enviPath

@article{Dost2022combatting,

title = {Combatting Over-Specialization Bias in Growing Chemical Databases},

author = {Katharina Dost and Zac Pullar-Strecker and Liam Brydon and Kunyang Zhang and Jasmin Hafner and Pat Riddle and J\"{o}rg Wicker},

doi = {https://doi.org/10.21203/rs.3.rs-2133331/v1},

year  = {2022},

date = {2022-10-05},

journal = {Research Square},

abstract = {Background: Predicting in advance the behavior of new chemical compounds can support the design process of new products by directing the research towards the most promising candidates and ruling out others. Such predictive models can be data-driven using Machine Learning or based on researchers' experience and depend on the collection of past results. In either case: models (or researchers) can only make reliable assumptions on compounds that are similar to what they have seen before. Therefore, consequent usage of these predictive models shapes the dataset and causes a continuous specialization shrinking the applicability domain of all trained models on this dataset in the future, and increasingly harming model-based exploration of the space. 



Proposed Solution: In this paper, we propose CANCELS (CounterActiNg Compound spEciaLization biaS), a technique that helps to break the dataset specialization spiral. Aiming for a smooth distribution of the compounds in the dataset, we identify areas in the space that fall short and suggest additional experiments that help bridge the gap. Thereby, we generally improve the dataset quality in an entirely unsupervised manner and create awareness of potential flaws in the data. CANCELS does not aim to cover the entire compound space and hence retains a desirable degree of specialization to a specified research domain. 



Results: An extensive set of experiments on the use-case of biodegradation pathway prediction not only reveals that the bias spiral can indeed be observed but also that CANCELS produces meaningful results. Additionally, we demonstrate that mitigating the observed bias is crucial as it cannot only intervene with the continuous specialization process, but also significantly improves a predictor's performance while reducing the amount of required experiments. Overall, we believe that CANCELS can support researchers in their experimentation process to not only better understand their data and potential flaws, but also to grow the dataset in a sustainable way. All code is available under github.com/KatDost/Cancels.},

note = {preprint},

keywords = {},

pubstate = {forthcoming},

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

https://chemrxiv.org/articles/preprint/Holistic_Evaluation_of_Biodegradation_Pathway_Prediction_Assessing_Multi-Step_Reactions_and_Intermediate_Products/14315963

https://dx.doi.org/10.26434/chemrxiv.14315963},

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

year  = {2021},

date = {2021-09-03},

urldate = {2021-09-03},

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{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{latino2017eawag,

title = {Eawag-Soil in enviPath: a new resource for exploring regulatory pesticide soil biodegradation pathways and half-life data},

author = {Diogo Latino and J\"{o}rg Wicker and Martin G\"{u}tlein and Emanuel Schmid and Stefan Kramer and Kathrin Fenner},

doi = {10.1039/C6EM00697C},

year  = {2017},

date = {2017-01-01},

journal = {Environmental Science: Process \& Impact},

publisher = {The Royal Society of Chemistry},

abstract = {Developing models for the prediction of microbial biotransformation pathways and half-lives of trace organic contaminants in different environments requires as training data easily accessible and sufficiently large collections of respective biotransformation data that are annotated with metadata on study conditions. Here, we present the Eawag-Soil package, a public database that has been developed to contain all freely accessible regulatory data on pesticide degradation in laboratory soil simulation studies 

for pesticides registered in the EU (282 degradation pathways, 1535 reactions, 1619 compounds and 4716 biotransformation half-life values with corresponding metadata on study conditions). We provide a thorough description of this novel data resource, and discuss important features of the pesticide soil degradation data that are relevant for model development. Most notably, the variability of half-life values for individual compounds is large and only about one order of magnitude lower than the entire range of median half-life values spanned by all compounds, demonstrating the need to consider study conditions in the development of more accurate models for biotransformation prediction. We further show how the data can be used to find missing rules relevant for predicting soil biotransformation pathways. From this analysis, eight examples of reaction types were presented that should trigger the formulation of new biotransformation rules, e.g., Ar-OH methylation, or the extension of existing rules e.g., hydroxylation in aliphatic rings. The data were also used to exemplarily explore the dependence of half-lives of different amide pesticides on chemical class and experimental parameters. This analysis highlighted the value of considering initial transformation reactions for the development of meaningful quantitative-structure biotransformation relationships (QSBR), which is a novel opportunity of f ered by the simultaneous encoding of transformation reactions and corresponding half-lives in Eawag-Soil. Overall, Eawag-Soil provides an unprecedentedly rich collection of manually extracted and curated biotransformation data, which should be useful in a great variety of applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wicker2016envipath,

title = {enviPath - The Environmental Contaminant Biotransformation Pathway Resource},

author = {J\"{o}rg Wicker and Tim Lorsbach and Martin G\"{u}tlein and Emanuel Schmid and Diogo Latino and Stefan Kramer and Kathrin Fenner},

editor = {Michael Galperin},

url = {http://nar.oxfordjournals.org/content/44/D1/D502.abstract},

doi = {10.1093/nar/gkv1229},

year  = {2016},

date = {2016-01-01},

journal = {Nucleic Acid Research},

volume = {44},

number = {D1},

pages = {D502-D508},

abstract = {The University of Minnesota Biocatalysis/Biodegradation Database and Pathway Prediction System (UM-BBD/PPS) has been a unique resource covering microbial biotransformation pathways of primarily xenobiotic chemicals for over 15 years. This paper introduces the successor system, enviPath (The Environmental Contaminant Biotransformation Pathway Resource), which is a complete redesign and reimplementation of UM-BBD/PPS. enviPath uses the database from the UM-BBD/PPS as a basis, extends the use of this database, and allows users to include their own data to support multiple use cases. Relative reasoning is supported for the refinement of predictions and to allow its extensions in terms of previously published, but not implemented machine learning models. User access is simplified by providing a REST API that simplifies the inclusion of enviPath into existing workflows. An RDF database is used to enable simple integration with other databases. enviPath is publicly available at https://envipath.org with free and open access to its core data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wicker2010predicting,

title = {Predicting biodegradation products and pathways: a hybrid knowledge- and machine learning-based approach},

author = {J\"{o}rg Wicker and Kathrin Fenner and Lynda Ellis and Larry Wackett and Stefan Kramer},

url = {http://bioinformatics.oxfordjournals.org/content/26/6/814.full},

doi = {10.1093/bioinformatics/btq024},

year  = {2010},

date = {2010-01-01},

journal = {Bioinformatics},

volume = {26},

number = {6},

pages = {814-821},

publisher = {Oxford University Press},

abstract = {Motivation: Current methods for the prediction of biodegradation products and pathways of organic environmental pollutants either do not take into account domain knowledge or do not provide probability estimates. In this article, we propose a hybrid knowledge- and machine learning-based approach to overcome these limitations in the context of the University of Minnesota Pathway Prediction System (UM-PPS). The proposed solution performs relative reasoning in a machine learning framework, and obtains one probability estimate for each biotransformation rule of the system. As the application of a rule then depends on a threshold for the probability estimate, the trade-off between recall (sensitivity) and precision (selectivity) can be addressed and leveraged in practice.Results: Results from leave-one-out cross-validation show that a recall and precision of ∼0.8 can be achieved for a subset of 13 transformation rules. Therefore, it is possible to optimize precision without compromising recall. We are currently integrating the results into an experimental version of the UM-PPS server.Availability: The program is freely available on the web at http://wwwkramer.in.tum.de/research/applications/biodegradation/data.Contact: kramer@in.tum.de},

keywords = {},

pubstate = {published},

tppubtype = {article}

}