Artificial Intelligence Can Accurately Predict Human Response to New Drug Compounds
The journey from identifying a potential therapeutic compound to FDA approval of a new drug can take well over a decade and cost well over a billion dollars. A team of CITY UNIVERSITY OF NEW YORK Graduate from Center researchers has developed a novel artificial intelligence model that could significantly improve the accuracy and reduce the time and cost of the drug development process.
The new model, called CODE-AE, can screen novel drug compounds to accurately predict efficacy in humans, according to a paper to be published today (October 17) in Nature Machine Intelligence. It was also able to identify personalized drugs for over 9,000 patients in tests, which could help treat their conditions. Scientists anticipate that the technique will significantly speed up drug discovery and precision medicine.
Accurate and robust prediction of patient-specific responses to a new chemical compound is critical for developing safe and effective therapeutics, as well as selecting an existing drug for a specific patient. However, directly testing a drug's efficacy in humans is unethical and impossible. To evaluate the therapeutic effect of a drug molecule, cell or tissue models are frequently used as a surrogate of the human body. Unfortunately, drug efficacy and toxicity in human patients do not always correlate with drug effect in a disease model. This knowledge gap is a major contributor to drug discovery's high costs and low productivity rates.
"Our new machine learning model can address the translational challenge from disease models to humans," said Lei Xie, senior author of the paper and a professor of computer science, biology, and biochemistry at the CITY UNIVERSITY OF NEW YORK Graduate from Center and Hunter College. "CODE-AE employs biology-inspired design and makes use of recent advances in machine learning." One of its components, for example, employs similar techniques in Deepfake image generation."
According to You Wu, a CITY UNIVERSITY OF NEW YORK Graduate from Center Ph.D. student and co-author of the paper, the new model can provide a solution to the problem of not having enough patient data to train a generalized machine learning model. "Although many methods for using cell-line screens to predict clinical responses have been developed, Wu said, "their performances are unreliable due to data incongruity and discrepancies." "CODE-AE effectively alleviated the data-discrepancy problem by extracting intrinsic biological signals masked by noise and confounding factors."
As a result, CODE-AE significantly outperforms state-of-the-art methods in predicting patient-specific drug responses based solely on cell-line compound screens.
The next challenge for the research team in advancing the technology's use in drug discovery is to develop a method for CODE-AE to predict the effect of a new drug's concentration and metallization human bodies. The researchers also mentioned that the AI model could be tweaked to accurately predict drug side effects in humans.
10,000 Times Quicker: New Breakthrough Could Change The Field Of Medical Micro Robots
Biodegradable micro robots that dissolve into the body after delivering cells and medications have been mass-produced by scientists.
Professor Hongsoo Choi's team at the Daegu Gyeongbuk Institute of Science & Technology collaborated with Professor Sung-Won Kim's team at Seoul St. Mary's Hospital, Catholic University of Korea, and Professor Bradley J. Nelson's team at ETH Zurich to develop a technology that can produce more than 100 micro robots per minute that can be disintegrated in the body.
There are numerous approaches to developing micro robots for minimally invasive targeted precision treatment. The ultra-fine 3D printing process known as the two-photon polymerization method, which triggers polymerization in synthetic resin by intersecting two lasers, is the most popular.
This technique can create structures with nanometer-level precision. The disadvantage is that creating a single micro robot takes a long time because voxels, or 3D-printed pixels, must be cured sequentially. Furthermore, the magnetic nanoparticles in the robot may block the light path during the two-photon polymerization process. The process result may not be uniform when highly concentrated magnetic nanoparticles are used.
To overcome the limitations of the current micro robot production technique, DGIST Professor Hongsoo Choi's research team developed a method for producing micro robots at a high speed of 100 per minute by flowing a mixture of magnetic nanoparticles and biodegradable gelatin methacrylate, which can be cured by light, onto a microfluidic chip. When compared to the existing two-photon polymerization method, this method can produce micro robots 10,000 times faster.
The micro robot created with this technology was then cultured with human nasal turbinates stem cells collected from the human nose to induce stem cell adherence to the micro robot's surface. A stem cell with a micro robot inside and stem cells attached to the outside surface was created using this method. The robot moves as the magnetic nanoparticles within it respond to an external magnetic field and can be moved to the desired position.
In the case of existing stem cell therapy, selective cell delivery was difficult. The stem cell-carrying micro robot, on the other hand, can move to the desired location in real-time by controlling the magnetic field generated by the electromagnetic field control system. The researchers experimented to see if the stem cell-carrying micro robot could reach the target point by passing through a maze-shaped microchannel, and the robot was able to move to the desired location.
Furthermore, the micro robot's degradability was assessed by incubating the stem cell harboring the micro robot with a degrading enzyme. The micro robot was entirely dissolved after 6 hours of incubation, and the magnetic nanoparticles inside the robot were gathered by the magnetic field generated by the magnetic field control system. Stem cells proliferated near the site of the micro robot's disintegration. Following that, the stem cells were stimulated to differentiate into nerve cells to demonstrate correct differentiation; the stem cells differentiated into nerve cells after about 21 days. This investigation demonstrated that using a micro robot to deliver stem cells to a specific site was feasible and that the delivered stem cells might function as a targeted precision therapeutic agent by demonstrating proliferation and differentiation.
The researchers also confirmed that the stem cells transported by the micro robot had normal electrical and physiological properties. The study's ultimate goal is to ensure that the stem cells delivered by the robot normally perform their bridge role when the connection between the existing nerve cells is severed. Hippocampal neurons taken from rat embryos that transmit electrical signals stably were used to corroborate this. The equivalent cell was attached to the micro robot's surface, cultivated on a micro-sized electrode chip, and electrical impulses from hippocampus neurons were observed after 28 days. The micro robot's ability to function as a cell delivery platform was therefore validated.
"We expect that the technologies developed through this study, such as mass production of micro robots, precise operation by electromagnetic fields, and stem cell delivery and differentiation, will dramatically increase the efficiency of targeted precision therapy in the future," said DGIST Professor Hongsoo Choi.
You must be logged in to post a comment.