Posts Tagged ‘computational algorithm’

Robotically Driven System Could Reduce Cost of Discovering Drugs

Reporter: Irina Robu, PhD

However, their approach had only been tested using synthetic or previously acquired data, the team’s current model builds on this by letting the computer choose which experiments to do. The experiments were then carried out using liquid-handling robots and an automated microscope.

A total of 9,216 experiments were done, each consisting of acquiring images for a given cell clone in the presence of a given drug. The challenge for the algorithm was to learn how proteins were affected in each of these experiments, without performing all of them.

The originality of this work was to identify new phenotypes on its own as part of the learning process. To do this, it clustered the images to form phenotypes. The phenotypes were used to form a predictive model, so the learner could estimate the outcomes of unmeasured experiments. The basis of the model was to identify different sets of proteins that responded similarly to sets of drugs, so that it could predict the trend in the unmeasured experiments. The learner repeated the process for a total of 30 rounds, completing 2,697 out of the 9,216 possible experiments. As it progressively performed the experiments, it identified more phenotypes and more patterns in how sets of proteins were affected by sets of drugs.

Using an assortment of calculations, the team determined that the algorithm was able to learn a 92% accurate model for how the 96 drugs affected the 96 proteins, from only 29% of the experiments conducted.

Read Full Post »

Swansea University Uses Artificial Intelligence to Detect Cancer. Reporter: Evelina Cohn Budu Ph.D.

Swansea University is a well known and respected University in UK, a research -led institution with an excellent reputation for the quality of its student experience.

Their new type of research involving algorithms and mathematics in evaluation and identification of cancer cells.

Prof Paul Rees in collaboration with specialists from US, Germany, London and Newcastle, from the University College of Engineering, conducted a research in which the technology of fingerprint recognition software was taught to recognize cells and pinpoint them. “The algorithm recognizes the specific cells of interest by giving examples of the cells to be identified ” he said. After learning how the cells look like, the algorithm can identify target cells in a new population.
Along with these characteristics, the group of researchers can identify the age of a cell, which is very important to determine the cycle of a certain cell in a certain moment.

The research is an international collaboration with the Broad Institute of MIT  and Harvard In Cambridge Massachusetts USA, Hemholtz Zentrum in Munich, The Francis Crick Institute in London and Newcastle Upon Tyne University . The group’s paper entitled “Label -free cell cycle analysis for high-throughput imaging flow cytometry”, was published in Nature Communications on January 7, 2016.

Prof. Dr. Fabian Theis of the Helmholz Zentrum Munich , expert in “Computational Modelling in Biology” said that this discovery can open up a completely new perspective in responding to different research questions, not only cell analysis.

The computer uses algorithms to learn what cells look like

Source: http:// http://www.bbc.co.uk

Here is an example of how the artificial intelligence can be used to find an algorithm.

sources : in http://www.bbc.com/news/uk-wales-south-west-wales-35306035


Read Full Post »