How AlphaFold shaped the structural coverage of the human transmembrane proteome

Jambrich, Marton A; Tusnády, Gábor; Dobson, László

doi:10.1101/2023.04.18.537193

Cited by 7 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we assumed that low results of proteins with MemMoRF may have arisen from the AlphaFold's capabilities for predicting their structures, since they involve several single-pass, bitopic transmembrane proteins. We also indirectly investigated this possibility, and used a transmembrane protein set with failed AlphaFold predictions (33), which group of proteins (low-AF, Table 1) resulted also very low MCC scores. Interestingly, excluding residues with a pLDDT score lower than 50 increased the TPR, F1, and MCC scores.…”

Section: Resultsmentioning

confidence: 99%

Lightway access to AlphaMissense data that demonstrates a balanced performance of this missense mutation predictor

Tordai,

Torres,

Csepi

et al. 2023

Preprint

View full text Add to dashboard Cite

Single amino acid substitutions can profoundly affect protein folding, dynamics, and function, leading to potential pathological consequences. The ability to discern between benign and pathogenic substitutions is pivotal for therapeutic interventions and research directions. Given the limitations in experimental examination of these variants, AlphaMissense has emerged as a promising predictor of the pathogenicity of single nucleotide polymorphism variants. In our study, we assessed the efficacy of AlphaMissense across several protein groups, such as mitochondrial, housekeeping, transmembrane proteins, and specific proteins like CFTR, using ClinVar data for validation. Our comprehensive evaluation showed that AlphaMissense delivers outstanding performance, with MCC scores predominantly between 0.6 and 0.74. We observed low performance on the CFTR and disordered, membrane-interacting MemMoRF datasets. However, an enhanced performance with CFTR was shown when benchmarked against the CFTR2 database. Our results also emphasize that quality of AlphaFold’s predictions can seriously influence AlphaMissense predictions. Most importantly, AlphaMissense’s consistent capability in predicting pathogenicity across diverse protein groups, spanning both transmembrane and soluble domains was found. Moreover, the prediction of likely-pathogenic labels for IBS and CFTR coupling helix residues emphasizes AlphaMissense’s potential as a tool for pinpointing functionally significant sites. Additionally, to make AlphaMissense predictions more accessible, we have introduced a user-friendly web resource (https://alphamissense.hegelab.org) to enhance the utility of this valuable tool. Our insights into AlphaMissense’s capability, along with this online resource, underscore its potential to significantly aid both research and clinical applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Lightway access to AlphaMissense data that demonstrates a balanced performance of this missense mutation predictor

Tordai,

Torres,

Csepi

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Because of their reliance on the construction of MSAs, profile-based methods can have high computational overhead for database construction, query preparation, or both. Protein structure searches also show higher sensitivity than sequence searches (Jambrich et al, 2023 ). Until recently, the utility of structure searches for protein annotation was limited by the lack of extensive reference databases and the inability to predict structures quickly and reliably for sequences lacking experimentally determined structures.…”

Section: Introductionmentioning

confidence: 99%

Sensitive remote homology search by local alignment of small positional embeddings from protein language models

Johnson,

Peshwa,

Sun

2024

eLife

View full text Add to dashboard Cite

Accurately detecting distant evolutionary relationships between proteins remains an ongoing challenge in bioinformatics. Search methods based on primary sequence struggle to accurately detect homology between sequences with less than 20% amino acid identity. Profile- and structure-based strategies extend sensitive search capabilities into this twilight zone of sequence similarity but require slow pre-processing steps. Recently, whole-protein and positional embeddings from deep neural networks have shown promise for providing sensitive sequence comparison and annotation at long evolutionary distances. Embeddings are generally faster to compute than profiles and predicted structures but still suffer several drawbacks related to the ability of whole-protein embeddings to discriminate domain-level homology, and the database size and search speed of methods using positional embeddings. In this work, we show that low-dimensionality positional embeddings can be used directly in speed-optimized local search algorithms. As a proof of concept, we use the ESM2 3B model to convert primary sequences directly into the 3Di alphabet or amino acid profiles and use these embeddings as input to the highly optimized Foldseek, HMMER3, and HH-suite search algorithms. Our results suggest that positional embeddings as small as a single byte can provide sufficient information for dramatically improved sensitivity over amino acid sequence searches without sacrificing search speed.

show abstract

Analysis of AlphaMissense data in different protein groups and structural context

Tordai,

Torres,

Csepi

et al. 2024

Sci Data

View full text Add to dashboard Cite

Single amino acid substitutions can profoundly affect protein folding, dynamics, and function. The ability to discern between benign and pathogenic substitutions is pivotal for therapeutic interventions and research directions. Given the limitations in experimental examination of these variants, AlphaMissense has emerged as a promising predictor of the pathogenicity of missense variants. Since heterogenous performance on different types of proteins can be expected, we assessed the efficacy of AlphaMissense across several protein groups (e.g. soluble, transmembrane, and mitochondrial proteins) and regions (e.g. intramembrane, membrane interacting, and high confidence AlphaFold segments) using ClinVar data for validation. Our comprehensive evaluation showed that AlphaMissense delivers outstanding performance, with MCC scores predominantly between 0.6 and 0.74. We observed low performance on disordered datasets and ClinVar data related to the CFTR ABC protein. However, a superior performance was shown when benchmarked against the high quality CFTR2 database. Our results with CFTR emphasizes AlphaMissense’s potential in pinpointing functional hot spots, with its performance likely surpassing benchmarks calculated from ClinVar and ProteinGym datasets.

show abstract

How AlphaFold shaped the structural coverage of the human transmembrane proteome

Cited by 7 publications

References 40 publications

Lightway access to AlphaMissense data that demonstrates a balanced performance of this missense mutation predictor

Lightway access to AlphaMissense data that demonstrates a balanced performance of this missense mutation predictor

Sensitive remote homology search by local alignment of small positional embeddings from protein language models

Analysis of AlphaMissense data in different protein groups and structural context

Contact Info

Product

Resources

About