Related papers: TrinityDNA: A Bio-Inspired Foundational Model for …
The task of understanding and interpreting the complex information encoded within genomic sequences remains a grand challenge in biological research and clinical applications. In this context, recent advancements in large language model…
We propose generative neural network methods to generate DNA sequences and tune them to have desired properties. We present three approaches: creating synthetic DNA sequences using a generative adversarial network; a DNA-based variant of…
Genomic (DNA) sequences encode an enormous amount of information for gene regulation and protein synthesis. Similar to natural language models, researchers have proposed foundation models in genomics to learn generalizable features from…
The functions of proteins and RNAs are determined by a myriad of interactions between their constituent residues, but most quantitative models of how molecular phenotype depends on genotype must approximate this by simple additive effects.…
The rapid advancement of DNA sequencing has produced vast genomic datasets, yet interpreting and engineering genomic function remain fundamental challenges. Recent large language models have opened new avenues for genomic analysis, but…
Foundation models for single-cell RNA sequencing (scRNA-seq) have shown promising capabilities in capturing gene expression patterns. However, current approaches face critical limitations: they ignore biological prior knowledge encoded in…
Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences…
Genome data are crucial in modern medicine, offering significant potential for diagnosis and treatment. Thanks to technological advancements, many millions of healthy and diseased genomes have already been sequenced; however, obtaining the…
Computer simulations are indispensable for analyzing complex systems, yet high-fidelity models often incur prohibitive computational costs. Multi-fidelity frameworks address this challenge by combining inexpensive low-fidelity simulations…
Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called…
DNA sequence classification requires not only high predictive accuracy but also the ability to uncover latent site interactions, combinatorial regulation, and epistasis-like higher-order dependencies. Although the standard Transformer…
Modeling genomic sequences faces two unsolved challenges: the information density varies widely across different regions, while there is no clearly defined minimum vocabulary unit. Relying on either four primitive bases or independently…
Genomic foundation models have the potential to decode DNA syntax, yet face a fundamental tradeoff in their input representation. Standard fixed-vocabulary tokenizers fragment biologically meaningful motifs such as codons and regulatory…
We consider the task of detecting regulatory elements in the human genome directly from raw DNA. Past work has focused on small snippets of DNA, making it difficult to model long-distance dependencies that arise from DNA's 3-dimensional…
We study DNA self-assembly and DNA computation using a coarse-grained DNA model within the directional dynamic bonding framework {[}C. Svaneborg, Comp. Phys. Comm. 183, 1793 (2012){]}. In our model, a single nucleotide or domain is…
Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstream application, creating significant overhead as model sizes…
Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is structurally misaligned with sparse and discontinuous genomic…
Inspired by the success of unsupervised pre-training paradigms, researchers have applied these approaches to DNA pre-training. However, we argue that these approaches alone yield suboptimal results because pure DNA sequences lack sufficient…
The Genomic Foundation Model (GFM) paradigm is expected to facilitate the extraction of generalizable representations from massive genomic data, thereby enabling their application across a spectrum of downstream applications. Despite…
Coarse-grained models have played an important role in the study of the behavior of DNA at length scales beyond a few hundred base pairs. Traditionally, these models have relied on structurally featureless and sequence-independent…