@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 = {2023-12-06},

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 = {2023-05-29},

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}

}

@article{Miller2023denovo,

title = {De novo network analysis reveals autism causal genes and developmental links to co-occurring traits},

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

url = {https://www.medrxiv.org/content/10.1101/2023.04.24.23289060v1},

doi = {10.26508/lsa.202302142},

year  = {2023},

date = {2023-08-08},

urldate = {2023-08-08},

journal = {Life Science Alliance},

volume = {6},

number = {10},

abstract = {Autism is a complex neurodevelopmental condition that manifests in various ways. Autism is often accompanied by other conditions, such as attention-deficit/hyperactivity disorder and schizophrenia, which can complicate diagnosis and management. Although research has investigated the role of specific genes in autism, their relationship with co-occurring traits is not fully understood. To address this, we conducted a two-sample Mendelian randomisation analysis and identified four genes located at the 17q21.31 locus that are putatively causal for autism in fetal cortical tissue (LINC02210, LRRC37A4P, RP11-259G18.1, and RP11-798G7.6). LINC02210 was also identified as putatively causal for autism in adult cortical tissue. By integrating data from expression quantitative trait loci, genes and protein interactions, we identified that the 17q21.31 locus contributes to the intersection between autism and other neurological traits in fetal cortical tissue. We also identified a distinct cluster of co-occurring traits, including cognition and worry, linked to the genetic loci at 3p21.1. Our findings provide insights into the relationship between autism and co-occurring traits, which could be used to develop predictive models for more accurate diagnosis and better clinical management.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Dost2023Combatting,

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},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-023-00716-w



},

doi = {10.1186/s13321-023-00716-w},

issn = {1758-2946},

year  = {2023},

date = {2023-05-19},

urldate = {2023-05-19},

journal = {Journal of Cheminformatics},

volume = {15},

issue = {1},

pages = {53},

abstract = {Background



Predicting in advance the behavior of new chemical compounds can support the design process of new products by directing the research toward 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 about 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 number 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.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bensemann2023from,

title = {From What You See to What We Smell: Linking Human Emotions to Bio-markers in Breath},

author = {Joshua Bensemann and Hasnain Cheena and David Tse Jung Huang and Elizabeth Broadbent and Jonathan Williams and J\"{o}rg Wicker},

url = {https://ieeexplore.ieee.org/document/10123109

https://doi.org/10.17608/k6.auckland.22777364 

https://doi.org/10.17608/k6.auckland.22777352 },

doi = {10.1109/TAFFC.2023.3275216},

issn = {1949-3045},

year  = {2023},

date = {2023-05-11},

urldate = {2023-05-11},

journal = {IEEE Transactions on Affective Computing},

pages = {1-13},

abstract = {Research has shown that the composition of breath can differ based on the human’s behavioral patterns and mental and physical states immediately before being collected. These breath-collection techniques have also been extended to observe the general processes occurring in groups of humans and can link them to what those groups are collectively experiencing. In this research, we applied machine learning techniques to the breath data collected from cinema audiences. These techniques included XGBOOST Regression, Hierarchical Clustering, and Item Basket analyses created using the Apriori algorithm. They were conducted to find associations between the biomarkers in the crowd’s breath and the movie’s audio-visual stimuli and thematic events. This analysis enabled us to directly link what the group was experiencing and their biological response to that experience. We first extracted visual and auditory features from a movie to achieve this. We compared it to the biomarkers in the crowd’s breath using regression and pattern mining techniques. Our results supported the theory that a crowd’s collective experience directly correlates to the biomarkers in the crowd’s breath. Consequently, these findings suggest that visual and auditory experiences have predictable effects on the human

body that can be monitored without requiring expensive or invasive neuroimaging techniques.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Roeslin2023development,

title = {Development of a Seismic Loss Prediction Model for Residential Buildings using Machine Learning \textendash Christchurch, New Zealand},

author = {Samuel Roeslin and Quincy Ma and Pavan Chigullapally and J\"{o}rg Wicker and Liam Wotherspoon},

url = {https://nhess.copernicus.org/articles/23/1207/2023/},

doi = {10.5194/nhess-23-1207-2023},

year  = {2023},

date = {2023-03-22},

urldate = {2023-03-22},

journal = {Natural Hazards and Earth System Sciences},

volume = {23},

number = {3},

pages = {1207-1226},

abstract = {This paper presents a new framework for the seismic loss prediction of residential buildings in Christchurch, New Zealand. It employs data science techniques, geospatial tools, and machine learning (ML) trained on insurance claims data from the Earthquake Commission (EQC) collected following the 2010\textendash2011 Canterbury Earthquake Sequence (CES). The seismic loss prediction obtained from the ML model is shown to outperform the output from existing risk analysis tools for New Zealand for each of the main earthquakes of the CES. In addition to the prediction capabilities, the ML model delivered useful insights into the most important features contributing to losses during the CES. ML correctly highlighted that liquefaction significantly influenced buildings losses for the 22 February 2011 earthquake. The results are consistent with observations, engineering knowledge, and previous studies, confirming the potential of data science and ML in the analysis of insurance claims data and the development of seismic loss prediction models using empirical loss data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}