doi.bio/arne_elofsson

Arne Elofsson

Overview

Arne Elofsson is a Professor of Bioinformatics at Stockholm University. Elofsson's research focuses on combining large-scale life-science data with artificial intelligence to advance our understanding of molecular processes and the human proteome. He is an expert in protein bioinformatics and machine learning methods, with a particular interest in protein-protein interactions and the structure of proteins.

Education

Arne Elofsson received his PhD in Medicine from the Karolinska Institutet.

Career

Arne Elofsson has been a Professor at Stockholm University since 1999. He also has affiliations with the Science for Life Laboratory (SciLifeLab) and the University of Stockholm, Stockholm Bioinformatics Center.

Research

Arne Elofsson's research primarily revolves around bioinformatics, protein structure, sequence, and evolution. He has made significant contributions to the field of protein structure prediction and modelling, particularly through the use of machine learning and artificial intelligence techniques.

Notable Works

• Accurate contact-based modelling of repeat proteins predicts the structure of new repeats protein families – Claudio Bassot and Arne Elofsson developed methods to predict the structure of repeat proteins directly from their primary sequences. They achieved high accuracy in modelling repeat proteins, which are abundant in eukaryotic proteomes and play important roles in signalling pathways.
• The evolutionary history of topological variations in the CPA/AT transporters – Govindarajan Sudha et al., including Elofsson, explored the structural transitions of CPA/AT transporters, classifying them into four fold-types. They shed light on the evolutionary mechanisms that shape topological variations in membrane proteins.
• Protein Contact Map Prediction Based on ResNet and DenseNet – In this work, Elofsson and colleagues proposed a novel deep neural network framework that combines ResNet and DenseNet for improved prediction accuracy of protein contact maps.
• The Use of GC-, Codon-, and Amino Acid-frequencies to Understand the Evolutionary Forces at a Genomic Scale – Elofsson and co-authors examined the variation in GC content across different organisms and its impact on amino acid frequencies. They identified selective forces acting on codon frequencies and their effects on amino acid composition.
• A Bi-LSTM Based Ensemble Algorithm for Prediction of Protein Secondary Structure – Elofsson and co-authors developed a Bi-LSTM based ensemble model for predicting protein secondary structure, achieving up to 1% improvement over state-of-the-art methods.

Awards and Recognition

Arne Elofsson has been recognised for his contributions to the field, with his work on AlphaFold being named the scientific breakthrough in Science in 2021 and the method of the year in Nature Methods.

## References

Arne Elofsson

Early Life and Education

Arne Elofsson is a Professor of Bioinformatics at Stockholm University, where he has been since 1999. Elofsson completed his PhD in Medicine at the Karolinska Institutet.

Career and Research

Elofsson is an expert in protein bioinformatics and machine learning methods. His research focuses on combining large-scale life-science data with artificial intelligence to advance our understanding of the molecular processes that govern life. He has developed novel deep-learning methods to accurately describe the human proteome.

Elofsson has made significant contributions to the field of protein structure prediction and modelling. He has worked on developing methods to predict protein-protein interactions using AI, specifically the fold-and-dock algorithm PconsDock, and structural modelling by Alphafold. He has also made advancements in contact-based modelling of repeat proteins, predicting their structure directly from their primary sequences.

In addition to his work on protein structure, Elofsson has also published on the evolutionary history of topological variations in CPA/AT transporters, using integrated topology annotation methods to classify them into fold-types.

Notable Publications

• Accurate contact-based modelling of repeat proteins predicts the structure of new repeats protein families (Bassot & Elofsson, 2021)
• The evolutionary history of topological variations in the CPA/AT transporters (Sudha et al., 2021)
• Protein Contact Map Prediction Based on ResNet and DenseNet (Elofsson, 2021)
• Discovery of widespread transcription initiation at microsatellites predictable by sequence-based deep neural network (Bréhélin, 2021)
• Estimating the impact of mobility patterns on COVID-19 infection rates in 11 European countries (Elofsson, 2020)

Google Scholar

Arne Elofsson

Science for Life Laboratory and department of Biochemistry and Biophysics, Stockholm University

http://bioinfo.se/

Prediction of transmembrane alpha-helices in prokaryotic membrane proteins: the dense alignment surface method. M Cserzö, E Wallin, I Simon, G von Heijne, A Elofsson Protein engineering 10 (6), 673-676, 1997 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:u5HHmVD_uO8C Cited by: 1366

3D-Jury: a simple approach to improve protein structure predictions K Ginalski, A Elofsson, D Fischer, L Rychlewski Bioinformatics 19 (8), 1015-1018, 2003 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:u-x6o8ySG0sC Cited by: 905

The TOPCONS web server for consensus prediction of membrane protein topology and signal peptides KD Tsirigos, C Peters, N Shu, L Käll, A Elofsson Nucleic acids research 43 (W1), W401-W407, 2015 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:ZfRJV9d4-WMC Cited by: 875

Can correct protein models be identified? B Wallner, A Elofsson Protein science 12 (5), 1073-1086, 2003 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:2osOgNQ5qMEC Cited by: 818

Detecting sequence signals in targeting peptides using deep learning JJA Armenteros, M Salvatore, O Emanuelsson, O Winther, G Von Heijne, … Life science alliance 2 (5), 2019 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:q3CdL3IzO_QC Cited by: 735

TOPCONS: consensus prediction of membrane protein topology A Bernsel, H Viklund, A Hennerdal, A Elofsson Nucleic acids research 37 (suppl2), W465-W468, 2009 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationfor_view=s3OCM3AAAAAJ:8k81kl-MbHgC Cited by: 618

Improved prediction of protein-protein interactions using AlphaFold2 P Bryant, G Pozzati, A Elofsson Nature communications 13 (1), 1265, 2022 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:ODE9OILHJdcC Cited by: 553

Structure is three to ten times more conserved than sequence—a study of structural response in protein cores K Illergård, DH Ardell, A Elofsson Proteins: Structure, Function, and Bioinformatics 77 (3), 499-508, 2009 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:HDshCWvjkbEC Cited by: 514

MaxSub: an automated measure for the assessment of protein structure prediction quality N Siew, A Elofsson, L Rychlewski, D Fischer Bioinformatics 16 (9), 776-785, 2000 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:d1gkVwhDpl0C Cited by: 482

OCTOPUS: improving topology prediction by two-track ANN-based preference scores and an extended topological grammar H Viklund, A Elofsson Bioinformatics 24 (15), 1662-1668, 2008 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:M3ejUd6NZC8C Cited by: 466

What properties characterize the hub proteins of the protein-protein interaction network of Saccharomyces cerevisiae? D Ekman, S Light, ÅK Björklund, A Elofsson Genome biology 7, 1-13, 2006 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:Tyk-4Ss8FVUC Cited by: 434

Molecular recognition of a single sphingolipid species by a protein’s transmembrane domain FX Contreras, AM Ernst, P Haberkant, P Björkholm, E Lindahl, B Gönen, … Nature 481 (7382), 525-529, 2012 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:maZDTaKrznsC Cited by: 400

A structural biology community assessment of AlphaFold2 applications M Akdel, DEV Pires, EP Pardo, J Jänes, AO Zalevsky, B Mészáros, … Nature Structural & Molecular Biology 29 (11), 1056-1067, 2022 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:OcBU2YAGkTUC Cited by: 391

Pcons: A neural‐network–based consensus predictor that improves fold recognition J Lundström, L Rychlewski, J Bujnicki, A Elofsson Protein science 10 (11), 2354-2362, 2001 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:9yKSN-GCB0IC Cited by: 375

Prediction of membrane-protein topology from first principles A Bernsel, H Viklund, J Falk, E Lindahl, G Von Heijne, A Elofsson Proceedings of the National Academy of Sciences 105 (20), 7177-7181, 2008 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:Se3iqnhoufwC Cited by: 357

Prediction of MHC class I binding peptides, using SVMHC P Dönnes, A Elofsson BMC bioinformatics 3, 1-8, 2002 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:UeHWp8X0CEIC Cited by: 352

DisProt 7.0: a major update of the database of disordered proteins D Piovesan, F Tabaro, I Mičetić, M Necci, F Quaglia, CJ Oldfield, … Nucleic acids research 45 (D1), D219-D227, 2017 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:zLWjf1WUPmwC Cited by: 329

Membrane protein structure: prediction versus reality A Elofsson, G Heijne Annu. Rev. Biochem. 76 (1), 125-140, 2007 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:YsMSGLbcyi4C Cited by: 311

Best α‐helical transmembrane protein topology predictions are achieved using hidden Markov models and evolutionary information H Viklund, A Elofsson Protein Science 13 (7), 1908-1917, 2004 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:Y0pCki6q_DkC Cited by: 309

Expansion of protein domain repeats ÅK Björklund, D Ekman, A Elofsson PLoS computational biology 2 (8), e114, 2006 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=s3OCM3AAAAAJ&citationforview=s3OCM3AAAAAJ:0EnyYjriUFMC Cited by: 289

Co-authors

Gunnar von Heijne googlescholarauthorid gunnarvonheijne.md:saYivoAAAAJ

Björn Wallner googlescholarauthorid björnwallner.md:ivKVtiMAAAAJ

daniel fischer googlescholarauthorid danielfischer.md:6BL4WukAAAAJ

Leszek Rychlewski googlescholarauthorid leszekrychlewski.md:xqVfeacAAAAJ

Nanjiang Shu googlescholarauthorid nanjiangshu.md:1a9GihIAAAAJ

David Menéndez Hurtado googlescholarauthorid davidmenéndez_hurtado.md:trHoljcAAAAJ

Åsa K Björklund googlescholarauthorid åsak_björklund.md:7OLM6wcAAAAJ

Erik Lindahl googlescholarauthorid eriklindahl.md:HK-33X4AAAAJ

Marcin J. Skwark googlescholarauthorid marcinj._skwark.md:BYQfb18AAAAJ

Patrick Bryant googlescholarauthorid patrickbryant.md:KPlaFQQAAAAJ

Konstantinos Tsirigos, PhD Bioinforma… googlescholarauthorid konstantinostsirigos,phdbioinforma….md:ZpuhuVcAAAAJ

Christoph Peters googlescholarauthorid christophpeters.md:XrLntUcAAAAJ

Mirco Michel googlescholarauthorid mircomichel.md:3nrKvUgAAAAJ

Sikander Hayat googlescholarauthorid sikanderhayat.md:TDXjMOEAAAAJ

Andreas Bernsel googlescholarauthorid andreasbernsel.md:Cv4ub30AAAAJ

Susana Cristobal googlescholarauthorid susanacristobal.md:_8zXSosAAAAJ

Janusz Bujnicki googlescholarauthorid januszbujnicki.md:v9HadIcAAAAJ

Olof Emanuelsson googlescholarauthorid olofemanuelsson.md:CQdpP5UAAAAJ

Ole Winther googlescholarauthorid olewinther.md:7VAwhzUAAAAJ

Lukas Käll googlescholarauthorid lukaskäll.md:aZALISYAAAAJ