Back to top

Paper titled Modeling aspects of the language of life through transfer-learning protein sequences published at BMC Bioinformatics Journal

The paper titled "Modeling aspects of the language of life through transfer-learning protein sequences" was pusblished at BMC Bioinformatics Journal.

Abstract:

Background One common task in Computational Biology is the prediction of aspects of protein function and structure from their amino acid sequence. For 26 years, most state-of-the-art approaches toward this end have been marrying machine learning and evolutionary information. The retrieval of related proteins from ever growing sequence databases is becoming so time-consuming that the analysis of entire proteomes becomes challenging. On top, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome.

Results We introduce a novel way to represent protein sequences as continuous vectors (embeddings) by using the deep bi-directional model ELMo taken from natural language processing (NLP). The model has effectively captured the biophysical properties of protein sequences from unlabeled big data (UniRef50). After training, this knowledge is transferred to single protein sequences by predicting relevant sequence features. We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple convolutional neural networks on existing data sets for two completely different prediction tasks. At the per-residue level, we significantly improved secondary structure (for NetSurfP-2.0 data set: Q3=79%±1, Q8=68%±1) and disorder predictions (MCC=0.59±0.03) over methods not using evolutionary information. At the per-protein level, we predicted subcellular localization in ten classes (for DeepLoc data set: Q10=68%±1) and distinguished membrane-bound from water-soluble proteins (Q2= 87%±1). All results built upon the embeddings gained from the new tool SeqVec neither explicitly nor implicitly using evolutionary information. Nevertheless, it improved over some methods using such information. Where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created the vector representation on average in 0.03 seconds.

Conclusion We have shown that transfer learning can be used to capture biochemical or biophysical properties of protein sequences from large unlabeled sequence databases. The effectiveness of the proposed approach was showcased for different prediction tasks using only single protein sequences. SeqVec embeddings enable predictions that outperform even some methods using evolutionary information. Thus, they prove to condense the underlying principles of protein sequences. This might be the first step towards competitive predictions based only on single protein sequences.

 

Resources:

https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-019-3220-8

https://www.gauss-centre.eu/news/research-highlights/article/high-performance-computing-and-artificial-intelligence-decode-the-language-of-life-in-proteins/

 


'ProPerData - A process model to support GDPR compliance' published as technical report

Abstract

The General Data Protection Regulation (GDPR) has changed the perception towards privacy and data protection worldwide. Passed in 2016 and in force since 2018, the regulation has been a steady part of the academic and practical discourse over the past years. However, companies still struggle with the task of becoming compliant, mainly because of the large interdisciplinary scope and the overall complexity of the regulation. Once established, maintaining GDPR compliance in an accelerating business environment remains a challenge.

With this report, we present ProPerData, a process model for the protection of personal data. It addresses software developers and enterprise architects of large organizations and aims to provide a structured overview of the GDPR and a clear definition of responsibilities.

ProPerData is organized along 11 tasks that are derived from the GDPR. 16 work units of ProPerData are assigned to the tasks and executed by ProPerData stakeholders. We account for 6 resources that support the work units and 13 work products that result from them. The work units take place at one or more of the 10 stages or events of ProPerData.

 

Huth, D., Matthes, F.: "ProPerData - A process model to support GDPR compliance". Technical Report. Technical University of Munich, Munich 2020.

 


Document Automation Tool Study is Published

We are happy to announce that our survey about document automation tools for the legal domain has been published.

The survey evaluates 13 document automation tools in accordance with requirements, which were identified with respect to the legal domain.

Please find the result of our survey here.

We would like to sincerely thank the 13 vendors who participated in our study and granted us access to their tools for conducting the study.

 

 


Three papers accepted for publication at ICEIS 2020

Three papers from the sebis chair were accepted for publication at the 22nd International Conference on Enterprise Information Systems in Prague, May 5-7 2020:

 

Huth, D., Vilser, M., Bondel, G. and Matthes, F.: "Empirical Task Analysis of Data Protection Management and its Collaboration with Enterprise Architecture Management". Proceedings of the 22nd International Conference on Enterprise Information Systems (ICEIS), Prague 2020 - to appear

 

Bondel, G., Nägele, S., Koch, F., Matthes, F.: "Barriers for the Advancement of an API Economy in the German Automotive Industry and Potential Measures to Overcome these Barriers". Proceedings of the 22nd International Conference on Enterprise Information Systems (ICEIS), Prague 2020 - to appear

 

Bondel, G., Buchelt, S., Urlberger, H., Ulrich, N., Kabelin, C., Matthes, F.: "Towards a Change Management Framework for Cloud Transitions: Findings from a Case Study at a German Machine Manufacturer". Proceedings of the 22nd International Conference on Enterprise Information Systems (ICEIS), Prague 2020 - to appear

 


Three papers presented at HICSS 2020

Three sebis research papers were presented at the 53rd Hawaii International Conference on Systems Sciences (HICSS) 2020:

 

Huth, D., Burmeister, F., Matthes, F., and Schirmer, I. 2020. "Empirical Results on the Collaboration Between Enterprise Architecture and Data Protection Management during the Implementation of the GDPR"

Abstract: The European General Data Protection Regulation’s (GDPR) large imminent fines cause companies worldwide to undertake major efforts for privacy compliance. Any company doing business with European customers has to adhere to new processing principles and documentation requirements, and provide extensive access rights to data subjects.
Enterprise architecture management (EAM) provides a theoretical and methodical framework to align business and IT and has been used, among others, to identify and address concerns that arose from regulation.
In this work, we report results from 24 qualitative interviews with 29 enterprise architects on how EAM supports the work of data protection management (DPM) experts. We derive a conceptual framework with four different levels of EAM support for DPM, and discuss high-level recommendations for each level.

 

Burmeister, F., Huth, D., Schirmer, I., Drews, P., and Matthes, F. 2020. "Enhancing Information Governance with Enterprise Architecture Management : Design Principles Derived from Benefits and Barriers in the GDPR Implementation"

Abstract: Businesses today are increasingly dependent on how they transform information into economic value, while simultaneously being compliant with intensified privacy requirements, resulting from legal acts like the General Data Protection Regulation (GDPR). As a consequence, realizing information governance has become a topic more important than ever to balance the beneficial use and protection of information. This paper argues that enterprise architecture management (EAM) can be a key to GDPR implementation as one important domain of information governance by providing transparency on information integration throughout an organization. Based on 24 interviews with 29 enterprise architects, we identified a multiplicity of benefits and barriers within the interplay of EAM and GDPR implementation and derived seven design principles that should foster EAM to enhance information governance.

 

Kleehaus, M., Corpancho, N., Huth, D., Matthes, F. 2020. "Discovery of Microservice-based IT Landscapes at Runtime: Algorithms and Visualizations"

Abstract: The documentation of IT landscapes is a challenging task which is still performed mainly manually. Technology and software development trends like agile practices and microservice-based architectures exacerbate the endeavours to keep documentation up-to-date. Recent research efforts for automating this task have not addressed runtime data for gathering the architecture and remain unclear regarding proper algorithms and visualization support. In this paper, we want to close this research gap by presenting two algorithms that 1) discover the IT landscape based on historical data and 2) create continuously architecture snapshots based on new incoming runtime data. We especially consider scenarios in which runtime artifacts or communications paths were removed from the architecture as those cases are challenging to unveil from runtime data. We evaluate our prototype by analyzing the monitoring data from 79 days of a big automotive company. The algorithms provided promising results. The implemented prototype allows stakeholders to explore the snapshots in order to analyze the emerging behavior of the microservice-based IT landscape.