Accurate prediction of functional effect of single amino acid variants with deep learning.

The assessment of functional effect of amino acid variants is a critical biological problem in proteomics for clinical medicine and protein engineering. Although natively occurring variants offer insights into deleterious variants, high-throughput deep mutational experiments enable comprehensive investigation of amino acid variants for a given protein. However, these mutational experiments are too expensive to dissect millions of variants on thousands of proteins. Thus, computational approaches have been proposed, but they heavily rely on hand-crafted evolutionary conservation, limiting their accuracy. Recent advancement in transformers provides a promising solution to precisely estimate the functional effects of protein variants on high-throughput experimental data. Here, we introduce a novel deep learning model, namely Rep2Mut-V2, which leverages learned representation from transformer models. Rep2Mut-V2 significantly enhances the prediction accuracy for 27 types of measurements of functional effects of protein variants. In the evaluation of 38 protein datasets with 118,933 single amino acid variants, Rep2Mut-V2 achieved an average Spearman's correlation coefficient of 0.7. This surpasses the performance of six state-of-the-art methods, including the recently released methods ESM, DeepSequence and EVE. Even with limited training data, Rep2Mut-V2 outperforms ESM and DeepSequence, showing its potential to extend high-throughput experimental analysis for more protein variants to reduce experimental cost. In conclusion, Rep2Mut-V2 provides accurate predictions of the functional effects of single amino acid variants of protein coding sequences. This tool can significantly aid in the interpretation of variants in human disease studies.

Accurate Prediction of Transcriptional Activity of Single Missense Variants in HIV Tat with Deep Learning.

Tat is an essential gene for increasing the transcription of all HIV genes, and affects HIV replication, HIV exit from latency, and AIDS progression. The Tat gene frequently mutates in vivo and produces variants with diverse activities, contributing to HIV viral heterogeneity as well as drug-resistant clones. Thus, identifying the transcriptional activities of Tat variants will help to better understand AIDS pathology and treatment. We recently reported the missense mutation landscape of all single amino acid Tat variants. In these experiments, a fraction of double missense alleles exhibited intragenic epistasis. However, it is too time-consuming and costly to determine the effect of the variants for all double mutant alleles through experiments. Therefore, we propose a combined GigaAssay/deep learning approach. As a first step to determine activity landscapes for complex variants, we evaluated a deep learning framework using previously reported GigaAssay experiments to predict how transcription activity is affected by Tat variants with single missense substitutions. Our approach achieved a 0.94 Pearson correlation coefficient when comparing the predicted to experimental activities. This hybrid approach can be extensible to more complex Tat alleles for a better understanding of the genetic control of HIV genome transcription.

Disease named entity recognition using long-short dependencies.

The automatic extraction of disease named entity is a challenging research problem that has attracted attention from the biomedical text mining community. Handcrafted feature methods were employed for this task given a little success since they are limited by the scope of the expert. Lately, deep learning-based methods have been employed to solve this issue. However, most architectures used for this task take into consideration long dependencies only. The proposed method is a two-stage deep neural network model. We start by discovering local dependencies and creating high-level features from word embedding inputs using a deep convolutional neural network. Then we identify long dependencies using a bi-directional recurrent neural network. To solve the problem of unbalanced dataset given by the BMEWO tagging schema and to enforce sequence modeling, we developed a new POS-based tagging schema that subdivides the dominant class into smaller more balanced units. The proposed system was trained and tested on NCBI and achieved an [Formula: see text]-score of 85.59 outperforming the current state-of-the-art methods. Our research results show the effectiveness of using both long and short dependencies. The results also illustrate the benefits of combining different word embedding techniques and the incorporation of morphological features in this task.