Cancer-specific high-throughput annotation of somatic mutations: computational prediction of driver missense mutations

Advancing cancer driver gene detection via Schur complement graph augmentation and independent subspace feature extraction

Accurately identifying cancer driver genes (CDGs) is crucial for guiding cancer treatment and has recently received great attention from researchers. However, the high complexity and heterogeneity of cancer gene regulatory networks limit the precition accuracy of existing deep learning models. To address this, we introduce a model called SCIS-CDG that utilizes Schur complement graph augmentation and independent subspace feature extraction techniques to effectively predict potential CDGs. Firstly, a random Schur complement strategy is adopted to generate two augmented views of gene network within a graph contrastive learning framework. Rapid randomization of the random Schur complement strategy enhances the model's generalization and its ability to handle complex networks effectively. Upholding the Schur complement principle in expectations promotes the preservation of the original gene network's vital structure in the augmented views. Subsequently, we employ feature extraction technology using multiple independent subspaces, each trained with independent weights to reduce inter-subspace dependence and improve the model's expressiveness. Concurrently, we introduced a feature expansion component based on the structure of the gene network to address issues arising from the limited dimensionality of node features. Moreover, it can alleviate the challenges posed by the heterogeneity of cancer gene networks to some extent. Finally, we integrate a learnable attention weight mechanism into the graph neural network (GNN) encoder, utilizing feature expansion technology to optimize the significance of various feature levels in the prediction task. Following extensive experimental validation, the SCIS-CDG model has exhibited high efficiency in identifying known CDGs and uncovering potential unknown CDGs in external datasets. Particularly when compared to previous conventional GNN models, its performance has seen significant improved. The code and data are publicly available at: https://github.com/mxqmxqmxq/SCIS-CDG.

A latent variable model for evaluating mutual exclusivity and co-occurrence between driver mutations in cancer

A key challenge in cancer genomics is understanding the functional relationships and dependencies between combinations of somatic mutations that drive cancer development. Such driver mutations frequently exhibit patterns of mutual exclusivity or co-occurrence across tumors, and many methods have been developed to identify such dependency patterns from bulk DNA sequencing data of a cohort of patients. However, while mutual exclusivity and co-occurrence are described as properties of driver mutations, existing methods do not explicitly disentangle functional, driver mutations from neutral, passenger mutations. In particular, nearly all existing methods evaluate mutual exclusivity or co-occurrence at the gene level, marking a gene as mutated if any mutation - driver or passenger - is present. Since some genes have a large number of passenger mutations, existing methods either restrict their analyses to a small subset of suspected driver genes - limiting their ability to identify novel dependencies - or make spurious inferences of mutual exclusivity and co-occurrence involving genes with many passenger mutations. We introduce DIALECT, an algorithm to identify dependencies between pairs of driver mutations from somatic mutation counts. We derive a latent variable mixture model for drivers and passengers that combines existing probabilistic models of passenger mutation rates with a latent variable describing the unknown status of a mutation as a driver or passenger. We use an expectation maximization (EM) algorithm to estimate the parameters of our model, including the rates of mutually exclusivity and co-occurrence between drivers. We demonstrate that DIALECT more accurately infers mutual exclusivity and co-occurrence between driver mutations compared to existing methods on both simulated mutation data and somatic mutation data from 5 cancer types in The Cancer Genome Atlas (TCGA).

LncRNAs in necroptosis: Deciphering their role in cancer pathogenesis and therapy

Necroptosis, a controlled type of cell death that is different from apoptosis, has become a key figure in the aetiology of cancer and offers a possible target for treatment. A growing number of biological activities, including necroptosis, have been linked to long noncoding RNAs (lncRNAs), a varied family of RNA molecules with limited capacity to code for proteins. The complex interactions between LncRNAs and important molecular effectors of necroptosis, including mixed lineage kinase domain-like pseudokinase (MLKL) and receptor-interacting protein kinase 3 (RIPK3), will be investigated. We will explore the many methods that LncRNAs use to affect necroptosis, including protein-protein interactions, transcriptional control, and post-transcriptional modification. Additionally, the deregulation of certain LncRNAs in different forms of cancer will be discussed, highlighting their dual function in influencing necroptotic processes as tumour suppressors and oncogenes. The goal of this study is to thoroughly examine the complex role that LncRNAs play in controlling necroptotic pathways and how that regulation affects the onset and spread of cancer. In the necroptosis for cancer treatment, this review will also provide insight into the possible therapeutic uses of targeting LncRNAs. Techniques utilising LncRNA-based medicines show promise in controlling necroptotic pathways to prevent cancer from spreading and improve the effectiveness of treatment.

Follicular lymphoma B cells exhibit heterogeneous transcriptional states with associated somatic alterations and tumor microenvironments

Follicular lymphoma (FL) is an indolent non-Hodgkin lymphoma of germinal center origin, which presents with significant biologic and clinical heterogeneity. Using RNA-seq on B cells sorted from 87 FL biopsies, combined with machine-learning approaches, we identify 3 transcriptional states that divide the biological ontology of FL B cells into inflamed, proliferative, and chromatin-modifying states, with relationship to prior GC B cell phenotypes. When integrated with whole-exome sequencing and immune profiling, we find that each state was associated with a combination of mutations in chromatin modifiers, copy-number alterations to TNFAIP3, and T follicular helper cells (Tfh) cell interactions, or primarily by a microenvironment rich in activated T cells. Altogether, these data define FL B cell transcriptional states across a large cohort of patients, contribute to our understanding of FL heterogeneity at the tumor cell level, and provide a foundation for guiding therapeutic intervention.

Computational approaches for identifying disease-causing mutations in proteins

Advancements in genome sequencing have expanded the scope of investigating mutations in proteins across different diseases. Amino acid mutations in a protein alter its structure, stability and function and some of them lead to diseases. Identification of disease-causing mutations is a challenging task and it will be helpful for designing therapeutic strategies. Hence, mutation data available in the literature have been curated and stored in several databases, which have been effectively utilized for developing computational methods to identify deleterious mutations (drivers), using sequence and structure-based properties of proteins. In this chapter, we describe the contents of specific databases that have information on disease-causing and neutral mutations followed by sequence and structure-based properties. Further, characteristic features of disease-causing mutations will be discussed along with computational methods for identifying cancer hotspot residues and disease-causing mutations in proteins.

Advances in computational methods for identifying cancer driver genes

Cancer driver genes (CDGs) are crucial in cancer prevention, diagnosis and treatment. This study employed computational methods for identifying CDGs, categorizing them into four groups. The major frameworks for each of these four categories were summarized. Additionally, we systematically gathered data from public databases and biological networks, and we elaborated on computational methods for identifying CDGs using the aforementioned databases. Further, we summarized the algorithms, mainly involving statistics and machine learning, used for identifying CDGs. Notably, the performances of nine typical identification methods for eight types of cancer were compared to analyze the applicability areas of these methods. Finally, we discussed the challenges and prospects associated with methods for identifying CDGs. The present study revealed that the network-based algorithms and machine learning-based methods demonstrated superior performance.

Identifying cancer driver genes in individual tumours

Cancer is a heterogeneous disease with a strong genetic component making it suitable for precision medicine approaches aimed at identifying the underlying molecular drivers within a tumour. Large scale population-level cancer sequencing consortia have identified many actionable mutations common across both cancer types and sub-types, resulting in an increasing number of successful precision medicine programs. Nonetheless, such approaches fail to consider the effects of mutations unique to an individual patient and may miss rare driver mutations, necessitating personalised approaches to driver-gene prioritisation. One approach is to quantify the functional importance of individual mutations in a single tumour based on how they affect the expression of genes in a gene interaction network (GIN). These GIN-based approaches can be broadly divided into those that utilise an existing reference GIN and those that construct de novo patient-specific GINs. These single-tumour approaches have several limitations that likely influence their results, such as use of reference cohort data, network choice, and approaches to mathematical approximation, and more research is required to evaluate the in vitro and in vivo applicability of their predictions. This review examines the current state of the art methods that identify driver genes in single tumours with a focus on GIN-based driver prioritisation.

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.

ASCARIS: Positional feature annotation and protein structure-based representation of single amino acid variations

Background

Genomic variations may cause deleterious effects on protein functionality and perturb biological processes. Elucidating the effects of variations is critical for developing novel treatment strategies for diseases of genetic origin. Computational approaches have been aiding the work in this field by modeling and analyzing the mutational landscape. However, new approaches are required, especially for accurate representation and data-centric analysis of sequence variations.

Method

In this study, we propose ASCARIS (Annotation and StruCture-bAsed RepresentatIon of Single amino acid variations), a method for the featurization (i.e., quantitative representation) of single amino acid variations (SAVs), which could be used for a variety of purposes, such as predicting their functional effects or building multi-omics-based integrative models. ASCARIS utilizes the direct and spatial correspondence between the location of the SAV on the sequence/structure and 30 different types of positional feature annotations (e.g., active/lipidation/glycosylation sites; calcium/metal/DNA binding, inter/transmembrane regions, etc.), along with structural features and physicochemical properties. The main novelty of this method lies in constructing reusable numerical representations of SAVs via functional annotations.

Results

We statistically analyzed the relationship between these features and the consequences of variations and found that each carries information in this regard. To investigate potential applications of ASCARIS, we trained variant effect prediction models that utilize our SAV representations as input. We carried out an ablation study and a comparison against the state-of-the-art methods and observed that ASCARIS has a competing and complementary performance against widely-used predictors. ASCARIS can be used alone or in combination with other approaches to represent SAVs from a functional perspective. ASCARIS is available as a programmatic tool at https://github.com/HUBioDataLab/ASCARIS and as a web-service at https://huggingface.co/spaces/HUBioDataLab/ASCARIS.

F-box DNA Helicase 1 (FBH1) Contributes to the Destabilization of DNA Damage Repair Machinery in Human Cancers

Homologous recombination (HR) is the major mechanism of rescue of stalled replication forks or repair of DNA double-strand breaks (DSBs) during S phase or mitosis. In human cells, HR is facilitated by the BRCA2-BRCA1-PALB2 module, which loads the RAD51 recombinase onto a resected single-stranded DNA end to initiate repair. Although the process is essential for error-free repair, unrestrained HR can cause chromosomal rearrangements and genome instability. F-box DNA Helicase 1 (FBH1) antagonizes the role of BRCA2-BRCA1-PALB2 to restrict hyper-recombination and prevent genome instability. Here, we analyzed reported FBH1 mutations in cancer cells using the Catalogue of Somatic Mutations in Cancers (COSMIC) to understand how they interact with the BRCA2-BRCA1-PALB2. Consistent with previous results from yeast, we find that FBH1 mutations co-occur with BRCA2 mutations and to some degree BRCA1 and PALB2. We also describe some co-occurring mutations with RAD52, the accessory RAD51 loader and facilitator of single-strand annealing, which is independent of RAD51. In silico modeling was used to investigate the role of key FBH1 mutations on protein function, and a Q650K mutation was found to destabilize the protein structure. Taken together, this work highlights how mutations in several DNA damage repair genes contribute to cellular transformation and immortalization.

PredinID: Predicting Pathogenic Inframe Indels in Human Through Graph Convolution Neural Network With Graph Sampling Technique

Inframe insertion/deletion (indel) variants may alter protein sequence and function, which are closely related to an extensive variety of diseases. Although recent researches have paid attention to the associations between inframe indels and diseases, modeling indels in silico and interpreting their pathogenicity remain challenging, mainly due to the lack of experimental information and computational methodologies. In this article, we propose a novel computational method named PredinID (Predictor for inframe InDels) via graph convolutional network (GCN). PredinID leverages k-nearest neighbor algorithm to construct the feature graph for aggregating more informative representation, regarding the pathogenic inframe indel prediction as a node classification task. An edge-based sampling strategy is designed for extracting information from both the potential connections of feature space and the topological structure of subgraphs. Evaluated by 5-fold cross-validations, the PredinID method achieves satisfactory performance and is superior to four classic machine learning algorithms and two GCN methods. Comprehensive experiments show that PredinID has superior performances when compared with the state-of-the-art methods on the independent test set. Moreover, we also implement a web server at http://predinid.bio.aielab.cc/, to facilitate the use of the model.

Analysis of genomic alterations in primary central nervous system lymphoma

Primary central nervous system lymphoma (PCNSL) is a rare and special type of non-Hodgkin lymphoma with a significantly worse median overall prognosis than that of non-Hodgkin lymphoma outside the brain. Clarifying the genomic characteristics and alterations in PCNSL could provide clues regarding its distinctive pathophysiology and new treatment options. However, current knowledge about the genomics of PCNSL is limited. In this study, next-generation sequencing (NGS) was performed to investigate the genomic profile of PCNSL. Samples from 12 patients diagnosed with PCNSL at our institution were analyzed for gene mutations using NGS. This study showed that missense mutations were the most common mutation type. C > A/G > T accounted for most of the single-base mutations, which reflected the preference of the tumor sample mutation type and may serve as an important prognostic factor. The most significantly mutated gene was myeloid differentiation factor 88 (MYD88) (0.55), followed by CD79B, LRP1B, and PRDM1 (0.36). None of the cases showed a high tumor mutational burden. In addition to the traditional driver genes, we also identified some new possible ones such as MET, PIM1, and RSBN1L. Enrichment analysis revealed that genes mutated in PCNSL were involved in many pathways and functional protein activities, such as the extracellular matrix and adhesion molecules. The most common genetic alterations in PCNSL were identified using NGS. Mutations in multiple genes highlights the complex molecular heterogeneity of PCNSL. Enrichment analysis revealed possible pathogenesis. Further exploration of new driver genes could provide novel insights into diagnosis and precision medicine for PCNSL.

Pan-cancer proteogenomics connects oncogenic drivers to functional states

Cancer driver events refer to key genetic aberrations that drive oncogenesis; however, their exact molecular mechanisms remain insufficiently understood. Here, our multi-omics pan-cancer analysis uncovers insights into the impacts of cancer drivers by identifying their significant cis-effects and distal trans-effects quantified at the RNA, protein, and phosphoprotein levels. Salient observations include the association of point mutations and copy-number alterations with the rewiring of protein interaction networks, and notably, most cancer genes converge toward similar molecular states denoted by sequence-based kinase activity profiles. A correlation between predicted neoantigen burden and measured T cell infiltration suggests potential vulnerabilities for immunotherapies. Patterns of cancer hallmarks vary by polygenic protein abundance ranging from uniform to heterogeneous. Overall, our work demonstrates the value of comprehensive proteogenomics in understanding the functional states of oncogenic drivers and their links to cancer development, surpassing the limitations of studying individual cancer types.

Actionability classification of variants of unknown significance correlates with functional effect

Genomically-informed therapy requires consideration of the functional impact of genomic alterations on protein expression and/or function. However, a substantial number of variants are of unknown significance (VUS). The MD Anderson Precision Oncology Decision Support (PODS) team developed an actionability classification scheme that categorizes VUS as either "Unknown" or "Potentially" actionable based on their location within functional domains and/or proximity to known oncogenic variants. We then compared PODS VUS actionability classification with results from a functional genomics platform consisting of mutant generation and cell viability assays. 106 (24%) of 438 VUS in 20 actionable genes were classified as oncogenic in functional assays. Variants categorized by PODS as Potentially actionable (N = 204) were more likely to be oncogenic than those categorized as Unknown (N = 230) (37% vs 13%, p = 4.08e-09). Our results demonstrate that rule-based actionability classification of VUS can identify patients more likely to have actionable variants for consideration with genomically-matched therapy.

Autoimmune alleles at the major histocompatibility locus modify melanoma susceptibility

Autoimmunity and cancer represent two different aspects of immune dysfunction. Autoimmunity is characterized by breakdowns in immune self-tolerance, while impaired immune surveillance can allow for tumorigenesis. The class I major histocompatibility complex (MHC-I), which displays derivatives of the cellular peptidome for immune surveillance by CD8+ T cells, serves as a common genetic link between these conditions. As melanoma-specific CD8+ T cells have been shown to target melanocyte-specific peptide antigens more often than melanoma-specific antigens, we investigated whether vitiligo- and psoriasis-predisposing MHC-I alleles conferred a melanoma-protective effect. In individuals with cutaneous melanoma from both The Cancer Genome Atlas (n = 451) and an independent validation set (n = 586), MHC-I autoimmune-allele carrier status was significantly associated with a later age of melanoma diagnosis. Furthermore, MHC-I autoimmune-allele carriers were significantly associated with decreased risk of developing melanoma in the Million Veteran Program (OR = 0.962, p = 0.024). Existing melanoma polygenic risk scores (PRSs) did not predict autoimmune-allele carrier status, suggesting these alleles provide orthogonal risk-relevant information. Mechanisms of autoimmune protection were neither associated with improved melanoma-driver mutation association nor improved gene-level conserved antigen presentation relative to common alleles. However, autoimmune alleles showed higher affinity relative to common alleles for particular windows of melanocyte-conserved antigens and loss of heterozygosity of autoimmune alleles caused the greatest reduction in presentation for several conserved antigens across individuals with loss of HLA alleles. Overall, this study presents evidence that MHC-I autoimmune-risk alleles modulate melanoma risk unaccounted for by current PRSs.

Bootstrap confidence for molecular evolutionary estimates from tumor bulk sequencing data

Bulk sequencing is commonly used to characterize the genetic diversity of cancer cell populations in tumors and the evolutionary relationships of cancer clones. However, bulk sequencing produces aggregate information on nucleotide variants and their sample frequencies, necessitating computational methods to predict distinct clone sequences and their frequencies within a sample. Interestingly, no methods are available to measure the statistical confidence in the variants assigned to inferred clones. We introduce a bootstrap resampling approach that combines clone prediction and statistical confidence calculation for every variant assignment. Analysis of computer-simulated datasets showed the bootstrap approach to work well in assessing the reliability of predicted clones as well downstream inferences using the predicted clones (e.g., mapping metastatic migration paths). We found that only a fraction of inferences have good bootstrap support, which means that many inferences are tentative for real data. Using the bootstrap approach, we analyzed empirical datasets from metastatic cancers and placed bootstrap confidence on the estimated number of mutations involved in cell migration events. We found that the numbers of driver mutations involved in metastatic cell migration events sourced from primary tumors are similar to those where metastatic tumors are the source of new metastases. So, mutations with driver potential seem to keep arising during metastasis. The bootstrap approach developed in this study is implemented in software available at https://github.com/SayakaMiura/CloneFinderPlus.

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.

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.

Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications

Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.

Protein Arginine Methyltransferase 5 (PRMT5) Mutations in Cancer Cells

Arginine methylation is a form of posttranslational modification that regulates many cellular functions such as development, DNA damage repair, inflammatory response, splicing, and signal transduction, among others. Protein arginine methyltransferase 5 (PRMT5) is one of nine identified methyltransferases, and it can methylate both histone and non-histone targets. It has pleiotropic functions, including recruitment of repair machinery to a chromosomal DNA double strand break (DSB) and coordinating the interplay between repair and checkpoint activation. Thus, PRMT5 has been actively studied as a cancer treatment target, and small molecule inhibitors of its enzymatic activity have already been developed. In this report, we analyzed all reported PRMT5 mutations appearing in cancer cells using data from the Catalogue of Somatic Mutations in Cancers (COSMIC). Our goal is to classify mutations as either drivers or passengers to understand which ones are likely to promote cellular transformation. Using gold standard artificial intelligence algorithms, we uncovered several key driver mutations in the active site of the enzyme (D306H, L315P, and N318K). In silico protein modeling shows that these mutations may affect the affinity of PRMT5 for S-adenosylmethionine (SAM), which is required as a methyl donor. Electrostatic analysis of the enzyme active site shows that one of these mutations creates a tunnel in the vicinity of the SAM binding site, which may allow interfering molecules to enter the enzyme active site and decrease its activity. We also identified several non-coding mutations that appear to affect PRMT5 splicing. Our analyses provide insights into the role of PRMT5 mutations in cancer cells. Additionally, since PRMT5 single molecule inhibitors have already been developed, this work may uncover future directions in how mutations can affect targeted inhibition.

Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data

BACKGROUND

It remains an important challenge to predict the functional consequences or clinical impacts of genetic variants in human diseases, such as cancer. An increasing number of genetic variants in cancer have been discovered and documented in public databases such as COSMIC, but the vast majority of them have no functional or clinical annotations. Some databases, such as CiVIC are available with manual annotation of functional mutations, but the size of the database is small due to the use of human annotation. Since the unlabeled data (millions of variants) typically outnumber labeled data (thousands of variants), computational tools that take advantage of unlabeled data may improve prediction accuracy.

RESULT

To leverage unlabeled data to predict functional importance of genetic variants, we introduced a method using semi-supervised generative adversarial networks (SGAN), incorporating features from both labeled and unlabeled data. Our SGAN model incorporated features from clinical guidelines and predictive scores from other computational tools. We also performed comparative analysis to study factors that influence prediction accuracy, such as using different algorithms, types of features, and training sample size, to provide more insights into variant prioritization. We found that SGAN can achieve competitive performances with small labeled training samples by incorporating unlabeled samples, which is a unique advantage compared to traditional machine learning methods. We also found that manually curated samples can achieve a more stable predictive performance than publicly available datasets.

CONCLUSIONS

By incorporating much larger samples of unlabeled data, the SGAN method can improve the ability to detect novel oncogenic variants, compared to other machine-learning algorithms that use only labeled datasets. SGAN can be potentially used to predict the pathogenicity of more complex variants such as structural variants or non-coding variants, with the availability of more training samples and informative features.

From multi-omics data to the cancer druggable gene discovery: a novel machine learning-based approach

The development of targeted drugs allows precision medicine in cancer treatment and optimal targeted therapies. Accurate identification of cancer druggable genes helps strengthen the understanding of targeted cancer therapy and promotes precise cancer treatment. However, rare cancer-druggable genes have been found due to the multi-omics data's diversity and complexity. This study proposes deep forest for cancer druggable genes discovery (DF-CAGE), a novel machine learning-based method for cancer-druggable gene discovery. DF-CAGE integrated the somatic mutations, copy number variants, DNA methylation and RNA-Seq data across ˜10 000 TCGA profiles to identify the landscape of the cancer-druggable genes. We found that DF-CAGE discovers the commonalities of currently known cancer-druggable genes from the perspective of multi-omics data and achieved excellent performance on OncoKB, Target and Drugbank data sets. Among the ˜20 000 protein-coding genes, DF-CAGE pinpointed 465 potential cancer-druggable genes. We found that the candidate cancer druggable genes (CDG) are clinically meaningful and divided the CDG into known, reliable and potential gene sets. Finally, we analyzed the omics data's contribution to identifying druggable genes. We found that DF-CAGE reports druggable genes mainly based on the copy number variations (CNVs) data, the gene rearrangements and the mutation rates in the population. These findings may enlighten the future study and development of new drugs.

Gain-of-Function Variomics and Multi-omics Network Biology for Precision Medicine

Traditionally, disease causal mutations were thought to disrupt gene function. However, it becomes more clear that many deleterious mutations could exhibit a "gain-of-function" (GOF) behavior. Systematic investigation of such mutations has been lacking and largely overlooked. Advances in next-generation sequencing have identified thousands of genomic variants that perturb the normal functions of proteins, further contributing to diverse phenotypic consequences in disease. Elucidating the functional pathways rewired by GOF mutations will be crucial for prioritizing disease-causing variants and their resultant therapeutic liabilities. In distinct cell types (with varying genotypes), precise signal transduction controls cell decision, including gene regulation and phenotypic output. When signal transduction goes awry due to GOF mutations, it would give rise to various disease types. Quantitative and molecular understanding of network perturbations by GOF mutations may provide explanations for 'missing heritability" in previous genome-wide association studies. We envision that it will be instrumental to push current paradigm toward a thorough functional and quantitative modeling of all GOF mutations and their mechanistic molecular events involved in disease development and progression. Many fundamental questions pertaining to genotype-phenotype relationships remain unresolved. For example, which GOF mutations are key for gene regulation and cellular decisions? What are the GOF mechanisms at various regulation levels? How do interaction networks undergo rewiring upon GOF mutations? Is it possible to leverage GOF mutations to reprogram signal transduction in cells, aiming to cure disease? To begin to address these questions, we will cover a wide range of topics regarding GOF disease mutations and their characterization by multi-omic networks. We highlight the fundamental function of GOF mutations and discuss the potential mechanistic effects in the context of signaling networks. We also discuss advances in bioinformatic and computational resources, which will dramatically help with studies on the functional and phenotypic consequences of GOF mutations.

Predicting mutational function using machine learning

Genetic variations are one of the major causes of phenotypic variations between human individuals. Although beneficial as being the substrate of evolution, germline mutations may cause diseases, including Mendelian diseases and complex diseases such as diabetes and heart diseases. Mutations occurring in somatic cells are a main cause of cancer and likely cause age-related phenotypes and other age-related diseases. Because of the high abundance of genetic variations in the human genome, i.e., millions of germline variations per human subject and thousands of additional somatic mutations per cell, it is technically challenging to experimentally verify the function of every possible mutation and their interactions. Significant progress has been made to solve this problem using computational approaches, especially machine learning (ML). Here, we review the progress and achievements made in recent years in this field of research. We classify the computational models in two ways: one according to their prediction goals including protein structural alterations, gene expression changes, and disease risks, and the other according to their methodologies, including non-machine learning methods, classical machine learning methods, and deep neural network methods. For models in each category, we discuss their architecture, prediction accuracy, and potential limitations. This review provides new insights into the applications and future directions of computational approaches in understanding the role of mutations in aging and disease.

DriverMP enables improved identification of cancer driver genes

BACKGROUND

Cancer is widely regarded as a complex disease primarily driven by genetic mutations. A critical concern and significant obstacle lies in discerning driver genes amid an extensive array of passenger genes.

FINDINGS

We present a new method termed DriverMP for effectively prioritizing altered genes on a cancer-type level by considering mutated gene pairs. It is designed to first apply nonsilent somatic mutation data, protein‒protein interaction network data, and differential gene expression data to prioritize mutated gene pairs, and then individual mutated genes are prioritized based on prioritized mutated gene pairs. Application of this method in 10 cancer datasets from The Cancer Genome Atlas demonstrated its great improvements over all the compared state-of-the-art methods in identifying known driver genes. Then, a comprehensive analysis demonstrated the reliability of the novel driver genes that are strongly supported by clinical experiments, disease enrichment, or biological pathway analysis.

CONCLUSIONS

The new method, DriverMP, which is able to identify driver genes by effectively integrating the advantages of multiple kinds of cancer data, is available at https://github.com/LiuYangyangSDU/DriverMP. In addition, we have developed a novel driver gene database for 10 cancer types and an online service that can be freely accessed without registration for users. The DriverMP method, the database of novel drivers, and the user-friendly online server are expected to contribute to new diagnostic and therapeutic opportunities for cancers.

A network-based method for identifying cancer driver genes based on node control centrality

Cancer is one of the major contributors to human mortality and has a serious influence on human survival and health. In biomedical research, the identification of cancer driver genes (cancer drivers for short) is an important task; cancer drivers can promote the progression and generation of cancer. To identify cancer drivers, many methods have been developed. These computational models only identify coding cancer drivers; however, non-coding drivers likewise play significant roles in the progression of cancer. Hence, we propose a Network-based Method for identifying cancer Driver Genes based on node Control Centrality (NMDGCC), which can identify coding and non-coding cancer driver genes. The process of NMDGCC for identifying driver genes mainly includes the following two steps. In the first step, we construct a gene interaction network by using mRNAs and miRNAs expression data in the cancer state. In the second step, the control centrality of the node is used to identify cancer drivers in the constructed network. We use the breast cancer dataset from The Cancer Genome Atlas (TCGA) to verify the effectiveness of NMDGCC. Compared with the existing methods of cancer driver genes identification, NMDGCC has a better performance. NMDGCC also identifies 295 miRNAs as non-coding cancer drivers, of which 158 are related to tumorigenesis of BRCA. We also apply NMDGCC to identify driver genes related to the different breast cancer subtypes. The result shows that NMDGCC detects many cancer drivers of specific cancer subtypes.

Identification of potential driver mutations in glioblastoma using machine learning

Glioblastoma is a fast and aggressively growing tumor in the brain and spinal cord. Mutation of amino acid residues in targets proteins, which are involved in glioblastoma, alters the structure and function and may lead to disease. In this study, we collected a set of 9386 disease-causing (drivers) mutations based on the recurrence in patient samples and experimentally annotated as pathogenic and 8728 as neutral (passenger) mutations. We observed that Arg is highly preferred at the mutant sites of drivers, whereas Met and Ile showed preferences in passengers. Inspecting neighboring residues at the mutant sites revealed that the motifs YP, CP and GRH, are preferred in drivers, whereas SI, IQ and TVI are dominant in neutral. In addition, we have computed other sequence-based features such as conservation scores, Position Specific Scoring Matrices (PSSM) and physicochemical properties, and developed a machine learning-based method, GBMDriver (GlioBlastoma Multiforme Drivers), for distinguishing between driver and passenger mutations. Our method showed an accuracy and AUC of 73.59% and 0.82, respectively, on 10-fold cross-validation and 81.99% and 0.87 in a blind set of 1809 mutants. The tool is available at https://web.iitm.ac.in/bioinfo2/GBMDriver/index.html. We envisage that the present method is helpful to prioritize driver mutations in glioblastoma and assist in identifying therapeutic targets.

Genomic Profiling Identifies Putative Pathogenic Alterations in NSCLC Brain Metastases

Introduction

Brain metastases (BM) severely affect the prognosis and quality of life of patients with NSCLC. Recently, molecularly targeted agents were found to have promising activity against BM in patients with NSCLC whose primary tumors carry "druggable" mutations. Nevertheless, it remains critical to identify specific pathogenic alterations that drive NSCLC-BM and that can provide novel and more effective therapeutic targets.

Methods

To identify potentially targetable pathogenic alterations in NSCLC-BM, we profiled somatic copy number alterations (SCNAs) in 51 matched pairs of primary NSCLC and BM samples from 33 patients with lung adenocarcinoma and 18 patients with lung squamous cell carcinoma. In addition, we performed multiregion copy number profiling on 15 BM samples and whole-exome sequencing on 40 of 51 NSCLC-BM pairs.

Results

BM consistently had a higher burden of SCNAs compared with the matched primary tumors, and SCNAs were typically homogeneously distributed within BM, suggesting BM do not undergo extensive evolution once formed. By comparing focal SCNAs in matched NSCLC-BM pairs, we identified putative BM-driving alterations affecting multiple cancer genes, including several potentially targetable alterations in genes such as CDK12, DDR2, ERBB2, and NTRK1, which we validated in an independent cohort of 84 BM samples. Finally, we identified putative pathogenic alterations in multiple cancer genes, including genes involved in epigenome editing and 3D genome organization, such as EP300, CTCF, and STAG2, which we validated by targeted sequencing of an independent cohort of 115 BM samples.

Conclusions

Our study represents the most comprehensive genomic characterization of NSCLC-BM available to date, paving the way to functional studies aimed at assessing the potential of the identified pathogenic alterations as clinical biomarkers and targets.

Human papillomavirus integration perspective in small cell cervical carcinoma

Small cell cervical carcinoma (SCCC) is a rare but aggressive malignancy. Here, we report human papillomavirus features and genomic landscape in SCCC via high-throughput HPV captured sequencing, whole-genome sequencing, whole-transcriptome sequencing, and OncoScan microarrays. HPV18 infections and integrations are commonly detected. Besides MYC family genes (37.9%), we identify SOX (8.4%), NR4A (6.3%), ANKRD (7.4%), and CEA (3.2%) family genes as HPV-integrated hotspots. We construct the genomic local haplotype around HPV-integrated sites, and find tandem duplications and amplified HPV long control regions (LCR). We propose three prominent HPV integration patterns: duplicating oncogenes (MYCN, MYC, and NR4A2), forming fusions (FGFR3-TACC3 and ANKRD12-NDUFV2), and activating genes (MYC) via the cis-regulations of viral LCRs. Moreover, focal CNA amplification peaks harbor canonical cancer genes including the HPV-integrated hotspots within MYC family, SOX2, and others. Our findings may provide potential molecular criteria for the accurate diagnosis and efficacious therapies for this lethal disease.

Allostery: Allosteric Cancer Drivers and Innovative Allosteric Drugs

Here, we discuss the principles of allosteric activating mutations, propagation downstream of the signals that they prompt, and allosteric drugs, with examples from the Ras signaling network. We focus on Abl kinase where mutations shift the landscape toward the active, imatinib binding-incompetent conformation, likely resulting in the high affinity ATP outcompeting drug binding. Recent pharmacological innovation extends to allosteric inhibitor (GNF-5)-linked PROTAC, targeting Bcr-Abl1 myristoylation site, and broadly, allosteric heterobifunctional degraders that destroy targets, rather than inhibiting them. Designed chemical linkers in bifunctional degraders can connect the allosteric ligand that binds the target protein and the E3 ubiquitin ligase warhead anchor. The physical properties and favored conformational state of the engineered linker can precisely coordinate the distance and orientation between the target and the recruited E3. Allosteric PROTACs, noncompetitive molecular glues, and bitopic ligands, with covalent links of allosteric ligands and orthosteric warheads, increase the effective local concentration of productively oriented and placed ligands. Through covalent chemical or peptide linkers, allosteric drugs can collaborate with competitive drugs, degrader anchors, or other molecules of choice, driving innovative drug discovery.

Comparison of the mutational profiles of neuroendocrine breast tumours, invasive ductal carcinomas and pancreatic neuroendocrine carcinomas

The pathophysiology and the optimal treatment of breast neuroendocrine tumours (NETs) are unknown. We compared the mutational profiles of breast NETs (n = 53) with those of 724 publicly available invasive ductal carcinoma (IDC) and 98 pancreatic NET (PNET) cases. The only significantly different pathogenetic or unknown variant rate between breast NETs and IDCs was detected in the TP53 (11.3% in breast NETs and 41% in IDCs, adjusted p value 0.027) and ADCK2 (9.4% in breast NETs vs. 0.28% in IDCs, adjusted p value 0.045) genes. Between breast NETs and PNETs, different pathogenetic or unknown variant frequencies were detected in 30 genes. For example, MEN1 was mutated in only 6% of breast NETs and 37% in PNETs (adjusted p value 0.00050), and GATA3 pathogenetic or unknown variants were only found in 17.0% of breast NETs and 0% in PNETs (adjusted p value 0.0010). The most commonly affected oncogenic pathways in the breast NET cases were PI3K/Akt/mTOR, NOTCH and RTK-RAS pathways. Breast NETs had typically clock-like mutational signatures and signatures associated with defective DNA mismatch repair in their mutational landscape. Our results suggest that the breast NET mutational profile more closely resembles that of IDCs than that of PNETs. These results also revealed several potentially druggable targets, such as MMRd, in breast NETs. In conclusion, breast NETs are indeed a separate breast cancer entity, but their optimal treatment remains to be elucidated.

Tracking Clonal Evolution of Multiple Myeloma Using Targeted Next-Generation DNA Sequencing

Clonal evolution drives treatment failure in multiple myeloma (MM). Here, we used a custom 372-gene panel to track genetic changes occurring during MM progression at different stages of the disease. A tumor-only targeted next-generation DNA sequencing was performed on 69 samples sequentially collected from 30 MM patients. The MAPK/ERK pathway was mostly affected with KRAS mutated in 47% of patients. Acquisition and loss of mutations were observed in 63% and 37% of patients, respectively. Four different patterns of mutation evolution were found: branching-, mutation acquisition-, mutation loss- and a stable mutational pathway. Better response to anti-myeloma therapy was more frequently observed in patients who followed the mutation loss-compared to the mutation acquisition pathway. More than two-thirds of patients had druggable genes mutated (including cases of heavily pre-treated disease). Only 7% of patients had a stable copy number variants profile. Consequently, a redistribution in stages according to R-ISS between the first and paired samples (R-ISS″) was seen. The higher the R-ISS″, the higher the risk of MM progression and death. We provided new insights into the genetics of MM evolution, especially in heavily pre-treated patients. Additionally, we confirmed that redefining R-ISS at MM relapse is of high clinical value.

Enhancing Cancer Driver Gene Prediction by Protein-Protein Interaction Network

With the advances in gene sequencing technologies, millions of somatic mutations have been reported in the past decades, but mining cancer driver genes with oncogenic mutations from these data remains a critical and challenging area of research. In this study, we proposed a network-based classification method for identifying cancer driver genes with merging the multi-biological information. In this method, we construct a cancer specific genetic network from the human protein-protein interactome (PPI) to mine the network structure attributes, and combine biological information such as mutation frequency and differential expression of genes to achieve accurate prediction of cancer driver genes. Across seven different cancer types, the proposed algorithm always achieves high prediction accuracy, which is superior to the existing advanced methods. In the analysis of the predicted results, about 40 percent of the top 10 candidate genes overlap with the Cancer Gene Census database. Interestingly, the feature comparison indicates that the network based features are still more important than the biological features, including the mutation frequency and genetic differential expression. Further analyses also show that the integration of network structure attributes and biological information is valuable for predicting new cancer driver genes.

Discovery of pan-cancer related genes via integrative network analysis

Identification of cancer-related genes is helpful for understanding the pathogenesis of cancer, developing targeted drugs and creating new diagnostic and therapeutic methods. Considering the complexity of the biological laboratory methods, many network-based methods have been proposed to identify cancer-related genes at the global perspective with the increasing availability of high-throughput data. Some studies have focused on the tissue-specific cancer networks. However, cancers from different tissues may share common features, and those methods may ignore the differences and similarities across cancers during the establishment of modeling. In this work, in order to make full use of global information of the network, we first establish the pan-cancer network via differential network algorithm, which not only contains heterogeneous data across multiple cancer types but also contains heterogeneous data between tumor samples and normal samples. Second, the node representation vectors are learned by network embedding. In contrast to ranking analysis-based methods, with the help of integrative network analysis, we transform the cancer-related gene identification problem into a binary classification problem. The final results are obtained via ensemble classification. We further applied these methods to the most commonly used gene expression data involving six tissue-specific cancer types. As a result, an integrative pan-cancer network and several biologically meaningful results were obtained. As examples, nine genes were ultimately identified as potential pan-cancer-related genes. Most of these genes have been reported in published studies, thus showing our method's potential for application in identifying driver gene candidates for further biological experimental verification.

Systematic investigation of the prognostic impact of clonal status of somatic mutations across multiple cancer types

Tumors are genetically heterogeneous and many mutations are actually present in subclonal populations. The clonal status of mutations is valuable for accurate prognosis, clinical management. The aim of this study was to identify the clonal status of somatic mutations and systematically evaluate their prognostic values across various cancer types. We totally identified 227 clonal and 432 subclonal mutations contributed to prognosis and demonstrated the importance of clonal status in improving mutation-related clinical guidance. We further developed a customized multi-step approach to identify gene-specific prognostic patterns of clonal status at pan-cancer level and found some cancer-specific prognostic patterns. The 'subclonal-dependent risk' subpattern was one of the most common subpatterns, it usually accompanied by high genomic in-stability and high extent of intra-tumor heterogeneity and could be used to improve the accuracy of prognostic analysis. Our results revealed the importance of clonal status, especially subclonal mutation in clinical survival.

High-throughput functional evaluation of human cancer-associated mutations using base editors

Comprehensive phenotypic characterization of the many mutations found in cancer tissues is one of the biggest challenges in cancer genomics. In this study, we evaluated the functional effects of 29,060 cancer-related transition mutations that result in protein variants on the survival and proliferation of non-tumorigenic lung cells using cytosine and adenine base editors and single guide RNA (sgRNA) libraries. By monitoring base editing efficiencies and outcomes using surrogate target sequences paired with sgRNA-encoding sequences on the lentiviral delivery construct, we identified sgRNAs that induced a single primary protein variant per sgRNA, enabling linking those mutations to the cellular phenotypes caused by base editing. The functions of the vast majority of the protein variants (28,458 variants, 98%) were classified as neutral or likely neutral; only 18 (0.06%) and 157 (0.5%) variants caused outgrowing and likely outgrowing phenotypes, respectively. We expect that our approach can be extended to more variants of unknown significance and other tumor types.

VIPPID: a gene-specific single nucleotide variant pathogenicity prediction tool for primary immunodeficiency diseases

Distinguishing pathogenic variants from non-pathogenic ones remains a major challenge in clinical genetic testing of primary immunodeficiency (PID) patients. Most of the existing mutation pathogenicity prediction tools treat all mutations as homogeneous entities, ignoring the differences in characteristics of different genes, and use the same model for genes in different diseases. In this study, we developed a single nucleotide variant (SNV) pathogenicity prediction tool, Variant Impact Predictor for PIDs (VIPPID; https://mylab.shinyapps.io/VIPPID/), which was tailored for PIDs genes and used a specific model for each of the most prevalent PID known genes. It employed a Conditional Inference Forest model and utilized information of 85 features of SNVs and scores from 20 existing prediction tools. Evaluation of VIPPID showed that it had superior performance (area under the curve = 0.91) over non-specific conventional tools. In addition, we also showed that the gene-specific model outperformed the non-gene-specific models. Our study demonstrated that disease-specific and gene-specific models can improve SNV pathogenicity prediction performance. This observation supports the notion that each feature of mutations in the model can be potentially used, in a new algorithm, to investigate the characteristics and function of the encoded proteins.

CancerVar: An artificial intelligence-empowered platform for clinical interpretation of somatic mutations in cancer

Several knowledgebases are manually curated to support clinical interpretations of thousands of hotspot somatic mutations in cancer. However, discrepancies or even conflicting interpretations are observed among these databases. Furthermore, many previously undocumented mutations may have clinical or functional impacts on cancer but are not systematically interpreted by existing knowledgebases. To address these challenges, we developed CancerVar to facilitate automated and standardized interpretations for 13 million somatic mutations based on the AMP/ASCO/CAP 2017 guidelines. We further introduced a deep learning framework to predict oncogenicity for these variants using both functional and clinical features. CancerVar achieved satisfactory performance when compared to several independent knowledgebases and, using clinically curated datasets, demonstrated practical utility in classifying somatic variants. In summary, by integrating clinical guidelines with a deep learning framework, CancerVar facilitates clinical interpretation of somatic variants, reduces manual work, improves consistency in variant classification, and promotes implementation of the guidelines.

Evidence for reduced BRCA2 functional activity in Homo sapiens after divergence from the chimpanzee-human last common ancestor

We performed a comparative analysis of human and 12 non-human primates to identify sequence variations in known cancer genes. We identified 395 human-specific fixed non-silent substitutions that emerged during evolution of human. Using bioinformatics analyses for functional consequences, we identified a number of substitutions that are predicted to alter protein function; one of these mutations is located at the most evolutionarily conserved domain of human BRCA2.

Genome interpretation using in silico predictors of variant impact

Estimating the effects of variants found in disease driver genes opens the door to personalized therapeutic opportunities. Clinical associations and laboratory experiments can only characterize a tiny fraction of all the available variants, leaving the majority as variants of unknown significance (VUS). In silico methods bridge this gap by providing instant estimates on a large scale, most often based on the numerous genetic differences between species. Despite concerns that these methods may lack reliability in individual subjects, their numerous practical applications over cohorts suggest they are already helpful and have a role to play in genome interpretation when used at the proper scale and context. In this review, we aim to gain insights into the training and validation of these variant effect predicting methods and illustrate representative types of experimental and clinical applications. Objective performance assessments using various datasets that are not yet published indicate the strengths and limitations of each method. These show that cautious use of in silico variant impact predictors is essential for addressing genome interpretation challenges.

Machine learning methods for prediction of cancer driver genes: a survey paper

Identifying the genes and mutations that drive the emergence of tumors is a critical step to improving our understanding of cancer and identifying new directions for disease diagnosis and treatment. Despite the large volume of genomics data, the precise detection of driver mutations and their carrying genes, known as cancer driver genes, from the millions of possible somatic mutations remains a challenge. Computational methods play an increasingly important role in discovering genomic patterns associated with cancer drivers and developing predictive models to identify these elements. Machine learning (ML), including deep learning, has been the engine behind many of these efforts and provides excellent opportunities for tackling remaining gaps in the field. Thus, this survey aims to perform a comprehensive analysis of ML-based computational approaches to identify cancer driver mutations and genes, providing an integrated, panoramic view of the broad data and algorithmic landscape within this scientific problem. We discuss how the interactions among data types and ML algorithms have been explored in previous solutions and outline current analytical limitations that deserve further attention from the scientific community. We hope that by helping readers become more familiar with significant developments in the field brought by ML, we may inspire new researchers to address open problems and advance our knowledge towards cancer driver discovery.

TP53_PROF: a machine learning model to predict impact of missense mutations in TP53

Correctly identifying the true driver mutations in a patient’s tumor is a major challenge in precision oncology. Most efforts address frequent mutations, leaving medium- and low-frequency variants mostly unaddressed. For TP53, this identification is crucial for both somatic and germline mutations, with the latter associated with the Li-Fraumeni syndrome (LFS), a multiorgan cancer predisposition. We present TP53_PROF (prediction of functionality), a gene specific machine learning model to predict the functional consequences of every possible missense mutation in TP53, integrating human cell- and yeast-based functional assays scores along with computational scores. Variants were labeled for the training set using well-defined criteria of prevalence in four cancer genomics databases. The model’s predictions provided accuracy of 96.5%. They were validated experimentally, and were compared to population data, LFS datasets, ClinVar annotations and to TCGA survival data. Very high accuracy was shown through all methods of validation. TP53_PROF allows accurate classification of TP53 missense mutations applicable for clinical practice. Our gene specific approach integrated machine learning, highly reliable features and biological knowledge, to create an unprecedented, thoroughly validated and clinically oriented classification model. This approach currently addresses TP53 mutations and will be applied in the future to other important cancer genes.

A full-proteome, interaction-specific characterization of mutational hotspots across human cancers

Rapid accumulation of cancer genomic data has led to the identification of an increasing number of mutational hotspots with uncharacterized significance. Here we present a biologically informed computational framework that characterizes the functional relevance of all 1107 published mutational hotspots identified in approximately 25,000 tumor samples across 41 cancer types in the context of a human 3D interactome network, in which the interface of each interaction is mapped at residue resolution. Hotspots reside in network hub proteins and are enriched on protein interaction interfaces, suggesting that alteration of specific protein-protein interactions is critical for the oncogenicity of many hotspot mutations. Our framework enables, for the first time, systematic identification of specific protein interactions affected by hotspot mutations at the full proteome scale. Furthermore, by constructing a hotspot-affected network that connects all hotspot-affected interactions throughout the whole-human interactome, we uncover genome-wide relationships among hotspots and implicate novel cancer proteins that do not harbor hotspot mutations themselves. Moreover, applying our network-based framework to specific cancer types identifies clinically significant hotspots that can be used for prognosis and therapy targets. Overall, we show that our framework bridges the gap between the statistical significance of mutational hotspots and their biological and clinical significance in human cancers.

Molecular-based precision oncology clinical decision making augmented by artificial intelligence

The rapid growth and decreasing cost of Next-generation sequencing (NGS) technologies have made it possible to conduct routine large panel genomic sequencing in many disease settings, especially in the oncology domain. Furthermore, it is now known that optimal disease management of patients depends on individualized cancer treatment guided by comprehensive molecular testing. However, translating results from molecular sequencing reports into actionable clinical insights remains a challenge to most clinicians. In this review, we discuss about some representative systems that leverage artificial intelligence (AI) to facilitate some processes of clinicians' decision making based upon molecular data, focusing on their application in precision oncology. Some limitations and pitfalls of the current application of AI in clinical decision making are also discussed.

Pan-cancer analysis reveals molecular patterns associated with age

Older age is a strong risk factor for several diseases, including cancer. The etiology and biology of age-associated differences among cancers are poorly understood. To address this knowledge gap, we aim to delineate differences in tumor molecular characteristics between younger and older patients across a variety of tumor types from The Cancer Genome Atlas. We show that these groups exhibit widespread molecular differences in select tumor types. Our work shows that tumors in younger individuals exhibit a dysregulated molecular aging phenotype and are associated with hallmarks of premature senescence. Additionally, we find that these tumors are enriched for driver gene mutations, resulting in homologous recombination defects. Lastly, we observe a trend toward decreased immune infiltration and function in older patients and find that, immunologically, young tumor tissue resembles aged healthy tissue. Taken together, we find that tumors from young individuals possess unique characteristics that may be leveraged for therapy.

Codependency and mutual exclusivity for gene community detection from sparse single-cell transcriptome data

Single-cell RNA-seq (scRNA-seq) can be used to characterize cellular heterogeneity in thousands of cells. The reconstruction of a gene network based on coexpression patterns is a fundamental task in scRNA-seq analyses, and the mutual exclusivity of gene expression can be critical for understanding such heterogeneity. Here, we propose an approach for detecting communities from a genetic network constructed on the basis of coexpression properties. The community-based comparison of multiple coexpression networks enables the identification of functionally related gene clusters that cannot be fully captured through differential gene expression-based analysis. We also developed a novel metric referred to as the exclusively expressed index (EEI) that identifies mutually exclusive gene pairs from sparse scRNA-seq data. EEI quantifies and ranks the exclusive expression levels of all gene pairs from binary expression patterns while maintaining robustness against a low sequencing depth. We applied our methods to glioblastoma scRNA-seq data and found that gene communities were partially conserved after serum stimulation despite a considerable number of differentially expressed genes. We also demonstrate that the identification of mutually exclusive gene sets with EEI can improve the sensitivity of capturing cellular heterogeneity. Our methods complement existing approaches and provide new biological insights, even for a large, sparse dataset, in the single-cell analysis field.

Genomic and Transcriptomic Characterization of Relapsed SCLC Through Rapid Research Autopsy

Introduction

Relapsed SCLC is characterized by therapeutic resistance and high mortality rate. Despite decades of research, mechanisms responsible for therapeutic resistance have remained elusive owing to limited tissues available for molecular studies. Thus, an unmet need remains for molecular characterization of relapsed SCLC to facilitate development of effective therapies.

Methods

We performed whole-exome and transcriptome sequencing of metastatic tumor samples procured from research autopsies of five patients with relapsed SCLC. We implemented bioinformatics tools to infer subclonal phylogeny and identify recurrent genomic alterations. We implemented immune cell signature and single-sample gene set enrichment analyses on tumor and normal transcriptome data from autopsy and additional primary and relapsed SCLC data sets. Furthermore, we evaluated T cell-inflamed gene expression profiles in neuroendocrine (ASCL1, NEUROD1) and non-neuroendocrine (YAP1, POU2F3) SCLC subtypes.

Results

Exome sequencing revealed clonal heterogeneity (intertumor and intratumor) arising from branched evolution and identified resistance-associated truncal and subclonal alterations in relapsed SCLC. Transcriptome analyses further revealed a noninflamed phenotype in neuroendocrine SCLC subtypes (ASCL1, NEUROD1) associated with decreased expression of genes involved in adaptive antitumor immunity whereas non-neuroendocrine subtypes (YAP1, POU2F3) revealed a more inflamed phenotype.

Conclusions

Our results reveal substantial tumor heterogeneity and complex clonal evolution in relapsed SCLC. Furthermore, we report that neuroendocrine SCLC subtypes are immunologically cold, thus explaining decreased responsiveness to immune checkpoint blockade. These results suggest that the mechanisms of innate and acquired therapeutic resistances are subtype-specific in SCLC and highlight the need for continued investigation to bolster therapy selection and development for this cancer.

Identification of driver genes based on gene mutational effects and network centrality

BACKGROUND

As one of the deadliest diseases in the world, cancer is driven by a few somatic mutations that disrupt the normal growth of cells, and leads to abnormal proliferation and tumor development. The vast majority of somatic mutations did not affect the occurrence and development of cancer; thus, identifying the mutations responsible for tumor occurrence and development is one of the main targets of current cancer treatments.

RESULTS

To effectively identify driver genes, we adopted a semi-local centrality measure and gene mutation effect function to assess the effect of gene mutations on changes in gene expression patterns. Firstly, we calculated the mutation score for each gene. Secondly, we identified differentially expressed genes (DEGs) in the cohort by comparing the expression profiles of tumor samples and normal samples, and then constructed a local network for each mutation gene using DEGs and mutant genes according to the protein-protein interaction network. Finally, we calculated the score of each mutant gene according to the objective function. The top-ranking mutant genes were selected as driver genes. We name the proposed method as mutations effect and network centrality.

CONCLUSIONS

Four types of cancer data in The Cancer Genome Atlas were tested. The experimental data proved that our method was superior to the existing network-centric method, as it was able to quickly and easily identify driver genes and rare driver factors.

Moving pan-cancer studies from basic research toward the clinic

Although all cancers share common hallmarks, we have long realized that there is no silver-bullet treatment for the disease. Many clinical oncologists specialize in a single cancer type, based predominantly on the tissue of origin. With advances brought by genetics and cancer genomic research, we now know that cancers are profoundly different, both in origins and in genetic alterations. At the same time, commonalities such as key driver mutations, altered pathways, mutational, immune and microbial signatures and other areas (many revealed by pan-cancer studies) point to the intriguing possibility of targeting common traits across diverse cancer types with the same therapeutic strategies. Studies designed to delineate differences and similarities across cancer types are thus critical in discerning the basic dynamics of oncogenesis, as well as informing diagnoses, prognoses and therapies. We anticipate growing emphases on the development and application of therapies targeting underlying commonalities of different cancer types, while tailoring to the unique tissue environment and intrinsic molecular fingerprints of each cancer type and subtype. Here we summarize the facets of pan-cancer research and how they are pushing progress toward personalized medicine.