@article{PrasseKnaebelMachlicaetal.2019, author = {Prasse, Paul and Knaebel, Rene and Machlica, Lukas and Pevny, Tomas and Scheffer, Tobias}, title = {Joint detection of malicious domains and infected clients}, series = {Machine learning}, volume = {108}, journal = {Machine learning}, number = {8-9}, publisher = {Springer}, address = {Dordrecht}, issn = {0885-6125}, doi = {10.1007/s10994-019-05789-z}, pages = {1353 -- 1368}, year = {2019}, abstract = {Detection of malware-infected computers and detection of malicious web domains based on their encrypted HTTPS traffic are challenging problems, because only addresses, timestamps, and data volumes are observable. The detection problems are coupled, because infected clients tend to interact with malicious domains. Traffic data can be collected at a large scale, and antivirus tools can be used to identify infected clients in retrospect. Domains, by contrast, have to be labeled individually after forensic analysis. We explore transfer learning based on sluice networks; this allows the detection models to bootstrap each other. In a large-scale experimental study, we find that the model outperforms known reference models and detects previously unknown malware, previously unknown malware families, and previously unknown malicious domains.}, language = {en} } @article{PrasseIversenLienhardetal.2022, author = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Herwig, Ralf and Scheffer, Tobias}, title = {Pre-Training on In Vitro and Fine-Tuning on Patient-Derived Data Improves Deep Neural Networks for Anti-Cancer Drug-Sensitivity Prediction}, series = {MDPI}, volume = {14}, journal = {MDPI}, edition = {16}, publisher = {MDPI}, address = {Basel, Schweiz}, issn = {2072-6694}, doi = {10.3390/cancers14163950}, pages = {1 -- 14}, year = {2022}, abstract = {Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models' accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.}, language = {en} } @article{BickelBruecknerScheffer2009, author = {Bickel, Steffen and Br{\"u}ckner, Michael and Scheffer, Tobias}, title = {Discriminative learning under covariate shift}, issn = {1532-4435}, year = {2009}, abstract = {We address classification problems for which the training instances are governed by an input distribution that is allowed to differ arbitrarily from the test distribution-problems also referred to as classification under covariate shift. We derive a solution that is purely discriminative: neither training nor test distribution are modeled explicitly. The problem of learning under covariate shift can be written as an integrated optimization problem. Instantiating the general optimization problem leads to a kernel logistic regression and an exponential model classifier for covariate shift. The optimization problem is convex under certain conditions; our findings also clarify the relationship to the known kernel mean matching procedure. We report on experiments on problems of spam filtering, text classification, and landmine detection.}, language = {en} } @article{BickelBruecknerScheffer2009, author = {Bickel, Steffen and Brueckner, Michael and Scheffer, Tobias}, title = {Discriminative learning under covariate shift}, issn = {1532-4435}, year = {2009}, abstract = {We address classification problems for which the training instances are governed by an input distribution that is allowed to differ arbitrarily from the test distribution-problems also referred to as classification under covariate shift. We derive a solution that is purely discriminative: neither training nor test distribution are modeled explicitly. The problem of learning under covariate shift can be written as an integrated optimization problem. Instantiating the general optimization problem leads to a kernel logistic regression and an exponential model classifier for covariate shift. The optimization problem is convex under certain conditions; our findings also clarify the relationship to the known kernel mean matching procedure. We report on experiments on problems of spam filtering, text classification, and landmine detection.}, language = {en} } @article{HaiderScheffer2009, author = {Haider, Peter and Scheffer, Tobias}, title = {Bayesian clustering for email campaign detection}, isbn = {978-1-605-58516-1}, year = {2009}, language = {en} } @misc{PatilHaiderPopeetal.2011, author = {Patil, Kaustubh R. and Haider, Peter and Pope, Phillip B. and Turnbaugh, Peter J. and Morrison, Mark and Scheffer, Tobias and McHardy, Alice C.}, title = {Taxonomic metagenome sequence assignment with structured output models}, series = {Nature methods : techniques for life scientists and chemists}, volume = {8}, journal = {Nature methods : techniques for life scientists and chemists}, number = {3}, publisher = {Nature Publ. Group}, address = {London}, issn = {1548-7091}, doi = {10.1038/nmeth0311-191}, pages = {191 -- 192}, year = {2011}, language = {en} } @article{BruecknerKanzowScheffer2012, author = {Br{\"u}ckner, Michael and Kanzow, Christian and Scheffer, Tobias}, title = {Static prediction games for adversarial learning problems}, series = {Journal of machine learning research}, volume = {13}, journal = {Journal of machine learning research}, publisher = {Microtome Publishing}, address = {Cambridge, Mass.}, issn = {1532-4435}, pages = {2617 -- 2654}, year = {2012}, abstract = {The standard assumption of identically distributed training and test data is violated when the test data are generated in response to the presence of a predictive model. This becomes apparent, for example, in the context of email spam filtering. Here, email service providers employ spam filters, and spam senders engineer campaign templates to achieve a high rate of successful deliveries despite the filters. We model the interaction between the learner and the data generator as a static game in which the cost functions of the learner and the data generator are not necessarily antagonistic. We identify conditions under which this prediction game has a unique Nash equilibrium and derive algorithms that find the equilibrial prediction model. We derive two instances, the Nash logistic regression and the Nash support vector machine, and empirically explore their properties in a case study on email spam filtering.}, language = {en} } @misc{PrasseIversenLienhardetal.2022, author = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Herwig, Ralf and Scheffer, Tobias}, title = {Pre-Training on In Vitro and Fine-Tuning on Patient-Derived Data Improves Deep Neural Networks for Anti-Cancer Drug-Sensitivity Prediction}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, issn = {1866-8372}, doi = {10.25932/publishup-57734}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-577341}, pages = {1 -- 14}, year = {2022}, abstract = {Large-scale databases that report the inhibitory capacities of many combinations of candidate drug compounds and cultivated cancer cell lines have driven the development of preclinical drug-sensitivity models based on machine learning. However, cultivated cell lines have devolved from human cancer cells over years or even decades under selective pressure in culture conditions. Moreover, models that have been trained on in vitro data cannot account for interactions with other types of cells. Drug-response data that are based on patient-derived cell cultures, xenografts, and organoids, on the other hand, are not available in the quantities that are needed to train high-capacity machine-learning models. We found that pre-training deep neural network models of drug sensitivity on in vitro drug-sensitivity databases before fine-tuning the model parameters on patient-derived data improves the models' accuracy and improves the biological plausibility of the features, compared to training only on patient-derived data. From our experiments, we can conclude that pre-trained models outperform models that have been trained on the target domains in the vast majority of cases.}, language = {en} } @article{PrasseIversenLienhardetal.2022, author = {Prasse, Paul and Iversen, Pascal and Lienhard, Matthias and Thedinga, Kristina and Bauer, Christopher and Herwig, Ralf and Scheffer, Tobias}, title = {Matching anticancer compounds and tumor cell lines by neural networks with ranking loss}, series = {NAR: genomics and bioinformatics}, volume = {4}, journal = {NAR: genomics and bioinformatics}, number = {1}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {2631-9268}, doi = {10.1093/nargab/lqab128}, pages = {10}, year = {2022}, abstract = {Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drug components that are likely to achieve the highest efficacy for a cancer cell line at hand at a therapeutic dose. State of the art drug sensitivity models use regression techniques to predict the inhibitory concentration of a drug for a tumor cell line. This regression objective is not directly aligned with either of these principal goals of drug sensitivity models: We argue that drug sensitivity modeling should be seen as a ranking problem with an optimization criterion that quantifies a drug's inhibitory capacity for the cancer cell line at hand relative to its toxicity for healthy cells. We derive an extension to the well-established drug sensitivity regression model PaccMann that employs a ranking loss and focuses on the ratio of inhibitory concentration and therapeutic dosage range. We find that the ranking extension significantly enhances the model's capability to identify the most effective anticancer drugs for unseen tumor cell profiles based in on in-vitro data.}, language = {en} } @article{BauerHerwigLienhardetal.2021, author = {Bauer, Chris and Herwig, Ralf and Lienhard, Matthias and Prasse, Paul and Scheffer, Tobias and Schuchhardt, Johannes}, title = {Large-scale literature mining to assess the relation between anti-cancer drugs and cancer types}, series = {Journal of translational medicine}, volume = {19}, journal = {Journal of translational medicine}, number = {1}, publisher = {BioMed Central}, address = {London}, issn = {1479-5876}, doi = {10.1186/s12967-021-02941-z}, pages = {13}, year = {2021}, abstract = {Background: There is a huge body of scientific literature describing the relation between tumor types and anti-cancer drugs. The vast amount of scientific literature makes it impossible for researchers and physicians to extract all relevant information manually. Methods: In order to cope with the large amount of literature we applied an automated text mining approach to assess the relations between 30 most frequent cancer types and 270 anti-cancer drugs. We applied two different approaches, a classical text mining based on named entity recognition and an AI-based approach employing word embeddings. The consistency of literature mining results was validated with 3 independent methods: first, using data from FDA approvals, second, using experimentally measured IC-50 cell line data and third, using clinical patient survival data. Results: We demonstrated that the automated text mining was able to successfully assess the relation between cancer types and anti-cancer drugs. All validation methods showed a good correspondence between the results from literature mining and independent confirmatory approaches. The relation between most frequent cancer types and drugs employed for their treatment were visualized in a large heatmap. All results are accessible in an interactive web-based knowledge base using the following link: . Conclusions: Our approach is able to assess the relations between compounds and cancer types in an automated manner. Both, cancer types and compounds could be grouped into different clusters. Researchers can use the interactive knowledge base to inspect the presented results and follow their own research questions, for example the identification of novel indication areas for known drugs.}, language = {en} }