Projektbeschreibung
Die Sprache der DNS verstehen
Genomsequenzen funktionieren in gewisser Weise wie die menschliche Sprache: die Nukleotide und Codone übernehmen bei der Informationsübermittlung eine ähnliche Aufgabe wie Phoneme und Silben als Einheiten der gesprochenen Sprache. Eine Genomsequenz kann dazu dienen, ein Protein zu kodieren oder regulatorische oder strukturelle Informationen zu übermitteln. Das Forscherteam des EU-finanzierten Projekts LanguageOfDNA wird mithilfe von Algorithmen zur Verarbeitung von menschlicher Sprache RNS-Transkripte und unübersetzte Genomregionen klassifizieren. Die Entwicklung von Sprachmodellen der DNS/RNS wird es den Forschenden ermöglichen, jede beliebige Genomsequenz zu entschlüsseln und zur funktionellen Erforschung des menschlichen Genoms beizutragen.
Ziel
The genomics era dawned about two decades ago with the completion of a multi-billion project sequencing the complete human genome. Today a similar task is within reach of any modestly equipped lab, due to the advances in sequencing techniques. Thousands of new species are now having their genome sequenced per year. A volume of produced genomic data challenges the interpretation capacity of classical statistical methods, opening the doors for novel machine learning approaches.
A genomic sequence can be conceptually seen as a close parallel to a human language. Both utilize information (nucleotides/codons and phonemes/syllables) to encode and transmit a signal that can be faithfully decoded, with attention to error minimization, at the receiving end. Genomic messages are a product of multiple and often contradictory evolutionary pressures and are aimed to be decoded at the same time by many different actors in variable ways. For example, a genomic sequence could encode for a protein product, thus displaying a three-nucleotide / codon-based language model. However, it has also subtexts of the regulation (a codon sequence can include motifs aimed at RNA binding proteins), structural information (functional RNA folding patterns pressuring sequences to a specific direction) and so on.
The main challenge of applying machine learning models to the identification of genomic function is to find creative ways to untangle these multiple layers of subtexts and focus on each type of message separately. We will adapt algorithms recently developed for the processing of human languages and use them for the classification of RNA transcripts into functional classes and the classification of untranslated functional genomic regions (enhancers, transcription factor binding sites). We will create ready-to-use datasets to benchmark existing and future methods in this field and make all DNA/RNA language models publicly available.
Wissenschaftliches Gebiet
- humanitieslanguages and literaturegeneral language studies
- natural sciencesbiological sciencesgeneticsDNA
- natural sciencesbiological sciencesbiochemistrybiomoleculesproteins
- natural sciencesbiological sciencesgeneticsRNA
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Schlüsselbegriffe
Programm/Programme
Thema/Themen
Aufforderung zur Vorschlagseinreichung
Andere Projekte für diesen Aufruf anzeigenFinanzierungsplan
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Koordinator
601 77 Brno
Tschechien