Data Science for Science

The Coma Cluster contains more than 1,000 galaxies. Scientists have long been frustrated by large uncertainties in its mass. Credit: PSC  A galaxy, as you may know, is a huge collection of stars that has a certain overall shape and which moves as a unit across the cosmos. Even larger groupings such as galaxy clusters  exist. The individual galaxies in a cluster move about relative to each other and revolve around their common center of mass. Their velocities relative to our observation point can be gleaned from measurements of their red-shifts or blue-shifts.  Estimation of the mass of galaxy clusters is still fraught with uncertainties. It is not yet clear how to determine the three-dimensional structure of galaxy clusters which reduces further the confidence of estimating the mass.  But why estimate the mass? It is now known that stars in a galaxy revolve around the center of mass of the galaxy. But their velocities exceed the calculated velocity based on the dete...

  Hello! Today we have an entry in the field of medicine. What is skin cancer recurrence? An early-stage skin cancer type called  melanoma  is treatable if diagnosed early enough. Most melanoma deaths in the US occur because of recurrence of the disease which was early stage at the time of diagnosis. However, recurrence is not detected until the cancer starts to spread; called symptomatic metastatic progression. This is where prognostic tools can be helpful for regular surveillance and quick action to stave off mortality and ensure health. Also, identifying high-risk patients can help in determining who should receive special therapies and treatments. Enter Machine Learning. A team led by investigators at Massachusetts General Hospital performed two types Machine Learning prediction with nine different models: Melanoma Recurrence Classification: Where the prediction would be a probability that melanoma recurrence would occur. Time-To-Event Melanoma Recurrence Risk Predict...

      (Credit: Retinal scan courtesy UK Biobank) Artificial Intelligence can now identify patients with a high risk of heart attack just by an eye scan that can be taken at an optician or eye clinic. Sounds too good to be true? The size and pumping efficiency of the left ventricle (one of the four chambers) of the heart is linked to risk of heart attack. An oversized left-ventricle leads to higher risk of heart disease. In turn, the retinal scans are linked to the size and pumping efficiency of the left ventricle. Currently, risk of heart disease can be determined through expensive diagnostic tests using MRI and ECG which are available only in a hospital setting. These tests are also unavailable in less well-resourced healthcare systems in developing countries and unnecessarily increase healthcare costs in developed countries.  Retinal scans on the other hand are comparatively cheap and available in many optician practices. Patients who are found to be at high risk...

    (Photo credit: BBC) Are We Alone?  It is a question that humans have had ever since we realized there are other worlds, other planets out there in the cosmos. The implications of the answer to this question are staggering no matter what that answer is. In pursuit of an answer scientists have been searching for planets that could potentially harbor life. Planets that are outside of our solar system are termed Exoplanets. The exploratory pursuit is to find "earth-like" exoplanets because these would have the greatest chance of harboring life as we know it. Determining the habitability of exoplanets is not an easy task. Existing ML methods such as Metric-based quantification (using metrics like surface temperature) or Supervised Learning (based mainly on estimated surface temperature) are not reliable enough.  Astronomers from the Indian Institute of Astrophysics along with astronomers from BITS Pilani and Goa campus designed an anomaly detection method to identify ...

  Drug development for the treatment of various diseases is the cornerstone of medicine for human health. Drug development is an expensive and time-consuming process. Most drugs developed up to the human-trials stage end up having no effect at all or too many side-effects. These drugs are thus discarded resulting in wasted time, money and effort. The cost of these drugs end up on the price tags of drugs that do become successful. Before drug development can even take place the drug discovery process must occur. Briefly, drug discovery involves a process of finding promising drug-like molecules that can bind or "dock" properly onto certain protein targets. After successfully docking to the protein, the binding drug, also known as the ligand, can stop a protein from functioning. If this happens to an essential protein of a bacterium, it can kill the bacterium, conferring protection to the human body. Drug discovery, the process of discovering new candidate medications, involves...

Hubble Deep Field. Courtesy: Encyclopedia Britannica Space is vast. The number of objects in the Universe is literally astronomical. The first step toward exploring these objects is to identify them aka classify them. Objects could be stars, galaxies, quasars, supernovae etc. Due to the sheer number and complexity of objects the task is very challenging to do manually. The further away a source of light is, the harder it is to distinguish its features and thus classify it. Astronomers have now sought the aid of AI in this task. A machine learning pipeline called SHEEP has been developed. SHEEP first extracts the photometric redshift of celestial objects and then uses this as one of the data features fed into an ML model for training. SHEEP combines several ML algorithms: XGBoost , LightGBM , and Catboost to obtain better classification performance. SHEEP contains two distinct classification methodologies: (i) Multi-class and (ii) one versus all with correction by a meta-learner. ...

Courtesy: UNDP Moldova Civilian drones today are flown under very specific and safe weather and wind conditions. This is because these drones have adaptive control algorithms that are lacking. This applies to remote-controlled drones as well as autonomous ones. The direct and specific effect of various wind conditions on aircraft dynamics, performance, and stability cannot be accurately characterised as a simple mathematical model. Engineers at Caltech have developed Neural-Fly, a deep-learning method that can help drones cope with new and unknown wind conditions in real time. Existing Machine Learning methods require a huge amount of data to train the model and adapting these large models in real-time is all but impossible. To overcome this, Neural-Fly was developed with a "separation strategy". Only a few parameters of the neural network must be updated in real time and this is achieved with a new meta-learning algorithm, which pre-trains the neural network so that only the...