Drug discovery is known as “bench-to-bedside” because of its long duration and high cost. It takes 11 to 16 years and about $1 billion to $2 billion to bring a drug to market. But now AI is revolutionizing drug development, offering better speed and profitability.
AI in drug development has changed our approach and strategy to biomedical research and innovation. It helped researchers to reduce the complexity of the disease process and identify biological targets.
Let’s take a closer look at what the future holds for drug discovery.
Understanding the role of AI: How is it being used for drug discovery?
AI has improved various stages of the drug discovery process due to its ability to analyze vast amounts of data and make complex predictions. Here’s how:
1. Target identification
Target identification is the first step in drug discovery, which involves combining proteins, enzymes and receptors in the body with drugs to produce therapeutic effects on diseases.
AI can use large clinical databases that contain key information about the target’s identity. These data sources may include biomedical research, biomolecular data, clinical trial data, protein structures, etc.
Trained AI models with biomedical techniques such as gene expression can understand complex biological diseases and identify biological targets for drug candidates. For example, researchers have developed various AI techniques to identify new anti-cancer targets.
2. Target selection
AI in drug discovery can help researchers select promising targets based on their disease correlates and predicted therapeutic utility. With robust pattern recognition, AI can select entirely new targets that have no prior reference in published patents, not just published medical literature.
3. Prioritize medication
At this stage, AI evaluates and guides drug combinations, prioritizing research to further evaluate and advance their development. Compared to previous ranking techniques, AI-based approaches are more effective in identifying the most promising candidates. For example, researchers have developed a computational framework based on deep learning to identify and prioritize new drugs for Alzheimer’s disease.
4. Compound filter
AI models can predict the chemical properties and bioactivity of compounds and provide insight into adverse effects. They can analyze data from a variety of sources, including previous studies and databases, to identify any risks or side effects associated with a particular compound. For example, researchers have developed deep learning tools to screen chemical libraries containing billions of molecules to dramatically speed up large-scale compound searches.
5. New drug design
Manual screening of large batches is a common practice in drug discovery. With AI, researchers can screen novel compounds with or without prior information and also predict the final 3D structure of the resulting drugs. For example, AlphaFold, developed by DeepMind, is an AI system that can predict protein structures. It contains a database of over 200 million protein structure predictions that can accelerate the drug design process.
5 examples of successful AI-based drug discovery
1) Abaucin
Antibiotics kill bacteria. But with a lack of new drugs and the rapid evolution of antibiotic resistance to older drugs, bacteria are becoming harder to treat. Abaucin, an AI-developed strong experimental antibiotic, is designed to kill Acinetobacter baumannii among the most dangerous superbug bacteria.
The researchers used AI to test thousands of drugs for the first time to see how well they worked against the bacterium Acinetobacter baumannii. This data is then used to train the AI to come up with a drug that can effectively treat it.
2) Target X in silico medicine
Insilico Medicine used its generative AI platform to develop a drug called Target X, now in Phase 1 clinical trials. Target X is designed for Idiopathic Pulmonary Fibrosis, a disease that can cause lung stiffness in older people if left untreated. Phase 1 includes 80 participants, and half receive a gradually higher dose. This helps to evaluate how the drug molecule interacts with the human body.
3) VRG50635 by Verge Genomics
Verge Genomics, an AI drug discovery company, used the AI platform CONVERGE to discover VRG-50635, a novel compound for the treatment of ALS, by analyzing human data points. The data points included information on brain and spinal cord tissue from patients with neurodegenerative diseases such as Parkinson’s, ALS and Alzheimer’s.
The platform first found the PIKfyve enzyme as a potential target for ALS and proposed VRG50635 as a promising PIKfyve inhibitor, which could be a candidate for treating ALS. The process took four years, and now the candidate is in phase 1 of human trials.
4) Knowledge-A2a receptor
Exyntia, an AI medtech company, is responsible for the first AI-designed molecule for immuno-oncology therapy – a type of cancer treatment that uses the body’s immune system to fight cancer cells. Their AI drug has entered the stage of human clinical trials. Its potential lies in its ability to target the A2a receptor to promote anti-tumor activity while ensuring minimal side effects on the body and brain.
Using generative AI, they have created some other compounds to attack different diseases
5) Absci-de Novo Antibodies with Zero-Shot Generating AI
Absci, a generative AI drug discovery company, has demonstrated the use of zero-shot generative AI for computer simulation of de novo antibodies. Zero-shot learning means that the AI model is not explicitly tested on the current input data during training. Therefore, this process itself can generate new antibodies.
AI-powered de novo therapeutic antibodies can cut the time it takes to develop new drugs from six years to 18 to 24 months, increasing their chances of success in the clinic. The company’s technology can test and validate 3 million AI-generated designs every week. This new development could deliver novel treatments to every patient immediately, representing a significant industry shift.
What does the future of AI and drug discovery hold?
In addition to its many healthcare applications, AI can make the drug discovery process faster and smarter by analyzing vast data sets and predicting promising drug targets and candidates. Using generative AI, biotech companies can identify indicators of patient response and rapidly develop personalized treatment plans.
A report suggests that soon more medtech companies will incorporate AI and ML into early-stage drug discovery, helping to create a $50 billion market over the next ten years, making AI in pharmaceuticals a huge growth potential. AI can reduce overall drug discovery costs, making more new drugs available to patients more quickly.
If you want to learn more about AI and how it will shape our future, visit unite.ai.
[ad_2]