1
|
Chen K, Zhou Y, Ding M, Wang Y, Ren Z, Yang Y. Self-supervised learning on millions of primary RNA sequences from 72 vertebrates improves sequence-based RNA splicing prediction. Brief Bioinform 2024; 25:bbae163. [PMID: 38605640 PMCID: PMC11009468 DOI: 10.1093/bib/bbae163] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2024] [Revised: 02/22/2024] [Accepted: 03/19/2024] [Indexed: 04/13/2024] Open
Abstract
Language models pretrained by self-supervised learning (SSL) have been widely utilized to study protein sequences, while few models were developed for genomic sequences and were limited to single species. Due to the lack of genomes from different species, these models cannot effectively leverage evolutionary information. In this study, we have developed SpliceBERT, a language model pretrained on primary ribonucleic acids (RNA) sequences from 72 vertebrates by masked language modeling, and applied it to sequence-based modeling of RNA splicing. Pretraining SpliceBERT on diverse species enables effective identification of evolutionarily conserved elements. Meanwhile, the learned hidden states and attention weights can characterize the biological properties of splice sites. As a result, SpliceBERT was shown effective on several downstream tasks: zero-shot prediction of variant effects on splicing, prediction of branchpoints in humans, and cross-species prediction of splice sites. Our study highlighted the importance of pretraining genomic language models on a diverse range of species and suggested that SSL is a promising approach to enhance our understanding of the regulatory logic underlying genomic sequences.
Collapse
Affiliation(s)
- Ken Chen
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Yue Zhou
- Peng Cheng Laboratory, Shenzhen, China
| | - Maolin Ding
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
| | - Yu Wang
- Peng Cheng Laboratory, Shenzhen, China
| | | | - Yuedong Yang
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
- Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education, China
| |
Collapse
|
2
|
Jain S, Bakolitsa C, Brenner SE, Radivojac P, Moult J, Repo S, Hoskins RA, Andreoletti G, Barsky D, Chellapan A, Chu H, Dabbiru N, Kollipara NK, Ly M, Neumann AJ, Pal LR, Odell E, Pandey G, Peters-Petrulewicz RC, Srinivasan R, Yee SF, Yeleswarapu SJ, Zuhl M, Adebali O, Patra A, Beer MA, Hosur R, Peng J, Bernard BM, Berry M, Dong S, Boyle AP, Adhikari A, Chen J, Hu Z, Wang R, Wang Y, Miller M, Wang Y, Bromberg Y, Turina P, Capriotti E, Han JJ, Ozturk K, Carter H, Babbi G, Bovo S, Di Lena P, Martelli PL, Savojardo C, Casadio R, Cline MS, De Baets G, Bonache S, Díez O, Gutiérrez-Enríquez S, Fernández A, Montalban G, Ootes L, Özkan S, Padilla N, Riera C, De la Cruz X, Diekhans M, Huwe PJ, Wei Q, Xu Q, Dunbrack RL, Gotea V, Elnitski L, Margolin G, Fariselli P, Kulakovskiy IV, Makeev VJ, Penzar DD, Vorontsov IE, Favorov AV, Forman JR, Hasenahuer M, Fornasari MS, Parisi G, Avsec Z, Çelik MH, Nguyen TYD, Gagneur J, Shi FY, Edwards MD, Guo Y, Tian K, Zeng H, Gifford DK, Göke J, Zaucha J, Gough J, Ritchie GRS, Frankish A, Mudge JM, Harrow J, Young EL, Yu Y, Huff CD, Murakami K, Nagai Y, Imanishi T, Mungall CJ, Jacobsen JOB, Kim D, Jeong CS, Jones DT, Li MJ, Guthrie VB, Bhattacharya R, Chen YC, Douville C, Fan J, Kim D, Masica D, Niknafs N, Sengupta S, Tokheim C, Turner TN, Yeo HTG, Karchin R, Shin S, Welch R, Keles S, Li Y, Kellis M, Corbi-Verge C, Strokach AV, Kim PM, Klein TE, Mohan R, Sinnott-Armstrong NA, Wainberg M, Kundaje A, Gonzaludo N, Mak ACY, Chhibber A, Lam HYK, Dahary D, Fishilevich S, Lancet D, Lee I, Bachman B, Katsonis P, Lua RC, Wilson SJ, Lichtarge O, Bhat RR, Sundaram L, Viswanath V, Bellazzi R, Nicora G, Rizzo E, Limongelli I, Mezlini AM, Chang R, Kim S, Lai C, O’Connor R, Topper S, van den Akker J, Zhou AY, Zimmer AD, Mishne G, Bergquist TR, Breese MR, Guerrero RF, Jiang Y, Kiga N, Li B, Mort M, Pagel KA, Pejaver V, Stamboulian MH, Thusberg J, Mooney SD, Teerakulkittipong N, Cao C, Kundu K, Yin Y, Yu CH, Kleyman M, Lin CF, Stackpole M, Mount SM, Eraslan G, Mueller NS, Naito T, Rao AR, Azaria JR, Brodie A, Ofran Y, Garg A, Pal D, Hawkins-Hooker A, Kenlay H, Reid J, Mucaki EJ, Rogan PK, Schwarz JM, Searls DB, Lee GR, Seok C, Krämer A, Shah S, Huang CV, Kirsch JF, Shatsky M, Cao Y, Chen H, Karimi M, Moronfoye O, Sun Y, Shen Y, Shigeta R, Ford CT, Nodzak C, Uppal A, Shi X, Joseph T, Kotte S, Rana S, Rao A, Saipradeep VG, Sivadasan N, Sunderam U, Stanke M, Su A, Adzhubey I, Jordan DM, Sunyaev S, Rousseau F, Schymkowitz J, Van Durme J, Tavtigian SV, Carraro M, Giollo M, Tosatto SCE, Adato O, Carmel L, Cohen NE, Fenesh T, Holtzer T, Juven-Gershon T, Unger R, Niroula A, Olatubosun A, Väliaho J, Yang Y, Vihinen M, Wahl ME, Chang B, Chong KC, Hu I, Sun R, Wu WKK, Xia X, Zee BC, Wang MH, Wang M, Wu C, Lu Y, Chen K, Yang Y, Yates CM, Kreimer A, Yan Z, Yosef N, Zhao H, Wei Z, Yao Z, Zhou F, Folkman L, Zhou Y, Daneshjou R, Altman RB, Inoue F, Ahituv N, Arkin AP, Lovisa F, Bonvini P, Bowdin S, Gianni S, Mantuano E, Minicozzi V, Novak L, Pasquo A, Pastore A, Petrosino M, Puglisi R, Toto A, Veneziano L, Chiaraluce R, Ball MP, Bobe JR, Church GM, Consalvi V, Cooper DN, Buckley BA, Sheridan MB, Cutting GR, Scaini MC, Cygan KJ, Fredericks AM, Glidden DT, Neil C, Rhine CL, Fairbrother WG, Alontaga AY, Fenton AW, Matreyek KA, Starita LM, Fowler DM, Löscher BS, Franke A, Adamson SI, Graveley BR, Gray JW, Malloy MJ, Kane JP, Kousi M, Katsanis N, Schubach M, Kircher M, Mak ACY, Tang PLF, Kwok PY, Lathrop RH, Clark WT, Yu GK, LeBowitz JH, Benedicenti F, Bettella E, Bigoni S, Cesca F, Mammi I, Marino-Buslje C, Milani D, Peron A, Polli R, Sartori S, Stanzial F, Toldo I, Turolla L, Aspromonte MC, Bellini M, Leonardi E, Liu X, Marshall C, McCombie WR, Elefanti L, Menin C, Meyn MS, Murgia A, Nadeau KCY, Neuhausen SL, Nussbaum RL, Pirooznia M, Potash JB, Dimster-Denk DF, Rine JD, Sanford JR, Snyder M, Cote AG, Sun S, Verby MW, Weile J, Roth FP, Tewhey R, Sabeti PC, Campagna J, Refaat MM, Wojciak J, Grubb S, Schmitt N, Shendure J, Spurdle AB, Stavropoulos DJ, Walton NA, Zandi PP, Ziv E, Burke W, Chen F, Carr LR, Martinez S, Paik J, Harris-Wai J, Yarborough M, Fullerton SM, Koenig BA, McInnes G, Shigaki D, Chandonia JM, Furutsuki M, Kasak L, Yu C, Chen R, Friedberg I, Getz GA, Cong Q, Kinch LN, Zhang J, Grishin NV, Voskanian A, Kann MG, Tran E, Ioannidis NM, Hunter JM, Udani R, Cai B, Morgan AA, Sokolov A, Stuart JM, Minervini G, Monzon AM, Batzoglou S, Butte AJ, Greenblatt MS, Hart RK, Hernandez R, Hubbard TJP, Kahn S, O’Donnell-Luria A, Ng PC, Shon J, Veltman J, Zook JM. CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods. Genome Biol 2024; 25:53. [PMID: 38389099 PMCID: PMC10882881 DOI: 10.1186/s13059-023-03113-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2023] [Accepted: 11/17/2023] [Indexed: 02/24/2024] Open
Abstract
BACKGROUND The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. The five complete editions of the CAGI community experiment comprised 50 challenges, in which participants made blind predictions of phenotypes from genetic data, and these were evaluated by independent assessors. RESULTS Performance was particularly strong for clinical pathogenic variants, including some difficult-to-diagnose cases, and extends to interpretation of cancer-related variants. Missense variant interpretation methods were able to estimate biochemical effects with increasing accuracy. Assessment of methods for regulatory variants and complex trait disease risk was less definitive and indicates performance potentially suitable for auxiliary use in the clinic. CONCLUSIONS Results show that while current methods are imperfect, they have major utility for research and clinical applications. Emerging methods and increasingly large, robust datasets for training and assessment promise further progress ahead.
Collapse
|
3
|
Smith C, Kitzman JO. Benchmarking splice variant prediction algorithms using massively parallel splicing assays. Genome Biol 2023; 24:294. [PMID: 38129864 PMCID: PMC10734170 DOI: 10.1186/s13059-023-03144-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Accepted: 12/13/2023] [Indexed: 12/23/2023] Open
Abstract
BACKGROUND Variants that disrupt mRNA splicing account for a sizable fraction of the pathogenic burden in many genetic disorders, but identifying splice-disruptive variants (SDVs) beyond the essential splice site dinucleotides remains difficult. Computational predictors are often discordant, compounding the challenge of variant interpretation. Because they are primarily validated using clinical variant sets heavily biased to known canonical splice site mutations, it remains unclear how well their performance generalizes. RESULTS We benchmark eight widely used splicing effect prediction algorithms, leveraging massively parallel splicing assays (MPSAs) as a source of experimentally determined ground-truth. MPSAs simultaneously assay many variants to nominate candidate SDVs. We compare experimentally measured splicing outcomes with bioinformatic predictions for 3,616 variants in five genes. Algorithms' concordance with MPSA measurements, and with each other, is lower for exonic than intronic variants, underscoring the difficulty of identifying missense or synonymous SDVs. Deep learning-based predictors trained on gene model annotations achieve the best overall performance at distinguishing disruptive and neutral variants, and controlling for overall call rate genome-wide, SpliceAI and Pangolin have superior sensitivity. Finally, our results highlight two practical considerations when scoring variants genome-wide: finding an optimal score cutoff, and the substantial variability introduced by differences in gene model annotation, and we suggest strategies for optimal splice effect prediction in the face of these issues. CONCLUSION SpliceAI and Pangolin show the best overall performance among predictors tested, however, improvements in splice effect prediction are still needed especially within exons.
Collapse
Affiliation(s)
- Cathy Smith
- Department of Human Genetics, University of Michigan Medical School, Ann Arbor, MI, 48109, USA
- Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI, 48109, USA
| | - Jacob O Kitzman
- Department of Human Genetics, University of Michigan Medical School, Ann Arbor, MI, 48109, USA.
- Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI, 48109, USA.
| |
Collapse
|
4
|
Wang R, Helbig I, Edmondson AC, Lin L, Xing Y. Splicing defects in rare diseases: transcriptomics and machine learning strategies towards genetic diagnosis. Brief Bioinform 2023; 24:bbad284. [PMID: 37580177 PMCID: PMC10516351 DOI: 10.1093/bib/bbad284] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Revised: 07/10/2023] [Accepted: 07/20/2023] [Indexed: 08/16/2023] Open
Abstract
Genomic variants affecting pre-messenger RNA splicing and its regulation are known to underlie many rare genetic diseases. However, common workflows for genetic diagnosis and clinical variant interpretation frequently overlook splice-altering variants. To better serve patient populations and advance biomedical knowledge, it has become increasingly important to develop and refine approaches for detecting and interpreting pathogenic splicing variants. In this review, we will summarize a few recent developments and challenges in using RNA sequencing technologies for rare disease investigation. Moreover, we will discuss how recent computational splicing prediction tools have emerged as complementary approaches for revealing disease-causing variants underlying splicing defects. We speculate that continuous improvements to sequencing technologies and predictive modeling will not only expand our understanding of splicing regulation but also bring us closer to filling the diagnostic gap for rare disease patients.
Collapse
Affiliation(s)
- Robert Wang
- Center for Computational and Genomic Medicine, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Genomics and Computational Biology Graduate Program, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Ingo Helbig
- The Epilepsy NeuroGenetics Initiative, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Division of Neurology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Department of Neurology, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Andrew C Edmondson
- Center for Computational and Genomic Medicine, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Department of Pediatrics, Division of Human Genetics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
| | - Lan Lin
- Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
- Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
| | - Yi Xing
- Center for Computational and Genomic Medicine, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA
- Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| |
Collapse
|
5
|
Smith C, Kitzman JO. Benchmarking splice variant prediction algorithms using massively parallel splicing assays. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.05.04.539398. [PMID: 37205456 PMCID: PMC10187268 DOI: 10.1101/2023.05.04.539398] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/21/2023]
Abstract
Background Variants that disrupt mRNA splicing account for a sizable fraction of the pathogenic burden in many genetic disorders, but identifying splice-disruptive variants (SDVs) beyond the essential splice site dinucleotides remains difficult. Computational predictors are often discordant, compounding the challenge of variant interpretation. Because they are primarily validated using clinical variant sets heavily biased to known canonical splice site mutations, it remains unclear how well their performance generalizes. Results We benchmarked eight widely used splicing effect prediction algorithms, leveraging massively parallel splicing assays (MPSAs) as a source of experimentally determined ground-truth. MPSAs simultaneously assay many variants to nominate candidate SDVs. We compared experimentally measured splicing outcomes with bioinformatic predictions for 3,616 variants in five genes. Algorithms' concordance with MPSA measurements, and with each other, was lower for exonic than intronic variants, underscoring the difficulty of identifying missense or synonymous SDVs. Deep learning-based predictors trained on gene model annotations achieved the best overall performance at distinguishing disruptive and neutral variants. Controlling for overall call rate genome-wide, SpliceAI and Pangolin also showed superior overall sensitivity for identifying SDVs. Finally, our results highlight two practical considerations when scoring variants genome-wide: finding an optimal score cutoff, and the substantial variability introduced by differences in gene model annotation, and we suggest strategies for optimal splice effect prediction in the face of these issues. Conclusion SpliceAI and Pangolin showed the best overall performance among predictors tested, however, improvements in splice effect prediction are still needed especially within exons.
Collapse
Affiliation(s)
- Cathy Smith
- Department of Human Genetics, University of Michigan Medical School, Ann Arbor, MI 48109, USA
- Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI 48109, USA
| | - Jacob O. Kitzman
- Department of Human Genetics, University of Michigan Medical School, Ann Arbor, MI 48109, USA
- Department of Computational Medicine and Bioinformatics, University of Michigan Medical School, Ann Arbor, MI 48109, USA
| |
Collapse
|
6
|
Rogalska ME, Vivori C, Valcárcel J. Regulation of pre-mRNA splicing: roles in physiology and disease, and therapeutic prospects. Nat Rev Genet 2023; 24:251-269. [PMID: 36526860 DOI: 10.1038/s41576-022-00556-8] [Citation(s) in RCA: 50] [Impact Index Per Article: 50.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/10/2022] [Indexed: 12/23/2022]
Abstract
The removal of introns from mRNA precursors and its regulation by alternative splicing are key for eukaryotic gene expression and cellular function, as evidenced by the numerous pathologies induced or modified by splicing alterations. Major recent advances have been made in understanding the structures and functions of the splicing machinery, in the description and classification of physiological and pathological isoforms and in the development of the first therapies for genetic diseases based on modulation of splicing. Here, we review this progress and discuss important remaining challenges, including predicting splice sites from genomic sequences, understanding the variety of molecular mechanisms and logic of splicing regulation, and harnessing this knowledge for probing gene function and disease aetiology and for the design of novel therapeutic approaches.
Collapse
Affiliation(s)
- Malgorzata Ewa Rogalska
- Genome Biology Program, Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Spain
| | - Claudia Vivori
- Genome Biology Program, Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Spain
- Department of Medicine and Life Sciences, Universitat Pompeu Fabra (UPF), Barcelona, Spain
- The Francis Crick Institute, London, UK
| | - Juan Valcárcel
- Genome Biology Program, Centre for Genomic Regulation (CRG), The Barcelona Institute of Science and Technology, Barcelona, Spain.
- Department of Medicine and Life Sciences, Universitat Pompeu Fabra (UPF), Barcelona, Spain.
- Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain.
| |
Collapse
|
7
|
Cortés-López M, Schulz L, Enculescu M, Paret C, Spiekermann B, Quesnel-Vallières M, Torres-Diz M, Unic S, Busch A, Orekhova A, Kuban M, Mesitov M, Mulorz MM, Shraim R, Kielisch F, Faber J, Barash Y, Thomas-Tikhonenko A, Zarnack K, Legewie S, König J. High-throughput mutagenesis identifies mutations and RNA-binding proteins controlling CD19 splicing and CART-19 therapy resistance. Nat Commun 2022; 13:5570. [PMID: 36138008 PMCID: PMC9500061 DOI: 10.1038/s41467-022-31818-y] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2021] [Accepted: 07/05/2022] [Indexed: 11/29/2022] Open
Abstract
Following CART-19 immunotherapy for B-cell acute lymphoblastic leukaemia (B-ALL), many patients relapse due to loss of the cognate CD19 epitope. Since epitope loss can be caused by aberrant CD19 exon 2 processing, we herein investigate the regulatory code that controls CD19 splicing. We combine high-throughput mutagenesis with mathematical modelling to quantitatively disentangle the effects of all mutations in the region comprising CD19 exons 1-3. Thereupon, we identify ~200 single point mutations that alter CD19 splicing and thus could predispose B-ALL patients to developing CART-19 resistance. Furthermore, we report almost 100 previously unknown splice isoforms that emerge from cryptic splice sites and likely encode non-functional CD19 proteins. We further identify cis-regulatory elements and trans-acting RNA-binding proteins that control CD19 splicing (e.g., PTBP1 and SF3B4) and validate that loss of these factors leads to pervasive CD19 mis-splicing. Our dataset represents a comprehensive resource for identifying predictive biomarkers for CART-19 therapy. Multiple alternative splicing events in CD19 mRNA have been associated with resistance/relapse to CD19 CAR-T therapy in patients with B cell malignancies. Here, by combining patient data and a high-throughput mutagenesis screen, the authors identify single point mutations and RNA-binding proteins that can control CD19 splicing and be associated with CD19 CAR-T therapy resistance.
Collapse
Affiliation(s)
| | - Laura Schulz
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Mihaela Enculescu
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Claudia Paret
- Department of Pediatric Hematology/Oncology, Center for Pediatric and Adolescent Medicine, University Medical Center of the Johannes Gutenberg University Mainz, 55131, Mainz, Germany.,University Cancer Center (UCT), University Medical Center of the Johannes Gutenberg University Mainz, 55131, Mainz, Germany.,German Cancer Consortium (DKTK), site Frankfurt/Mainz, Germany, German Cancer Research Center (DKFZ), 69120, Heidelberg, Germany
| | - Bea Spiekermann
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Mathieu Quesnel-Vallières
- Department of Genetics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 19104, USA.,Department of Biochemistry and Biophysics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Manuel Torres-Diz
- Division of Cancer Pathobiology, Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA
| | - Sebastian Unic
- Department of Systems Biology, Institute for Biomedical Genetics (IBMG), University of Stuttgart, Allmandring 30E, 70569, Stuttgart, Germany
| | - Anke Busch
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Anna Orekhova
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Monika Kuban
- Department of Systems Biology, Institute for Biomedical Genetics (IBMG), University of Stuttgart, Allmandring 30E, 70569, Stuttgart, Germany
| | - Mikhail Mesitov
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Miriam M Mulorz
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Rawan Shraim
- Division of Cancer Pathobiology, Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA.,Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, 19104, USA
| | - Fridolin Kielisch
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany
| | - Jörg Faber
- Department of Pediatric Hematology/Oncology, Center for Pediatric and Adolescent Medicine, University Medical Center of the Johannes Gutenberg University Mainz, 55131, Mainz, Germany.,University Cancer Center (UCT), University Medical Center of the Johannes Gutenberg University Mainz, 55131, Mainz, Germany.,German Cancer Consortium (DKTK), site Frankfurt/Mainz, Germany, German Cancer Research Center (DKFZ), 69120, Heidelberg, Germany
| | - Yoseph Barash
- Department of Genetics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Andrei Thomas-Tikhonenko
- Division of Cancer Pathobiology, Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA.,Department of Pathology & Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Kathi Zarnack
- Buchmann Institute for Molecular Life Sciences (BMLS), Max-von-Laue-Str. 15, 60438, Frankfurt, Germany. .,Faculty Biological Sciences, Goethe University Frankfurt, Max-von-Laue-Str. 15, 60438, Frankfurt, Germany.
| | - Stefan Legewie
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany. .,Department of Systems Biology, Institute for Biomedical Genetics (IBMG), University of Stuttgart, Allmandring 30E, 70569, Stuttgart, Germany. .,Stuttgart Research Center for Systems Biology (SRCSB), University of Stuttgart, Stuttgart, Germany.
| | - Julian König
- Institute of Molecular Biology (IMB), Ackermannweg 4, 55128, Mainz, Germany.
| |
Collapse
|
8
|
Casadio R, Savojardo C, Fariselli P, Capriotti E, Martelli PL. Turning Failures into Applications: The Problem of Protein ΔΔG Prediction. METHODS IN MOLECULAR BIOLOGY (CLIFTON, N.J.) 2022; 2449:169-185. [PMID: 35507262 DOI: 10.1007/978-1-0716-2095-3_6] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Indexed: 01/17/2023]
Abstract
After nearly two decades of research in the field of computational methods based on machine learning and knowledge-based potentials for ΔG and ΔΔG prediction upon variations, we now realize that all the approaches are poorly performing when tested on specific cases and that there is large space for improvement. Why this is so? Is it wrong the underlying assumption that experimental protein thermodynamics in solution reflects the thermodynamics of a single protein? Both machine learning and knowledge-based computational methods are rigorous and we know the solid theory behind. We are now in a critical situation, which suggests that predictions of protein instability upon variation should be considered with care. In the following, we will show how to cope with the problem of understanding which protein positions may be of interest for biotechnological and biomedical purposes. By applying a consensus procedure, we indicate possible strategies for the result interpretation.
Collapse
Affiliation(s)
- Rita Casadio
- Biocomputing Group, Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy.
| | - Castrense Savojardo
- Biocomputing Group, Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy
| | - Piero Fariselli
- Department of Medical Sciences, University of Torino, Turin, Italy
| | - Emidio Capriotti
- Biocomputing Group, Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy
| | - Pier Luigi Martelli
- Biocomputing Group, Department of Pharmacy and Biotechnology, University of Bologna, Bologna, Italy
| |
Collapse
|
9
|
Lin JH, Wu H, Zou WB, Masson E, Fichou Y, Le Gac G, Cooper DN, Férec C, Liao Z, Chen JM. Splicing Outcomes of 5' Splice Site GT>GC Variants That Generate Wild-Type Transcripts Differ Significantly Between Full-Length and Minigene Splicing Assays. Front Genet 2021; 12:701652. [PMID: 34422003 PMCID: PMC8375439 DOI: 10.3389/fgene.2021.701652] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Accepted: 07/13/2021] [Indexed: 12/18/2022] Open
Abstract
Combining data derived from a meta-analysis of human disease-associated 5' splice site GT>GC (i.e., +2T>C) variants and a cell culture-based full-length gene splicing assay (FLGSA) of forward engineered +2T>C substitutions, we recently estimated that ∼15-18% of +2T>C variants can generate up to 84% wild-type transcripts relative to their wild-type counterparts. Herein, we analyzed the splicing outcomes of 20 +2T>C variants that generate some wild-type transcripts in two minigene assays. We found a high discordance rate in terms of the generation of wild-type transcripts, not only between FLGSA and the minigene assays but also between the different minigene assays. In the pET01 context, all 20 wild-type minigene constructs generated the expected wild-type transcripts; of the 20 corresponding variant minigene constructs, 14 (70%) generated wild-type transcripts. In the pSPL3 context, only 18 of the 20 wild-type minigene constructs generated the expected wild-type transcripts whereas 8 of the 18 (44%) corresponding variant minigene constructs generated wild-type transcripts. Thus, in the context of a particular type of variant, we raise awareness of the limitations of minigene splicing assays and emphasize the importance of sequence context in regulating splicing. Whether or not our findings apply to other types of splice-altering variant remains to be investigated.
Collapse
Affiliation(s)
- Jin-Huan Lin
- Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Hao Wu
- Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Wen-Bin Zou
- Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Emmanuelle Masson
- Univ Brest, Inserm, EFS, UMR 1078, GGB, Brest, France.,Service de Génétique Médicale et de Biologie de la Reproduction, CHRU Brest, Brest, France
| | - Yann Fichou
- Univ Brest, Inserm, EFS, UMR 1078, GGB, Brest, France.,Laboratory of Excellence GR-Ex, Paris, France
| | - Gerald Le Gac
- Univ Brest, Inserm, EFS, UMR 1078, GGB, Brest, France.,Service de Génétique Médicale et de Biologie de la Reproduction, CHRU Brest, Brest, France.,Laboratory of Excellence GR-Ex, Paris, France
| | - David N Cooper
- Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, United Kingdom
| | - Claude Férec
- Univ Brest, Inserm, EFS, UMR 1078, GGB, Brest, France.,Service de Génétique Médicale et de Biologie de la Reproduction, CHRU Brest, Brest, France
| | - Zhuan Liao
- Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Jian-Min Chen
- Univ Brest, Inserm, EFS, UMR 1078, GGB, Brest, France
| |
Collapse
|
10
|
Lord J, Baralle D. Splicing in the Diagnosis of Rare Disease: Advances and Challenges. Front Genet 2021; 12:689892. [PMID: 34276790 PMCID: PMC8280750 DOI: 10.3389/fgene.2021.689892] [Citation(s) in RCA: 32] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2021] [Accepted: 06/07/2021] [Indexed: 12/13/2022] Open
Abstract
Mutations which affect splicing are significant contributors to rare disease, but are frequently overlooked by diagnostic sequencing pipelines. Greater ascertainment of pathogenic splicing variants will increase diagnostic yields, ending the diagnostic odyssey for patients and families affected by rare disorders, and improving treatment and care strategies. Advances in sequencing technologies, predictive modeling, and understanding of the mechanisms of splicing in recent years pave the way for improved detection and interpretation of splice affecting variants, yet several limitations still prohibit their routine ascertainment in diagnostic testing. This review explores some of these advances in the context of clinical application and discusses challenges to be overcome before these variants are comprehensively and routinely recognized in diagnostics.
Collapse
Affiliation(s)
- Jenny Lord
- School of Human Development and Health, Faculty of Medicine, University of Southampton, Southampton, United Kingdom
| | - Diana Baralle
- School of Human Development and Health, Faculty of Medicine, University of Southampton, Southampton, United Kingdom
- Wessex Clinical Genetics Service, University Hospital Southampton NHS Foundation Trust, Southampton, United Kingdom
| |
Collapse
|
11
|
Cheng J, Çelik MH, Kundaje A, Gagneur J. MTSplice predicts effects of genetic variants on tissue-specific splicing. Genome Biol 2021; 22:94. [PMID: 33789710 PMCID: PMC8011109 DOI: 10.1186/s13059-021-02273-7] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2020] [Accepted: 01/14/2021] [Indexed: 12/20/2022] Open
Abstract
We develop the free and open-source model Multi-tissue Splicing (MTSplice) to predict the effects of genetic variants on splicing of cassette exons in 56 human tissues. MTSplice combines MMSplice, which models constitutive regulatory sequences, with a new neural network that models tissue-specific regulatory sequences. MTSplice outperforms MMSplice on predicting tissue-specific variations associated with genetic variants in most tissues of the GTEx dataset, with largest improvements on brain tissues. Furthermore, MTSplice predicts that autism-associated de novo mutations are enriched for variants affecting splicing specifically in the brain. We foresee that MTSplice will aid interpreting variants associated with tissue-specific disorders.
Collapse
Affiliation(s)
- Jun Cheng
- Department of Informatics, Technical University of Munich, Boltzmannstraße, Garching, 85748, Germany.
| | - Muhammed Hasan Çelik
- Department of Informatics, Technical University of Munich, Boltzmannstraße, Garching, 85748, Germany
| | - Anshul Kundaje
- Department of Computer Science, Stanford University, Stanford, CA, USA
- Department of Genetics, Stanford University, Stanford, CA, USA
| | - Julien Gagneur
- Department of Informatics, Technical University of Munich, Boltzmannstraße, Garching, 85748, Germany.
- Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany.
- Institute of Human Genetics, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.
| |
Collapse
|
12
|
Lin JH, Masson E, Boulling A, Hayden M, Cooper DN, Férec C, Liao Z, Chen JM. 5' splice site GC>GT and GT>GC variants differ markedly in terms of their functionality and pathogenicity. Hum Mutat 2020; 41:1358-1364. [PMID: 32369867 DOI: 10.1002/humu.24029] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2019] [Revised: 03/27/2020] [Accepted: 04/19/2020] [Indexed: 12/11/2022]
Abstract
In the human genome, most 5' splice sites (~99%) employ the canonical GT dinucleotide whereas a small minority (~1%) use the noncanonical GC dinucleotide. The functionality and pathogenicity of 5' splice site GT>GC (+2T>C) variants have been extensively studied but we know very little about 5' splice site GC>GT (+2C>T) variants. Herein, we have addressed this deficiency by performing a meta-analysis of reported +2C>T "pathogenic" variants together with a functional analysis of engineered +2C>T substitutions using a cell culture-based full-length gene splicing assay. Our results establish proof of concept that +2C>T variants are qualitatively different from +2T>C variants in terms of their functionality and suggest that, in sharp contrast to +2T>C variants, most if not all +2C>T variants have no pathological relevance. Our findings have important implications for interpreting the clinical relevance of +2C>T variants and understanding the evolutionary switching between GT and GC 5' splice sites in mammalian genomes.
Collapse
Affiliation(s)
- Jin-Huan Lin
- EFS, Univ Brest, INSERM, UMR 1078, GGB, Brest, France.,Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Emmanuelle Masson
- EFS, Univ Brest, INSERM, UMR 1078, GGB, Brest, France.,CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France
| | | | - Matthew Hayden
- Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - David N Cooper
- Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Claude Férec
- EFS, Univ Brest, INSERM, UMR 1078, GGB, Brest, France.,CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France
| | - Zhuan Liao
- Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China.,Shanghai Institute of Pancreatic Diseases, Shanghai, China
| | - Jian-Min Chen
- EFS, Univ Brest, INSERM, UMR 1078, GGB, Brest, France
| |
Collapse
|
13
|
Chen JM, Lin JH, Masson E, Liao Z, Férec C, Cooper DN, Hayden M. The Experimentally Obtained Functional Impact Assessments of 5' Splice Site GT'GC Variants Differ Markedly from Those Predicted. Curr Genomics 2020; 21:56-66. [PMID: 32655299 PMCID: PMC7324893 DOI: 10.2174/1389202921666200210141701] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2019] [Revised: 01/30/2020] [Accepted: 02/03/2020] [Indexed: 01/26/2023] Open
Abstract
Introduction: 5' splice site GT>GC or +2T>C variants have been frequently reported to cause human genetic disease and are routinely scored as pathogenic splicing mutations. However, we have recently demonstrated that such variants in human disease genes may not invariably be pathogenic. Moreover, we found that no splicing prediction tools appear to be capable of reliably distinguishing those +2T>C variants that generate wild-type transcripts from those that do not. Methodology Herein, we evaluated the performance of a novel deep learning-based tool, SpliceAI, in the context of three datasets of +2T>C variants, all of which had been characterized functionally in terms of their impact on pre-mRNA splicing. The first two datasets refer to our recently described “in vivo” dataset of 45 known disease-causing +2T>C variants and the “in vitro” dataset of 103 +2T>C substitutions subjected to full-length gene splicing assay. The third dataset comprised 12 BRCA1 +2T>C variants that were recently analyzed by saturation genome editing. Results Comparison of the SpliceAI-predicted and experimentally obtained functional impact assessments of these variants (and smaller datasets of +2T>A and +2T>G variants) revealed that although SpliceAI performed rather better than other prediction tools, it was still far from perfect. A key issue was that the impact of those +2T>C (and +2T>A) variants that generated wild-type transcripts represents a quantitative change that can vary from barely detectable to an almost full expression of wild-type transcripts, with wild-type transcripts often co-existing with aberrantly spliced transcripts. Conclusion Our findings highlight the challenges that we still face in attempting to accurately identify splice-altering variants.
Collapse
Affiliation(s)
- Jian-Min Chen
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Jin-Huan Lin
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Emmanuelle Masson
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Zhuan Liao
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Claude Férec
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - David N Cooper
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| | - Matthew Hayden
- 1EFS, Univ Brest, Inserm, UMR 1078, GGB, F-29200Brest, France; 2Department of Gastroenterology, Changhai Hospital, Second Military Medical University, Shanghai, China; 3Shanghai Institute of Pancreatic Diseases, Shanghai, China; 4CHRU Brest, Service de Génétique Médicale et de Biologie de la Reproduction, Brest, France; 5Institute of Medical Genetics, School of Medicine, Cardiff University, Cardiff, UK
| |
Collapse
|
14
|
Andreoletti G, Pal LR, Moult J, Brenner SE. Reports from the fifth edition of CAGI: The Critical Assessment of Genome Interpretation. Hum Mutat 2019; 40:1197-1201. [PMID: 31334884 PMCID: PMC7329230 DOI: 10.1002/humu.23876] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2019] [Accepted: 07/19/2019] [Indexed: 12/20/2022]
Abstract
Interpretation of genomic variation plays an essential role in the analysis of cancer and monogenic disease, and increasingly also in complex trait disease, with applications ranging from basic research to clinical decisions. Many computational impact prediction methods have been developed, yet the field lacks a clear consensus on their appropriate use and interpretation. The Critical Assessment of Genome Interpretation (CAGI, /'kā-jē/) is a community experiment to objectively assess computational methods for predicting the phenotypic impacts of genomic variation. CAGI participants are provided genetic variants and make blind predictions of resulting phenotype. Independent assessors evaluate the predictions by comparing with experimental and clinical data. CAGI has completed five editions with the goals of establishing the state of art in genome interpretation and of encouraging new methodological developments. This special issue (https://onlinelibrary.wiley.com/toc/10981004/2019/40/9) comprises reports from CAGI, focusing on the fifth edition that culminated in a conference that took place 5 to 7 July 2018. CAGI5 was comprised of 14 challenges and engaged hundreds of participants from a dozen countries. This edition had a notable increase in splicing and expression regulatory variant challenges, while also continuing challenges on clinical genomics, as well as complex disease datasets and missense variants in diseases ranging from cancer to Pompe disease to schizophrenia. Full information about CAGI is at https://genomeinterpretation.org.
Collapse
Affiliation(s)
- Gaia Andreoletti
- Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA
| | - Lipika R. Pal
- Institute for Bioscience and Biotechnology Research, University of Maryland, 9600 Gudelsky Drive, Rockville, MD 20850
| | - John Moult
- Institute for Bioscience and Biotechnology Research, University of Maryland, 9600 Gudelsky Drive, Rockville, MD 20850
- Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, MD 20742
| | - Steven E. Brenner
- Department of Plant and Microbial Biology, University of California, Berkeley, CA 94720, USA
- Center for Computational Biology, University of California, Berkeley, CA 94720, USA
| |
Collapse
|