🚀 序列嵌入与基因表达预测代码片段

此代码片段可根据给定的DNA、RNA和蛋白质序列来获取嵌入向量和基因表达预测结果。

🚀 快速开始

以下是使用代码获取序列嵌入和基因表达预测的示例：

from transformers import AutoTokenizer, AutoModelForMaskedLM
import numpy as np
import torch

# Import the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained("isoformer-anonymous/Isoformer", trust_remote_code=True)
model = AutoModelForMaskedLM.from_pretrained("isoformer-anonymous/Isoformer",trust_remote_code=True)

protein_sequences = ["RSRSRSRSRSRSRSRSRSRSRL" * 9]
rna_sequences = ["ATTCCGGTTTTCA" * 9]
sequence_length = 196_608
rng = np.random.default_rng(seed=0)
dna_sequences = ["".join(rng.choice(list("ATCGN"), size=(sequence_length,)))]

torch_tokens = tokenizer(
    dna_input=dna_sequences, rna_input=rna_sequences, protein_input=protein_sequences
)
dna_torch_tokens = torch.tensor(torch_tokens[0]["input_ids"])
rna_torch_tokens = torch.tensor(torch_tokens[1]["input_ids"])
protein_torch_tokens = torch.tensor(torch_tokens[2]["input_ids"])

torch_output = model.forward(
    tensor_dna=dna_torch_tokens,
    tensor_rna=rna_torch_tokens,
    tensor_protein=protein_torch_tokens,
    attention_mask_rna=rna_torch_tokens != 1,
    attention_mask_protein=protein_torch_tokens != 1,
)

print(f"Gene expression predictions: {torch_output['gene_expression_predictions']}")
print(f"Final DNA embedding: {torch_output['final_dna_embeddings']}")

💻 使用示例

基础用法

# Import the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained("isoformer-anonymous/Isoformer", trust_remote_code=True)
model = AutoModelForMaskedLM.from_pretrained("isoformer-anonymous/Isoformer",trust_remote_code=True)

protein_sequences = ["RSRSRSRSRSRSRSRSRSRSRL" * 9]
rna_sequences = ["ATTCCGGTTTTCA" * 9]
sequence_length = 196_608
rng = np.random.default_rng(seed=0)
dna_sequences = ["".join(rng.choice(list("ATCGN"), size=(sequence_length,)))]

torch_tokens = tokenizer(
    dna_input=dna_sequences, rna_input=rna_sequences, protein_input=protein_sequences
)
dna_torch_tokens = torch.tensor(torch_tokens[0]["input_ids"])
rna_torch_tokens = torch.tensor(torch_tokens[1]["input_ids"])
protein_torch_tokens = torch.tensor(torch_tokens[2]["input_ids"])

torch_output = model.forward(
    tensor_dna=dna_torch_tokens,
    tensor_rna=rna_torch_tokens,
    tensor_protein=protein_torch_tokens,
    attention_mask_rna=rna_torch_tokens != 1,
    attention_mask_protein=protein_torch_tokens != 1,
)

print(f"Gene expression predictions: {torch_output['gene_expression_predictions']}")
print(f"Final DNA embedding: {torch_output['final_dna_embeddings']}")

此基础用法展示了如何导入模型和分词器，准备DNA、RNA和蛋白质序列，进行分词处理，最后通过模型前向传播得到基因表达预测和DNA嵌入结果。

高级用法

由于原文档未提供高级用法相关代码，暂无法展示。若有更多复杂场景的代码示例，可按照基础用法的流程，结合具体需求对序列数据和模型调用进行调整。