@article{miller2025unraveling,

title = {Unraveling ADHD: genes, co-occurring traits, and developmental dynamics},

author = {Catriona J Miller and Evgenija Golovina and Sreemol Gokuladhas and J\"{o}rg Wicker and Jessie C Jacobson and Justin M O\'Sullivan},

doi = {10.26508/lsa.202403029},

year  = {2025},

date = {2025-02-25},

journal = {Life Science Alliance},

volume = {8},

number = {5},

abstract = {Attention-deficit/hyperactivity disorder (ADHD) is a heterogeneous neurodevelopmental condition with a high prevalence of co-occurring conditions, contributing to increased difficulty in long-term management. Genome-wide association studies have identified variants shared between ADHD and co-occurring psychiatric disorders; however, the genetic mechanisms are not fully understood. We integrated gene expression and spatial organization data into a two-sample Mendelian randomization study for putatively causal ADHD genes in fetal and adult cortical tissues. We identified four genes putatively causal for ADHD in cortical tissues (fetal: ST3GAL3, PTPRF, PIDD1; adult: ST3GAL3, TIE1). Protein{textendash}protein interaction databases seeded with the causal ADHD genes identified biological pathways linking these genes with conditions (e.g., rheumatoid arthritis) and biomarkers (e.g., lymphocyte counts) known to be associated with ADHD, but without previously shown genetic relationships. The analysis was repeated on adult liver tissue, where putatively causal ADHD gene ST3GAL3 was linked to cholesterol traits. This analysis provides insight into the tissue-dependent temporal relationships between ADHD, co-occurring traits, and biomarkers. Importantly, it delivers evidence for the genetic interplay between co-occurring conditions, both previously studied and unstudied, with ADHD.The multimorbid3D pipeline was created and run in Python (version 3.8.8). All visualizations and data analysis were performed in R (version 4.2.0) through RStudio (version 2022.02.2). Table S16 lists the datasets and software that have been used in our analyses. All scripts are available on GitHub (https://github.com/Catriona-Miller/ADHD_Co-occurring_Traits).Table S16. Software and datasets used for this analysis.Ethics statementEthics approval was obtained from the University of Auckland Human Participants Ethics Committee (Decoding SNPs in context, UAHPEC19373).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Brydon2024b,

title = {Predictive Modeling of Biodegradation Pathways Using Transformer Architectures},

author = {Liam Brydon and Kunyang Zhang and Gillian Dobbie and Katerina Taskova and J\"{o}rg Wicker},

url = { https://doi.org/10.21203/rs.3.rs-5200860/v3},

doi = {10.1186/s13321-025-00969-7},

issn = {1758-2946},

year  = {2025},

date = {2025-02-17},

urldate = {2024-10-24},

journal = {Journal of Cheminformatics},

volume = {17},

number = {1},

pages = {21},

abstract = {In recent years, the integration of machine learning techniques into chemical reaction product prediction has opened new avenues for understanding and predicting the behaviour of chemical substances. The necessity for such predictive methods stems from the growing regulatory and social awareness of the environmental consequences associated with the persistence and accumulation of chemical residues. Traditional biodegradation prediction methods rely on expert knowledge to perform predictions. However, creating this expert knowledge is becoming increasingly prohibitive due to the complexity and diversity of newer datasets, leaving existing methods unable to perform predictions on these datasets. We formulate the product prediction problem as a sequence-to-sequence generation task and take inspiration from natural language processing and other reaction prediction tasks. In doing so, we reduce the need for the expensive manual creation of expert-based rules. },

howpublished = {ResearchSquare},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Albrecht2024forecasting,

title = {Forecasting severe respiratory disease hospitalizations using machine learning algorithms},

author = {Steffen Albrecht and David Broderick and Katharina Dost and Isabella Cheung and Nhung Nghiem and Milton Wu and Johnny Zhu and Nooriyan Poonawala-Lohani and Sarah Jamison and Damayanthi Rasanathan and Sue Huang and Adrian Trenholme and Alicia Stanley and Shirley Lawrence and Samantha Marsh and Lorraine Castelino and Janine Paynter and Nikki Turner and Peter McIntyre and Pat Riddle and Cameron Grant and Gillian Dobbie and J\"{o}rg Wicker},

url = {https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-024-02702-0},

doi = {10.1186/s12911-024-02702-0},

issn = {1472-6947},

year  = {2024},

date = {2024-10-09},

urldate = {2024-10-07},

journal = {BMC Medical Informatics and Decision Making},

volume = {24},

issue = {1},

pages = {293},

abstract = {Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload. In this study, we explore the capability of forecasting models to predict the number of hospital admissions in Auckland, New Zealand, within a three-week time horizon. Furthermore, we evaluate probabilistic forecasts and the impact on model performance when integrating laboratory data describing the circulation of respiratory viruses.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hua2023systematic,

title = {A Systematic Review of Aspect-based Sentiment Analysis: Domains, Methods, and Trends},

author = {Yan Cathy Hua and Paul Denny and J\"{o}rg Wicker and Katerina Taskova},

url = {https://link.springer.com/article/10.1007/s10462-024-10906-z

https://arxiv.org/abs/2311.10777},

doi = {10.1007/s10462-024-10906-z},

issn = {1573-7462},

year  = {2024},

date = {2024-09-17},

urldate = {2023-11-17},

journal = {Artificial Intelligence Review},

volume = {57},

number = {11},

pages = {296},

abstract = {Aspect-based sentiment analysis (ABSA) is a fine-grained type of sentiment analysis that identifies aspects and their associated opinions from a given text. With the surge of digital opinionated text data, ABSA gained increasing popularity for its ability to mine more detailed and targeted insights. Many review papers on ABSA subtasks and solution methodologies exist, however, few focus on trends over time or systemic issues relating to research application domains, datasets, and solution approaches. To fill the gap, this paper presents a systematic literature review (SLR) of ABSA studies with a focus on trends and high-level relationships among these fundamental components. This review is one of the largest SLRs on ABSA. To our knowledge, it is also the first to systematically examine the interrelations among ABSA research and data distribution across domains, as well as trends in solution paradigms and approaches. Our sample includes 727 primary studies screened from 8550 search results without time constraints via an innovative automatic filtering process. Our quantitative analysis not only identifies trends in nearly two decades of ABSA research development but also unveils a systemic lack of dataset and domain diversity as well as domain mismatch that may hinder the development of future ABSA research. We discuss these findings and their implications and propose suggestions for future research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hafner2023advancements,

title = {Advancements in Biotransformation Pathway Prediction: Enhancements, Datasets, and Novel Functionalities in enviPath},

author = {Jasmin Hafner and Tim Lorsbach and Sebastian Schmidt and Liam Brydon and Katharina Dost and Kunyang Zhang and Kathrin Fenner and J\"{o}rg Wicker},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-024-00881-6

https://envipath.org},

doi = {10.1186/s13321-024-00881-6},

issn = {1758-2946},

year  = {2024},

date = {2024-08-06},

urldate = {2024-08-06},

journal = {Journal of Cheminformatics},

volume = {16},

number = {1},

pages = {93},

abstract = {enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data and prediction system are freely available both via a web interface and a public REST API. Since its initial release in 2016, we extended the data available in enviPath and improved the performance of the prediction system and usability of the overall system. We now provide three diverse data sets, covering microbial biotransformation in different environments and under different experimental conditions. This also enabled developing a pathway prediction model that is applicable to a more diverse set of chemicals. In the prediction engine, we implemented a new evaluation tailored towards pathway prediction, which returns a more honest and holistic view on the performance. We also implemented a novel applicability domain algorithm, which allows the user to estimate how well the model will perform on their data. Finally, we improved the implementation to speed up the overall system and provide new functionality via a plugin system.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lyu2023regional,

title = {Regional Bias in Monolingual English Language Models},

author = {Jiachen Lyu and Katharina Dost and Yun Sing Koh and J\"{o}rg Wicker},

url = {https://link.springer.com/article/10.1007/s10994-024-06555-6

https://dx.doi.org/10.21203/rs.3.rs-3713494/v1},

doi = {10.1007/s10994-024-06555-6},

issn = {1573-0565},

year  = {2024},

date = {2024-07-09},

urldate = {2024-07-09},

journal = {Machine Learning},

abstract = { In Natural Language Processing (NLP), pre-trained language models (LLMs) are widely employed and refined for various tasks. These models have shown considerable social and geographic biases creating skewed or even unfair representations of certain groups. Research focuses on biases toward L2 (English as a second language) regions but neglects bias within L1 (first language) regions. In this work, we ask if there is regional bias within L1 regions already inherent in pre-trained LLMs and, if so, what the consequences are in terms of downstream model performance. We contribute an investigation framework specifically tailored for low-resource regions, offering a method to identify bias without imposing strict requirements for labeled datasets. Our research reveals subtle geographic variations in the word embeddings of BERT, even in cultures traditionally perceived as similar. These nuanced features, once captured, have the potential to significantly impact downstream tasks. Generally, models exhibit comparable performance on datasets that share similarities, and conversely, performance may diverge when datasets differ in their nuanced features embedded within the language. It is crucial to note that estimating model performance solely based on standard benchmark datasets may not necessarily apply to the datasets with distinct features from the benchmark datasets. Our proposed framework plays a pivotal role in identifying and addressing biases detected in word embeddings, particularly evident in low-resource regions such as New Zealand.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Long2023adducthunter,

title = {AdductHunter: Identifying Protein-Metal Complex Adducts in Mass Spectra},

author = {Derek Long and Liam Eade and Katharina Dost and Samuel M Meier-Menches and David C Goldstone and Matthew P Sullivan and Christian Hartinger and J\"{o}rg Wicker and Katerina Taskova},

url = {https://adducthunter.wickerlab.org

https://doi.org/10.21203/rs.3.rs-3322854/v1},

doi = {10.1186/s13321-023-00797-7},

issn = {1758-2946},

year  = {2024},

date = {2024-02-06},

urldate = {2024-02-06},

journal = {Journal of Cheminformatics},

volume = {16},

issue = {1},

abstract = {Mass spectrometry (MS) is an analytical technique for molecule identification that can be used for investigating protein-metal complex interactions. Once the MS data is collected, the mass spectra are usually interpreted manually to identify the adducts formed as a result of the interactions between proteins and metal-based species. However, with increasing resolution, dataset size, and species complexity, the time required to identify adducts and the error-prone nature of manual assignment have become limiting factors in MS analysis. AdductHunter is a open-source web-based analysis tool that  automates the peak identification process using constraint integer optimization to find feasible combinations of protein and fragments, and dynamic time warping to calculate the dissimilarity between the theoretical isotope pattern of a species and its experimental isotope peak distribution. Empirical evaluation on a collection of 22 unique MS datasetsshows fast and accurate identification of protein-metal complex adducts in deconvoluted mass spectra.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}