1
|
Barash M, McNevin D, Fedorenko V, Giverts P. Machine learning applications in forensic DNA profiling: A critical review. Forensic Sci Int Genet 2024; 69:102994. [PMID: 38086200 DOI: 10.1016/j.fsigen.2023.102994] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Revised: 11/06/2023] [Accepted: 11/26/2023] [Indexed: 01/29/2024]
Abstract
Machine learning (ML) is a range of powerful computational algorithms capable of generating predictive models via intelligent autonomous analysis of relatively large and often unstructured data. ML has become an integral part of our daily lives with a plethora of applications, including web, business, automotive industry, clinical diagnostics, scientific research, and more recently, forensic science. In the field of forensic DNA, the manual analysis of complex data can be challenging, time-consuming, and error-prone. The integration of novel ML-based methods may aid in streamlining this process while maintaining the high accuracy and reproducibility required for forensic tools. Due to the relative novelty of such applications, the forensic community is largely unaware of ML capabilities and limitations. Furthermore, computer science and ML professionals are often unfamiliar with the forensic science field and its specific requirements. This manuscript offers a brief introduction to the capabilities of machine learning methods and their applications in the context of forensic DNA analysis and offers a critical review of the current literature in this rapidly developing field.
Collapse
Affiliation(s)
- Mark Barash
- Department of Justice Studies, San José State University, San Jose, CA, United States; Centre for Forensic Science, School of Mathematical and Physical Sciences, Faculty of Science, University of Technology Sydney, Broadway, Ultimo, NSW 2007, Australia.
| | - Dennis McNevin
- Centre for Forensic Science, School of Mathematical and Physical Sciences, Faculty of Science, University of Technology Sydney, Broadway, Ultimo, NSW 2007, Australia
| | - Vladimir Fedorenko
- The Educational and Scientific Laboratory of Forensic Materials Engineering of the Saratov State University, Russia
| | - Pavel Giverts
- Division of Identification and Forensic Science, Israel Police HQ, Haim Bar-Lev Road, Jerusalem, Israel
| |
Collapse
|
2
|
Becher D, Jmel H, Kheriji N, Sarno S, Kefi R. Genetic landscape of forensic DNA phenotyping markers among Mediterranean populations. Forensic Sci Int 2024; 354:111906. [PMID: 38128201 DOI: 10.1016/j.forsciint.2023.111906] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Accepted: 12/02/2023] [Indexed: 12/23/2023]
Abstract
Forensic DNA Phenotyping can reveal the appearance of an unknown individual by predicting the External Visible Characteristics (EVC) from DNA obtained at the crime scene. Our aim is to characterize the genetic landscape of Human identification markers responsible for EVC among Mediterranean populations compared to other worldwide groups. We conducted an exhaustive search for genes involved in EVC variation. Then, variants located on these genes were extracted from public genotypic data of Mediterranean, American, African and East Asiatic populations. The genetic landscape of these Human identification markers, their allelic distribution and admixture analyses, were determined using plink, R and ADMIXTURE softwares. Our results showed that the Mediterranean populations appear close to the Mexican populations and distinguished from sub Saharan African populations living in the USA and from East Asiatic populations. We highlighted a total of 103454 common variants shared between the studied populations and among them, 25 common variants associated with EVC. Interestingly, genotype frequencies results showed that the rs17646946, rs13016869, rs977588, rs1805008 and rs2240751 variants located respectively in the TCHH, PRKCE, OCA2, MC1R and MFSD12 genes are significantly different between the Mediterranean and Asiatic populations. The genotype frequencies of the variants rs977589 and rs7179994 located in the OCA2 gene, and of rs12913832 and rs2240751 located respectively in HERC2 and MFSD12 genes are significantly different between the Mediterranean and American populations. Our work generates a large number of EVC variants that could be a valuable resource for future studies in the forensic field.
Collapse
Affiliation(s)
- Dorra Becher
- Laboratory of Biomedical Genomics and Oncogenetics, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; Directorate of Technical and Scientific Police, Sub-Directorate of Forensic and Scientific Laboratories, Tunis,Tunisia; University of Carthage, National Institute of Applied Science and Technology, Tunis, Tunisia
| | - Haifa Jmel
- Laboratory of Biomedical Genomics and Oncogenetics, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; Genetic Typing Service, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; University of Tunis El Manar, 2092 El Manar I, Tunis, Tunisia
| | - Nadia Kheriji
- Laboratory of Biomedical Genomics and Oncogenetics, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; University of Tunis El Manar, 2092 El Manar I, Tunis, Tunisia
| | - Stefania Sarno
- Laboratory of Molecular Anthropology and Centre for Genome Biology, Department of Biological, Geological and Environmental Sciences, University of Bologna, Bologna, Italy
| | - Rym Kefi
- Laboratory of Biomedical Genomics and Oncogenetics, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; Genetic Typing Service, Institut Pasteur de Tunis, BP 74, 13 Place Pasteur, Tunis 1002, Tunisia; University of Tunis El Manar, 2092 El Manar I, Tunis, Tunisia.
| |
Collapse
|
5
|
Palmal S, Adhikari K, Mendoza-Revilla J, Fuentes-Guajardo M, Silva de Cerqueira CC, Bonfante B, Chacón-Duque JC, Sohail A, Hurtado M, Villegas V, Granja V, Jaramillo C, Arias W, Lozano RB, Everardo-Martínez P, Gómez-Valdés J, Villamil-Ramírez H, Hünemeier T, Ramallo V, Parolin ML, Gonzalez-José R, Schüler-Faccini L, Bortolini MC, Acuña-Alonzo V, Canizales-Quinteros S, Gallo C, Poletti G, Bedoya G, Rothhammer F, Balding D, Faux P, Ruiz-Linares A. Prediction of eye, hair and skin colour in Latin Americans. Forensic Sci Int Genet 2021; 53:102517. [PMID: 33865096 DOI: 10.1016/j.fsigen.2021.102517] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2020] [Revised: 03/19/2021] [Accepted: 03/30/2021] [Indexed: 10/21/2022]
Abstract
Here we evaluate the accuracy of prediction for eye, hair and skin pigmentation in a dataset of > 6500 individuals from Mexico, Colombia, Peru, Chile and Brazil (including genome-wide SNP data and quantitative/categorical pigmentation phenotypes - the CANDELA dataset CAN). We evaluated accuracy in relation to different analytical methods and various phenotypic predictors. As expected from statistical principles, we observe that quantitative traits are more sensitive to changes in the prediction models than categorical traits. We find that Random Forest or Linear Regression are generally the best performing methods. We also compare the prediction accuracy of SNP sets defined in the CAN dataset (including 56, 101 and 120 SNPs for eye, hair and skin colour prediction, respectively) to the well-established HIrisPlex-S SNP set (including 6, 22 and 36 SNPs for eye, hair and skin colour prediction respectively). When training prediction models on the CAN data, we observe remarkably similar performances for HIrisPlex-S and the larger CAN SNP sets for the prediction of hair (categorical) and eye (both categorical and quantitative), while the CAN sets outperform HIrisPlex-S for quantitative, but not for categorical skin pigmentation prediction. The performance of HIrisPlex-S, when models are trained in a world-wide sample (although consisting of 80% Europeans, https://hirisplex.erasmusmc.nl), is lower relative to training in the CAN data (particularly for hair and skin colour). Altogether, our observations are consistent with common variation of eye and hair colour having a relatively simple genetic architecture, which is well captured by HIrisPlex-S, even in admixed Latin Americans (with partial European ancestry). By contrast, since skin pigmentation is a more polygenic trait, accuracy is more sensitive to prediction SNP set size, although here this effect was only apparent for a quantitative measure of skin pigmentation. Our results support the use of HIrisPlex-S in the prediction of categorical pigmentation traits for forensic purposes in Latin America, while illustrating the impact of training datasets on its accuracy.
Collapse
Affiliation(s)
- Sagnik Palmal
- UMR 7268 ADES, CNRS, Aix-Marseille Université, EFS, Faculté de Médecine Timone, Marseille 13005, France
| | - Kaustubh Adhikari
- School of Mathematics and Statistics, Faculty of Science, Technology, Engineering and Mathematics, The Open University, Milton Keynes MK7 6AA, UK; Department of Genetics, Evolution and Environment, and UCL Genetics Institute, University College London, London WC1E 6BT, UK
| | - Javier Mendoza-Revilla
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú; Unit of Human Evolutionary Genetics, Institut Pasteur, Paris 75015, France
| | - Macarena Fuentes-Guajardo
- Departamento de Tecnología Médica, Facultad de Ciencias de la Salud, Universidad de Tarapacá, Arica 1000000, Chile
| | | | - Betty Bonfante
- UMR 7268 ADES, CNRS, Aix-Marseille Université, EFS, Faculté de Médecine Timone, Marseille 13005, France
| | - Juan Camilo Chacón-Duque
- Division of Vertebrates and Anthropology, Department of Earth Sciences, Natural History Museum, London SW7 5BD, UK
| | - Anood Sohail
- Department of Biotechnology, Kinnaird College for Women, 93 - Jail Road, Lahore 54000, Pakistan
| | - Malena Hurtado
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú
| | - Valeria Villegas
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú
| | - Vanessa Granja
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú
| | - Claudia Jaramillo
- Department of Biotechnology, Kinnaird College for Women, 93 - Jail Road, Lahore 54000, Pakistan; GENMOL (Genética Molecular), Universidad de Antioquia, Medellín 5001000, Colombia
| | - William Arias
- GENMOL (Genética Molecular), Universidad de Antioquia, Medellín 5001000, Colombia
| | - Rodrigo Barquera Lozano
- National Institute of Anthropology and History, Mexico City 6600, Mexico; Department of Archaeogenetics, Max Planck Institute for the Science of Human History (MPI-SHH), Jena 07745, Germany
| | | | - Jorge Gómez-Valdés
- National Institute of Anthropology and History, Mexico City 6600, Mexico
| | - Hugo Villamil-Ramírez
- Unidad de Genomica de Poblaciones Aplicada a la Salud, Facultad de Química, UNAM-Instituto Nacional de Medicina Genómica, Mexico City 4510, Mexico
| | - Tábita Hünemeier
- Departamento de Genética e Biologia Evolutiva, Instituto de Biociências, Universidade de São Paulo, São Paulo, SP 05508-090, Brazil
| | - Virginia Ramallo
- Departamento de Genética, Universidade Federal do Rio Grande do Sul, Porto Alegre 90040-060, Brazil; Instituto Patagónico de Ciencias Sociales y Humanas, Centro Nacional Patagónico, CONICET, Puerto Madryn U9129ACD, Argentina
| | - Maria-Laura Parolin
- Instituto de Diversidad y Evolución Austral (IDEAus), Centro Nacional Patagónico, CONICET, Puerto Madryn, Argentina
| | - Rolando Gonzalez-José
- Instituto Patagónico de Ciencias Sociales y Humanas, Centro Nacional Patagónico, CONICET, Puerto Madryn U9129ACD, Argentina
| | - Lavinia Schüler-Faccini
- Departamento de Genética, Universidade Federal do Rio Grande do Sul, Porto Alegre 90040-060, Brazil
| | - Maria-Cátira Bortolini
- Departamento de Genética, Universidade Federal do Rio Grande do Sul, Porto Alegre 90040-060, Brazil
| | | | - Samuel Canizales-Quinteros
- Unidad de Genomica de Poblaciones Aplicada a la Salud, Facultad de Química, UNAM-Instituto Nacional de Medicina Genómica, Mexico City 4510, Mexico
| | - Carla Gallo
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú
| | - Giovanni Poletti
- Laboratorios de Investigación y Desarrollo, Facultad de Ciencias y Filosofía, Universidad Peruana Cayetano Heredia, Lima 31, Perú
| | - Gabriel Bedoya
- GENMOL (Genética Molecular), Universidad de Antioquia, Medellín 5001000, Colombia
| | - Francisco Rothhammer
- Instituto de Alta Investigación, Universidad de Tarapacá, Arica 1000000, Chile; Programa de Genetica Humana, ICBM, Facultad de Medicina, Universidad de Chile, Santiago, Arica 1000000, Chile
| | - David Balding
- Department of Genetics, Evolution and Environment, and UCL Genetics Institute, University College London, London WC1E 6BT, UK; Melbourne Integrative Genomics, Schools of BioSciences and Mathematics & Statistics, University of Melbourne, Melbourne, VIC 3010, Australia
| | - Pierre Faux
- UMR 7268 ADES, CNRS, Aix-Marseille Université, EFS, Faculté de Médecine Timone, Marseille 13005, France.
| | - Andrés Ruiz-Linares
- UMR 7268 ADES, CNRS, Aix-Marseille Université, EFS, Faculté de Médecine Timone, Marseille 13005, France; Department of Genetics, Evolution and Environment, and UCL Genetics Institute, University College London, London WC1E 6BT, UK; Ministry of Education Key Laboratory of Contemporary Anthropology and Collaborative Innovation Center of Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Yangpu District, Shanghai, China.
| |
Collapse
|
6
|
Yardman-Frank JM, Fisher DE. Skin pigmentation and its control: From ultraviolet radiation to stem cells. Exp Dermatol 2020; 30:560-571. [PMID: 33320376 DOI: 10.1111/exd.14260] [Citation(s) in RCA: 63] [Impact Index Per Article: 15.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
In the light of substantial discoveries in epithelial and hair pigmentation pathophysiology, this review summarizes the current understanding of skin pigmentation mechanisms. Melanocytes are pigment-producing cells, and their key regulating transcription factor is the melanocyte-specific microphthalmia-associated transcription factor (m-MITF). Ultraviolet (UV) radiation is a unique modulator of skin pigmentation influencing tanning pathways. The delayed tanning pathway occurs as UVB produces keratinocyte DNA damage, causing p53-mediated expression of the pro-opiomelanocortin (POMC) gene that is processed to release α-melanocyte-stimulating hormone (α-MSH). α-MSH stimulates the melanocortin 1 receptor (MC1R) on melanocytes, leading to m-MITF expression and melanogenesis. POMC cleavage also releases β-endorphin, which creates a neuroendocrine pathway that promotes UV-seeking behaviours. Mutations along the tanning pathway can affect pigmentation and increase the risk of skin malignancies. MC1R variants have received considerable attention, yet the allele is highly polymorphic with varied phenotypes. Vitiligo presents with depigmented skin lesions due to autoimmune destruction of melanocytes. UVB phototherapy stimulates melanocyte stem cells in the hair bulge to undergo differentiation and upwards migration resulting in perifollicular repigmentation of vitiliginous lesions, which is under sophisticated signalling control. Melanocyte stem cells, normally quiescent, undergo cyclic activation/differentiation and downward migration with the hair cycle, providing pigment to hair follicles. Physiological hair greying results from progressive loss of melanocyte stem cells and can be accelerated by acute stress-induced, sympathetic driven hyperproliferation of the melanocyte stem cells. Ultimately, by reviewing the pathways governing epithelial and follicular pigmentation, numerous areas of future research and potential points of intervention are highlighted.
Collapse
Affiliation(s)
| | - David E Fisher
- Department of Dermatology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| |
Collapse
|