Esm2 T6 8M UR50D Sequence Classifier V1

🚀 ESM-2序列分类器

这是一个基于GPT - 4生成的合成数据训练的小型序列分类器，它可以将蛋白质序列分为三个类别：酶（类别 0）、受体蛋白（类别 1）和结构蛋白（类别 2）。该分类器使用了 facebook/esm2_t6_8M_UR50D 进行训练，这是 ESM - 2模型 之一。

此模型尚未经过充分测试，仅用于实验和教育目的，请谨慎使用。

🚀 快速开始

✨ 主要特性

• 基于GPT - 4生成的合成数据训练，可将蛋白质序列分为酶、受体蛋白和结构蛋白三类。
• 使用 facebook/esm2_t6_8M_UR50D 模型进行训练。

📦 安装指南

文档未提及安装步骤，故跳过此章节。

💻 使用示例

基础用法

# Load the trained model and tokenizer
model = EsmForSequenceClassification.from_pretrained("AmelieSchreiber/esm2_t6_8M_UR50D_sequence_classifier_v1")
tokenizer = AutoTokenizer.from_pretrained("facebook/esm2_t6_8M_UR50D")

# Suppose these are your new sequences that you want to classify
# Additional Family 0: Enzymes
new_sequences_0 = [
    "ACGYLKTPKLADPPVLRGDSSVTKAICKPDPVLEK",
    "GVALDECKALDYLPGKPLPMDGKVCQCGSKTPLRP",
    "VLPGYTCGELDCKPGKPLPKCGADKTQVATPFLRG",
    "TCGALVQYPSCADPPVLRGSDSSVKACKKLDPQDK",
    "GALCEECKLCPGADYKPMDGDRLPAAATSKTRPVG",
    "PAVDCKKALVYLPKPLPMDGKVCRGSKTPKTRPYG",
    "VLGYTCGALDCKPGKPLPKCGADKTQVATPFLRGA",
    "CGALVQYPSCADPPVLRGSDSSVKACKKLDPQDKT",
    "ALCEECKLCPGADYKPMDGDRLPAAATSKTRPVGK",
    "AVDCKKALVYLPKPLPMDGKVCRGSKTPKTRPYGR",
]

# Additional Family 1: Receptor Proteins
new_sequences_1 = [
    "VGQRFYGGRQKNRHCELSPLPSACRGSVQGALYTD",
    "KDQVLTVPTYACRCCPKMDSKGRVPSTLRVKSARS",
    "PLAGVACGRGLDYRCPRKMVPGDLQVTPATQRPYG",
    "CGVRLGYPGCADVPLRGRSSFAPRACMKKDPRVTR",
    "RKGVAYLYECRKLRCRADYKPRGMDGRRLPKASTT",
    "RPTGAVNCKQAKVYRGLPLPMMGKVPRVCRSRRPY",
    "RLDGGYTCGQALDCKPGRKPPKMGCADLKSTVATP",
    "LGTCRKLVRYPQCADPPVMGRSSFRPKACCRQDPV",
    "RVGYAMCSPKLCSCRADYKPPMGDGDRLPKAATSK",
    "QPKAVNCRKAMVYRPKPLPMDKGVPVCRSKRPRPY",
]

# Additional Family 2: Structural Proteins
new_sequences_2 = [
    "VGKGFRYGSSQKRYLHCQKSALPPSCRRGKGQGSAT",
    "KDPTVMTVGTYSCQCPKQDSRGSVQPTSRVKTSRSK",
    "PLVGKACGRSSDYKCPGQMVSGGSKQTPASQRPSYD",
    "CGKKLVGYPSSKADVPLQGRSSFSPKACKKDPQMTS",
    "RKGVASLYCSSKLSCKAQYSKGMSDGRSPKASSTTS",
    "RPKSAASCEQAKSYRSLSLPSMKGKVPSKCSRSKRP",
    "RSDVSYTSCSQSKDCKPSKPPKMSGSKDSSTVATPS",
    "LSTCSKKVAYPSSKADPPSSGRSSFSMKACKKQDPPV",
    "RVGSASSEPKSSCSVQSYSKPSMSGDSSPKASSTSK",
    "QPSASNCEKMSSYRPSLPSMSKGVPSSRSKSSPPYQ",
]

# Tokenize the sequences and convert to tensors
# Merge all sequences
new_sequences = new_sequences_0 + new_sequences_1 + new_sequences_2
inputs = tokenizer(new_sequences, return_tensors="pt", padding=True, truncation=True)

# Use the model to get the logits
with torch.no_grad():
    logits = model(**inputs).logits

# Get the predicted class for each sequence
predicted_class_ids = torch.argmax(logits, dim=-1)

# Print the predicted class for each sequence
for sequence, predicted_class in zip(new_sequences, predicted_class_ids):
    print(f"Sequence: {sequence}, Predicted class: {predicted_class.item()}")

📚 详细文档

文档未提及详细说明内容，故跳过此章节。

🔧 技术细节

文档未提及技术实现细节，故跳过此章节。

📄 许可证

本项目采用MIT许可证。