Lowered Cost of Protein Production, Thanks to AI.

  Researchers at the Michigan Institute of Technology found a way to using artificial intelligence to make the production of protein cheaper. The article explains the importance of industrial yeast and how it is the main contributor to the production of protein and how it is responsible for the manufacturing of vaccines. The AI tool observed the genetic code of a yeast and used that information to predict the best codons for manufacturing.  This AI tool showed to enhance the yeast's production of six different proteins. J. Christopher Love, Professor of Chemical Engineering at MIT, described predictive tools to be time efficient and save money.

Figure 1. K. phaffi is a type of yeast the model learned pattens of codon from in this project and it is important in the biopharmaceutical industry. 

    Technology is constantly evolving and scientists and researchers should take advantage of the possibilities that it brings.  I agree, using artificial intelligence in science could be scary because of potential errors, but this model bases its predictions off of observations of other genetic codes. This article mentioned that the model was trained in trastuzumab, which is an antibody used for cancer treatment. Using this model has the abilities lower costs of production of vaccines and other important compounds that are currently needed. I believe if this research is able to save time on protein production, and ultimately help people, it should definitely be used. 

Source: 

https://news.mit.edu/2026/new-ai-model-could-cut-costs-developing-protein-drugs-0216 

Another source on this topic:

https://nationaltoday.com/us/ma/cambridge/news/2026/02/18/ai-model-may-slash-protein-drug-development-costs/

A New Digital Breakthrough for Early Dementia Detection

A New Digital Breakthrough for Early Dementia Detection

    Alzheimer's disease is a process in which the appearance of buildup proteins in the form of amyloid plaques and neurofibrillary tangles occurs in the brain. This causes the brain cells to die and shrink over time. This disease is a common cause of dementia [2]. This disease has been hard for doctors in primary care to detect in its early stages, so researchers have been developing artificial intelligence to detect it early with no extra cost or time.

    The researchers at Indiana University School of Medicine, the Regenstrief Institute, Eskenazi Health, the University of Miami, and Lamar University used a digital method to test older patients in which each patient automatically received a 10-question survey called the Quick Dementia Rating System through the patient portal. At the same time, an AI tool scanned patients' electronic health records in the background for early signs of dementia [1]. It scans for clues linked to dementia, such as memory concerns or vascular issues. This program runs silently in the background of the health system, and doctors only get alerted when something looks concerning.

    This system was tested in over 5,000 patients. The results show that the AI survey approach increased new dementia diagnoses by 31% within one year without additional work for doctors. The survey also helped raise up follow-up tests, such as brain scans and cognitive assessments, by 41%. This new digital survey is giving patients access to help much sooner than before [1]. 

    I think this approach is a step forward in dementia detection because of how much faster it detects, as well as making it easier for primary care doctors. Since the AI tool is free and works in the background, it helps clinics use it without extra time or resources. Seeing AI used this way shows how it can be used to improve patient care. I think this is a great use of AI and how this early detection can happen quickly and quietly, giving the patients a better chance to get help before the disease worsens. 

Resources

[1]S. Ktori, “New AI Tool Boosts Early Detection of Dementia in Primary Care,” GEN - Genetic Engineering and Biotechnology News, Nov. 10, 2025. https://www.genengnews.com/topics/artificial-intelligence/new-ai-tool-boosts-early-detection-of-dementia-in-primary-care/ (accessed Nov. 13, 2025).

[2]Mayo Clinic, “Alzheimer’s disease,” Mayo Clinic, Nov. 08, 2024. https://www.mayoclinic.org/diseases-conditions/alzheimers-disease/symptoms-causes/syc-20350447

[3]M. A. Boustani et al., “Digital Detection of Dementia in Primary Care,” JAMA Network Open, vol. 8, no. 11, pp. e2542222–e2542222, Nov. 2025, doi: https://doi.org/10.1001/jamanetworkopen.2025.42222.

AI and Genetics : A Smarter Way to Predict Disease

           

             A new study from Mount Sinai School of Medicine has taken to AI to predict the likelihood of rare genetic mutations that cause disease. They have created a machine that can assign a ‘penetrance score’ to genetic variants that foresee the probability of a mutation inside the genome that can lead to disease.

The AI machinery was programed by using data from over 1 million health records that contained information on common diseases and everyday lab tests. This allowed the model to assess the real-world impact of genetic variants, providing a ‘spectrum of risk’ rather than a 100% yes or 100% no determination of the mutation. According to the MSSM the models scores offer a more accurate prediction of disease risks associated with specific genetic variant. It can qualitatively and quantitatively assess the likelihood of premature disease and health care workers can provide patients with a preventative outlook on their health and make patients aware of any preventative measures necessary to get ahead of any diseases. 

         

Looking in the future with a machine such as this, it expands the knowledge and broadens the range of different outcomes individualized to specific genetic profiles. The MSSM also plans to expand the AI model to broaden its range of disease and genetic variants to help ‘diverse populations’ as well as being a better tool across all the different genetic backgrounds there are in the world. In a world where AI has perhaps become a bad thing, this is what the future needs it for. 

AI-designed DNA Controls Genes in Mammalian Cells For the First Time

    A study carried out at the Centre for Genomic Regulation(CGR) in Barcelona, had recently discovered the first reported instance of generative AI designing synthetic molecules that can successfully control gene expression in healthy mammalian cells. The model can be told to create synthetic fragments of DNA with custom criteria, and then predict which combination of nucleotides (A, T, C, G) are needed for the gene expression patterns required in specific types of cells. Researchers then chemically synthesized roughly 250 nucleotide DNA fragments and then add them to a virus, which will then carry the modified DNA into a desired cell. 

    For proof that the AI modification was successful, researchers asked the AI to design synthetic fragments that activate a gene coding for a fluorescent protein in certain cells while leaving other gene expression patterns untouched. They created the desired fragments from scratch and transferred them into a mouse's genome, where the modified sequence fused with the mouse's genome in random places. The results of this study could be used to find new ways for gene therapy developers to boost or weaken the activity of genes in certain cells or tissues. This use of AI can also be used to find alter a person's genes and make treatments more effective and reduce side effects. This concept hasn't been tested yet, but researchers intend to start investigating this soon. AI-generated enhancers can help engineer ultra-selective switches that can be designed to have specific on/off patterns required in specific types of cells. A level of accuracy which is crucial for creating therapies that avoid unintended effects in healthy cells.

AI helping diagnose neurodevelopmental disorders?

 

    A group of researchers from Texas Children's Hospital and Baylor College of Medicine came up with an advanced AI tool that’s helping scientists figure out which genes are involved in brain development disorders like autism, epilepsy, and developmental delays. Basically, the AI looks at genes we already know are linked to these conditions and uses that info to guess which other genes might also be involved. It pulls in loads of data, including stuff from developing human brains to make its predictions. What’s really cool? It can spot both dominant and recessive gene mutations. This means faster and more accurate diagnoses for kids, and maybe even better treatments down the line. Bottom line, AI is making gene research faster, smarter, and way more powerful. This could be a game-changer for understanding and treating developmental disorders.

    My opinion: I think this is an extremely out of the box way of thinking, but in a good way. It shows that we are able to use AI in a multitude of ways. Caution should be taken as well, because AI was created by humans and humans are not perfect. I say this to shed light on AI helping with the tedious objectives, it's important to note that we check over its work. 

Link to article: New AI tool enhances discovery of genes involved in neurodevelopmental conditions

AI tool detects health-threatening genetic variants in vast haystacks.

Scientists have developed a way to sift through a person's genetic blueprint to find disease-causing variants. An issue that has frustrated doctors is that each human has an average of 4 million variants, sections of genetic code where we are different. Kyle Farh is the vice president of AI at the biotechnology company Illumina, where he and his team created an algorithm called PrimateAI-3D, using the genetic blueprints of 233 different primate species. The scientist looks for areas where the sequence is the same from one primate to another, which is a sign that any change is a problem. The new AI algorithm has a selection 1000 times as large as the archive used in most hospitals, ClinVar. PrimateAI-3D shows the three-dimensional structure of proteins, which can distinguish which mutations are harmful. 

They have tested the new tool on a biomedical database of more than 450,000 people in the United Kingdom’s Biobank. They found 97% of the population carried a rare variant that has an effect on health. With this new tool, they are able to predict health factors from the genome. Genomes are codes made up of four different chemical bases that build up DNA. One genome comprises approximately 3,200,000,000 nucleotides of DNA. In my opinion, having an AI model for something so complicated makes a lot of sense, and I don’t understand why it wasn’t implemented before. Machines have been running code in computer systems and figuring out the coordinates that send astronauts to space for decades. I think using artificial intelligence in this fashion is a great way to utilize the resources that are taking over many aspects of our daily lives.