ARSINFORMATICA

"Artificial intelligence, branching processes and coalescent – Searching the Information from a genetic Cornucopia"

 Partecipanti

Mappa

 Word cloud

Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.

 Obiettivo del progetto (Objective)

'The objective of the multidisciplinary ArSInformatiCa project is to reinforce the international dimension of a research career of European computer scientist by training him in complementary skills in a world-class research centre, the George R. Brown School of Engineering at William M. Rice University in Houston, USA. The research will be carried out in two fields of information sciences: artificial intelligence (in particular machine learning) and distributed computer simulations applied to retrieval meaningful information from the whole-genome-scale variation data produced by high throughput genotyping technologies. In particular, the interest will be given to inherited predisposition to complex genetic diseases, including autoimmune diseases and cancers. An extremely large amount of data from the currently launched 1000 Genomes Project and Cancer Genome Project, requires a development of new advanced information technologies for understanding these data. This is an important challenge for information sciences, which motivates the goal of the ArSInformatiCa project. The progress in machine learning will not be limited to genetic applications. Rather, the methods developed, will be verified by application to human/cancer genetics with a potential to benefit wider and general context of data mining in very large and multidimensional data repositories. An example is the development of applicant’s rule-based method known as quasi-dominant rough set approach. While this method will be primarily tested in search for signatures of natural selection at molecular level in genes involved in human familial cancers, it is expected to become a general machine learning approach. Having a clear perspective of a long-term collaboration between Rice University and European research institutions, the ArSInformatiCa project will also contribute to the excellence of the European Research Area by a research inspired by the project results and performed after its completion.'

Introduzione (Teaser)

Evolution of brain structure over billions of years enabled conscious thought in humans. Computer technology and artificial intelligence based on the human brain organisation is a tentative step in this direction.

Descrizione progetto (Article)

Today's electronic computers can serially process information and solve complex problems far faster than humans. However, qualitative functions which the brain performs by naturally recognising patterns to make judgements are still extremely difficult for computers.

The http://www.arsinformatica.eu/ (ARSINFORMATICA) project explored machine learning to comb through genomic data and find links between genotypes and diseases and understand natural selection. Researchers are also studying the dynamics of evolution within the environment of a tumour.

Mathematical models were developed to study how gene barriers could have remained between anatomically modern humans and Neanderthals. The period of coexistence of Neanderthals and Homo Sapiens is the basis of the intriguing problem. The ARSINFORMATICA scientists are looking into the interbreeding between the two populations to confirm the findings of recent DNA-based studies.

The first scientific papers with the results of the ARSINFORMATICA project have already been presented at international conferences. These mathematical models of human population evolution were used to develop scientific software to carry out forward-in-time simulations of human evolution. The intermingling of Neanderthal DNA with the gene pool of anatomically modern humans was also described.

The ultimate objective of the ARSINFORMATICA project is to reinforce the international dimension of research on computational biology and bioinformatics in Poland. During the first reporting period, collaborative links were also established with the United States of America.

Facilitating long-term research collaboration at European and international levels will contribute to the European Research Area. The practical machine learning tools and techniques developed are expected to find applications beyond human genetics. In particular, machine learning algorithms along with data mining processes should help in pattern recognition even with unstructured data.