Descripción del proyecto
Descodificación del lenguaje del ADN
Las secuencias genómicas se parecen al lenguaje de los humanos en la medida en que los nucleótidos y codones transmiten información de una forma similar a cómo los fonemas y sílabas constituyen las unidades del lenguaje hablado. Una secuencia genómica puede codificar una proteína o podría transmitir un mensaje regulador o estructural. Los científicos del proyecto LanguageOfDNA, financiado con fondos europeos, emplearán algoritmos diseñados para tratar los lenguajes humanos para clasificar transcripciones del ARN y regiones genómicas sin traducir. A través de la creación de modelos de lenguaje de ADN/ARN, serán capaces de interpretar cualquier secuencia genómica y contribuir a la delineación funcional del genoma humano.
Objetivo
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.
Ámbito científico
- humanitieslanguages and literaturegeneral language studies
- natural sciencesbiological sciencesgeneticsDNA
- natural sciencesbiological sciencesbiochemistrybiomoleculesproteins
- natural sciencesbiological sciencesgeneticsRNA
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Palabras clave
Programa(s)
Régimen de financiación
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinador
601 77 Brno
Chequia