Team name: Cheetahs Case: Telelink (iGEM) Provider: IBM Business Understanding The task for the Telelink case is to obtain the complete set of genome traces found in a single food sample and ALL organisms that should not be found in the food sample. The business needs a solution to this DNA Sequence identification case for improved […]
case-kaufland Case: Kaufland Provider: Microsoft Azure 2 Vauchers WA35RI0X42N6OADQCS W3N370B4P6FZKNB5DT
We developed workflow utilizing Blast and Centrifuge toolkits, that is able to provide precise metagenomics information about food composition, from comparing DNA reads with reference genomes of various species. Our workflow is optimized to work on Google Cloud instance (Compute Engine) with 24 CPUs and 200 GB of RAM.
This paper presents a DNN-based approach to learn entities relations from distant-labeled free text. The proposed approach presents task-specific data cleaning, which despite effective in removing textual noise is preserving semantics necessary for the training process. The cleaned-up dataset is then used to build a number of bLSTM attention-based DNN models, hyper-tuned using recall as an optimization objective. The resulting models are then joined into an ensemble that deliver our best result
Datathlon 2018 entry – Hristo Piyankov