Mutation prediction in the SARS-CoV-2 genome using attention-based neural machine translation.

Severe acute respiratory syndrome coronavirus 2 (SARS­CoV­2) has been evolving rapidly after causing havoc worldwide in 2020. Since then, it has been very hard to contain the virus owing to its frequently mutating nature. Changes in its genome lead to viral evolution, rendering it more resistant to existing vaccines and drugs. Predicting viral mutations beforehand will help in gearing up against more infectious and virulent versions of the virus in turn decreasing the damage caused by them. In this paper, we have proposed different NMT (neural machine translation) architectures based on RNNs (recurrent neural networks) to predict mutations in the SARS-CoV-2-selected non-structural proteins (NSP), i.e., NSP1, NSP3, NSP5, NSP8, NSP9, NSP13, and NSP15. First, we created and pre-processed the pairs of sequences from two languages using k-means clustering and nearest neighbors for training a neural translation machine. We also provided insights for training NMTs on long biological sequences. In addition, we evaluated and benchmarked our models to demonstrate their efficiency and reliability.

PRIEST: predicting viral mutations with immune escape capability of SARS-CoV-2 using temporal evolutionary information.

The dynamic evolution of the severe acute respiratory syndrome coronavirus 2 virus is primarily driven by mutations in its genetic sequence, culminating in the emergence of variants with increased capability to evade host immune responses. Accurate prediction of such mutations is fundamental in mitigating pandemic spread and developing effective control measures. This study introduces a robust and interpretable deep-learning approach called PRIEST. This innovative model leverages time-series viral sequences to foresee potential viral mutations. Our comprehensive experimental evaluations underscore PRIEST's proficiency in accurately predicting immune-evading mutations. Our work represents a substantial step in utilizing deep-learning methodologies for anticipatory viral mutation analysis and pandemic response.

Social network analysis of cell networks improves deep learning for prediction of molecular pathways and key mutations in colorectal cancer.

Colorectal cancer (CRC) is a primary global health concern, and identifying the molecular pathways, genetic subtypes, and mutations associated with CRC is crucial for precision medicine. However, traditional measurement techniques such as gene sequencing are costly and time-consuming, while most deep learning methods proposed for this task lack interpretability. This study offers a new approach to enhance the state-of-the-art deep learning methods for molecular pathways and key mutation prediction by incorporating cell network information. We build cell graphs with nuclei as nodes and nuclei connections as edges of the network and leverage Social Network Analysis (SNA) measures to extract abstract, perceivable, and interpretable features that explicitly describe the cell network characteristics in an image. Our approach does not rely on precise nuclei segmentation or feature extraction, is computationally efficient, and is easily scalable. In this study, we utilize the TCGA-CRC-DX dataset, comprising 499 patients and 502 diagnostic slides from primary colorectal tumours, sourced from 36 distinct medical centres in the United States. By incorporating the SNA features alongside deep features in two multiple instance learning frameworks, we demonstrate improved performance for chromosomal instability (CIN), hypermutated tumour (HM), TP53 gene, BRAF gene, and Microsatellite instability (MSI) status prediction tasks (2.4%-4% and 7-8.8% improvement in AUROC and AUPRC on average). Additionally, our method achieves outstanding performance on MSI prediction in an external PAIP dataset (99% AUROC and 98% AUPRC), demonstrating its generalizability. Our findings highlight the discrimination power of SNA features and how they can be beneficial to deep learning models' performance and provide insights into the correlation of cell network profiles with molecular pathways and key mutations.

A novel transformer-based aggregation model for predicting gene mutations in lung adenocarcinoma.

In recent years, predicting gene mutations on whole slide imaging (WSI) has gained prominence. The primary challenge is extracting global information and achieving unbiased semantic aggregation. To address this challenge, we propose a novel Transformer-based aggregation model, employing a self-learning weight aggregation mechanism to mitigate semantic bias caused by the abundance of features in WSI. Additionally, we adopt a random patch training method, which enhances model learning richness by randomly extracting feature vectors from WSI, thus addressing the issue of limited data. To demonstrate the model's effectiveness in predicting gene mutations, we leverage the lung adenocarcinoma dataset from Shandong Provincial Hospital for prior knowledge learning. Subsequently, we assess TP53, CSMD3, LRP1B, and TTN gene mutations using lung adenocarcinoma tissue pathology images and clinical data from The Cancer Genome Atlas (TCGA). The results indicate a notable increase in the AUC (Area Under the ROC Curve) value, averaging 4%, attesting to the model's performance improvement. Our research offers an efficient model to explore the correlation between pathological image features and molecular characteristics in lung adenocarcinoma patients. This model introduces a novel approach to clinical genetic testing, expected to enhance the efficiency of identifying molecular features and genetic testing in lung adenocarcinoma patients, ultimately providing more accurate and reliable results for related studies.

Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network.

BACKGROUND: In cancer genomic medicine, finding driver mutations involved in cancer development and tumor growth is crucial. Machine-learning methods to predict driver missense mutations have been developed because variants are frequently detected by genomic sequencing. However, even though the abnormalities in molecular networks are associated with cancer, many of these methods focus on individual variants and do not consider molecular networks. Here we propose a new network-based method, Net-DMPred, to predict driver missense mutations considering molecular networks. Net-DMPred consists of the graph part and the prediction part. In the graph part, molecular networks are learned by a graph neural network (GNN). The prediction part learns whether variants are driver variants using features of individual variants combined with the graph features learned in the graph part. RESULTS: Net-DMPred, which considers molecular networks, performed better than conventional methods. Furthermore, the prediction performance differed by the molecular network structure used in learning, suggesting that it is important to consider not only the local network related to cancer but also the large-scale network in living organisms. CONCLUSIONS: We propose a network-based machine learning method, Net-DMPred, for predicting cancer driver missense mutations. Our method enables us to consider the entire graph architecture representing the molecular network because it uses GNN. Net-DMPred is expected to detect driver mutations from a lot of missense mutations that are not known to be associated with cancer.

A Computational Workflow to Predict Biological Target Mutations: The Spike Glycoprotein Case Study.

The biological target identification process, a pivotal phase in the drug discovery workflow, becomes particularly challenging when mutations affect proteins' mechanisms of action. COVID-19 Spike glycoprotein mutations are known to modify the affinity toward the human angiotensin-converting enzyme ACE2 and several antibodies, compromising their neutralizing effect. Predicting new possible mutations would be an efficient way to develop specific and efficacious drugs, vaccines, and antibodies. In this work, we developed and applied a computational procedure, combining constrained logic programming and careful structural analysis based on the Structural Activity Relationship (SAR) approach, to predict and determine the structure and behavior of new future mutants. "Mutations rules" that would track statistical and functional types of substitutions for each residue or combination of residues were extracted from the GISAID database and used to define constraints for our software, having control of the process step by step. A careful molecular dynamics analysis of the predicted mutated structures was carried out after an energy evaluation of the intermolecular and intramolecular interactions using the HINT (Hydrophatic INTeraction) force field. Our approach successfully predicted, among others, known Spike mutants.

A Bayesian walker coupled with a computational workflow that generates the micro-evolution of SARS-CoV-2 and makes predictions of new mutations that can emerge.

In this work, a Bayesian walker was constructed that generates mutations that are more prone as per UNIPROT variant data. The Bayesian walker was used to search the mutational landscape of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) and a computational workflow was followed to evaluate whether a particular mutation would satisfy natural selection's fitness criteria. For SARS-CoV-2, the empirical known fitness criteria derived from SARS-CoV-2 micro-evolution data is 3-fold criteria. Mutations that have emerged on the Spike protein of SARS-CoV-2 are ones that preserve the structural integrity of the Spike, retain, or increase infectivity and are Immune evasive as per literature reports. Based on the molecular mechanism of infectivity and Immune evasion of SARS-CoV-2, a molecular modelling workflow was adopted to investigate the evolutionary feasibility of the mutations generated by the walker, to check whether the mutations satisfy the 3-fold fitness criteria for SARS-CoV-2 micro-evolution. It was found that the walker (mutation generator) coupled with the computational workflow to evaluate the evolutionary fitness of the generated mutations, re-generated the mutants corresponding to the Alpha, Beta and Gamma variants of SARS-CoV-2 demonstrating the ability of the methodology to generate the micro-evolution of SARS-CoV-2. Having demonstrated the ability of the methodology to generate the micro-evolution of SARS-CoV-2, the computational methodology was used to make predictions for new mutants that could emerge.Communicated by Ramaswamy H. Sarma.

Histopathological bladder cancer gene mutation prediction with hierarchical deep multiple-instance learning.

Gene mutation detection is usually carried out by molecular biological methods, which is expensive and has a long-time cycle. In contrast, pathological images are ubiquitous. If clinically significant gene mutations can be predicted only through pathological images, it will greatly promote the widespread use of gene mutation detection in clinical practice. However, current gene mutation prediction methods based on pathological images are ineffective because of the inability to identify mutated regions in gigapixel Whole Slide Image (WSI). To address this challenge, hereby we propose a carefully designed framework for WSI-based gene mutation prediction, which consists of three parts. (i) The first part of cancerous area segmentation, based on supervised learning, quickly filters out a large number of non-mutated regions; (ii) the second part of cancerous patch clustering, based on the representations derived from contrastive learning, ensures the comprehensiveness of patch selection; and (iii) the third part of mutation classification, based on the proposed hierarchical deep multi-instance learning method (HDMIL), ensures that sufficient patches are considered and inaccurate selections are ignored. In addition, benefiting from a two-stage attention mechanism in HDMIL, the patches that are highly correlated with gene mutations can be identified. This interpretability can help a pathologist to analyze the correlation between gene mutation and histopathological morphology. Experimental results demonstrate that the proposed gene mutation prediction framework significantly outperforms the state-of-the-art methods. In the TCGA bladder cancer dataset, five clinically relevant gene mutations are well predicted.

PredDSMC: A predictor for driver synonymous mutations in human cancers.

Introduction: Driver mutations play a critical role in the occurrence and development of human cancers. Most studies have focused on missense mutations that function as drivers in cancer. However, accumulating experimental evidence indicates that synonymous mutations can also act as driver mutations. Methods: Here, we proposed a computational method called PredDSMC to accurately predict driver synonymous mutations in human cancers. We first systematically explored four categories of multimodal features, including sequence features, splicing features, conservation scores, and functional scores. Further feature selection was carried out to remove redundant features and improve the model performance. Finally, we utilized the random forest classifier to build PredDSMC. Results: The results of two independent test sets indicated that PredDSMC outperformed the state-of-the-art methods in differentiating driver synonymous mutations from passenger mutations. Discussion: In conclusion, we expect that PredDSMC, as a driver synonymous mutation prediction method, will be a valuable method for gaining a deeper understanding of synonymous mutations in human cancers.

Cancer driver mutations: predictions and reality.

Cancer cells accumulate many genetic alterations throughout their lifetime, but only a few of them drive cancer progression, termed driver mutations. Driver mutations may vary between cancer types and patients, can remain latent for a long time and become drivers at particular cancer stages, or may drive oncogenesis only in conjunction with other mutations. The high mutational, biochemical, and histological tumor heterogeneity makes driver mutation identification very challenging. In this review we summarize recent efforts to identify driver mutations in cancer and annotate their effects. We underline the success of computational methods to predict driver mutations in finding novel cancer biomarkers, including in circulating tumor DNA (ctDNA). We also report on the boundaries of their applicability in clinical research.

Multimodal integration of image, epigenetic and clinical data to predict BRAF mutation status in melanoma.

BACKGROUND: In machine learning, multimodal classifiers can provide more generalised performance than unimodal classifiers. In clinical practice, physicians usually also rely on a range of information from different examinations for diagnosis. In this study, we used BRAF mutation status prediction in melanoma as a model system to analyse the contribution of different data types in a combined classifier because BRAF status can be determined accurately by sequencing as the current gold standard, thus nearly eliminating label noise. METHODS: We trained a deep learning-based classifier by combining individually trained random forests of image, clinical and methylation data to predict BRAF-V600 mutation status in primary and metastatic melanomas of The Cancer Genome Atlas cohort. RESULTS: With our multimodal approach, we achieved an area under the receiver operating characteristic curve of 0.80, whereas the individual classifiers yielded areas under the receiver operating characteristic curve of 0.63 (histopathologic image data), 0.66 (clinical data) and 0.66 (methylation data) on an independent data set. CONCLUSIONS: Our combined approach can predict BRAF status to some extent by identifying BRAF-V600 specific patterns at the histologic, clinical and epigenetic levels. The multimodal classifiers have improved generalisability in predicting BRAF mutation status.

TEMPO: A transformer-based mutation prediction framework for SARS-CoV-2 evolution.

The widespread of SARS-CoV-2 presents a significant threat to human society, as well as public health and economic development. Extensive efforts have been undertaken to battle against the pandemic, whereas effective approaches such as vaccination would be weakened by the continuous mutations, leading to considerable attention being attracted to the mutation prediction. However, most previous studies lack attention to phylogenetics. In this paper, we propose a novel and effective model TEMPO for predicting the mutation of SARS-CoV-2 evolution. Specifically, we design a phylogenetic tree-based sampling method to generate sequence evolution data. Then, a transformer-based model is presented for the site mutation prediction after learning the high-level representation of these sequence data. We conduct experiments to verify the effectiveness of TEMPO, leveraging a large-scale SARS-CoV- 2 dataset. Experimental results show that TEMPO is effective for mutation prediction of SARS- CoV-2 evolution and outperforms several state-of-the-art baseline methods. We further perform mutation prediction experiments of other infectious viruses, to explore the feasibility and robustness of TEMPO, and experimental results verify its superiority. The codes and datasets are freely available at https://github.com/ZJUDataIntelligence/TEMPO.

Learn to Estimate Genetic Mutation and Microsatellite Instability with Histopathology H&E Slides in Colon Carcinoma.

Colorectal cancer is one of the most common malignancies and the third leading cause of cancer-related mortality worldwide. Identifying KRAS, NRAS, and BRAF mutations and estimating MSI status is closely related to the individualized therapeutic judgment and oncologic prognosis of CRC patients. In this study, we introduce a cascaded network framework with an average voting ensemble strategy to sequentially identify the tumor regions and predict gene mutations & MSI status from whole-slide H&E images. Experiments on a colorectal cancer dataset indicate that the proposed method can achieve higher fidelity in both gene mutation prediction and MSI status estimation. In the testing set, our method achieves 0.792, 0.886, 0.897, and 0.764 AUCs for KRAS, NRAS, BRAF, and MSI, respectively. The results suggest that the deep convolutional networks have the potential to provide diagnostic insight and clinical guidance directly from pathological H&E slides.

Deep learning-based tumor microenvironment segmentation is predictive of tumor mutations and patient survival in non-small-cell lung cancer.

BACKGROUND: Despite the fact that tumor microenvironment (TME) and gene mutations are the main determinants of progression of the deadliest cancer in the world - lung cancer, their interrelations are not well understood. Digital pathology data provides a unique insight into the spatial composition of the TME. Various spatial metrics and machine learning approaches were proposed for prediction of either patient survival or gene mutations from this data. Still, these approaches are limited in the scope of analyzed features and in their explainability, and as such fail to transfer to clinical practice. METHODS: Here, we generated 23,199 image patches from 26 hematoxylin-and-eosin (H&E)-stained lung cancer tissue sections and annotated them into 9 different tissue classes. Using this dataset, we trained a deep neural network ARA-CNN. Next, we applied the trained network to segment 467 lung cancer H&E images from The Cancer Genome Atlas (TCGA) database. We used the segmented images to compute human-interpretable features reflecting the heterogeneous composition of the TME, and successfully utilized them to predict patient survival and cancer gene mutations. RESULTS: We achieved per-class AUC ranging from 0.72 to 0.99 for classifying tissue types in lung cancer with ARA-CNN. Machine learning models trained on the proposed human-interpretable features achieved a c-index of 0.723 in the task of survival prediction and AUC up to 73.5% for PDGFRB in the task of mutation classification. CONCLUSIONS: We presented a framework that accurately predicted survival and gene mutations in lung adenocarcinoma patients based on human-interpretable features extracted from H&E slides. Our approach can provide important insights for designing novel cancer treatments, by linking the spatial structure of the TME in lung adenocarcinoma to gene mutations and patient survival. It can also expand our understanding of the effects that the TME has on tumor evolutionary processes. Our approach can be generalized to different cancer types to inform precision medicine strategies.

TargetMM: Accurate Missense Mutation Prediction by Utilizing Local and Global Sequence Information with Classifier Ensemble.

AIM AND OBJECTIVE: Missense mutation (MM) may lead to various human diseases by disabling proteins. Accurate prediction of MM is important and challenging for both protein function annotation and drug design. Although several computational methods yielded acceptable success rates, there is still room for further enhancing the prediction performance of MM. MATERIALS AND METHODS: In the present study, we designed a new feature extracting method, which considers the impact degree of residues in the microenvironment range to the mutation site. Stringent cross-validation and independent test on benchmark datasets were performed to evaluate the efficacy of the proposed feature extracting method. Furthermore, three heterogeneous prediction models were trained and then ensembled for the final prediction. By combining the feature representation method and classifier ensemble technique, we reported a novel MM predictor called TargetMM for identifying the pathogenic mutations from the neutral ones. RESULTS: Comparison outcomes based on statistical evaluation demonstrate that TargetMM outperforms the prior advanced methods on the independent test data. The source codes and benchmark datasets of TargetMM are freely available at https://github.com/sera616/TargetMM.git for academic use.

Using structural analysis to clarify the impact of single nucleotide variants in neurexin/neuroligin revealed in clinical genomic sequencing.

The synapse is a highly specialized and dynamic structure, which is involved in regulating neurotransmission. Nerve cell adhesion molecule is a kind of transmembrane protein that mediates the interaction between cells and cells, cells and extracellular matrix, and plays a role in cell recognition, metastasis, and transmembrane signal transduction. Among nerve cell adhesion molecules, Neurexins (NRXNs) and Neuroligins (NLGNs) have been focused due to the relation with autism and other neuropsychiatric diseases. The previous research discovered numerous variants in NRXNs and NLGNs reported in neurodevelopmental disorders by genomic sequencing. However, structural variants in synaptic molecules caused by genome variants still prevent us from understanding the molecular mechanism of diseases. Thus, we sought to conduct a comprehensive risk assessment of the known NRXN and NLGN gene variants by protein structure analysis. In this study, we analyzed the structural properties of the NRXN/NLGN complex by calculating free energy in residue scanning, in combination with existing risk evaluation tools to focus on candidate missense mutations. Our calculations show that five candidate missense mutations in NLGNs can reduce the stability of NLGNs and even prevent the formation of NRXN/NLGN complexes, namely R87W, R204H, R437H, R437C and R583W. In addition, we found that the affinity of the amino acid substitution (Leu593Phe) (ΔΔG(affinity)) changes the affinity of the NLGN dimer. Overall, we have identified important potential pathological variants that provide clues to biomarkers. Communicated by Ramaswamy H. Sarma.

MutTMPredictor: Robust and accurate cascade XGBoost classifier for prediction of mutations in transmembrane proteins.

Transmembrane proteins have critical biological functions and play a role in a multitude of cellular processes including cell signaling, transport of molecules and ions across membranes. Approximately 60% of transmembrane proteins are considered as drug targets. Missense mutations in such proteins can lead to many diverse diseases and disorders, such as neurodegenerative diseases and cystic fibrosis. However, there are limited studies on mutations in transmembrane proteins. In this work, we first design a new feature encoding method, termed weight attenuation position-specific scoring matrix (WAPSSM), which builds upon the protein evolutionary information. Then, we propose a new mutation prediction algorithm (cascade XGBoost) by leveraging the idea learned from consensus predictors and gcForest. Multi-level experiments illustrate the effectiveness of WAPSSM and cascade XGBoost algorithms. Finally, based on WAPSSM and other three types of features, in combination with the cascade XGBoost algorithm, we develop a new transmembrane protein mutation predictor, named MutTMPredictor. We benchmark the performance of MutTMPredictor against several existing predictors on seven datasets. On the 546 mutations dataset, MutTMPredictor achieves the accuracy (ACC) of 0.9661 and the Matthew's Correlation Coefficient (MCC) of 0.8950. While on the 67,584 dataset, MutTMPredictor achieves an MCC of 0.7523 and area under curve (AUC) of 0.8746, which are 0.1625 and 0.0801 respectively higher than those of the existing best predictor (fathmm). Besides, MutTMPredictor also outperforms two specific predictors on the Pred-MutHTP datasets. The results suggest that MutTMPredictor can be used as an effective method for predicting and prioritizing missense mutations in transmembrane proteins. The MutTMPredictor webserver and datasets are freely accessible at http://csbio.njust.edu.cn/bioinf/muttmpredictor/ for academic use.

NP-59 Adrenal Scintigraphy as an Imaging Biomarker to Predict KCNJ5 Mutation in Primary Aldosteronism Patients.

Purpose: Somatic KCNJ5 mutation occurs in half of unilateral primary aldosteronism (PA) and is associated with more severe phenotype. Mutation status can only be identified by tissue sample from adrenalectomy. NP-59 adrenal scintigraphy is a noninvasive functional study for disease activity assessment. This study aimed to evaluate the predictive value of NP-59 adrenal scintigraphy in somatic KCNJ5 mutation among PA patients who received adrenalectomy. Methods: Sixty-two PA patients who had NP-59 adrenal scintigraphy before adrenalectomy with available KCNJ5 mutation status were included. Two semiquantitative parameters, adrenal to liver ratio (ALR) and lesion to contralateral ratio of bilateral adrenal glands (CON) derived from NP-59 adrenal scintigraphy, of mutated and wild-type patients were compared. Cutoff values calculated by receiver-operating characteristic (ROC) analysis were used as a predictor of KCNJ5 mutation. Results: Twenty patients had KCNJ5 mutation and 42 patients were wild type. Patients harboring KCNJ5 mutation had both higher ALR and CON (p = 0.0031 and 0.0833, respectively) than wild-type patients. With ALR and CON cutoff of 2.10 and 1.95, the sensitivity and specificity to predict KCNJ5 mutation were 85%, 57% and 45%, 93%, respectively. Among 20 patients with KCNJ5 mutation, 16 showed G151R point mutation (KCNJ5- G151R) and 4 showed L168R point mutation (KCNJ5-L168R), which former one had significantly lower ALR (p=0.0471). Conclusion: PA patients harboring somatic KCNJ5 mutation had significantly higher NP-59 uptake regarding to ALR and CON than those without mutation. APAs with KCNJ5-L168R point mutation showed significantly higher ALR than those with KCNJ5-G151R point mutation.

A novel method for conserved sequence extraction with prospective mutation prediction for SARS-CoV-2 PCR primer design.

While the whole genomic sequence of SARS-CoV-2 had been revealed, it was also demonstrated that the genome of SARS-CoV-2 exhibits identity with the genome of SARS-CoV and MERS-CoV with ratios of 80 % and 50 % respectively. In the light of SARS-CoV-2 infection and mortality data, diagnosis and treatment of COVID-19 came into prominence around the world. As such many RT-PCR kits have been developed by biotechnology scientists. However viruses are fast mutating organisms and in order to increase accuracy, feasibility in long term and avoid the off target results of RT-PCR assays, regions of viral genome with low mutation rate and designing of primers targeting these regions are quite important. In this scope, we are presenting a novel algorithm that could be used for finding low mutation rate regions of SARS-CoV-2 and primers that were designed according to findings from our algorithm in this study.

Disease characterization using a partial correlation-based sample-specific network.

A single-sample network (SSN) is a biological molecular network constructed from single-sample data given a reference dataset and can provide insights into the mechanisms of individual diseases and aid in the development of personalized medicine. In this study, we proposed a computational method, a partial correlation-based single-sample network (P-SSN), which not only infers a network from each single-sample data given a reference dataset but also retains the direct interactions by excluding indirect interactions (https://github.com/hyhRise/P-SSN). By applying P-SSN to analyze tumor data from the Cancer Genome Atlas and single cell data, we validated the effectiveness of P-SSN in predicting driver mutation genes (DMGs), producing network distance, identifying subtypes and further classifying single cells. In particular, P-SSN is highly effective in predicting DMGs based on single-sample data. P-SSN is also efficient for subtyping complex diseases and for clustering single cells by introducing network distance between any two samples.