Predicting non-coding RNA function using Artificial Intelligence

Non-coding RNAs (ncRNAs) represent the majority of human gene products, and are involved in various important biological processes, being considered relevant disease biomarkers and therapeutic agents. However, information about these biomolecules remains sparsely distributed, mostly in the form of scientific research articles. It is then of pivotal importance to aggregate and summarize the existing information.

Natural Language Processing (NLP) methods applied to text mining enable automatic information extraction and summarization from textual data. These techniques can be used to generate collections of annotated sentences expressing relations between entities, called relational corpora.

In this work we developed a text mining pipeline to generate a ncRNA-phenotype relational corpus (ncoRP) using Distant Supervision Relation Extraction (DSRE), comprising 21,608 annotated articles, 2,835 unique ncRNAs, 1,118 unique phenotypes and 35,295 unique relations, with a precision of 0.761 and F1-score of 0.593, calculated through human validation. DSRE methods require a set of pre-documented relations to function, as such, a high-fidelity ncRNA-phenotype relation dataset, consisting of 214,300 unique relations, was created by the aggregation of five comprehensive ncRNA-disease functional annotation databases. Then, both ncoRP and the relation dataset represent important contributions towards solving the problem with the sparseness of information about ncRNAs.

Large Language Models (LLMs) are an emergent type of language model, showing great capabilities in general task-solving through text generation, without the requirement of fine-tuning with large datasets. This benefit shows promise for applications in Relation Extraction (RE), when compared to data-intensive state-of-the-art deep learning methods. In this work, a LLM RE methodology is proposed and evaluated, achieving an F1-score of 0.978 by combining the RE task with a preceding sentence filtering task and applying prompting principles such as in-context learning and Chain-of-Thought self-explanation.