InDel Marker Miner
- The software at present through the Samtools, GATK, Varscan, SOAPIndel and Pindel five software detection results of the depth of mining, can effectively improve the recovery rate of InDel molecular marker detection, the correct rate and F value.
Soybean QTL database
- We applied our method on a soybean QTL database curation, from which 2278 records were extracted from 228 papers with a precision rate of 96.9% and a recall rate of 83.3%. F value for the method is 89.6%.
Bar Graph Miner
- The experimental results such as PCR and phenotypic data analysis in biomedical literatures was usually depicted by images. Along with the development of text mining technology, a large number of studies had focused on the extraction of quantitative data and no longer limited to text contents. The automatic location and obtaining of the image data become an important approach to efficiently understand and reorganize knowledge.
Gene-Phenotype Relation Extraction Pipeline
- This is the pipeline for gene-phenotype relation extraction from biomedical literature. Combined with abbreviation revision and sentence template extraction, we improve our word-embedding-to-sentence-embedding cascaded approach to recognize phenotypes. The dictionary- and rule-based method is applied for gene recognition. The OLLIE is used to identify gene-phenotype relations.