Motivation: The accurate identification of chemicals in text is important for many applications, including computer-assisted reconstruction of metabolic networks or retrieval of information about substances in drug development. But due to the diversity of naming conventions and traditions for such molecules, this task is highly complex and should be supported by computational tools. Results: We present ChemSpot, a named entity recognition (NER) tool for identifying mentions of chemicals in natural language texts, including trivial names, drugs, abbreviations, molecular formulas and International Union of Pure and Applied Chemistry entities. Since the different classes of relevant entities have rather different naming characteristics, ChemSpot uses a hybrid approach combining a Conditional Random Field with a dictionary. It achieves an F₁ measure of 68.1% on the SCAI corpus, outperforming the only other freely available chemical NER tool, OSCAR4, by 10.8 percentage points. Availability: ChemSpot is freely available at: http://www.informatik.hu-berlin.de/wbi/resources Contact:leser@informatik.hu-berlin.de

SUMMARY: Precise real time estimates of earthquake magnitude and location are essential for early warning and rapid response. While recently multiple deep learning approaches for fast assessment of earthquakes have been proposed, they usually rely on either seismic records from a single station or from a fixed set of seismic stations. Here we introduce a new model for real-time magnitude and location estimation using the attention based transformer networks. Our approach incorporates waveforms from a dynamically varying set of stations and outperforms deep learning baselines in both magnitude and location estimation performance. Furthermore, it outperforms a classical magnitude estimation algorithm considerably and shows promising performance in comparison to a classical localization algorithm. Our model is applicable to real-time prediction and provides realistic uncertainty estimates based on probabilistic inference. In this work, we furthermore conduct a comprehensive study of the requirements on training data, the training procedures and the typical failure modes. Using three diverse and large scale data sets, we conduct targeted experiments and a qualitative error analysis. Our analysis gives several key insights. First, we can precisely pinpoint the effect of large training data; for example, a four times larger training set reduces average errors for both magnitude and location prediction by more than half, and reduces the required time for real time assessment by a factor of four. Secondly, the basic model systematically underestimates large magnitude events. This issue can be mitigated, and in some cases completely resolved, by incorporating events from other regions into the training through transfer learning. Thirdly, location estimation is highly precise in areas with sufficient training data, but is strongly degraded for events outside the training distribution, sometimes producing massive outliers. Our analysis suggests that these characteristics are not only present for our model, but for most deep learning models for fast assessment published so far. They result from the black box modeling and their mitigation will likely require imposing physics derived constraints on the neural network. These characteristics need to be taken into consideration for practical applications.

The recognition of biomedical concepts in natural text (named entity recognition, NER) is a key technology for automatic or semi-automatic analysis of textual resources. Precise NER tools are a prerequisite for many applications working on text, such as information retrieval, information extraction or document classification. Over the past years, the problem has achieved considerable attention in the bioinformatics community and experience has shown that NER in the life sciences is a rather difficult problem. Several systems and algorithms have been devised and implemented. In this paper, the problems and resources in NER research are described, the principal algorithms underlying most systems sketched, and the current state-of-the-art in the field surveyed.

SUMMARY: Earthquakes are major hazards to humans, buildings and infrastructure. Early warning methods aim to provide advance note of incoming strong shaking to enable preventive action and mitigate seismic risk. Their usefulness depends on accuracy, the relation between true, missed and false alerts and timeliness, the time between a warning and the arrival of strong shaking. Current approaches suffer from apparent aleatoric uncertainties due to simplified modelling or short warning times. Here we propose a novel early warning method, the deep-learning based transformer earthquake alerting model (TEAM), to mitigate these limitations. TEAM analyses raw, strong motion waveforms of an arbitrary number of stations at arbitrary locations in real-time, making it easily adaptable to changing seismic networks and warning targets. We evaluate TEAM on two regions with high seismic hazard, Japan and Italy, that are complementary in their seismicity. On both data sets TEAM outperforms existing early warning methods considerably, offering accurate and timely warnings. Using domain adaptation, TEAM even provides reliable alerts for events larger than any in the training data, a property of highest importance as records from very large events are rare in many regions.

Motivation: Many areas of modern biology are concerned with the management, storage, visualization, comparison and analysis of networks, but no appropriate query language for such complex data structures yet exists. Results: We have designed and implemented the pathway query language (PQL) for querying large protein interaction or pathway databases. PQL is based on a simple graph data model with extensions reflecting properties of biological objects. Queries match subgraphs in the database based on node properties and paths between nodes. The syntax is easy to learn for anybody familiar with SQL. As an important feature, a query may require a certain structure in the database to exist but return a different subgraph. We have tested PQL queries on networks of up to 16 000 nodes and found it to scale very well. Availability: The code is available on request from the author. Contact:leser@informatik.hu-berlin.de