Assessing predictors for new post translational modification sites: A case study on hydroxylation

Deep Learning Approaches for Detection of Breast Adenocarcinoma Causing Carcinogenic Mutations

Genes are composed of DNA and each gene has a specific sequence. Recombination or replication within the gene base ends in a permanent change in the nucleotide collection in a DNA called mutation and some mutations can lead to cancer. Breast adenocarcinoma starts in secretary cells. Breast adenocarcinoma is the most common of all cancers that occur in women. According to a survey within the United States of America, there are more than 282,000 breast adenocarcinoma patients registered each 12 months, and most of them are women. Recognition of cancer in its early stages saves many lives. A proposed framework is developed for the early detection of breast adenocarcinoma using an ensemble learning technique with multiple deep learning algorithms, specifically: Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Bi-directional LSTM. There are 99 types of driver genes involved in breast adenocarcinoma. This study uses a dataset of 4127 samples including men and women taken from more than 12 cohorts of cancer detection institutes. The dataset encompasses a total of 6170 mutations that occur in 99 genes. On these gene sequences, different algorithms are applied for feature extraction. Three types of testing techniques including independent set testing, self-consistency testing, and a 10-fold cross-validation test is applied to validate and test the learning approaches. Subsequently, multiple deep learning approaches such as LSTM, GRU, and bi-directional LSTM algorithms are applied. Several evaluation metrics are enumerated for the validation of results including accuracy, sensitivity, specificity, Mathew’s correlation coefficient, area under the curve, training loss, precision, recall, F1 score, and Cohen’s kappa while the values obtained are 99.57, 99.50, 99.63, 0.99, 1.0, 0.2027, 99.57, 99.57, 99.57, and 99.14 respectively.

In silico prediction of post-translational modifications in therapeutic antibodies

Monoclonal antibodies are susceptible to chemical and enzymatic modifications during manufacturing, storage, and shipping. Deamidation, isomerization, and oxidation can compromise the potency, efficacy, and safety of therapeutic antibodies. Recently, in silico tools have been used to identify liable residues and engineer antibodies with better chemical stability. Computational approaches for predicting deamidation, isomerization, oxidation, glycation, carbonylation, sulfation, and hydroxylation are reviewed here. Although liable motifs have been used to improve the chemical stability of antibodies, the accuracy of in silico predictions can be improved using machine learning and molecular dynamic simulations. In addition, there are opportunities to improve predictions for specific stress conditions, develop in silico prediction of novel modifications in antibodies, and predict the impact of modifications on physical stability and antigen-binding.

Current status of PTMs structural databases: applications, limitations and prospects

Protein 3D structures, determined by their amino acid sequences, are the support of major crucial biological functions. Post-translational modifications (PTMs) play an essential role in regulating these functions by altering the physicochemical properties of proteins. By virtue of their importance, several PTM databases have been developed and released in decades, but very few of these databases incorporate real 3D structural data. Since PTMs influence the function of the protein and their aberrant states are frequently implicated in human diseases, providing structural insights to understand the influence and dynamics of PTMs is crucial for unraveling the underlying processes. This review is dedicated to the current status of databases providing 3D structural data on PTM sites in proteins. Some of these databases are general, covering multiple types of PTMs in different organisms, while others are specific to one particular type of PTM, class of proteins or organism. The importance of these databases is illustrated with two major types of in silico applications: predicting PTM sites in proteins using machine learning approaches and investigating protein structure-function relationships involving PTMs. Finally, these databases suffer from multiple problems and care must be taken when analyzing the PTMs data.

Development of an experiment-split method for benchmarking the generalization of a PTM site predictor: Lysine methylome as an example

Many computational classifiers have been developed to predict different types of post-translational modification sites. Their performances are measured using cross-validation or independent test, in which experimental data from different sources are mixed and randomly split into training and test sets. However, the self-reported performances of most classifiers based on this measure are generally higher than their performances in the application of new experimental data. It suggests that the cross-validation method overestimates the generalization ability of a classifier. Here, we proposed a generalization estimate method, dubbed experiment-split test, where the experimental sources for the training set are different from those for the test set that simulate the data derived from a new experiment. We took the prediction of lysine methylome (Kme) as an example and developed a deep learning-based Kme site predictor (called DeepKme) with outstanding performance. We assessed the experiment-split test by comparing it with the cross-validation method. We found that the performance measured using the experiment-split test is lower than that measured in terms of cross-validation. As the test data of the experiment-split method were derived from an independent experimental source, this method could reflect the generalization of the predictor. Therefore, we believe that the experiment-split method can be applied to benchmark the practical performance of a given PTM model. DeepKme is free accessible via https://github.com/guoyangzou/DeepKme.

The performance of a model for predicting post-translational modification sites is commonly evaluated using the cross-validation method, where the data derived from different experimental sources are mixed and randomly separated into the training dataset and validation dataset. However, the performance measured through cross-validation is generally higher than the performance in the application of new experimental data, indicating that the cross-validation method overestimates the generalization of a model. In this study, we proposed a generalization estimate method, dubbed experiment-split test, where the experimental sources for the training set are different from those for the test set that simulate the data derived from a new experiment. We took the prediction of lysine methylome as an example and developed a deep learning-based Kme site predictor DeepKme with outstanding performance. We found that the performance measured by the experiment-split method is lower than that measured in terms of cross-validation. As the test data of the experiment-split method were derived from an independent experimental source, this method could reflect the generalization of the prediction model. Therefore, the experiment-split method can be applied to benchmark the practical prediction performance.

Comparing a Novel Malformation Syndrome Caused by Pathogenic Variants in FBRSL1 to AUTS2 Syndrome

Truncating variants in specific exons of Fibrosin-like protein 1 (FBRSL1) were recently reported to cause a novel malformation and intellectual disability syndrome. The clinical spectrum includes microcephaly, facial dysmorphism, cleft palate, skin creases, skeletal anomalies and contractures, postnatal growth retardation, global developmental delay as well as respiratory problems, hearing impairment and heart defects. The function of FBRSL1 is largely unknown, but pathogenic variants in the FBRSL1 paralog Autism Susceptibility Candidate 2 (AUTS2) are causative for an intellectual disability syndrome with microcephaly (AUTS2 syndrome). Some patients with AUTS2 syndrome also show additional symptoms like heart defects and contractures overlapping with the phenotype presented by patients with FBRSL1 mutations. For AUTS2, a dual function, depending on different isoforms, was described and suggested for FBRSL1. Both, nuclear FBRSL1 and AUTS2 are components of the Polycomb subcomplexes PRC1.3 and PRC1.5. These complexes have essential roles in developmental processes, cellular differentiation and proliferation by regulating gene expression via histone modification. In addition, cytoplasmic AUTS2 controls neural development, neuronal migration and neurite extension by regulating the cytoskeleton. Here, we review recent data on FBRSL1 in respect to previously published data on AUTS2 to gain further insights into its molecular function, its role in development as well as its impact on human genetics.

A global map of associations between types of protein posttranslational modifications and human genetic diseases

There are >200 types of protein posttranslational modifications (PTMs) described in eukaryotes, each with unique proteome coverage and functions. We hypothesized that some genetic diseases may be caused by the removal of a specific type of PTMs by genomic variants and the consequent deregulation of particular functions. We collected >320,000 human PTMs representing 59 types and crossed them with >4M nonsynonymous DNA variants annotated with predicted pathogenicity and disease associations. We report >1.74M PTM-variant co-occurrences that an enrichment analysis distributed into 215 pairwise associations between 18 PTM types and 148 genetic diseases. Of them, 42% were not previously described. Removal of lysine acetylation exerts the most pronounced effect, and less studied PTM types such as S-glutathionylation or S-nitrosylation show relevance. Using pathogenicity predictions, we identified PTM sites that may produce particular diseases if prevented. Our results provide evidence of a substantial impact of PTM-specific removal on the pathogenesis of genetic diseases and phenotypes.

•

There is an enrichment of disease-associated nsSNVs preventing certain types of PTMs

•

We report 215 pairwise associations between 18 PTM types and 148 genetic diseases

•

The removal of lysine acetylation exerts the most pronounced effect

•

We report a set of PTM sites that may produce particular diseases if prevented