app.py

import numpy as np
import torch
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
from transformers import BertForSequenceClassification,BertTokenizer

import gradio as gr
from typing import Dict


num_labels=14
model = BertForSequenceClassification.from_pretrained("owaiskha9654/Multi-Label-Classification-of-PubMed-Articles", num_labels=num_labels)
tokenizer = BertTokenizer.from_pretrained('owaiskha9654/Multi-Label-Classification-of-PubMed-Articles', do_lower_case=True) 


def Multi_Label_Classification_of_Pubmed_Articles(model_input: str) -> Dict[str, float]:
    
    # Encoding input data
    encodings = tokenizer.batch_encode_plus(model_input,max_length=1024,padding=True,truncation=True) # tokenizer's encoding method
    outs = model(torch.tensor(encodings['input_ids']), token_type_ids=None, attention_mask=torch.tensor(encodings['attention_mask']))
    b_logit_pred = outs[0]
    pred_label = torch.sigmoid(b_logit_pred)
    
    ret ={
        "Anatomy [A]": float(pred_label[0][0]),
        "Organisms [B]": float(pred_label[0][1]),
        "Diseases [C]": float(pred_label[0][2]),
        "Chemicals and Drugs [D]": float(pred_label[0][3]),
        "Analytical, Diagnostic and Therapeutic Techniques, and Equipment [E]": float(pred_label[0][4]),
        "Psychiatry and Psychology [F]": float(pred_label[0][5]),
        "Phenomena and Processes [G]": float(pred_label[0][6]),
        "Disciplines and Occupations [H]": float(pred_label[0][7]),
        "Anthropology, Education, Sociology, and Social Phenomena [I]": float(pred_label[0][8]),
        "Technology, Industry, and Agriculture [J]": float(pred_label[0][9]),
        "Information Science [L]": float(pred_label[0][10]),
        "Named Groups [M]": float(pred_label[0][11]),
        "Health Care [N]": float(pred_label[0][12]),
        "Geographicals [Z]": float(pred_label[0][13])}
    return ret


model_input = gr.Textbox("Input text here (Note: This is trained to classify Medical Articles)", show_label=False)
model_output = gr.Label("Multi Label MeSH Result", num_top_classes=14, show_label=True, label="MeSH(Medical Subheadings) Labels assigned to this article")


examples = [
    (
        "A case of a patient with type 1 neurofibromatosis associated with popliteal and coronary artery aneurysms is described in which cross-sectional",
        "imaging provided diagnostic information.",
        "The aim of this study was to compare the exercise intensity and competition load during Time Trial (TT), Flat (FL), Medium Mountain (MM) and High ",
        "Mountain (HM) stages based heart rate (HR) and session rating of perceived exertion (RPE).METHODS: We monitored both HR and RPE of 12 professional ",
        "cyclists during two consecutive 21-day cycling races in order to analyze the exercise intensity and competition load (TRIMPHR and TRIMPRPE).",
        "RESULTS:The highest (P<0.05) mean HR was found in TT (169±2 bpm) versus those observed in FL (135±1 bpm), MM (139±3 bpm), HM (143±1 bpm)"
    ),
    (
        "The association of body mass index (BMI) with blood pressure may be stronger in Asian than non-Asian populations, however, longitudinal studies ",
        "with direct comparisons between ethnicities are lacking. We compared the relationship of BMI with incident hypertension over approximately 9.5 years",
        " of follow-up in young (24-39 years) and middle-aged (45-64 years) Chinese Asians (n=5354), American Blacks (n=6076) and American Whites (n=13451).",
        "We estimated risk differences using logistic regression models and calculated adjusted incidences and incidence differences. ",
        "To facilitate comparisons across ethnicities, standardized estimates were calculated using mean covariate values for age, sex, smoking, education",
        "and field center, and included the quadratic terms for BMI and age. Weighted least-squares regression models with were constructed to summarize",
        "ethnic-specific incidence differences across BMI. Wald statistics and p-values were calculated based on chi-square distributions. The association of",
        "BMI with the incidence difference for hypertension was steeper in Chinese (p<0.05) than in American populations during young and middle-adulthood.",
        "For example, at a BMI of 25 vs 21 kg/m2 the adjusted incidence differences per 1000 persons (95% CI) in young adults with a BMI of 25 vs those with",
        "a BMI of 21 was 83 (36- 130) for Chinese, 50 (26-74) for Blacks and 30 (12-48) for Whites"
    )
]

title = "Thoucentric Paper Night Multi Label Classification of Pubmed Articles"
description = "The traditional machine learning models give a lot of pain when we do not have sufficient labeled data for the specific task or domain we care about to train a reliable model. Transfer learning allows us to deal with these scenarios by leveraging the already existing labeled data of some related task or domain. We try to store this knowledge gained in solving the source task in the source domain and apply it to our problem of interest. In this work, I have utilized Transfer Learning utilizing BertForSequenceClassification model to fine tune on Pubmed MultiLabel classification Dataset."
article = (
    "Author: Owais Ahmad \n"
    "Model Trained Kaggle on <a href=\"https://www.kaggle.com/code/owaiskhan9654/multi-label-classification-of-pubmed-articles\">Link</a> \n "
    "HuggingFace Model Repo <a href=\"https://huggingface.co/owaiskha9654/Multi-Label-Classification-of-PubMed-Articles\">Link</a> \n"
)



app = gr.Interface(
    Multi_Label_Classification_of_Pubmed_Articles, 
	inputs=model_input,
    outputs=model_output, 
    examples=examples,
    title=title,
	description=description,
    article=article,
    allow_flagging='never',
    analytics_enabled=False,
)

app.launch()