Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
Ghent University（根特大学）；University of Edinburgh（爱丁堡大学）
Utku Ozbulak, Solha Kang, Jasper Zuallaert, Stephen Depuydt, Joris Vankerschaver
备注：
Accepted for publication at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Workshop on Learning Meaningful Representations of Life (LMRL)
Even though deep neural networks (DNNs) achieve state-of-the-art results for a number of problems involving genomic data, getting DNNs to explain their decision-making process has been a major challenge due to their black-box nature. One way to get DNNs to explain their reasoning for prediction is via attribution methods which are assumed to highlight the parts of the input that contribute to the prediction the most. Given the existence of numerous attribution methods and a lack of quantitative results on the fidelity of those methods, selection of an attribution method for sequence-based tasks has been mostly done qualitatively. In this work, we take a step towards identifying the most faithful attribution method by proposing a computational approach that utilizes point mutations. Providing quantitative results on seven popular attribution methods, we find Layerwise Relevance Propagation (LRP) to be the most appropriate one for translation initiation, with LRP identifying two important biological features for translation: the integrity of Kozak sequence as well as the detrimental effects of premature stop codons.
DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome
Stony Brook University（石溪大学）；Renaissance School of Medicine, Stony Brook University（石溪大学文艺复兴医学院）；Northwestern University Feinberg School of Medicine（西北大学范伯格医学院）；Northwestern University（西北大学）
Guangdong Key Laboratory of Brain-Inspired Intelligent Computation（广东省脑启发智能计算重点实验室）；Southern University of Science and Technology（南方科技大学）；Research Institute of Trust-worthy Autonomous Systems（可信自主系统研究所）；School of Computer Science, University of Birmingham（伯明翰大学计算机科学学院）
Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powerful tools in other research fields, e.g., drug discovery and genomics. In this survey, we conduct a comprehensive review of the neural network interpretability research. We first clarify the definition of interpretability as it has been used in many…
The Kolmogorov-Arnold stochasticity parameter technique is applied for the first time to the study of cancer genome sequencing, to reveal mutations. Using data generated by next generation sequencing technologies, we have analyzed the exome sequences of brain tumor patients with matched tumor and normal blood. We show that mutations contained in sequencing data can be revealed using this technique thus providing a new methodology for determining subsequences of given length containing mutations i.e. its value differs from those of subsequences without mutations. A potential application for thi…
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Broad Institute of Harvard and MIT（哈佛-麻省理工学院博德研究所）；Dana-Farber Cancer Institute（丹娜-法伯癌症研究所）；Harvard University（哈佛大学）
The rapidly emerging field of deep learning-based computational pathology has demonstrated promise in developing objective prognostic models from histology whole slide images. However, most prognostic models are either based on histology or genomics alone and do not address how histology and genomics can be integrated to develop joint image-omic prognostic models. Additionally identifying explainable morphological and molecular descriptors from these models that govern such prognosis is of interest. We used multimodal deep learning to integrate gigapixel whole slide pathology images, RNA-seq a…
Cambridge Cancer Genomics（剑桥癌症基因组学公司）；The University of Edinburgh（爱丁堡大学）
Identifying the mutations that drive cancer growth is key in clinical decision making and precision oncology. As driver mutations confer selective advantage and thus have an increased likelihood of occurrence, frequency-based statistical models are currently favoured. These methods are not suited to rare, low frequency, driver mutations. The alternative approach to address this is through functional-impact scores, however methods using this approach are highly prone to false positives. In this paper, we propose a novel combination method for driver mutation identification, which uses the power…
In recent years, cancer genome sequencing and other high-throughput studies of cancer genomes have generated many notable discoveries. In this review, Novel genomic alteration mechanisms, such as chromothripsis (chromosomal crisis) and kataegis (mutation storms), and their implications for cancer are discussed. Genomic alterations spur cancer genome evolution. Thus, the relationship between cancer clonal evolution and cancer stems cells is commented. The key question in cancer biology concerns how these genomic alterations support cancer development and metastasis in the context of biological …
It is generally difficult to predict the positions of mutations in genomic DNA at the nucleotide level. Retroviral DNA insertion is one mode of mutation, resulting in host infections that are difficult to treat. This mutation process involves the integration of retroviral DNA into the host-infected cellular genomic DNA following the interaction between host DNA and a pre-integration complex consisting of retroviral DNA and integrase. Here, we report that retroviral insertion sites around a hotspot within the Zfp521 and N-myc genes can be predicted by a periodic function that is deduced using t…
Cancers evolve from mutation of a single cell with sequential clonal and subclonal expansion of somatic mutation acquisition. Inferring clonal and subclonal structures from bulk or single cell tumor genomic sequencing data has a huge impact on cancer evolution studies. Clonal state and mutational order can provide detailed insight into tumor origin and its future development. In the past decade, a variety of methods have been developed for subclonal reconstruction using bulk tumor sequencing data. As these methods have been developed in different programming languages and using different input…
Explainable convolutional neural network model provides an alternative genome-wide association perspective on mutations in SARS-CoV-2
University of Tennessee at Chattanooga（田纳西大学查塔努加分校）；North Carolina Agricultural and Technical State University（北卡罗来纳农工州立大学）；Shenandoah University（谢南多厄大学）；Catholic University of America（美国天主教大学）；Old Dominion University（奥多明尼昂大学）
The phenotypic consequences of individual mutations are modulated by the wild type genetic background in which they occur.Although such background dependence is widely observed, we do not know whether general patterns across species and traits exist, nor about the mechanisms underlying it. We also lack knowledge on how mutations interact with genetic background to influence gene expression, and how this in turn mediates mutant phenotypes. Furthermore, how genetic background influences patterns of epistasis remains unclear. To investigate the genetic basis and genomic consequences of genetic ba…
The Z_64-algebra of the genetic code and DNA sequences of length N was recently stated. In order to beat the limits of this structure such as the impossibility of non-coding region analysis in genomes and the impossibility of the insertions and deletions analysis (indel mutations), we have develop a cycle group structure over the of extended base triplets of DNA X_1X_2X_3, X_i belong to {O, A, C, G, U}, where the letter O denote the base omission (deletion) in the codon. The obtained group is isomorphic to the abelian 5-group Z_125 of integer module 125. Next, it is defined the abelian finite …
Universidade Federal do Rio Grande do Sul（南里奥格兰德联邦大学）；Hospital de Clínicas de Porto Alegre（阿雷格里港临床医院）
Identifying the genes and mutations that drive the emergence of tumors is a major step to improve understanding of cancer and identify 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 identifying genomic patterns associated with cancer drivers and developing models to predict driver events. Machine learning (ML) has been the…
Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models
Center for Foundation Models；Generative AI \& Department of Computer Science, Northwestern University, USA；School of Natural Sciences, University of California at Merced, USA；Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory, USA；Systems Biology Division, Lawrence Berkeley National Laboratory, USA；Department of Statistics；Data Science, Northwestern University, USA
Recent breakthroughs in cancer research have come via the up-and-coming field of pathway analysis. By applying statistical methods to prior known gene and protein regulatory information, pathway analysis provides a meaningful way to interpret genomic data. While many gene/protein regulatory relationships have been studied, never before has such a significant amount data been made available in organized forms of gene/protein regulatory networks and pathways. However, pathway analysis research is still in its infancy, especially when applying it to solve practical problems. In this paper we prop…
Cambridge Cancer Genomics（剑桥癌症基因组学公司）；The University of Cambridge（剑桥大学）
The genomic profile underlying an individual tumor can be highly informative in the creation of a personalized cancer treatment strategy for a given patient; a practice known as precision oncology. This involves next generation sequencing of a tumor sample and the subsequent identification of genomic aberrations, such as somatic mutations, to provide potential candidates of targeted therapy. The identification of these aberrations from sequencing noise and germline variant background poses a classic classification-style problem. This has been previously broached with many different supervised …
Greehey Children’s Cancer Research Institute, University of Texas Health Science Center at San Antonio（德克萨斯大学圣安东尼奥健康科学中心格里希儿童癌症研究所）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Northwestern Polytechnical University（西北工业大学）；Department of Epidemiology and Biostatistics, University of Texas Health Science Center at San Antonio（德克萨斯大学圣安东尼奥健康科学中心流行病学与生物统计学系）
The study of high-throughput genomic profiles from a pharmacogenomics viewpoint has provided unprecedented insights into the oncogenic features modulating drug response. A recent screening of ~1,000 cancer cell lines to a collection of anti-cancer drugs illuminated the link between genotypes and vulnerability. However, due to essential differences between cell lines and tumors, the translation into predicting drug response in tumors remains challenging. Here we proposed a DNN model to predict drug response based on mutation and expression profiles of a cancer cell or a tumor. The model contain…
The study of genomic variation has provided key insights into the functional role of mutations. Predominantly, studies have focused on single nucleotide variants (SNV), which are relatively easy to detect and can be described with rich mathematical models. However, it has been observed that genomes are highly plastic, and that whole regions can be moved, removed or duplicated in bulk. These structural variants (SV) have been shown to have significant impact on the phenotype, but their study has been held back by the combinatorial complexity of the underlying models. We describe here a general …
Hepatocellular carcinoma (HCC) is the most common primary liver malignancy and is a leading cause of cancer-related death worldwide. However, cure is not possible with currently used therapies, and there is not so much approved targeted therapy for HCC despite numerous attempts and clinical trials. So, it is essential to identify additional therapeutic strategies to block the growth of HCC tumors. As a cancer disease, it is associated with aberrant genomic and transcriptional landscapes. We sought to use a systematic drug repositioning bioinformatics approach to identify novel candidate drugs …
Cancer-inspired Genomics Mapper Model for the Generation of Synthetic DNA Sequences with Desired Genomics Signatures
School of Mechanical Engineering, Tel Aviv University（特拉维夫大学机械工程学院）；Department of Cancer Biology, Cancer Institute, University College London（伦敦大学学院癌症研究所癌症生物学系）
Motivation: We introduce TRONCO (TRanslational ONCOlogy), an open-source R package that implements the state-of-the-art algorithms for the inference of cancer progression models from (epi)genomic mutational profiles. TRONCO can be used to extract population-level models describing the trends of accumulation of alterations in a cohort of cross-sectional samples, e.g., retrieved from publicly available databases, and individual-level models that reveal the clonal evolutionary history in single cancer patients, when multiple samples, e.g., multiple biopsies or single-cell sequencing data, are ava…
The pathogenesis of cancer in human is still poorly understood. With the rapid development of high-throughput sequencing technologies, huge volumes of cancer genomics data have been generated. Deciphering those data poses great opportunities and challenges to computational biologists. One of such key challenges is to distinguish driver mutations, genes as well as pathways from passenger ones. Mutual exclusivity of gene mutations (each patient has no more than one mutation in the gene set) has been observed in various cancer types and thus has been used as an important property of a driver gene…
Determining the primary site of origin for metastatic tumors is one of the open problems in cancer care because the efficacy of treatment often depends on the cancer tissue of origin. Classification methods that can leverage tumor genomic data and predict the site of origin are therefore of great value. Because tumor DNA point mutation data is very sparse, only limited accuracy (64.5% for 12 tumor classes) was previously demonstrated by methods that rely on point mutations as features (1). Tumor classification accuracy can be greatly improved (to over 90% for 33 classes) by relying on gene exp…
Phenotypic divergence of Homo sapiens is driven by the evolution of human-specific genomic regulatory networks via two mechanistically distinct pathways of creation of divergent regulatory DNA sequences
Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局资讯通信研究院）；National University of Singapore（新加坡国立大学）；Singapore General Hospital（新加坡中央医院）；National Cancer Centre（新加坡国立癌症中心）
Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and the fourth most common cause of cancer-related death worldwide. Understanding the underlying gene mutations in HCC provides great prognostic value for treatment planning and targeted therapy. Radiogenomics has revealed an association between non-invasive imaging features and molecular genomics. However, imaging feature identification is laborious and error-prone. In this paper, we propose an end-to-end deep learning framework for mutation prediction in APOB, COL11A1 and ATRX genes using multiphasic CT scans. Con…
Broad Institute of Harvard and MIT（哈佛大学与麻省理工学院博德研究所）；Dana-Farber Cancer Institute（丹娜法伯癌症研究院）；Department of Biomedical Informatics, Harvard Medical School（哈佛医学院生物医学信息学系）
Cancer diagnosis, prognosis, and therapeutic response predictions are based on morphological information from histology slides and molecular profiles from genomic data. However, most deep learning-based objective outcome prediction and grading paradigms are based on histology or genomics alone and do not make use of the complementary information in an intuitive manner. In this work, we propose Pathomic Fusion, an interpretable strategy for end-to-end multimodal fusion of histology image and genomic (mutations, CNV, RNA-Seq) features for survival outcome prediction. Our approach models pairwise…
Background: Many genome-wide association studies have detected genomic regions associated with traits, yet understanding the functional causes of association often remains elusive. Utilizing systems approaches and focusing on intermediate molecular phenotypes might facilitate biologic understanding. Results: The availability of exome sequencing of two populations of African-Americans and European-Americans from the Atherosclerosis Risk in Communities study allowed us to investigate the effects of annotated loss-of-function (LoF) mutations on 122 serum metabolites. To assess the findings, we bu…
