Publications

What is a Publication?
1687 Publications visible to you, out of a total of 1687

Abstract (Expand)

Fine-tuning biomedical pre-trained language models (BioPLMs) such as BioBERT has become a common practice dominating leaderboards across various natural language processing tasks. Despite their success and wide adoption, prevailing fine-tuning approaches for named entity recognition (NER) naively train BioPLMs on targeted datasets without considering class distributions. This is problematic especially when dealing with imbalanced biomedical gold-standard datasets for NER in which most biomedical entities are underrepresented. In this paper, we address the class imbalance problem and propose WeLT, a cost-sensitive fine-tuning approach based on new re-scaled class weights for the task of biomedical NER. We evaluate WeLT’s fine-tuning performance on mixed-domain and domain-specific BioPLMs using eight biomedical gold-standard datasets. We compare our approach against vanilla fine-tuning and three other existing re-weighting schemes. Our results show the positive impact of handling the class imbalance problem. WeLT outperforms all the vanilla fine-tuned models. Furthermore, our method demonstrates advantages over other existing weighting schemes in most experiments.

Authors: Ghadeer Mobasher, Wolfgang Müller, Olga Krebs, Michael Gertz

Date Published: 2023

Publication Type: Proceedings

Abstract

Not specified

Authors: Dilek Koptekin, Eren Yüncü, Ricardo Rodríguez-Varela, N. Ezgi Altınışık, Nikolaos Psonis, Natalia Kashuba, Sevgi Yorulmaz, Robert George, Duygu Deniz Kazancı, Damla Kaptan, Kanat Gürün, Kıvılcım Başak Vural, Hasan Can Gemici, Despoina Vassou, Evangelia Daskalaki, Cansu Karamurat, Vendela K. Lagerholm, Ömür Dilek Erdal, Emrah Kırdök, Aurelio Marangoni, Andreas Schachner, Handan Üstündağ, Ramaz Shengelia, Liana Bitadze, Mikheil Elashvili, Eleni Stravopodi, Mihriban Özbaşaran, Güneş Duru, Argyro Nafplioti, C. Brian Rose, Tuğba Gencer, Gareth Darbyshire, Alexander Gavashelishvili, Konstantine Pitskhelauri, Özlem Çevik, Osman Vuruşkan, Nina Kyparissi-Apostolika, Ali Metin Büyükkarakaya, Umay Oğuzhanoğlu, Sevinç Günel, Eugenia Tabakaki, Akper Aliev, Anar Ibrahimov, Vaqif Shadlinski, Adamantios Sampson, Gülşah Merve Kılınç, Çiğdem Atakuman, Alexandros Stamatakis, Nikos Poulakakis, Yılmaz Selim Erdal, Pavlos Pavlidis, Jan Storå, Füsun Özer, Anders Götherström, Mehmet Somel

Date Published: 2023

Publication Type: Journal

Abstract (Expand)

Abstract Motivation Missing data and incomplete lineage sorting (ILS) are two major obstacles to accurate species tree inference. Gene tree summary methods such as ASTRAL and ASTRID have been developedy methods such as ASTRAL and ASTRID have been developed to account for ILS. However, they can be severely affected by high levels of missing data. Results We present Asteroid, a novel algorithm that infers an unrooted species tree from a set of unrooted gene trees. We show on both empirical and simulated datasets that Asteroid is substantially more accurate than ASTRAL and ASTRID for very high proportions (>80%) of missing data. Asteroid is several orders of magnitude faster than ASTRAL for datasets that contain thousands of genes. It offers advanced features such as parallelization, support value computation and support for multi-copy and multifurcating gene trees. Availability and implementation Asteroid is freely available at https://github.com/BenoitMorel/Asteroid. Supplementary information Supplementary data are available at Bioinformatics online.

Authors: Benoit Morel, Tom A Williams, Alexandros Stamatakis

Date Published: 2023

Publication Type: Journal

Abstract (Expand)

Abstract Summary Maximum likelihood (ML) is a widely used phylogenetic inference method. ML implementations heavily rely on numerical optimization routines that use internal numerical thresholds totion routines that use internal numerical thresholds to determine convergence. We systematically analyze the impact of these threshold settings on the log-likelihood and runtimes for ML tree inferences with RAxML-NG, IQ-TREE, and FastTree on empirical datasets. We provide empirical evidence that we can substantially accelerate tree inferences with RAxML-NG and IQ-TREE by changing the default values of two such numerical thresholds. At the same time, altering these settings does not significantly impact the quality of the inferred trees. We further show that increasing both thresholds accelerates the RAxML-NG bootstrap without influencing the resulting support values. For RAxML-NG, increasing the likelihood thresholds ϵLnL and ϵbrlen to 10 and 103, respectively, results in an average tree inference speedup of 1.9 ± 0.6 on Data collection 1, 1.8 ± 1.1 on Data collection 2, and 1.9 ± 0.8 on Data collection 2 for the RAxML-NG bootstrap compared to the runtime under the current default setting. Increasing the likelihood threshold ϵLnL to 10 in IQ-TREE results in an average tree inference speedup of 1.3 ± 0.4 on Data collection 1 and 1.3 ± 0.9 on Data collection 2. Availability and implementation All MSAs we used for our analyses, as well as all results, are available for download at https://cme.h-its.org/exelixis/material/freeLunch_data.tar.gz. Our data generation scripts are available at https://github.com/tschuelia/ml-numerical-analysis.

Authors: Julia Haag, Lukas Hübner, Alexey M Kozlov, Alexandros Stamatakis

Date Published: 2023

Publication Type: Journal

Abstract

Not specified

Authors: Nikolaos Psonis, Despoina Vassou, Argyro Nafplioti, Eugenia Tabakaki, Pavlos Pavlidis, Alexandros Stamatakis, Nikos Poulakakis

Date Published: 2023

Publication Type: Journal

Abstract

Not specified

Authors: Vishnu Varma, Bernhard Müller, Fabian R. N. Schneider

Date Published: 2023

Publication Type: Journal

Abstract

Not specified

Authors: Ben Bruers, Marilyn Cruces, Markus Demleitner, Guenter Duckeck, Michael Düren, Niclas Eich, Torsten Enßlin, Johannes Erdmann, Martin Erdmann, Peter Fackeldey, Christian Felder, Benjamin Fischer, Stefan Fröse, Stefan Funk, Martin Gasthuber, Andrew Grimshaw, Daniela Hadasch, Moritz Hannemann, Alexander Kappes, Raphael Kleinemühl, Oleksiy M. Kozlov, Thomas Kuhr, Michael Lupberger, Simon Neuhaus, Pardis Niknejadi, Judith Reindl, Daniel Schindler, Astrid Schneidewind, Frank Schreiber, Markus Schumacher, Kilian Schwarz, Achim Streit, R. Florian von Cube, Rod Walker, Cyrus Walther, Sebastian Wozniewski, Kai Zhou

Date Published: 2023

Publication Type: Journal

Powered by
(v.1.16.0)
Copyright © 2008 - 2024 The University of Manchester and HITS gGmbH