%0 Journal Article %1 rosen2019averagecase %A Rosen, Y M %A Paten, B J %D 2019 %J Algorithms Mol Biol %K HMM Li_and_Stephens algorithms genome_data haplotype_inference methods %P 11-11 %R 10.1186/s13015-019-0144-9 %T An average-case sublinear forward algorithm for the haploid Li and Stephens model %U https://pubmed.ncbi.nlm.nih.gov/30988694/ %V 14 %X Hidden Markov models of haplotype inheritance such as the Li and Stephens model allow for computationally tractable probability calculations using the forward algorithm as long as the representative reference panel used in the model is sufficiently small. Specifically, the monoploid Li and Stephens model and its variants are linear in reference panel size unless heuristic approximations are used. However, sequencing projects numbering in the thousands to hundreds of thousands of individuals are underway, and others numbering in the millions are anticipated.To make the forward algorithm for the haploid Li and Stephens model computationally tractable for these datasets, we have created a numerically exact version of the algorithm with observed average case sublinear runtime with respect to reference panel size k when tested against the 1000 Genomes dataset.We show a forward algorithm which avoids any tradeoff between runtime and model complexity. Our algorithm makes use of two general strategies which might be applicable to improving the time complexity of other future sequence analysis algorithms: sparse dynamic programming matrices and lazy evaluation.

@article{rosen2019averagecase, abstract = {Hidden Markov models of haplotype inheritance such as the Li and Stephens model allow for computationally tractable probability calculations using the forward algorithm as long as the representative reference panel used in the model is sufficiently small. Specifically, the monoploid Li and Stephens model and its variants are linear in reference panel size unless heuristic approximations are used. However, sequencing projects numbering in the thousands to hundreds of thousands of individuals are underway, and others numbering in the millions are anticipated.To make the forward algorithm for the haploid Li and Stephens model computationally tractable for these datasets, we have created a numerically exact version of the algorithm with observed average case sublinear runtime with respect to reference panel size k when tested against the 1000 Genomes dataset.We show a forward algorithm which avoids any tradeoff between runtime and model complexity. Our algorithm makes use of two general strategies which might be applicable to improving the time complexity of other future sequence analysis algorithms: sparse dynamic programming matrices and lazy evaluation.}, added-at = {2020-07-02T19:48:43.000+0200}, author = {Rosen, Y M and Paten, B J}, biburl = {https://www.bibsonomy.org/bibtex/27e23b7b54ff299820b39d6c10d747378/peter.ralph}, doi = {10.1186/s13015-019-0144-9}, interhash = {a75738ef619cdbde2584eef93b80507b}, intrahash = {7e23b7b54ff299820b39d6c10d747378}, journal = {Algorithms Mol Biol}, keywords = {HMM Li_and_Stephens algorithms genome_data haplotype_inference methods}, pages = {11-11}, pmid = {30988694}, timestamp = {2020-07-02T19:48:43.000+0200}, title = {An average-case sublinear forward algorithm for the haploid {Li} and {Stephens} model}, url = {https://pubmed.ncbi.nlm.nih.gov/30988694/}, volume = 14, year = 2019 }