paper-with-me

Papers

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

2023-06-27 · NeurIPS 2023 11 · Eric Nguyen, Michael Poli, Marjan Faizi, Armin Thomas, Callum Birch-Sykes, Michael Wornow, Aman Patel, Clayton Rabideau, Stefano Massaroli, Yoshua Bengio, Stefano Ermon, Stephen A. Baccus, Chris Ré

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 unlabeled genome data that can then be fine-tuned for downstream tasks such as identifying regulatory elements. Due to the quadratic scaling of attention, previous Transformer-based genomic models have used 512 to 4k tokens as context (<0.001% of the human genome), significantly limiting the modeling of long-range interactions in DNA. In addition, these methods rely on tokenizers or fixed k-mers to aggregate meaningful DNA units, losing single nucleotide resolution where subtle genetic variations can completely alter protein function via single nucleotide polymorphisms (SNPs). Recently, Hyena, a large language model based on implicit convolutions was shown to match attention in quality while allowing longer context lengths and lower time complexity. Leveraging Hyena's new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 1 million tokens at the single nucleotide-level - an up to 500x increase over previous dense attention-based models. HyenaDNA scales sub-quadratically in sequence length (training up to 160x faster than Transformer), uses single nucleotide tokens, and has full global context at each layer. We explore what longer context enables - including the first use of in-context learning in genomics. On fine-tuned benchmarks from the Nucleotide Transformer, HyenaDNA reaches state-of-the-art (SotA) on 12 of 18 datasets using a model with orders of magnitude less parameters and pretraining data. On the GenomicBenchmarks, HyenaDNA surpasses SotA on 7 of 8 datasets on average by +10 accuracy points. Code at https://github.com/HazyResearch/hyena-dna.

📄 PDF Abstract BibTeX arXiv:2306.15794

Code (4)

HazyResearch/hyena-dna 공식 구현 pytorch
frederikkemarin/bend pytorch
jimmylihui/OpenGenome pytorch
jimmylihui/genbench pytorch

Tasks

4kIn-Context LearningLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Leveraging State Space Models in Long Range Genomics

2025-04-07 · Matvei Popov, Aymen Kallala, Anirudha Ramesh, Narimane Hennouni 외

Long-range dependencies are critical for understanding genomic structure and function, yet most conventional methods struggle with them. Widely adopted transformer-based models, while excelling at short-context tasks, ar…

BenchmarkingGPUState Space Models

Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling

2024-03-05 · Yair Schiff, Chia-Hsiang Kao, Aaron Gokaslan, Tri Dao 외

Large-scale sequence modeling has sparked rapid advances that now extend into biology and genomics. However, modeling genomic sequences introduces challenges such as the need to model long-range token interactions, the e…

Mamba

Fast and Low-Cost Genomic Foundation Models via Outlier Removal

2025-05-01 · Haozheng Luo, Chenghao Qiu, Maojiang Su, Zhihan Zhou 외

We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GERM. Unlike existing GFM benchmarks, GERM offers the first comprehensive evaluation framework to systematically asses…

Adversarial AttackAdversarial RobustnessComputational EfficiencyDNA analysis+5

Reverse-Complement Consistency for DNA Language Models

2025-09-23 · Mingqian Ma arxiv

A fundamental property of DNA is that the reverse complement (RC) of a sequence often carries identical biological meaning. However, state-of-the-art DNA language models frequently fail to capture this symmetry, producin…

Data Augmentation

DNA Language Model and Interpretable Graph Neural Network Identify Genes and Pathways Involved in Rare Diseases

2024-10-20 · Ali Saadat, Jacques Fellay

Identification of causal genes and pathways is a critical step for understanding the genetic underpinnings of rare diseases. We propose novel approaches to gene prioritization and pathway identification using DNA languag…

Graph Neural NetworkLanguage ModelingLanguage Modelling