license: apache-2.0

模型概述

PlantCaduceus 是一个基于16种被子植物基因组预训练的DNA语言模型。该模型采用Caduceus和Mamba架构，通过掩码语言建模目标，旨在从跨越1.6亿年演化历史的16个物种中学习进化保守性和DNA序列语法。我们训练了不同参数规模的PlantCaduceus系列模型：

• PlantCaduceus_l20：20层，384隐藏维度，2000万参数
• PlantCaduceus_l24：24层，512隐藏维度，4000万参数
• PlantCaduceus_l28：28层，768隐藏维度，1.12亿参数
• PlantCaduceus_l32：32层，1024隐藏维度，2.25亿参数

我们强烈推荐使用最大模型(PlantCaduceus_l32)进行零样本评分估计。

使用方法

from transformers import AutoModel, AutoModelForMaskedLM, AutoTokenizer
import torch
model_path = 'kuleshov-group/PlantCaduceus_l32'
device = "cuda:0" if torch.cuda.is_available() else "cpu"
model = AutoModelForMaskedLM.from_pretrained(model_path, trust_remote_code=True, device_map=device)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

sequence = "ATGCGTACGATCGTAG"
encoding = tokenizer.encode_plus(
            sequence,
            return_tensors="pt",
            return_attention_mask=False,
            return_token_type_ids=False
        )
input_ids = encoding["input_ids"].to(device)
with torch.inference_mode():
    outputs = model(input_ids=input_ids, output_hidden_states=True)

引用文献

@article {Zhai2024.06.04.596709,
	author = {Zhai, Jingjing and Gokaslan, Aaron and Schiff, Yair and Berthel, Ana and Liu, Zong-Yan and Miller, Zachary R and Scheben, Armin and Stitzer, Michelle C and Romay, Cinta and Buckler, Edward S. and Kuleshov, Volodymyr},
	title = {Cross-species plant genomes modeling at single nucleotide resolution using a pre-trained DNA language model},
	elocation-id = {2024.06.04.596709},
	year = {2024},
	doi = {10.1101/2024.06.04.596709},
	URL = {https://www.biorxiv.org/content/early/2024/06/05/2024.06.04.596709},
	eprint = {https://www.biorxiv.org/content/early/2024/06/05/2024.06.04.596709.full.pdf},
	journal = {bioRxiv}
}

联系方式

翟晶晶 (jz963@cornell.edu)