledge of digital tools and biotechnology, one of the barriers.
Among the most common internal barriers that biotechnology companies face when implementing digital tools, the lack of available professionals with knowledge of both the biotech sector and the technologies themselves stands out.
The document highlights other barriers such as internal adaptation issues to new processes and ways of working, data standardization, and the high investment required for the implementation of these digital tools.
Speaking of external barriers, one of the most frequently mentioned is the lack of funding programs to implement new digital tools, in addition to the limited access currently available to databases.
It is worth noting at this point that, based on current regulations, in many cases, drugs or targets identified using Artificial Intelligence also have to undergo the traditional approval process.
How can the adoption of digital tools be expedited?
One of the main demands presented as a way to overcome the obstacles faced in the implementation of digital tools in the biotechnological sector is the promotion of new university programs that integrate biotechnology with technological knowledge. Additionally, there is a need for complementary training plans with technology in different fields.
The document emphasizes the need for funding programs focused on promoting this technological transition. Other requirements that would facilitate the adoption of digital tools in the biotech sector are also highlighted, such as having a well-structured database that can be jointly maintained by public and private entities.
Finally, it is necessary to promote the promotion of consortia between companies and public institutions to encourage their interaction and technological implementation.