• Publicationsclose
• Research softwareclose
• 2022-2022close
• Open Source close
• Knowmad Institut close

BIIGLE is a web-based software for image and video annotation that enables collaborative research on large datasets. It offers tools for manual and computer-assisted annotation, quality control and the collaboration on custom taxonomies to describe objects. BIIGLE is freely available and can be installed in cloud environments, a local network or on mobile platforms during research expeditions. The public instance on biigle.de is free for non-commercial use.

 The videos of surgical operations such as endoscopic videos, microscopic videos, and OR videos, are a rich source of data, that can reveal surgical improvement points and thus greatly benefit the improvement of surgical procedures. For this purpose, a software system, Video Annotation Software, is designed and developed to enhance data extraction from the videos of different types of surgery. In addition to the surgical video analysis, the software system has the potential for many other video analyses in other fields.

BioVAE is a pre-trained latent variable language model for biomedical text mining. Large scale pre-trained language models (PLMs) have advanced state-of-the-art (SOTA) performance on various biomedical text mining tasks. The power of such PLMs can be combined with the advantages of deep generative models. These are examples of these combinations. However, they are trained only on general domain text, and biomedical models are still missing. In this work, we describe BioVAE, the first large scale pre-trained latent variable language model for the biomedical domain, which uses the OPTIMUS framework to train on large volumes of biomedical text. The model shows SOTA performance on several biomedical text mining tasks when compared to existing publicly available biomedical PLMs.

AIDE (Annotation-effIcient Deep lEarning) is a deep learning framework for automatic medical image segmentation with imperfect datasets, including those having limited annotations, lacking target domain annotations, and containing noisy annotations. Automatic segmentation of medical images plays an essential role in both scientific research and medical care. Deep learning approaches have presented encouraging performances, but existing high-performance methods typically rely on very large training datasets with high-quality manual annotations, which are normally difficult or even impossible to obtain in many clinical applications.

BERT-Kcr is a tool for prediction of lysine crotonylation sites by a transfer learning method with pre-trained BERT models.

MISTIC (MISsense deleTeriousness predICtor), a prediction tool to reveal disease-relevant deleterious missense variants based on an original combination of two complementary machine learning algorithms using a soft voting system that integrates 113 missense features, ranging from multi-ethnic minor allele frequencies and evolutionary conservation, to physiochemical and biochemical properties of amino acids.

FSA (Fast Statistical Alignment) is a probabilistic multiple sequence alignment algorithm which uses a "distance-based" approach to aligning homologous protein, RNA or DNA sequence. FSA brings the high accuracies previously available only for small-scale analyses of proteins or RNAs to large-scale problems such as aligning thousands of sequences or megabase-long sequences.

This is replication code associated with an article, ""Null Effects of a Progressive Prosecution Policy on Marijuana Enforcement." Please see the ReadMe file for more detialed information Dr. Herchel Smith Fund, Williams College

The Viral Host Range database represents a unique resource for the community to rapidly find, document analyze and disseminate data related to the range of hosts that a virus can infect. Over the years, countless host range experiments have been performed in many laboratories. However, these data are not readily available to the community and are therefore underexploited. The VHRdb is an online resource that centralizes experimental data related to the host range of viruses. While it originates from bacteriophages and bacteria interaction studies, its design is compatible with viruses infecting all living forms. Users can browse publicly available data to find which host is infected by a virus, and vice versa. Users can also upload their own data while keeping it private or making it public, analyze results across independent sets of data, generate and visualize outputs. Data implemented in the VHRdb are linked to users and, if available, to publications and sequence identifiers.

MIGNON (Mechanistic InteGrative aNalysis Of rNa-seq data) is a versatile workflow to integrate RNA-seq genomic and transcriptomic data into mechanistic models of signaling pathways.