@article{pullar-strecker2021hitting,

title = {Hitting the Target: Stopping Active Learning at the Cost-Based Optimum},

author = {Zac Pullar-Strecker and Katharina Dost and Eibe Frank and J\"{o}rg Wicker},

url = {https://arxiv.org/abs/2110.03802},

year  = {2021},

date = {2021-10-08},

urldate = {2021-10-08},

journal = {arXiv preprint},

abstract = {Active learning allows machine learning models to be trained using fewer labels while retaining similar performance to traditional fully supervised learning. An active learner selects the most informative data points, requests their labels, and retrains itself. While this approach is promising, it leaves an open problem of how to determine when the model is `good enough' without the additional labels required for traditional evaluation. In the past, different stopping criteria have been proposed aiming to identify the optimal stopping point. However, optimality can only be expressed as a domain-dependent trade-off between accuracy and the number of labels, and no criterion is superior in all applications. This paper is the first to give actionable advice to practitioners on what stopping criteria they should use in a given real-world scenario. We contribute the first large-scale comparison of stopping criteria, using a cost measure to quantify the accuracy/label trade-off, public implementations of all stopping criteria we evaluate, and an open-source framework for evaluating stopping criteria. Our research enables practitioners to substantially reduce labelling costs by utilizing the stopping criterion which best suits their domain.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tam2021holisticb,

title = {Holistic Evaluation of Biodegradation Pathway Prediction: Assessing Multi-Step Reactions and Intermediate Products},

author = {Jason Tam and Tim Lorsbach and Sebastian Schmidt and J\"{o}rg Wicker},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-021-00543-x},

doi = {10.1186/s13321-021-00543-x},

year  = {2021},

date = {2021-09-03},

urldate = {2021-08-23},

journal = {Journal of Cheminformatics},

volume = {13},

number = {1},

pages = {63},

abstract = {The prediction of metabolism and biotransformation pathways of xenobiotics is a highly desired tool in environmental sciences, drug discovery, and (eco)toxicology. Several systems predict single transformation steps or complete pathways as series of parallel and subsequent steps. Their performance is commonly evaluated on the level of a single transformation step. Such an approach cannot account for some specific challenges that are caused by specific properties of biotransformation experiments. That is, missing transformation products in the reference data that occur only in low concentrations, e.g. transient intermediates or higher-generation metabolites. Furthermore, some rule-based prediction systems evaluate the performance only based on the defined set of transformation rules. Therefore, the performance of these models cannot be directly compared. In this paper, we introduce a new evaluation framework that extends the evaluation of biotransformation prediction from single transformations to whole pathways, taking into account multiple generations of metabolites. We introduce a procedure to address transient intermediates and propose a weighted scoring system that acknowledges the uncertainty of higher-generation metabolites. We implemented this framework in enviPath and demonstrate its strict performance metrics on predictions of in vitro biotransformation and degradation of xenobiotics in soil. Our approach is model-agnostic and can be transferred to other prediction systems. It is also capable of revealing knowledge gaps in terms of incompletely defined sets of transformation rules.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{chang2021intriguing,

title = {Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning},

author = {Luke Chang and Katharina Dost and Kaiqi Zhai and Ambra Demontis and Fabio Roli and Gillian Dobbie and J\"{o}rg Wicker},

url = {https://arxiv.org/abs/2105.00495},

year  = {2021},

date = {2021-05-02},

journal = {arxiv},

volume = {2105.00495},

abstract = {Defending machine learning models from adversarial attacks is still a challenge: none of the robust models is utterly immune to adversarial examples to date. Different defences have been proposed; however, most of them are tailored to particular ML models and adversarial attacks, therefore their effectiveness and applicability are strongly limited. A similar problem plagues cheminformatics: Quantitative Structure-Activity Relationship (QSAR) models struggle to predict biological activity for the entire chemical space because they are trained on a very limited amount of compounds with known effects. This problem is relieved with a technique called Applicability Domain (AD), which rejects the unsuitable compounds for the model. Adversarial examples are intentionally crafted inputs that exploit the blind spots which the model has not learned to classify, and adversarial defences try to make the classifier more robust by covering these blind spots. There is an apparent similarity between AD and adversarial defences. Inspired by the concept of AD, we propose a multi-stage data-driven defence that is testing for: Applicability: abnormal values, namely inputs not compliant with the intended use case of the model; Reliability: samples far from the training data; and Decidability: samples whose predictions contradict the predictions of their neighbours. It can be applied to any classification model and is not limited to specific types of adversarial attacks. With an empirical analysis, this paper demonstrates how Applicability Domain can effectively reduce the vulnerability of ML models to adversarial examples. },

note = {preprint},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tam2021holistic,

title = {Holistic Evaluation of Biodegradation Pathway Prediction: Assessing Multi-Step Reactions and Intermediate Products},

author = {Jason Tam and Tim Lorsbach and Sebastian Schmidt and J\"{o}rg Wicker},

url = {https://chemrxiv.org/articles/preprint/Holistic_Evaluation_of_Biodegradation_Pathway_Prediction_Assessing_Multi-Step_Reactions_and_Intermediate_Products/14315963},

doi = {10.26434/chemrxiv.14315963},

year  = {2021},

date = {2021-03-27},

urldate = {2021-03-27},

journal = {ChemRxiv},

abstract = {The prediction of metabolism and biotransformation pathways of xenobiotics is a highly desired tool in environmental and life sciences. There are several systems that currently predict single transformation steps or complete pathways as series of parallel and subsequent steps.  Their accuracy is often evaluated on the level of a single transformation step.  Such an approach cannot account for some specific challenges that are related to the nature of the biotransformation experiments.  This is particularly true for missing transformation products in the reference data that occur only in low concentrations, e.g.  transient intermediates or higher-generation metabolites. Furthermore, some rule-based prediction systems evaluate accuracy only based on the defined set of transformation rules. Therefore, the performance of different models cannot be directly compared.In this paper, we introduce a new evaluation framework that extends the evaluation of biotransformation prediction to holistically evaluating predicted pathways, taking into account multiple generations of metabolites.  We introduce a procedure to address transient intermediates and propose a weighted scoring system that acknowledges the uncertainty of higher-generation metabolites.  We implemented this framework in enviPath and demonstrate its strict performance metrics on predictions of in vitro biotransformation and degradation of xenobiotics in soil.Our approach is model-agnostic and can be transferred to other prediction systems.  It is also capable of revealing knowledge gaps  in  terms  of  incompletely  defined  sets  of  transformation rules.},

note = {preprint, accepted for publication at the Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{stepisnik2021comprehensive,

title = {A comprehensive comparison of molecular feature representations for use in predictive modeling},

author = {Toma\v{z} Stepi\v{s}nik and Bla\v{z} \v{S}krlj and J\"{o}rg Wicker and Dragi Kocev},

url = {http://www.sciencedirect.com/science/article/pii/S001048252030528X},

doi = {10.1016/j.compbiomed.2020.104197},

issn = {0010-4825},

year  = {2021},

date = {2021-03-01},

journal = {Computers in Biology and Medicine},

volume = {130},

pages = {104197},

abstract = {Machine learning methods are commonly used for predicting molecular properties to accelerate material and drug design. An important part of this process is deciding how to represent the molecules. Typically, machine learning methods expect examples represented by vectors of values, and many methods for calculating molecular feature representations have been proposed. In this paper, we perform a comprehensive comparison of different molecular features, including traditional methods such as fingerprints and molecular descriptors, and recently proposed learnable representations based on neural networks. Feature representations are evaluated on 11 benchmark datasets, used for predicting properties and measures such as mutagenicity, melting points, activity, solubility, and IC50. Our experiments show that several molecular features work similarly well over all benchmark datasets. The ones that stand out most are Spectrophores, which give significantly worse performance than other features on most datasets. Molecular descriptors from the PaDEL library seem very well suited for predicting physical properties of molecules. Despite their simplicity, MACCS fingerprints performed very well overall. The results show that learnable representations achieve competitive performance compared to expert based representations. However, task-specific representations (graph convolutions and Weave methods) rarely offer any benefits, even though they are computationally more demanding. Lastly, combining different molecular feature representations typically does not give a noticeable improvement in performance compared to individual feature representations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{roeslin2020machine,

title = {A machine learning damage prediction model for the 2017 Puebla-Morelos, Mexico, earthquake},

author = {Samuel Roeslin and Quincy Ma and Hugon Ju\'{a}rez-Garcia and Alonso G\'{o}mez-Bernal and J\"{o}rg Wicker and Liam Wotherspoon},

doi = {https://doi.org/10.1177/8755293020936714},

year  = {2020},

date = {2020-07-30},

journal = {Earthquake Spectra},

volume = {36},

number = {2},

pages = {314-339},

abstract = {The 2017 Puebla, Mexico, earthquake event led to significant damage in many buildings in Mexico City. In the months following the earthquake, civil engineering students conducted detailed building assessments throughout the city. They collected building damage information and structural characteristics for 340 buildings in the Mexico City urban area, with an emphasis on the Roma and Condesa neighborhoods where they assessed 237 buildings. These neighborhoods are of particular interest due to the availability of seismic records captured by nearby recording stations, and preexisting information from when the neighborhoods were affected by the 1985 Michoac\'{a}n earthquake. This article presents a case study on developing a damage prediction model using machine learning. It details a framework suitable for working with future post-earthquake observation data. Four algorithms able to perform classification tasks were trialed. Random forest, the best performing algorithm, achieves more than 65% prediction accuracy. The study of the feature importance for the random forest shows that the building location, seismic demand, and building height are the parameters that influence the model output the most.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}