We encourage submissions bringing forward methods for discovering complex structures (e.g. interaction networks, molecule structures), statistical machine learning methods for analysis of various high-throughput omics data, and methods supporting systems-level data analysis. The submissions are organized into the following two tracks:
- Manuscripts Manuscripts (preferentially up to 5000 words) describing original work on machine learning in systems biology. These should describe method development and applications broadly in the topics listed above (see Workshop topics). Accepted proceedings track papers will be published in BMC Bioinformatics. The publications need to match the standards of the journal; please prepare your submissions using the BMC instructions, with the following exceptions: For the Easychair submission, please prepare a single PDF containing all figures and supplementary files. In addition, figures may be embedded in the main text. The publication is subject to open access fee of 1122 GBP (special reduced price negotiated by MLSB).
- Highlights Track abstracts (1-2 pages in any format) describing computational aspects of work that has been recently published in a journal (or is "in press") as well as unpublished/on-going work.
Submissions will be evaluated by at least three reviewers from an international programme committee of experts in the field. The most relevant and most original submissions will be accepted as full oral presentations and/or as poster presentations at the workshop.
Submission is through the Easychair system.
Poster abstracts can be submitted until August 19, 2016. The poster should be preferably of size A0 in portrait orientation (84.1 x 118.9cm; or 33.1 x 46.8 inches).
In addition, we will organise a poster pitching session, where you have the opportunity to give a 2 minute oral presentation of your poster.
Abstract of your poster will appear in an informal abstract book that will be available online (unless you instruct otherwise). The abstract should have length 1-2 pages (in arbitrary format).