For our synthetic datasets, we conduct two additional rounds of instruction evolution to increase complexity. As shown in Figure 3, the scores of instructions across the three datasets consistently increase.

Cancer is a disease characterized by the abnormal growth and division of cells in the body. Tumors can affect any part of the body and can be benign (non-cancerous) or malignant (cancerous), spreading to other parts of the body through the bloodstream or lymph system. Scientists at the University of California, San Francisco (UCSF) and IBM Research have created a virtual library of thousands of "command sentences" for cells using machine learning. These "sentences" are based on combinations of "words" that direct engineered immune cells to find and continuously eliminate cancer cells. This research, which was recently published in the journal Science, is the first time that advanced computational techniques have been applied to a field that has traditionally progressed through trial-and-error experimentation and the use of pre-existing molecules rather than synthetic ones to engineer cells.

Using new machine learning techniques, researchers at UC San Francisco (UCSF), in collaboration with a team at IBM Research, have developed a virtual molecular library of thousands of "command sentences" for cells, based on combinations of "words" that guided engineered immune cells to seek out and tirelessly kill cancer cells. The work, published online Dec. 8, 2022, in Science, represents the first time such sophisticated computational approaches have been applied to a field that, until now, has progressed largely through ad hoc tinkering and engineering cells with existing, rather than synthesized, molecules. The advance allows scientists to predict which elements -- natural or synthesized -- they should include in a cell to give it the precise behaviors required to respond effectively to complex diseases. "This is a vital shift for the field," said Wendell Lim, PhD, the Byers Distinguished Professor of Cellular and Molecular Pharmacology, who directs the UCSF Cell Design Institute and led the study. "Only by having that power of prediction can we get to a place where we can rapidly design new cellular therapies that carry out the desired activities."

Using new machine learning techniques, researchers at UC San Francisco (UCSF), in collaboration with a team at IBM Research, have developed a virtual molecular library of thousands of "command sentences" for cells, based on combinations of "words" that guided engineered immune cells to seek out and tirelessly kill cancer cells. The work, published online Dec. 8, 2022, in Science, represents the first time such sophisticated computational approaches have been applied to a field that until now has progressed largely through ad hoc tinkering and engineering cells with existing--rather than synthesized--molecules. The advance allows scientists to predict which elements--natural or synthesized--they should include in a cell to give it the precise behaviors required to respond effectively to complex diseases. "This is a vital shift for the field," said Wendell Lim, Ph.D., the Byers Distinguished Professor of Cellular and Molecular Pharmacology, who directs the UCSF Cell Design Institute and led the study. "Only by having that power of prediction can we get to a place where we can rapidly design new cellular therapies that carry out the desired activities."

As the CEO of one of the top global AI-powered biotechnology companies, I regularly get to see some of the world's most innovative techno parks and biotechnology hubs that are popping up all over the world. Over the past couple of years, I traveled to several such centers in the US, Canada, China, Singapore, and the Middle East. We even established one of our R&D centers at the Hong Kong Science and Technology Park. All of these centers have their advantages and disadvantages that often go in line with the government policies and I will try to cover some of these centers in my future posts and make a comparison. So far, some of the most impressive biotechnology hubs are in China and in Singapore.

There is no longer any doubt that artificial intelligence (AI) is advancing biological discovery and biomanufacturing operations. In biological discovery, AI systems such as AlphaFold and the Atomic Rotationally Equivariant Scorer are celebrated for their uncanny ability to predict tertiary structures for proteins and RNA molecules. In biomanufacturing, AI systems usually enjoy less fanfare. Yet they can provide valuable functions such as pattern recognition, real-time assessment of batch quality, multivariable control for continuous manufacturing, prediction/optimization of critical process parameters, and anomaly detection. Such functions are critical to the success of gene and cell therapy operations.

Stem cell therapy comes with its own set of challenges despite being a revolutionary discovery in modern healthcare. As we know, AI has several applications in the deep and diverse field of healthcare. So, stem cell AI's incredible capabilities can overcome those challenges and truly improve stem cell therapy in hospitals. Stem cell therapy, or regenerative cell therapy, is an operation that attempts to repair or replace diseased, dysfunctional or ruptured tissues in the body using stem cells. Stem cell therapy is an evolution of organ transplantation.

Cambridge, UK-based biotech startup Mogrify, which is working on systematizing the development of novel cell therapies in areas such as regenerative medicine, has closed an initial $16 million Series A. The raise follows a $4M seed in February -- taking its total raised to date to $20M. Put simply, Mogrify's approach entails analysis of vast amounts of genomic data in order to identify the specific energetic changes needed to flip an adult cell from one type to another without having to reset it to a stem cell state -- with huge potential utility for a wide variety of therapeutic use-cases. "What we're trying to do with Mogrify is systematize that process where you can say here's my source cell, here's my target cell, here are the differences between the networks… and here are the most likely points of intervention that we're going to have to make to drive the fate of an adult cell to another adult cell without going through a stem cell stage," says CEO and investor Dr Darrin Disley. So far he says it's successfully converted 15 cells out of 15 tries. "We're now rapidly moving those on through our own programs and partnership programs," he adds.

OncoImmunity AS will now become a subsidiary of NEC and operate under the name of NEC OncoImmunity AS. OncoImmunity AS, founded in 2014, is a bioinformatics company dedicated to the development of software solutions that facilitate the effective selection of patients for cancer immunotherapy, and identify optimal neoantigen targets for truly personalized cancer vaccines and cell therapies in a clinically actionable time frame. NEC announced its business strategy surrounding its AI-driven drug discovery business in May 2019. This acquisition is integral for enhancing the resources and capabilities that support the development of its individualized immunotherapy pipelines. NEC will maintain its focus on drug discovery, while NEC OncoImmunity AS continues its neoantigen prediction services.