Novel machine learning approaches revolutionize protein knowledge

N Bordin, C Dallago, M Heinzinger, S Kim… - Trends in Biochemical …, 2023 - cell.com
Breakthrough methods in machine learning (ML), protein structure prediction, and novel
ultrafast structural aligners are revolutionizing structural biology. Obtaining accurate models …

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

N Bordin, I Sillitoe, V Nallapareddy, C Rauer… - Communications …, 2023 - nature.com
Deep-learning (DL) methods like DeepMind's AlphaFold2 (AF2) have led to substantial
improvements in protein structure prediction. We analyse confident AF2 models from 21 …

Embeddings from protein language models predict conservation and variant effects

C Marquet, M Heinzinger, T Olenyi, C Dallago… - Human genetics, 2022 - Springer
The emergence of SARS-CoV-2 variants stressed the demand for tools allowing to interpret
the effect of single amino acid variants (SAVs) on protein function. While Deep Mutational …

Protein language-model embeddings for fast, accurate, and alignment-free protein structure prediction

K Weissenow, M Heinzinger, B Rost - Structure, 2022 - cell.com
Advanced protein structure prediction requires evolutionary information from multiple
sequence alignments (MSAs) from evolutionary couplings that are not always available …

Contrastive learning on protein embeddings enlightens midnight zone

M Heinzinger, M Littmann, I Sillitoe… - NAR genomics and …, 2022 - academic.oup.com
Experimental structures are leveraged through multiple sequence alignments, or more
generally through homology-based inference (HBI), facilitating the transfer of information …

Computational approaches to predict protein functional families and functional sites

C Rauer, N Sen, VP Waman, M Abbasian… - Current Opinion in …, 2021 - Elsevier
Understanding the mechanisms of protein function is indispensable for many biological
applications, such as protein engineering and drug design. However, experimental …

Nearest neighbor search on embeddings rapidly identifies distant protein relations

K Schütze, M Heinzinger, M Steinegger… - Frontiers in …, 2022 - frontiersin.org
Since 1992, all state-of-the-art methods for fast and sensitive identification of evolutionary,
structural, and functional relations between proteins (also referred to as “homology …

SETH predicts nuances of residue disorder from protein embeddings

D Ilzhöfer, M Heinzinger, B Rost - Frontiers in Bioinformatics, 2022 - frontiersin.org
Predictions for millions of protein three-dimensional structures are only a few clicks away
since the release of AlphaFold2 results for UniProt. However, many proteins have so-called …

[PDF][PDF] CATHe: detection of remote homologues for CATH superfamilies using embeddings from protein language models

V Nallapareddy, N Bordin, I Sillitoe, M Heinzinger… - …, 2023 - academic.oup.com
Motivation CATH is a protein domain classification resource that exploits an automated
workflow of structure and sequence comparison alongside expert manual curation to …

A roadmap for the functional annotation of protein families: a community perspective

V de Crécy-Lagard, R Amorin de Hegedus, C Arighi… - 2022 - academic.oup.com
Over the last 25 years, biology has entered the genomic era and is becoming a science of
'big data'. Most interpretations of genomic analyses rely on accurate functional annotations …