AI drug discovery is a hot drug development method spreading in the United States and even Japan. Both venture companies and major pharmaceutical companies, regardless of size, are investing in and researching drug discovery using AI (Artificial Intelligence) technology, and the market scale is expanding.
Behind the focus on AI drug discovery are the challenges of drug discovery, such as declining success rates and soaring costs; AI has the potential to dramatically streamline the drug discovery process by deriving new insights from large amounts of known information with its high data processing power. AI utilization, especially in the basic research phase, is just beginning, and there are growing opportunities for major breakthroughs in target candidates and their hypothesis generation.
As a new approach to such drug discovery, FRONTEO has launched "Drug Discovery AI Factory," an AI drug discovery support service specializing in hypothesis generation. AI and biologists are combined to generate novel and highly successful target candidates and their hypotheses.
What is AI Drug Discovery?
- Pharmaceutical Companies are Accelerating Implementation
AI drug discovery is an approach that utilizes artificial intelligence (AI) technology to drive the development and research process of new drugs.
By taking advantage of AI's strength in processing large amounts of data, it can efficiently analyze vast amounts of research information and molecular data, which can be expected to discover promising new drug candidates and speed up the drug discovery process.
If the research and development process can be made significantly more efficient, it is expected to shorten development times and reduce costs, and contribute to the discovery of new treatments and drugs, as well as the treatment of intractable diseases. This is why pharmaceutical companies are increasingly implementing AI into drug discovery.
"First in class" is the Mainstream of Drug Discovery
A "first in class" strategy is essential for success in the drug discovery field. "First in class" refers to drugs with new mechanisms of action that are discovered through unconventional approaches.
First-in-class drugs are more difficult to develop since they are groundbreaking ideas, but once they are approved and launched on the market, there is no competition from similar drugs and sales can be expected.
However, the reality is that it is extremely difficult to propose new ideas, in other words highly novel target molecules, which are necessary for first-in-class drugs.
Challenges in Drug Discovery and Why AI Drug Discovery is Expected
Drug discovery, or drug development, takes a long time and costs a lot, and the declining success rate in bringing drugs to market is a major challenge.
AI, which is good at processing large amounts of data, is being increasingly adopted in clinical trials and other areas of drug development, and in recent years it has been used to optimize candidate compounds, thereby contributing to speeding up the development period.
However, this is only in the phase after the pipeline (new drug candidates) has been identified. To increase the success rate of "first in class" drug discovery, it is essential to select targets at the start of drug discovery and generate hypotheses that determine the path of research and development. This is where the utilization of AI is expected.
Urgent need to utilize AI in the first half phase of drug discovery
It is said that the utilization of AI has not yet progressed in the basic research phase, which is the start of drug discovery.
In the basic research phase, target selection is done by researchers based on papers, but there are issues such as relying on personal knowledge and being biased. The burden of predicting important disease mechanisms (estimating the connection between target candidates and diseases) is also high, and it is extremely difficult to find an AI drug discovery support company that can provide such hypotheses, not only in Japan but also in the rest of the world.
Supporting the Success of Drug Discovery
- FRONTEO Drug Discovery AI Factory
For the challenges of idea conception and target molecule search and selection at the beginning of drug discovery, FRONTEO launched the Drug Discovery AI Factory, which supports drug discovery with AI. It is a platform that generates and continuously supplies hypotheses to generate new ideas and directions in drug discovery research.
Target Identification
Disease-related target molecules can be searched for in tens of millions of papers by AI, and highly novel targets can be discovered in a short time. AI can also draw a network of related genes for the entire disease in just 10 minutes, resulting in new discoveries.
Drug Repositioning (DR)
In drug repositioning (DR), in which new efficacy of drugs are discovered from existing compounds and other modalities, and developed as curative medicine for other diseases, new insights and ideas such as unknown connections and possibilities, are generated by utilizing AI to cover all types of paper information.
Suppressor Mutation Genes
We can also search for suppressor mutations for diseases caused by loss-of-function mutations. By drawing a unique gene network that includes AI-predicted connections, we can understand the network between genes and its strength, and predict suppressor mutant genes.
DDAIF Enables the Generation of "Hypotheses"
as a Starting Point for Drug Discovery
The hypothesis to initiate the development of a new drug includes,
-Target molecule: A gene or molecule etc., that is predicted to be associated with a disease.
-Disease mechanism: How the target molecule is related to the disease, etc.
-Patient information: Genome information, diseases, symptoms, etc., of the target patient group.
-Safety information: Toxicity of the drug candidate, etc.
-Feasibility: Proposed experimental model, etc.
FRONTEO believes that all of these factors need to be considered.
“Drug Discovery AI Factory” makes it possible to generate hypotheses in a single step for everything from candidate target molecules to analysis of mechanisms of action, genome information on related diseases, and proposals for new drug safety as well as its experimental models, by maximizing the utilization of AI, which has the strength of analyzing vast amounts of data.
AI and Biologists
FRONTEO can analyze information and derive innovative outputs in the highly specialized field of drug development because of the presence of biologists with expertise in both drug discovery and AI.
FRONTEO Drug Discovery AI Factory's team of researchers consists of biologists with extensive knowledge in the life science field. We have a deep understanding of the needs of pharmaceutical companies, and use proprietary analysis methods based on our self-developed AI engine and applications to generate hypotheses.
Supporting Drug Discovery with Five Analysis Methods DD-BKM
The Drug Discovery Best Known Methods (DD-BKM), a fusion of FRONTEO's natural language processing AI "KIBIT" and drug discovery researchers. We will generate hypotheses while acquiring new clues.
-Common-Unique Pathway Analysis ~Comparing disease networks to find common and unique pathways~.
-Two-dimensional Mapping Analysis ~AI analysis of medical papers and mapping by conceptual similarity~.
-Vector Addition Analysis ~Finding important factors using a natural language approach~.
-Multifaceted Analysis ~Comprehensive analysis of multidimensional items to analyze the potential of a gene as a drug target~.
-Virtual Experiments ~Virtual knockout of genes and simulation of pathway changes~.
FRONTEO's Aim for AI Drug Discovery and Future Development
The key to a hypothesis, the beginning of drug discovery, is novelty and probability of success. FRONTEO's Drug Discovery AI Factory takes hints from AI that are beyond the human imagination, and uses the experience and knowledge of researchers to create a hypothesis that is not just a list of candidates, but one that is novel and has a high probability of success.
FRONTEO Drug Discovery AI Factory, as a platform specializing in hypothesis generation, will incorporate AI into the future drug discovery process to overwhelmingly shorten its cost and promote further social implementation of AI in the field of drug discovery.