Deep Learning for Musculoskeletal Force Prediction

Abstract

Musculoskeletal models permit the determination of internal forces acting during dynamic movement, which is clinically useful, but traditional methods may suffer from slowness and a need for extensive input data. Recently, there has been interest in the use of supervised learning to build approximate models for computationally demanding processes, with benefits in speed and flexibility. Here, we use a deep neural network to learn the mapping from movement space to muscle space. Trained on a set of kinematic, kinetic and electromyographic measurements from 156 subjects during gait, the network's predictions of internal force magnitudes show good concordance with those derived by musculoskeletal modelling. In a separate set of experiments, training on data from the most widely known benchmarks of modelling performance, the international Grand Challenge competitions, generates predictions that better those of the winning submissions in four of the six competitions. Computational speedup facilitates incorporation into a lab-based system permitting real-time estimation of forces, and interrogation of the trained neural networks provides novel insights into population-level relationships between kinematic and kinetic factors.

http://bit.ly/2RpnIIK

Extinction and the Rise of the Dinosaurs

Paleontologists are still puzzling over why dinosaurs succeeded while crocodile cousins faded away.

-- Read more on ScientificAmerican.com

from ! Human Diseases via Alexandros G.Sfakianakis on Inoreader http://bit.ly/2TfktAS

The Dinosaur Who Went Out to Sea

The skeleton of a new carnivorous dinosaur bears damage caused by seagoing invertebrates.

-- Read more on ScientificAmerican.com

from ! Human Diseases via Alexandros G.Sfakianakis on Inoreader http://bit.ly/2CHs2uR

The ESCRT and autophagy machineries cooperate to repair ESX-1-dependent damage at the Mycobacterium-containing vacuole but have opposite impact on containing the infection

by Ana T. López-Jiménez, Elena Cardenal-Muñoz, Florence Leuba, Lilli Gerstenmaier, Caroline Barisch, Monica Hagedorn, Jason S. King, Thierry Soldati

Phagocytic cells capture and kill most invader microbes within the bactericidal phagosome, but some pathogens subvert killing by damaging the compartment and escaping to the cytosol. To prevent the leakage of pathogen virulence and host defence factors, as well as bacteria escape, host cells have to contain and repair the membrane damage, or finally eliminate the cytosolic bacteria. All eukaryotic cells engage various repair mechanisms to ensure plasma membrane integrity and proper compartmentalization of organelles, including the Endosomal Sorting Complex Required for Transport (ESCRT) and autophagy machineries. We show that during infection of Dictyostelium discoideum with Mycobacterium marinum, the ESCRT-I component Tsg101, the ESCRT-III protein Snf7/Chmp4/Vps32 and the AAA-ATPase Vps4 are recruited to sites of damage at the Mycobacterium-containing vacuole. Interestingly, damage separately recruits the ESCRT and the autophagy machineries. In addition, the recruitment of Vps32 and Vps4 to repair sterile membrane damage depends on Tsg101 but appears independent of Ca²⁺. Finally, in absence of Tsg101, M. marinum accesses prematurely the cytosol, where the autophagy machinery restricts its growth. We propose that ESCRT has an evolutionary conserved function to repair small membrane damage and to contain intracellular pathogens in intact compartments.

from Genes Mutations Carcinogenesis via alexandrossfakianakis on Inoreader http://bit.ly/2EWA98l

Diversification of DNA binding specificities enabled SREBP transcription regulators to expand the repertoire of cellular functions that they govern in fungi

by Valentina del Olmo Toledo, Robert Puccinelli, Polly M. Fordyce, J. Christian Pérez

The Sterol Regulatory Element Binding Proteins (SREBPs) are basic-helix-loop-helix transcription regulators that control the expression of sterol biosynthesis genes in higher eukaryotes and some fungi. Surprisingly, SREBPs do not regulate sterol biosynthesis in the ascomycete yeasts (Saccharomycotina) as this role was handed off to an unrelated transcription regulator in this clade. The SREBPs, nonetheless, expanded in fungi such as the ascomycete yeasts Candida spp., raising questions about their role and evolution in these organisms. Here we report that the fungal SREBPs diversified their DNA binding preferences concomitantly with an expansion in function. We establish that several branches of fungal SREBPs preferentially bind non-palindromic DNA sequences, in contrast to the palindromic DNA motifs recognized by most basic-helix-loop-helix proteins (including SREBPs) in higher eukaryotes. Reconstruction and biochemical characterization of the likely ancestor protein suggest that an intrinsic DNA binding promiscuity in the family was resolved by alternative mechanisms in different branches of fungal SREBPs. Furthermore, we show that two SREBPs in the human commensal yeast Candida albicans drive a transcriptional cascade that inhibits a morphological switch under anaerobic conditions. Preventing this morphological transition enhances C. albicans colonization of the mammalian intestine, the fungus' natural niche. Thus, our results illustrate how diversification in DNA binding preferences enabled the functional expansion of a family of eukaryotic transcription regulators.

from Genes Mutations Carcinogenesis via alexandrossfakianakis on Inoreader http://bit.ly/2QfqZWn

Bayesian multiple logistic regression for case-control GWAS

by Saikat Banerjee, Lingyao Zeng, Heribert Schunkert, Johannes Söding

Genetic variants in genome-wide association studies (GWAS) are tested for disease association mostly using simple regression, one variant at a time. Standard approaches to improve power in detecting disease-associated SNPs use multiple regression with Bayesian variable selection in which a sparsity-enforcing prior on effect sizes is used to avoid overtraining and all effect sizes are integrated out for posterior inference. For binary traits, the logistic model has not yielded clear improvements over the linear model. For multi-SNP analysis, the logistic model required costly and technically challenging MCMC sampling to perform the integration. Here, we introduce the quasi-Laplace approximation to solve the integral and avoid MCMC sampling. We expect the logistic model to perform much better than multiple linear regression except when predicted disease risks are spread closely around 0.5, because only close to its inflection point can the logistic function be well approximated by a linear function. Indeed, in extensive benchmarks with simulated phenotypes and real genotypes, our Bayesian multiple LOgistic REgression method (B-LORE) showed considerable improvements (1) when regressing on many variants in multiple loci at heritabilities ≥ 0.4 and (2) for unbalanced case-control ratios. B-LORE also enables meta-analysis by approximating the likelihood functions of individual studies by multivariate normal distributions, using their means and covariance matrices as summary statistics. Our work should make sparse multiple logistic regression attractive also for other applications with binary target variables. B-LORE is freely available from: http://bit.ly/2Qfr1gX.

from Genes Mutations Carcinogenesis via alexandrossfakianakis on Inoreader http://bit.ly/2Vp2hH9

Genetic regulation of the placental transcriptome underlies birth weight and risk of childhood obesity

by Shouneng Peng, Maya A. Deyssenroth, Antonio F. Di Narzo, Haoxiang Cheng, Zhongyang Zhang, Luca Lambertini, Arno Rusualepp, Jason C. Kovacic, Johan L. M. Bjorkegren, Carmen J. Marsit, Jia Chen, Ke Hao

GWAS identified variants associated with birth weight (BW), childhood obesity (CO) and childhood BMI (CBMI), and placenta is a critical organ for fetal development and postnatal health. We examined the role of placental transcriptome and eQTLs in mediating the genetic causes for BW, CO and CBMI, and applied integrative analysis (Colocalization and MetaXcan). GWAS loci associated with BW, CO, and CBMI were substantially enriched for placenta eQTLs (6.76, 4.83 and 2.26 folds, respectively). Importantly, compared to eQTLs of adult tissues, only placental eQTLs contribute significantly to both anthropometry outcomes at birth (BW) and childhood phenotypes (CO/CBMI). Eight, six and one transcripts colocalized with BW, CO and CBMI risk loci, respectively. Our study reveals that placental transcription in utero likely plays a key role in determining postnatal body size, and as such may hold new possibilities for therapeutic interventions to prevent childhood obesity.

from Genes Mutations Carcinogenesis via alexandrossfakianakis on Inoreader http://bit.ly/2Vg08xj