SETH predicts nuances of residue disorder from protein embeddings

Abstract

Predictions of millions of protein 3D structures are only a few clicks away since the release of AlphaFold2 results for entire data sets. However, many proteins have so-called intrinsically disordered regions (IDRs) that do not adopt unique structures in isolation. These IDRs are associated with several diseases, including Alzheimer's Disease. We showed that the absence of reliable AlphaFold2 predictions correlated only to a limited extent with IDRs. In contrast, many expert methods predict IDRs directly and reliably by combining complex machine learning models with expert-crafted input features and evolutionary information from multiple sequence alignments. Some of these input features are not always available and computationally expensive to generate, limiting their scalability. In this work, we present the novel prediction method SETH that predicts residue disorder from embeddings generated by the protein Language Model ProtT5, which explicitly only uses single sequences as input. Thereby SETH, a relatively shallow convolutional neural network, already outperformed much more complex state-of-the-art solutions while being much faster, allowing to create predictions for the human proteome in fewer than 30 minutes on a machine with one RTX A6000 GPU with 48GB RAM. Trained on a continuous disorder scale, our method captured subtle variations in disorder, thereby providing important information beyond the binary classification of other predictors. The new method is freely publicly available at: https://github.com/DagmarIlz/SETH.

ADOPT: intrinsic protein disorder prediction through deep bidirectional transformers

“…We note that these results have been reproduced by Ilzhoefer et al(71) after the original release of our work in a bioRxiv manuscript from May 26, 2022…”

LambdaPP: Fast and accessible protein-specific phenotype predictions

“… Panel A: residue level features: secondary structure, transmembrane topology, disordered residues, small molecule, nucleic or metal binding residues, residue conservation and average variation (23; 39; 42; 13; 29); Panel B: sequence-level features: predicted subcellular localization (64), and an excerpt of predicted GO-annotations (38); Panel C: effect of SAVs (wild-type sequence on x-axis, mutations on y-axis; darker color=higher effect) (42); and Panel D : predicted 3D structure (45). Interactive version at https://embed.predictprotein.org/#/Q9NZC2.…”

“…SETH (29), a two-layer CNN, predicts the degree of intrinsic disorder of a residue as defined by the chemical shift Z-scores (CheZOD) (48), where values below 8 signify disorder and values above 8 signify order. Different pLMs were compared (ProtT5 (23), ProSE(10), ESM-1b (54), ProtBERT (23), SeqVec (24)) with ProtT5 numerically outperforming the others.…”

“…2D and 3D viewer. Panel A displays the predicted residue level features (23; 39; 42; 13; 29) for TREM2_HUMAN, with a selected signal peptide prediction. Panel B shows how the selection affects the 3D visualization; the structure is turned, zoomed, and highlighted to best display the selected feature.…”

From sequence to function through structure: deep learning for protein design

“…In particular, we unconditionally (i.e., without priors on family, function or structure) generated a set of 100,000 protein sequences using ProtGPT2, and predicted secondary structure [22], Gene Ontology (GO) terms [44], residue ability to bind small molecules, nucleotides or metals [47], protein subcellular localization [46], transmembrane topology [41], residue conservation [42], residue disorder [43] and CATH family [45]. Remarkably, this generated a repertoire of 100,000 protein sequences with ∼12 predicted features of structure and function from a single script in approximately 3.5 hours ( Supplement 1 ).…”