MuLan-Methyl—multiple transformer-based language models for accurate DNA methylation prediction

W Zeng, A Gautam, DH Huson - GigaScience, 2023 - academic.oup.com
Transformer-based language models are successfully used to address massive text-related
tasks. DNA methylation is an important epigenetic mechanism, and its analysis provides …

Machine learning in biological physics: From biomolecular prediction to design

J Martin, M Lequerica Mateos, JN Onuchic… - Proceedings of the …, 2024 - pnas.org
Machine learning has been proposed as an alternative to theoretical modeling when
dealing with complex problems in biological physics. However, in this perspective, we argue …

Deep learning in modeling protein complex structures: From contact prediction to end-to-end approaches

P Lin, H Li, SY Huang - Current Opinion in Structural Biology, 2024 - Elsevier
Protein–protein interactions play crucial roles in many biological processes. Traditionally,
protein complex structures are normally built by protein–protein docking. With the rapid …

[HTML][HTML] Computational tools to predict context-specific protein complexes

A Csikász-Nagy, E Fichó, S Noto, I Reguly - Current Opinion in Structural …, 2024 - Elsevier
Interactions between thousands of proteins define cells' protein–protein interaction (PPI)
network. Some of these interactions lead to the formation of protein complexes. It is …

Protein fitness prediction is impacted by the interplay of language models, ensemble learning, and sampling methods

M Mardikoraem, D Woldring - Pharmaceutics, 2023 - mdpi.com
Advances in machine learning (ML) and the availability of protein sequences via high-
throughput sequencing techniques have transformed the ability to design novel diagnostic …

Applications of machine learning in phylogenetics

YK Mo, MW Hahn, ML Smith - Molecular Phylogenetics and Evolution, 2024 - Elsevier
Abstract Machine learning has increasingly been applied to a wide range of questions in
phylogenetic inference. Supervised machine learning approaches that rely on simulated …

Generative power of a protein language model trained on multiple sequence alignments

D Sgarbossa, U Lupo, AF Bitbol - Elife, 2023 - elifesciences.org
Computational models starting from large ensembles of evolutionarily related protein
sequences capture a representation of protein families and learn constraints associated to …

DR-BERT: a protein language model to annotate disordered regions

A Nambiar, JM Forsyth, S Liu, S Maslov - Structure, 2024 - cell.com
Despite their lack of a rigid structure, intrinsically disordered regions (IDRs) in proteins play
important roles in cellular functions, including mediating protein-protein interactions …

Playing the System: Can Puzzle Players Teach us How to Solve Hard Problems?

R Mutalova, R Sarrazin-Gendron, E Cai… - Proceedings of the …, 2023 - dl.acm.org
With nearly three billion players, video games are more popular than ever. Casual puzzle
games are among the most played categories. These games capitalize on the players' …

Pairing interacting protein sequences using masked language modeling

U Lupo, D Sgarbossa, AF Bitbol - Proceedings of the National Academy of …, 2024 - pnas.org
Predicting which proteins interact together from amino acid sequences is an important task.
We develop a method to pair interacting protein sequences which leverages the power of …