1
|
Gschwind AR, Mualim KS, Karbalayghareh A, Sheth MU, Dey KK, Jagoda E, Nurtdinov RN, Xi W, Tan AS, Jones H, Ma XR, Yao D, Nasser J, Avsec Ž, James BT, Shamim MS, Durand NC, Rao SSP, Mahajan R, Doughty BR, Andreeva K, Ulirsch JC, Fan K, Perez EM, Nguyen TC, Kelley DR, Finucane HK, Moore JE, Weng Z, Kellis M, Bassik MC, Price AL, Beer MA, Guigó R, Stamatoyannopoulos JA, Lieberman Aiden E, Greenleaf WJ, Leslie CS, Steinmetz LM, Kundaje A, Engreitz JM. An encyclopedia of enhancer-gene regulatory interactions in the human genome. bioRxiv 2023:2023.11.09.563812. [PMID: 38014075 PMCID: PMC10680627 DOI: 10.1101/2023.11.09.563812] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/29/2023]
Abstract
Identifying transcriptional enhancers and their target genes is essential for understanding gene regulation and the impact of human genetic variation on disease1-6. Here we create and evaluate a resource of >13 million enhancer-gene regulatory interactions across 352 cell types and tissues, by integrating predictive models, measurements of chromatin state and 3D contacts, and largescale genetic perturbations generated by the ENCODE Consortium7. We first create a systematic benchmarking pipeline to compare predictive models, assembling a dataset of 10,411 elementgene pairs measured in CRISPR perturbation experiments, >30,000 fine-mapped eQTLs, and 569 fine-mapped GWAS variants linked to a likely causal gene. Using this framework, we develop a new predictive model, ENCODE-rE2G, that achieves state-of-the-art performance across multiple prediction tasks, demonstrating a strategy involving iterative perturbations and supervised machine learning to build increasingly accurate predictive models of enhancer regulation. Using the ENCODE-rE2G model, we build an encyclopedia of enhancer-gene regulatory interactions in the human genome, which reveals global properties of enhancer networks, identifies differences in the functions of genes that have more or less complex regulatory landscapes, and improves analyses to link noncoding variants to target genes and cell types for common, complex diseases. By interpreting the model, we find evidence that, beyond enhancer activity and 3D enhancer-promoter contacts, additional features guide enhancerpromoter communication including promoter class and enhancer-enhancer synergy. Altogether, these genome-wide maps of enhancer-gene regulatory interactions, benchmarking software, predictive models, and insights about enhancer function provide a valuable resource for future studies of gene regulation and human genetics.
Collapse
Affiliation(s)
- Andreas R. Gschwind
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
| | - Kristy S. Mualim
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Department of Plant Biology, Carnegie Institute of Science, Stanford, CA, USA
| | - Alireza Karbalayghareh
- Computational and Systems Biology Program, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Maya U. Sheth
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
- Department of Bioengineering, Stanford University, Stanford, CA, USA
| | - Kushal K. Dey
- Computational and Systems Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, NY, USA
- Department of Epidemiology, Harvard T. H. Chan School of Public Health, Boston, MA, USA
| | - Evelyn Jagoda
- The Novo Nordisk Foundation Center for Genomic Mechanisms of Disease, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Gene Regulation Observatory, Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Ramil N. Nurtdinov
- Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
| | - Wang Xi
- Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- McKusick-Nathans Department of Genetic Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Anthony S. Tan
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
| | - Hank Jones
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
| | - X. Rosa Ma
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
| | - David Yao
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Joseph Nasser
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Present Address: Department of Systems Biology, Harvard Medical School, Boston, MA, USA
| | | | - Benjamin T. James
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Muhammad S. Shamim
- The Center for Genome Architecture, Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, USA
- Center for Theoretical Biological Physics, Rice University, Houston, TX, USA
- Department of Bioengineering, Rice University, Houston, TX, USA
- Medical Scientist Training Program, Baylor College of Medicine, Houston, Texas, USA
| | - Neva C. Durand
- Gene Regulation Observatory, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- The Center for Genome Architecture, Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, USA
- Center for Theoretical Biological Physics, Rice University, Houston, TX, USA
- Department of Computer Science, Rice University, Houston, TX, USA
| | - Suhas S. P. Rao
- The Center for Genome Architecture, Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, USA
- Department of Medicine, University of California San Francisco, San Francisco, CA, USA
- Department of Structural Biology, Stanford University, Stanford, CA, USA
| | - Ragini Mahajan
- The Center for Genome Architecture, Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, USA
- Center for Theoretical Biological Physics, Rice University, Houston, TX, USA
- Department of Biosciences, Rice University, Houston, TX, USA
| | - Benjamin R. Doughty
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Kalina Andreeva
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Jacob C. Ulirsch
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Present Address: Artificial Intelligence Laboratory, Illumina, Inc., San Diego, CA, USA
| | - Kaili Fan
- Program in Bioinformatics and Integrative Biology, University of Massachusetts Chan Medical School, Worcester, MA, USA
- Present Address: Department of Stem Cell and Regenerative Biology, Harvard University, Cambridge, MA, USA
| | | | - Tri C. Nguyen
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
| | | | - Hilary K. Finucane
- Department of Medicine, Massachusetts General Hospital, Boston, MA, USA
- Analytic and Translational Genetics Unit, Massachusetts General Hospital, Boston, MA, USA
- Stanley Center for Psychiatric Research, Broad Institute of MIT and Harvard, Cambridge, MA, USA
| | - Jill E. Moore
- Program in Bioinformatics and Integrative Biology, University of Massachusetts Chan Medical School, Worcester, MA, USA
| | - Zhiping Weng
- Program in Bioinformatics and Integrative Biology, University of Massachusetts Chan Medical School, Worcester, MA, USA
| | - Manolis Kellis
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Michael C. Bassik
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Alkes L. Price
- Department of Epidemiology, Harvard T. H. Chan School of Public Health, Boston, MA, USA
| | - Michael A. Beer
- Department of Biomedical Engineering, Johns Hopkins University School of Medicine, Baltimore, MD, USA
- McKusick-Nathans Department of Genetic Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Roderic Guigó
- Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Catalonia, Spain
| | - John A. Stamatoyannopoulos
- Altius Institute for Biomedical Sciences, Seattle, WA, USA
- Clinical Research Division, Fred Hutch Cancer Center, Seattle, WA, USA
| | - Erez Lieberman Aiden
- Broad Institute of MIT and Harvard, Cambridge, MA, USA
- The Center for Genome Architecture, Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, USA
- Center for Theoretical Biological Physics, Rice University, Houston, TX, USA
- Department of Computer Science, Rice University, Houston, TX, USA
| | - William J. Greenleaf
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Department of Applied Physics, Stanford University, Stanford, CA, USA
| | | | - Lars M. Steinmetz
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Stanford Genome Technology Center, Palo Alto, CA, USA
- European Molecular Biology Laboratory (EMBL), Genome Biology Unit, Heidelberg, Germany
| | - Anshul Kundaje
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Jesse M. Engreitz
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
- Basic Sciences and Engineering Initiative, Betty Irene Moore Children’s Heart Center, Lucile Packard Children’s Hospital, Stanford, CA, USA
- The Novo Nordisk Foundation Center for Genomic Mechanisms of Disease, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Gene Regulation Observatory, Broad Institute of MIT and Harvard, Cambridge, MA, USA
- Stanford Cardiovascular Institute, Stanford University, Stanford, CA, USA
| |
Collapse
|
2
|
Cheng J, Novati G, Pan J, Bycroft C, Žemgulytė A, Applebaum T, Pritzel A, Wong LH, Zielinski M, Sargeant T, Schneider RG, Senior AW, Jumper J, Hassabis D, Kohli P, Avsec Ž. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science 2023; 381:eadg7492. [PMID: 37733863 DOI: 10.1126/science.adg7492] [Citation(s) in RCA: 128] [Impact Index Per Article: 128.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2023] [Accepted: 08/23/2023] [Indexed: 09/23/2023]
Abstract
The vast majority of missense variants observed in the human genome are of unknown clinical significance. We present AlphaMissense, an adaptation of AlphaFold fine-tuned on human and primate variant population frequency databases to predict missense variant pathogenicity. By combining structural context and evolutionary conservation, our model achieves state-of-the-art results across a wide range of genetic and experimental benchmarks, all without explicitly training on such data. The average pathogenicity score of genes is also predictive for their cell essentiality, capable of identifying short essential genes that existing statistical approaches are underpowered to detect. As a resource to the community, we provide a database of predictions for all possible human single amino acid substitutions and classify 89% of missense variants as either likely benign or likely pathogenic.
Collapse
|
3
|
Lotfollahi M, Naghipourfar M, Luecken MD, Khajavi M, Büttner M, Wagenstetter M, Avsec Ž, Gayoso A, Yosef N, Interlandi M, Rybakov S, Misharin AV, Theis FJ. Mapping single-cell data to reference atlases by transfer learning. Nat Biotechnol 2022; 40:121-130. [PMID: 34462589 PMCID: PMC8763644 DOI: 10.1038/s41587-021-01001-7] [Citation(s) in RCA: 151] [Impact Index Per Article: 75.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2020] [Accepted: 06/28/2021] [Indexed: 02/07/2023]
Abstract
Large single-cell atlases are now routinely generated to serve as references for analysis of smaller-scale studies. Yet learning from reference data is complicated by batch effects between datasets, limited availability of computational resources and sharing restrictions on raw data. Here we introduce a deep learning strategy for mapping query datasets on top of a reference called single-cell architectural surgery (scArches). scArches uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building and contextualization of new datasets with existing references without sharing raw data. Using examples from mouse brain, pancreas, immune and whole-organism atlases, we show that scArches preserves biological state information while removing batch effects, despite using four orders of magnitude fewer parameters than de novo integration. scArches generalizes to multimodal reference mapping, allowing imputation of missing modalities. Finally, scArches retains coronavirus disease 2019 (COVID-19) disease variation when mapping to a healthy reference, enabling the discovery of disease-specific cell states. scArches will facilitate collaborative projects by enabling iterative construction, updating, sharing and efficient use of reference atlases.
Collapse
Affiliation(s)
- Mohammad Lotfollahi
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
- School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany
| | - Mohsen Naghipourfar
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
| | - Malte D Luecken
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
| | - Matin Khajavi
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
| | - Maren Büttner
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
| | - Marco Wagenstetter
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
| | - Žiga Avsec
- Department of Computer Science, Technical University of Munich, Munich, Germany
| | - Adam Gayoso
- Center for Computational Biology, University of California, Berkeley, Berkeley, CA, USA
| | - Nir Yosef
- Center for Computational Biology, University of California, Berkeley, Berkeley, CA, USA
- Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA
- Chan Zuckerberg Biohub, San Francisco, CA, USA
- Ragon Institute of MGH, MIT and Harvard, Cambridge, MA, USA
| | - Marta Interlandi
- Institute of Medical Informatics, University of Münster, Münster, Germany
| | - Sergei Rybakov
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany
- Department of Mathematics, Technical University of Munich, Munich, Germany
| | - Alexander V Misharin
- Division of Pulmonary and Critical Care Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA
| | - Fabian J Theis
- Helmholtz Center Munich-German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany.
- School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany.
- Department of Mathematics, Technical University of Munich, Munich, Germany.
| |
Collapse
|
4
|
Avsec Ž, Agarwal V, Visentin D, Ledsam JR, Grabska-Barwinska A, Taylor KR, Assael Y, Jumper J, Kohli P, Kelley DR. Effective gene expression prediction from sequence by integrating long-range interactions. Nat Methods 2021; 18:1196-1203. [PMID: 34608324 PMCID: PMC8490152 DOI: 10.1038/s41592-021-01252-x] [Citation(s) in RCA: 241] [Impact Index Per Article: 80.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Accepted: 07/27/2021] [Indexed: 02/08/2023]
Abstract
How noncoding DNA determines gene expression in different cell types is a major unsolved problem, and critical downstream applications in human genetics depend on improved solutions. Here, we report substantially improved gene expression prediction accuracy from DNA sequences through the use of a deep learning architecture, called Enformer, that is able to integrate information from long-range interactions (up to 100 kb away) in the genome. This improvement yielded more accurate variant effect predictions on gene expression for both natural genetic variants and saturation mutagenesis measured by massively parallel reporter assays. Furthermore, Enformer learned to predict enhancer-promoter interactions directly from the DNA sequence competitively with methods that take direct experimental data as input. We expect that these advances will enable more effective fine-mapping of human disease associations and provide a framework to interpret cis-regulatory evolution.
Collapse
|
5
|
Karollus A, Avsec Ž, Gagneur J. Predicting mean ribosome load for 5'UTR of any length using deep learning. PLoS Comput Biol 2021; 17:e1008982. [PMID: 33970899 PMCID: PMC8136849 DOI: 10.1371/journal.pcbi.1008982] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2020] [Revised: 05/20/2021] [Accepted: 04/19/2021] [Indexed: 01/07/2023] Open
Abstract
The 5’ untranslated region plays a key role in regulating mRNA translation and consequently protein abundance. Therefore, accurate modeling of 5’UTR regulatory sequences shall provide insights into translational control mechanisms and help interpret genetic variants. Recently, a model was trained on a massively parallel reporter assay to predict mean ribosome load (MRL)—a proxy for translation rate—directly from 5’UTR sequence with a high degree of accuracy. However, this model is restricted to sequence lengths investigated in the reporter assay and therefore cannot be applied to the majority of human sequences without a substantial loss of information. Here, we introduced frame pooling, a novel neural network operation that enabled the development of an MRL prediction model for 5’UTRs of any length. Our model shows state-of-the-art performance on fixed length randomized sequences, while offering better generalization performance on longer sequences and on a variety of translation-related genome-wide datasets. Variant interpretation is demonstrated on a 5’UTR variant of the gene HBB associated with beta-thalassemia. Frame pooling could find applications in other bioinformatics predictive tasks. Moreover, our model, released open source, could help pinpoint pathogenic genetic variants. The human genome carries a complex code. It consists of genes, which provide blueprints to assemble proteins, and regulatory elements, which control when, where, and how often particular genes are transcribed and translated into protein. To read the genome correctly and specifically to find the causes of inherited diseases, we need to be able to find and interpret these regulatory elements. Here, we focus on particular regions of the genome, the so-called 5’ untranslated regions, which play an important role in determining how often a transcribed gene is translated into protein. We develop deep learning models which can quantitatively interpret regulatory elements in human 5’ untranslated regions and use this information to predict a proxy of the translation efficiency. Our model generalizes a previous model to 5’ untranslated regions of any length, just as they are encountered in natural human genes. Because this model requires only the sequence as input, it can give estimates for the impact of mutations in the sequence, even if these particular mutations are very rare or entirely novel. Such estimates could help pinpoint mutations that disrupt the normal functioning of gene regulation, which could be used to better diagnose patients suffering from rare genetic disorders.
Collapse
Affiliation(s)
- Alexander Karollus
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, Munich, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany
- Institute of Human Genetics, Technical University of Munich, Munich, Germany
- Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany
- * E-mail:
| |
Collapse
|
6
|
Avsec Ž, Weilert M, Shrikumar A, Krueger S, Alexandari A, Dalal K, Fropf R, McAnany C, Gagneur J, Kundaje A, Zeitlinger J. Base-resolution models of transcription-factor binding reveal soft motif syntax. Nat Genet 2021; 53:354-366. [PMID: 33603233 PMCID: PMC8812996 DOI: 10.1038/s41588-021-00782-6] [Citation(s) in RCA: 203] [Impact Index Per Article: 67.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2020] [Accepted: 01/07/2021] [Indexed: 01/30/2023]
Abstract
The arrangement (syntax) of transcription factor (TF) binding motifs is an important part of the cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that uses DNA sequence to predict base-resolution chromatin immunoprecipitation (ChIP)-nexus binding profiles of pluripotency TFs. We develop interpretation tools to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions. Strikingly, Nanog preferentially binds with helical periodicity, and TFs often cooperate in a directional manner, which we validate using clustered regularly interspaced short palindromic repeat (CRISPR)-induced point mutations. Our model represents a powerful general approach to uncover the motifs and syntax of cis-regulatory sequences in genomics data.
Collapse
Affiliation(s)
- Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany,Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, Munich, Germany,Currently at DeepMind, London, UK
| | - Melanie Weilert
- Stowers Institute for Medical Research, Kansas City, MO, USA
| | - Avanti Shrikumar
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Sabrina Krueger
- Stowers Institute for Medical Research, Kansas City, MO, USA
| | - Amr Alexandari
- Department of Computer Science, Stanford University, Stanford, CA, USA
| | - Khyati Dalal
- Stowers Institute for Medical Research, Kansas City, MO, USA,The University of Kansas Medical Center, Kansas City, KS, USA
| | - Robin Fropf
- Stowers Institute for Medical Research, Kansas City, MO, USA
| | - Charles McAnany
- Stowers Institute for Medical Research, Kansas City, MO, USA
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Anshul Kundaje
- Department of Computer Science, Stanford University, Stanford, CA, USA,Department of Genetics, Stanford University, Stanford, CA, USA,correspondence: ,
| | - Julia Zeitlinger
- Stowers Institute for Medical Research, Kansas City, MO, USA,The University of Kansas Medical Center, Kansas City, KS, USA,correspondence: ,
| |
Collapse
|
7
|
Mount SM, Avsec Ž, Carmel L, Casadio R, Çelik MH, Chen K, Cheng J, Cohen NE, Fairbrother WG, Fenesh T, Gagneur J, Gotea V, Holzer T, Lin CF, Martelli PL, Naito T, Nguyen TYD, Savojardo C, Unger R, Wang R, Yang Y, Zhao H. Assessing predictions of the impact of variants on splicing in CAGI5. Hum Mutat 2019; 40:1215-1224. [PMID: 31301154 DOI: 10.1002/humu.23869] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2019] [Revised: 06/20/2019] [Accepted: 07/10/2019] [Indexed: 12/28/2022]
Abstract
Precision medicine and sequence-based clinical diagnostics seek to predict disease risk or to identify causative variants from sequencing data. The Critical Assessment of Genome Interpretation (CAGI) is a community experiment consisting of genotype-phenotype prediction challenges; participants build models, undergo assessment, and share key findings. In the past, few CAGI challenges have addressed the impact of sequence variants on splicing. In CAGI5, two challenges (Vex-seq and MaPSY) involved prediction of the effect of variants, primarily single-nucleotide changes, on splicing. Although there are significant differences between these two challenges, both involved prediction of results from high-throughput exon inclusion assays. Here, we discuss the methods used to predict the impact of these variants on splicing, their performance, strengths, and weaknesses, and prospects for predicting the impact of sequence variation on splicing and disease phenotypes.
Collapse
Affiliation(s)
- Stephen M Mount
- Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Maryland
| | - Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Liran Carmel
- Department of Genetics, The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem, Jerusalem, Israel
| | - Rita Casadio
- Department of Pharmacy and Biotechnology, Biocomputing Group, University of Bologna, Bologna, Italy
| | | | - Ken Chen
- School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China
| | - Jun Cheng
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Noa E Cohen
- Department of Genetics, The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem, Jerusalem, Israel.,The integrated program for Computer Science and Computational Biology, School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel
| | - William G Fairbrother
- Department of Molecular Biology, Cell Biology, and Biochemistry, Center For Computational Biology, Brown University, Providence, Rhode Island
| | - Tzila Fenesh
- The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Valer Gotea
- National Human Genome Research Institute (NHGRI), National Institutes of Health (NIH), Bethesda, Maryland
| | - Tamar Holzer
- The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel
| | - Chiao-Feng Lin
- Translational Informatics, DNAnexus, Mountain View, California
| | - Pier Luigi Martelli
- Department of Pharmacy and Biotechnology, Biocomputing Group, University of Bologna, Bologna, Italy
| | - Tatsuhiko Naito
- Department of Neurology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | | | - Castrense Savojardo
- Department of Pharmacy and Biotechnology, Biocomputing Group, University of Bologna, Bologna, Italy
| | - Ron Unger
- The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel
| | - Robert Wang
- Department of Bioengineering, University of California, Berkeley, California.,Department of Plant and Molecular Biology, University of California, Berkeley, California
| | - Yuedong Yang
- School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China
| | - Huiying Zhao
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
8
|
Cheng J, Çelik MH, Nguyen TYD, Avsec Ž, Gagneur J. CAGI 5 splicing challenge: Improved exon skipping and intron retention predictions with MMSplice. Hum Mutat 2019; 40:1243-1251. [PMID: 31070280 DOI: 10.1002/humu.23788] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2019] [Revised: 04/17/2019] [Accepted: 05/06/2019] [Indexed: 11/10/2022]
Abstract
Pathogenic genetic variants often primarily affect splicing. However, it remains difficult to quantitatively predict whether and how genetic variants affect splicing. In 2018, the fifth edition of the Critical Assessment of Genome Interpretation proposed two splicing prediction challenges based on experimental perturbation assays: Vex-seq, assessing exon skipping, and MaPSy, assessing splicing efficiency. We developed a modular modeling framework, MMSplice, the performance of which was among the best on both challenges. Here we provide insights into the modeling assumptions of MMSplice and its individual modules. We furthermore illustrate how MMSplice can be applied in practice for individual genome interpretation, using the MMSplice VEP plugin and the Kipoi variant interpretation plugin, which are directly applicable to VCF files.
Collapse
Affiliation(s)
- Jun Cheng
- Department of Informatics, Technical University of Munich, Garching, Germany.,Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, Munich, Germany
| | | | | | - Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany.,Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, Munich, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany.,Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, Munich, Germany
| |
Collapse
|
9
|
Abstract
As a data-driven science, genomics largely utilizes machine learning to capture dependencies in data and derive novel biological hypotheses. However, the ability to extract new insights from the exponentially increasing volume of genomics data requires more expressive machine learning models. By effectively leveraging large data sets, deep learning has transformed fields such as computer vision and natural language processing. Now, it is becoming the method of choice for many genomics modelling tasks, including predicting the impact of genetic variation on gene regulatory mechanisms such as DNA accessibility and splicing.
Collapse
Affiliation(s)
- Gökcen Eraslan
- Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.,School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany
| | - Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany.
| | - Fabian J Theis
- Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany. .,School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany. .,Department of Mathematics, Technical University of Munich, Garching, Germany.
| |
Collapse
|
10
|
Brechtmann F, Mertes C, Matusevičiūtė A, Yépez VA, Avsec Ž, Herzog M, Bader DM, Prokisch H, Gagneur J. OUTRIDER: A Statistical Method for Detecting Aberrantly Expressed Genes in RNA Sequencing Data. Am J Hum Genet 2018; 103:907-917. [PMID: 30503520 PMCID: PMC6288422 DOI: 10.1016/j.ajhg.2018.10.025] [Citation(s) in RCA: 76] [Impact Index Per Article: 12.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2018] [Accepted: 10/25/2018] [Indexed: 11/16/2022] Open
Abstract
RNA sequencing (RNA-seq) is gaining popularity as a complementary assay to genome sequencing for precisely identifying the molecular causes of rare disorders. A powerful approach is to identify aberrant gene expression levels as potential pathogenic events. However, existing methods for detecting aberrant read counts in RNA-seq data either lack assessments of statistical significance, so that establishing cutoffs is arbitrary, or rely on subjective manual corrections for confounders. Here, we describe OUTRIDER (Outlier in RNA-Seq Finder), an algorithm developed to address these issues. The algorithm uses an autoencoder to model read-count expectations according to the gene covariation resulting from technical, environmental, or common genetic variations. Given these expectations, the RNA-seq read counts are assumed to follow a negative binomial distribution with a gene-specific dispersion. Outliers are then identified as read counts that significantly deviate from this distribution. The model is automatically fitted to achieve the best recall of artificially corrupted data. Precision-recall analyses using simulated outlier read counts demonstrated the importance of controlling for covariation and significance-based thresholds. OUTRIDER is open source and includes functions for filtering out genes not expressed in a dataset, for identifying outlier samples with too many aberrantly expressed genes, and for detecting aberrant gene expression on the basis of false-discovery-rate-adjusted p values. Overall, OUTRIDER provides an end-to-end solution for identifying aberrantly expressed genes and is suitable for use by rare-disease diagnostic platforms.
Collapse
Affiliation(s)
- Felix Brechtmann
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
| | - Christian Mertes
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
| | - Agnė Matusevičiūtė
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
| | - Vicente A Yépez
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany; Quantitative Biosciences Munich, Gene Center, Department of Biochemistry, Ludwig-Maximilians Universität München, Feodor-Lynen-Str. 25, 81377 München, Germany
| | - Žiga Avsec
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany; Quantitative Biosciences Munich, Gene Center, Department of Biochemistry, Ludwig-Maximilians Universität München, Feodor-Lynen-Str. 25, 81377 München, Germany
| | - Maximilian Herzog
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
| | - Daniel M Bader
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
| | - Holger Prokisch
- Institute of Human Genetics, Helmholtz Zentrum München, Ingolstädter Landstr. 1, 85764 Neuherberg, Germany; Institute of Human Genetics, Klinikum rechts der Isar, Technical University of Munich, 13 Ismaninger Str. 22, 81675 München, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany; Quantitative Biosciences Munich, Gene Center, Department of Biochemistry, Ludwig-Maximilians Universität München, Feodor-Lynen-Str. 25, 81377 München, Germany.
| |
Collapse
|
11
|
Avsec Ž, Barekatain M, Cheng J, Gagneur J. Modeling positional effects of regulatory sequences with spline transformations increases prediction accuracy of deep neural networks. Bioinformatics 2018; 34:1261-1269. [PMID: 29155928 PMCID: PMC5905632 DOI: 10.1093/bioinformatics/btx727] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2017] [Revised: 10/16/2017] [Accepted: 11/15/2017] [Indexed: 12/01/2022] Open
Abstract
Motivation Regulatory sequences are not solely defined by their nucleic acid sequence but also by their relative distances to genomic landmarks such as transcription start site, exon boundaries or polyadenylation site. Deep learning has become the approach of choice for modeling regulatory sequences because of its strength to learn complex sequence features. However, modeling relative distances to genomic landmarks in deep neural networks has not been addressed. Results Here we developed spline transformation, a neural network module based on splines to flexibly and robustly model distances. Modeling distances to various genomic landmarks with spline transformations significantly increased state-of-the-art prediction accuracy of in vivo RNA-binding protein binding sites for 120 out of 123 proteins. We also developed a deep neural network for human splice branchpoint based on spline transformations that outperformed the current best, already distance-based, machine learning model. Compared to piecewise linear transformation, as obtained by composition of rectified linear units, spline transformation yields higher prediction accuracy as well as faster and more robust training. As spline transformation can be applied to further quantities beyond distances, such as methylation or conservation, we foresee it as a versatile component in the genomics deep learning toolbox. Availability and implementation Spline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at https://github.com/gagneurlab/Manuscript_Avsec_Bioinformatics_2017. Contact avsec@in.tum.de or gagneur@in.tum.de. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Žiga Avsec
- Department of Informatics, Technical University of Munich, Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Gene Center, Ludwig-Maximilians-Universität München, Munich, Germany
| | | | - Jun Cheng
- Department of Informatics, Technical University of Munich, Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Gene Center, Ludwig-Maximilians-Universität München, Munich, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Garching, Germany
| |
Collapse
|
12
|
Cheng J, Maier KC, Avsec Ž, Rus P, Gagneur J. Cis-regulatory elements explain most of the mRNA stability variation across genes in yeast. RNA 2017; 23:1648-1659. [PMID: 28802259 PMCID: PMC5648033 DOI: 10.1261/rna.062224.117] [Citation(s) in RCA: 33] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/24/2017] [Accepted: 07/31/2017] [Indexed: 05/09/2023]
Abstract
The stability of mRNA is one of the major determinants of gene expression. Although a wealth of sequence elements regulating mRNA stability has been described, their quantitative contributions to half-life are unknown. Here, we built a quantitative model for Saccharomyces cerevisiae based on functional mRNA sequence features that explains 59% of the half-life variation between genes and predicts half-life at a median relative error of 30%. The model revealed a new destabilizing 3' UTR motif, ATATTC, which we functionally validated. Codon usage proves to be the major determinant of mRNA stability. Nonetheless, single-nucleotide variations have the largest effect when occurring on 3' UTR motifs or upstream AUGs. Analyzing mRNA half-life data of 34 knockout strains showed that the effect of codon usage not only requires functional decapping and deadenylation, but also the 5'-to-3' exonuclease Xrn1, the nonsense-mediated decay genes, but not no-go decay. Altogether, this study quantitatively delineates the contributions of mRNA sequence features on stability in yeast, reveals their functional dependencies on degradation pathways, and allows accurate prediction of half-life from mRNA sequence.
Collapse
Affiliation(s)
- Jun Cheng
- Department of Informatics, Technical University of Munich, 85748 Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, 81377 München, Germany
| | - Kerstin C Maier
- Department of Molecular Biology, Max Planck Institute for Biophysical Chemistry, 37077 Göttingen, Germany
| | - Žiga Avsec
- Department of Informatics, Technical University of Munich, 85748 Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, 81377 München, Germany
| | - Petra Rus
- Department of Molecular Biology, Max Planck Institute for Biophysical Chemistry, 37077 Göttingen, Germany
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, 85748 Garching, Germany
- Graduate School of Quantitative Biosciences (QBM), Ludwig-Maximilians-Universität München, 81377 München, Germany
| |
Collapse
|