Marker Associations SNP Binary Base Open-Source Text Classification Model - Free for SNP Marker Binary Classification

Marker Associations Snp Binary Base

Developed by jambo

This model is a text classification model fine-tuned on PubMedBERT for the marker-association-snp-binary-baseline dataset, primarily used for binary classification tasks of SNP markers.

Text Classification

Transformers

Open Source License:MIT #Biomedical Text Classification #SNP Association Analysis #High Precision

Downloads 16

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext, specializing in binary classification tasks of SNP markers in the biomedical field.

Model Features

High Precision Classification

Achieved a precision of 0.938 and a recall of 0.906 on the evaluation set, demonstrating excellent performance.

Biomedical Domain Optimization

Fine-tuned on PubMedBERT, making it particularly suitable for processing biomedical text data.

Stable Performance

Maintained stable F1 scores and accuracy across multiple training rounds.

Model Capabilities

SNP Marker Classification

Biomedical Text Analysis

Binary Classification

Use Cases

Genomic Research

SNP Marker Association Analysis

Used to identify SNP markers associated with specific traits or diseases

Can achieve an F1 score of 0.9217

Biomedical Literature Mining

SNP Marker Extraction from Literature

Automatically identify and classify SNP markers from biomedical literature

🚀 marker-associations-snp-binary-base

This model is a fine - tuned version of [microsoft/BiomedNLP - PubMedBERT - base - uncased - abstract - fulltext](https://huggingface.co/microsoft/BiomedNLP - PubMedBERT - base - uncased - abstract - fulltext) on the marker - associations - snp - binary - base dataset. It can achieve high - precision text classification, providing reliable performance in relevant tasks.

🚀 Quick Start

This model is a fine - tuned version of [microsoft/BiomedNLP - PubMedBERT - base - uncased - abstract - fulltext](https://huggingface.co/microsoft/BiomedNLP - PubMedBERT - base - uncased - abstract - fulltext) on the marker - associations - snp - binary - base dataset. It achieves the following results on the evaluation set:

Loss: 0.4027
Precision: 0.9384
Recall: 0.9056
F1: 0.9217
Accuracy: 0.9108
Auc: 0.9578

✨ Features

Fine - tuned Model: Based on the [microsoft/BiomedNLP - PubMedBERT - base - uncased - abstract - fulltext] model, fine - tuned on the marker - associations - snp - binary - base dataset.
Multiple Metrics: Evaluated by multiple metrics such as precision, recall, F1, accuracy, and auc, showing excellent performance.

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e - 05
train_batch_size: 16
eval_batch_size: 16
seed: 1
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Auc
No log	1.0	153	0.2776	0.9	0.9441	0.9215	0.9067	0.9613
No log	2.0	306	0.4380	0.9126	0.9126	0.9126	0.8986	0.9510
No log	3.0	459	0.4027	0.9384	0.9056	0.9217	0.9108	0.9578
0.2215	4.0	612	0.3547	0.9449	0.8986	0.9211	0.9108	0.9642
0.2215	5.0	765	0.4465	0.9107	0.9266	0.9185	0.9047	0.9636
0.2215	6.0	918	0.5770	0.8970	0.9441	0.9199	0.9047	0.9666

Framework versions

Transformers 4.11.3
Pytorch 1.9.0+cu111
Tokenizers 0.10.3

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご