Metapredict: a fast, accurate, and easy-to-use predictor of consensus disorder and structure

A Comprehensive Report of Intrinsically Disordered Regions in Inherited Retinal Diseases

BACKGROUND/PURPOSE

A comprehensive review of the degree of disorder in all genes in the Retinal Information Network (RetNet) Database is implicated in inherited retinal diseases (IRDs). Their association with a missense variation was evaluated.

METHODS

IRD genes from RetNet were included in this study. Publicly available data on the genome aggregation database (gnomAD) were used to analyze the number of total and pathogenic missense variants. Metapredict, an accurate and high-performance predictor that reproduces consensus disorder scores, was used to calculate disorder.

MAIN OUTCOME MEASURES

The main outcome measures were percent disorder, percent pathogenicity, number of total missense variants, and percent total missense variation.

RESULTS

We included 287 RetNet genes with relevant data available from gnomAD. Mean percent disorder was 26.3% ± 26.0%, mean percent pathogenicity was 5.2% ± 11.0%, mean number of total missense variants was 424.4 ± 450.0, and mean percent total missense was 50.0% ± 13.4%. The percent disorder followed a bimodal distribution with the highest number of occurrences in the 0 to 10th disorder decile. The five outlier proteins in the first disorder decile with a higher-than-expected number of total missense variation were identified (HMCN1, ADGRV, USH2A, DYNC2H1, LAMA1, and SLC38A8). When excluded, % total missense was significantly associated with percent disorder (R = 0.238 and p = 0.0240).

CONCLUSIONS

This novel study examining all genes implicated in IRDs found that the majority genes had a disorder in the 0 to 10th decile and were relatively intolerant to missense variation. This may have future utility when interpreting variants of undetermined significance and missense variants.

Plant transcription factors - being in the right place with the right company

Transcriptional regulation underlies many of the growth and developmental processes that shape plants as well as their adaptation to their environment. Key to transcriptional control are transcription factors, DNA-binding proteins that serve two essential functions: to find the appropriate DNA contact sites in their target genes; and to recruit other proteins to execute transcriptional transactions. In recent years, protein structural, genomic, bioinformatic, and proteomic analyses have led to new insights into how these central functions are regulated. Here, we review new findings relating to plant transcription factor function and to their role in shaping transcription in the context of chromatin.

AlphaFold and Implications for Intrinsically Disordered Proteins

Accurate predictions of the three-dimensional structures of proteins from their amino acid sequences have come of age. AlphaFold, a deep learning-based approach to protein structure prediction, shows remarkable success in independent assessments of prediction accuracy. A significant epoch in structural bioinformatics was the structural annotation of over 98% of protein sequences in the human proteome. Interestingly, many predictions feature regions of very low confidence, and these regions largely overlap with intrinsically disordered regions (IDRs). That over 30% of regions within the proteome are disordered is congruent with estimates that have been made over the past two decades, as intense efforts have been undertaken to generalize the structure-function paradigm to include the importance of conformational heterogeneity and dynamics. With structural annotations from AlphaFold in hand, there is the temptation to draw inferences regarding the "structures" of IDRs and their interactomes. Here, we offer a cautionary note regarding the misinterpretations that might ensue and highlight efforts that provide concrete understanding of sequence-ensemble-function relationships of IDRs. This perspective is intended to emphasize the importance of IDRs in sequence-function relationships (SERs) and to highlight how one might go about extracting quantitative SERs to make sense of how IDRs function.

PARROT is a flexible recurrent neural network framework for analysis of large protein datasets

The rise of high-throughput experiments has transformed how scientists approach biological questions. The ubiquity of large-scale assays that can test thousands of samples in a day has necessitated the development of new computational approaches to interpret this data. Among these tools, machine learning approaches are increasingly being utilized due to their ability to infer complex nonlinear patterns from high-dimensional data. Despite their effectiveness, machine learning (and in particular deep learning) approaches are not always accessible or easy to implement for those with limited computational expertise. Here we present PARROT, a general framework for training and applying deep learning-based predictors on large protein datasets. Using an internal recurrent neural network architecture, PARROT is capable of tackling both classification and regression tasks while only requiring raw protein sequences as input. We showcase the potential uses of PARROT on three diverse machine learning tasks: predicting phosphorylation sites, predicting transcriptional activation function of peptides generated by high-throughput reporter assays, and predicting the fibrillization propensity of amyloid beta with data generated by deep mutational scanning. Through these examples, we demonstrate that PARROT is easy to use, performs comparably to state-of-the-art computational tools, and is applicable for a wide array of biological problems.