Using the heart as an investigational model, scientists at the Broad Institute of MIT and Harvard have designed an autoencoder-based machine-learning pipeline that can effectively predict a patient’s heart condition based on image data from ECGs and MRIs. The approach could also be used to detect markers related to cardiovascular diseases.
Nearly all areas of medical science have utilized artificial intelligence (AI) over the years. It has been effectively diagnosing diseases and predicting their transmission and prognosis. AI has been used to design therapeutic approaches effectively and has been helpful in the field of drug design. The use of AI in studying cardiovascular diseases has come a long way, especially machine learning-based systems. AI-based algorithms can be trained to predict cardiovascular disease outcomes using available diagnostic imaging technology.
Currently, the field of cardiology uses a variety of imaging technologies, such as ultrasound imaging, magnetic resonance imaging (MRI), computed tomography (CT), etc. The Electrocardiogram (ECG) is a widely used test to monitor the heart’s rhythm. These technologies generate a lot of data that can be utilized to analyze the condition of a person’s heart. The availability of several diagnostic modalities has raised the need for standardized tools for analyzing imaging data effectively. A multi-modal framework built on machine learning techniques has been suggested by researchers from The Broad Institute of MIT and Harvard. The proposed system can help doctors to understand the cardiovascular state of a person using data from MRIs and ECGs. In practice, clinicians can use data generated from the machine learning program to diagnose a patient appropriately.
Continue Reading
hi i hate being perceived on the internet 99% of the time but you should take this quiz i made about the immune system
what is she doing!! ~~~~ why!!!
With the fast fashion industry… how it is… finding sustainable ways to make fabric is super important. Fibers from synthetic fabrics make up 35% of the microplastics that make their way to the ocean. Natural fibers sourced from plants or animals are much more environmentally sound options, including silk.
Currently, the only way to get natural silk on a large scale is to harvest it from silkworms. You’ve probably heard about the strength and durability of spider silk (it is 6x stronger than Kevlar!) but as of yet there hasn’t been a good way of getting it. Raising spiders the way people do silkworms isn’t really an option. Spiders need a lot of room to build their webs compared to silkworms, and individual spiders don’t produce that much silk. Plus, when you put a whole bunch of spiders in captivity together, they tend to start eating each other.
Attempts to artificially recreate spider silk have also been less than successful. Spider silk has a surface layer of glycoproteins and lipids on it that works as a sort of anti-aging “skin”- allowing the silk to withstand conditions such as sunlight and humidity. But this layer has been very tricky to reproduce.
However, as scientists in China realized, silkworms produce that same kind of layer on their silk. So what if we just genetically modified silkworms to produce spider silk?
That is exactly what the researchers at Donghua University in Shanghai did. A team of researchers introduced spider silk protein genes to silkworms using CRISPR-Cas9 gene editing and microinjections in silkworm eggs. In addition to this, they altered the spider silk proteins so that they would interact properly with the other proteins in silkworm glands. And it worked! This is the first study ever to produce full length spider silk proteins from silkworms.
The applications of this are incredibly exciting. In addition to producing comfortable textiles and new, innovative bulletproof vests, silkworm generated spider silk could be used in cutting edge smart materials or even just to create better performing sutures. In the future, this team intends to research how to modify this new spider silk to be even stronger, and they are confident that “large-scale commercialization is on the horizon."
Cancer is one of the prominent causes of death globally, and discovering new methods to prevent and cure it is important for public health. Understanding the particular nutrients that cancer cells require is one of the strategies researchers are investigating to fight the disease.
Arginine is one of the important amino acids produced by our bodies naturally, and it is also abundantly found in food sources such as fish, meat, and nuts. According to the research published in Science Advances, cancer cells also need arginine to survive. It is possible to make tumors more susceptible to the body’s natural immune system and improve the effectiveness of treatment by depriving them of this nutrient.
The lack of this amino acid, which the researchers discovered to exist in various types of human cancers, forces the cancer cells to adapt. Cancer cells alter specific proteins to improve their ability to absorb arginine and other amino acids when their levels of that amino acid fall. Amazingly, these cells also induce mutations that lessen their reliance on arginine in an effort to keep growing.
Continue Reading
I sometimes think about bacteria growing on (in?) an agar plate and how strange it must be from their perspective. To be taken from your (many times hostile) natural habitat and placed in (on?) an alien landscape made entirely of food that caters perfectly to your dietary needs. You live there, and your descendants thrive there for generations after, and then comes a Cataclysm. And they die in an inferno of steam and pressure, suddenly and unexpectedly.
And you never knew you were the fortunate ones. Your brethren lived their lives in other equally alien worlds, except theirs were tailored to kill them, torture them, or starve them of necessary nutrients. Their torment and your bliss serve a purpose ufathomable to you, a purpose of creatures so vast and unknowable, they might as well be Gods.
I think about bacteria sometimes.
Scientists from BGI-Research developed a new version of the Cultivated Genome Reference (CGR), a repository of high-quality draft genomes of the human gut microbiome. The current version of CGR, which is CGR2, has been further expanded to incorporate numerous high-quality draft genomes generated from cultivated bacteria. CGR2 classifies previously unidentified species and uncovers the functional and genomic diversity of bacterial strains. An in-depth analysis of carbohydrate-active enzymes (CAzymes) reveals the phyla with the largest and most diverse repertoires of these enzymes. CGR2 also enabled the identification of genes involved in the synthesis of secondary metabolites in the gut microbiome. The unraveling of the gut microbiome genomic landscape will enable the development of therapeutics and provide a deep insight into the evolution of the human gut microbiome.
Continue Reading