This web service enables complex queries of scientific literature by machine learning-based classification of article abstracts. BioReader (Biomedical Research Article Distiller) is trained by uploading corpora for two training categories - e.g. one positive and one negative for specific content - as well as one corpora of abstracts to be classified. The corpora are submitted as lists of PubMed IDs and the abstracts are automatically downloaded from PubMed, preprocessed, and the test corpus classified using the best performing classifier selected from ten implemented machine learning algorithms. BioReader is freely available for all users at