paper-with-me

Papers

DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome

2023-06-26 · Zhihan Zhou, Yanrong Ji, Weijian Li, Pratik Dutta, Ramana Davuluri, Han Liu

Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area. Existing works have largely hinged on k-mer, fixed-length permutations of A, T, C, and G, as the token of the genome language due to its simplicity. However, we argue that the computation and sample inefficiencies introduced by k-mer tokenization are primary obstacles in developing large genome foundational models. We provide conceptual and empirical insights into genome tokenization, building on which we propose to replace k-mer tokenization with Byte Pair Encoding (BPE), a statistics-based data compression algorithm that constructs tokens by iteratively merging the most frequent co-occurring genome segment in the corpus. We demonstrate that BPE not only overcomes the limitations of k-mer tokenization but also benefits from the computational efficiency of non-overlapping tokenization. Based on these insights, we introduce DNABERT-2, a refined genome foundation model that adapts an efficient tokenizer and employs multiple strategies to overcome input length constraints, reduce time and memory expenditure, and enhance model capability. Furthermore, we identify the absence of a comprehensive and standardized benchmark for genome understanding as another significant impediment to fair comparative analysis. In response, we propose the Genome Understanding Evaluation (GUE), a comprehensive multi-species genome classification dataset that amalgamates $36$ distinct datasets across $9$ tasks, with input lengths ranging from $70$ to $10000$. Through comprehensive experiments on the GUE benchmark, we demonstrate that DNABERT-2 achieves comparable performance to the state-of-the-art model with $21 \times$ fewer parameters and approximately $92 \times$ less GPU time in pre-training.

📄 PDF Abstract BibTeX arXiv:2306.15006

Code (6)

magics-lab/dnabert_2 공식 구현 pytorch
zhihan1996/dnabert_2 공식 구현 pytorch
frederikkemarin/bend pytorch
jerryji1993/dnabert pytorch
jimmylihui/OpenGenome pytorch
jimmylihui/genbench pytorch

Tasks

Computational EfficiencyCore Promoter DetectionCovid Variant PredictionData CompressionDNA analysisEpigenetic Marks PredictionGenome UnderstandingGPUPromoter DetectionSplice Site PredictionTranscription Factor Binding Site PredictionTranscription Factor Binding Site Prediction (Human)Transcription Factor Binding Site Prediction (Mouse)

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings

2024-02-13 · Zhihan Zhou, Weimin Wu, Harrison Ho, Jiayi Wang 외

We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic se…

Contrastive Learning

MetagenBERT: a Transformer-based Architecture using Foundational genomic Large Language Models for novel Metagenome Representation

2026-01-05 · Gaspar Roy, Eugeni Belda, Baptiste Hennecart, Yann Chevaleyre 외 arxiv

Metagenomic disease prediction commonly relies on species abundance tables derived from large, incomplete reference catalogs, constraining resolution and discarding valuable information contained in DNA reads. To overcom…

Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models

2025-09-13 · Weimin Wu, Xuefeng Song, Yibo Wen, Qinjie Lin 외 arxiv

We introduce Genome-Factory, the first integrated Python library for tuning, deploying, and interpreting genomic foundation models. Our core contribution is to simplify and unify the workflow for genomic model developmen…

parameter-efficient fine-tuning

BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects

2025-06-26 · Hongyang Li, Sanjoy Dey, Bum Chul Kwon, Michael Danziger 외

Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act …

ImputationPromoter Detection

Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2

2026-04-23 · Isabel Kurth, Paulo Yanez Sarmiento, Bernhard Y. Renard arxiv

Explaining deep neural network predictions on genome sequences enables biological insight and hypothesis generation-often of greater interest than predictive performance alone. While explanations of convolutional neural …