AD-LitMiner is a pathology evidence-based web service based on the mining of medical literature on Alzheimer's disease.
AD-LitMiner filters out the most valuable statements from the vast amount of biomedical literature for the users and provides drug recommendations for them, hopefully contributing some help to Alzheimer's disease research.

Read more about each of our focus areas below:

Alzheimer's disease

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder characterized by cognitive and behavioral impairment, which significantly impacts social and occupational functioning. It is most commonly diagnosed in older adults, and its etiology remains unclear. Research on Alzheimer's Disease focuses on understanding its pathogenesis, identifying therapeutic targets, and improving early diagnosis accuracy. Several hypotheses have been proposed to explain the onset of Alzheimer's Disease, including the accumulation of beta-amyloid plaques, abnormal phosphorylation of Tau protein, and inflammatory responses. Additionally, there are specific databases available for storing and sharing genetic, protein, and clinical data related to Alzheimer's Disease, which serve as valuable resources for researchers.

Biomedical Literature Mining

Biomedical Literature Mining is a method that utilizes natural language processing and machine learning techniques to extract and analyze biomedical entities (such as genes, proteins, and diseases) and their relationships from a large volume of biomedical literature. The goal of biomedical text mining is to assist researchers in efficiently accessing and organizing biomedical information to support basic research and drug development. Common methods in biomedical text mining include named entity recognition, relationship extraction, text classification, and text clustering. Biomedical text mining has important applications in drug discovery, gene function research, and clinical decision support.

Drug Repurposing

Drug repurposing, also known as drug repositioning, refers to the process of using existing drugs that have been approved for one disease to treat different diseases. Compared to traditional drug development, drug repurposing offers advantages in terms of time and cost, as these drugs have already undergone clinical trials and safety evaluations. Research on drug repurposing involves screening existing drugs for new indications, studying the mechanisms of action, and optimizing dosage and administration methods. Drug repurposing holds promise as a more efficient and cost-effective approach to drug development.

Hypothesis Generation

Hypothesis Generation refers to the process of proposing new drug repurposing hypotheses or predicting new indications for drugs through the analysis and mining of large-scale biomedical data. Research methods for hypothesis generation include knowledge graph-based reasoning, text mining, and machine learning techniques. Through hypothesis generation, researchers can discover potential associations between existing drugs and other diseases, providing new directions and possibilities for drug repurposing.


LOF/GOF mutations refer to mutations in genes that result in loss or gain of function. In the field of drug repurposing, researchers focus on the relationship between LOF/GOF mutations and drug treatment outcomes. By analyzing response data of drugs in the context of LOF/GOF mutations, researchers can identify which drugs are effective for specific mutation types, providing guidance for drug repurposing research and clinical applications.