Jinfeng Zhang

IID-KG: An ontology-aligned literature-derived knowledge graph for infectious and immune-mediated diseases

The paper constructs an IID-specific knowledge graph from biomedical literature to support disease ontology refinement and drug repurposing.

PXN Unlocks the Power of Public Gene Expression Data Through Cross-Technology Integration

PXN improves cross-platform gene expression data integration by removing technology-specific biases and enhancing differential expression analysis.

iKraph: a comprehensive, high-quality biomedical knowledge graph for AI-powered, data-driven biomedical research

The paper constructs a comprehensive biomedical knowledge graph (iKraph) using PubMed abstracts and integrates it with public databases to enable AI-powered knowledge discovery, demonstrating its utility in drug repurposing.

DisDock: A Deep Learning Method for Metal Ion-Protein Redocking

DisDock predicts protein-metal docking using a physics-driven deep learning method, achieving higher accuracy than existing approaches for various metal ions.

ProDCoNN-server: a web server for protein sequence prediction and design from a three-dimensional structure

ProDCoNN-server predicts and designs protein sequences from 3D structures using deep learning models, offering fast and accurate results with visualization tools.

Estimating the Designability of Protein Structures

This study estimates the designability of real proteins using a deep neural network model and validates the results with AlphaFold2 and RoseTTAFold.

Protein loop modeling and refinement using deep learning models

This paper introduces two deep learning models for protein loop modeling that improve accuracy without relying on multiple sequence alignments.

Applications of AlphaFold beyond Protein Structure Prediction

The paper applies AlphaFold to predict stability changes of engineered proteins and estimates the designability of a real protein structure.

A BERT-Based Hybrid System for Chemical Identification and Indexing in Full-Text Articles

The paper develops a hybrid system for chemical identification and indexing in full-text articles using BERT-based methods and dictionary matching, achieving high F1 scores on chemical NER and normalization.

Text Mining Drug-Protein Interactions using an Ensemble of BERT, Sentence BERT and T5 models

The paper develops an ensemble model combining BERT, Sentence BERT, and T5 to predict drug-protein interactions from text, achieving an F-1 score of 0.753 on a benchmark dataset.

Multi-label topic classification for COVID-19 literature annotation using an ensemble model based on PubMedBERT

The paper develops an ensemble model based on PubMedBERT for multi-label topic classification of COVID-19 literature, achieving an F1 score of 0.9247.

Developing a More Accurate Biomedical Literature Retrieval Method using Deep Learning and Citations in PubMed Central Full-text Articles

This study develops DeepSenSe, a deep learning method for sentence-based literature retrieval using PubMed Central data, showing improved performance over PubMed and Google Scholar.

Super-delta2: An Enhanced Differential Expression Analysis Procedure for Multi-Group Comparisons of RNA-seq Data

Super-delta2 is a differential expression analysis method for RNA-seq data that controls type I error and achieves high statistical power in multi-group comparisons.

Maximizing the Reusability of Gene Expression Data by Predicting Missing Metadata

This study develops a framework to predict missing metadata in gene expression datasets to improve their reusability, outperforming standard metrics like F1-score.

GRASP: a Bayesian network structure learning method using adaptive sequential Monte Carlo

GRASP is a Bayesian network structure learning method that uses adaptive sequential Monte Carlo to improve network discovery from genomic data.

iSeg: an efficient algorithm for segmentation of genomic and epigenomic data

iSeg is an efficient algorithm for genomic and epigenomic segmentation that uses dynamic programming and a novel data structure to identify and refine segments with statistical significance.