Research paper| Volume 25, P10-18, November 2016

Teaching artificial intelligence to read electropherograms


      • Considerable human resource is dedicated to interpreting electropherograms in forensic biology facilities.
      • Artificial neural networks are a powerful tool that can be used to recognise patterns and classify data.
      • We demonstrate an artificial neural network trained to ‘read’ electropherograms and show it generalised to unseen profiles.
      • There is potential for the use of artificial neural networks to be extended to reading complex, mixed electrophoretic data.


      Electropherograms are produced in great numbers in forensic DNA laboratories as part of everyday criminal casework. Before the results of these electropherograms can be used they must be scrutinised by analysts to determine what the identified data tells us about the underlying DNA sequences and what is purely an artefact of the DNA profiling process. A technique that lends itself well to such a task of classification in the face of vast amounts of data is the use of artificial neural networks. These networks, inspired by the workings of the human brain, have been increasingly successful in analysing large datasets, performing medical diagnoses, identifying handwriting, playing games, or recognising images. In this work we demonstrate the use of an artificial neural network which we train to ‘read’ electropherograms and show that it can generalise to unseen profiles.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Forensic Science International: Genetics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Perlin M.W.
        • Legler M.M.
        • Spencer C.E.
        • Smith J.L.
        • Allan W.P.
        • Belrose J.L.
        • et al.
        Validating TrueAllele® DNA mixture interpretation.
        J. Forensic Sci. 2011; 56: 1430-1447
        • Taylor D.
        • Bright J.-A.
        • Buckleton J.
        The interpretation of single source and mixed DNA profiles.
        Forensic Sci. Int. Genet. 2013; 7: 516-528
        • Goor R.M.
        • Neall L.F.
        • Hoffman D.
        • Sherry S.T.
        A mathematical approach to the analysis of multiplex DNA profiles.
        Bull. Math. Biol. 2010; 73: 1909-1931
        • Mohammed O.
        • Assaleh K.T.
        • Husseini G.A.
        • Majdalawieh A.F.
        • Woodward S.R.
        Novel algorithms for accurate DNA base-calling.
        J. Biomed. Sci. Eng. 2013; 6: 165-174
      1. V. Boža, B. Brejová, T. Vinař, Deepnano: Deep Recurrent Neural Networks for Base Calling in Minion Nanopore Reads, ArXiv: 160309195v1 [q-bioGN], 2016.

        • Turan M.K.
        • Elen A.
        • Sehirli E.
        Analysis of DNA gel electrophoresis images with backpropogation neural network based Canny edge detection algorithm.
        Int. J. Sci. Technol. Res. 2016; 2: 55-63
        • Azevedo F.
        • Carvalho L.
        • Grinberg L.
        • Farfel J.M.
        • Ferretti R.
        • Leite R.
        • et al.
        Equal numbers of neuronal and nonneuronal cells make the human brain an isometrically scaled-up primate brain.
        J. Comp. Neurol. 2009; 513: 532-541
      2. A. Trask, D. Gilmore, M. Russell, Modeling Order in Neural Word Embedding at Scale, arXiv: 150602338v3 [csCL], 2015.

      3. D. Powers, A. Atyabi, The problem of Cross-Validation: Averaging and Bias, Repetition and Significance Engineering and Technology (S-CET), Spring congress on. 2012, IEEE, 1–5.

        • Witten I.
        • Frank E.
        • Hall M.
        Credibility: Evaluating What's Been Learned Data Mining Practical Machine Learning Tools and Techniques.
        Elsevier Inc., Burlington, USA2011 (Chapter 5)
        • LeCunn Y.
        • Bottou L.
        • Bengio Y.
        • Haffner P.
        Gradient-based learning applied to document recognition.
        Proc. IEEE. 1998; 86: 2278-2344
        • Glorot X.
        • Bordes A.
        • Bengio Y.
        Deep sparse rectifier neural networks.
        Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS-11). 2011; : 315-323
      4. M. Plummer, Bayesian graphical models using MCMC, 2012. rjags.

        • Powers D.
        Evaluation: from precision, recall and F-measure to ROC, informedness, markedness & correlation.
        J. Mach. Learn. Technol. 2011; 2: 37-63
        • Powers D.
        Evaluation evaluation a monte carlo study.
        European Conference on Artifical Intelligence. 2008; (ArXiv: 150400854 [csAl])