Biology subjects

Huang, P.-Y.

Publications and source records attributed to Huang, P.-Y..

4 recordsLinked to original sources

bioRxiv2018

Small Data Challenge: Structural Analysis and Optimization of Convolutional Neural Networks with a Small Sample Size

Deep neural networks have gained immense popularity in the Big Data problem; however, the availability of training samples can be relatively limited in certain application domains, particularly medical imaging, and consequently leading to overfitting problems. This \"Small Data\" challenge may need a mindset that is entirely different from the existing Big Data paradigm. Here, under the small data setting, we examined whether the network structure has a substantial influence on the performance and whether the optimal structure is predominantly determined by sample size or data nature. To this end, we listed all possible combinations of layers given an upper bound of the VC-dimension to study how structural hyperparameters affected the performance. Our results showed that structural optimization improved accuracy by 27.99%, 16.44%, and 13.11% over random selection for a sample size of 100, 500, and 1,000 in the MNIST dataset, respectively, suggesting that the importance of the network structure increases as the sample size becomes smaller. Furthermore, the optimal network structure was mostly determined by the data nature (photographic, calligraphic, or medical images), and less affected by the sample size, suggesting that the optimal network structure is data-driven, not sample size driven. After network structure optimization, the conventional convolutional neural network could achieve 91.13% in accuracy with only 500 samples, 93.66% in accuracy with only 1000 samples for the MNIST dataset and 94.10% in accuracy with only 3300 samples for the Mitosis (microscopic) dataset. These results indicate the primary importance of the network structure and the nature of the data in facing the Small Data challenge.

bioengineering↗

bioRxiv2018

Small effect size leads to reproducibility failure in resting-state fMRI studies

Thousands of papers using resting-state functional magnetic resonance imaging (RS-fMRI) have been published on brain disorders. Results in each paper may have survived correction for multiple comparison. However, since there have been no robust results from large scale meta-analysis, we do not know how many of published results are truly positives. The present meta-analytic work included 60 original studies, with 57 studies (4 datasets, 2266 participants) that used a between-group design and 3 studies (1 dataset, 107 participants) that employed a within-group design. To evaluate the effect size of brain disorders, a very large neuroimaging dataset ranging from neurological to psychiatric isorders together with healthy individuals have been analyzed. Parkinsons disease off levodopa (PD-off) included 687 participants from 15 studies. PD on levodopa (PD-on) included 261 participants from 9 studies. Autism spectrum disorder (ASD) included 958 participants from 27 studies. The meta-analyses of a metric named amplitude of low frequency fluctuation (ALFF) showed that the effect size (Hedges g) was 0.19 - 0.39 for the 4 datasets using between-group design and 0.46 for the dataset using within-group design. The effect size of PD-off, PD-on and ASD were 0.23, 0.39, and 0.19, respectively. Using the meta-analysis results as the robust results, the between-group design results of each study showed high false negative rates (median 99%), high false discovery rates (median 86%), and low accuracy (median 1%), regardless of whether stringent or liberal multiple comparison correction was used. The findings were similar for 4 RS-fMRI metrics including ALFF, regional homogeneity, and degree centrality, as well as for another widely used RS-fMRI metric namely seed-based functional connectivity. These observations suggest that multiple comparison correction does not control for false discoveries across multiple studies when the effect sizes are relatively small. Meta-analysis on un-thresholded t-maps is critical for the recovery of ground truth. We recommend that to achieve high reproducibility through meta-analysis, the neuroimaging research field should share raw data or, at minimum, provide un-thresholded statistical images.

neuroscience↗

bioRxiv2017

NINJA-Associated ERF19 Negatively Regulates Arabidopsis Pattern-Triggered Immunity

Recognition of microbe-associated molecular patterns (MAMPs) derived from invading pathogens by plant pattern recognition receptors (PRRs) initiates defense responses known as pattern-triggered immunity (PTI). Transcription factors (TFs) orchestrate the onset of PTI through complex signaling networks. Here, we characterize the function of ERF19, a member of the Arabidopsis thaliana ethylene response factor (ERF) family. ERF19 was found to act as a negative regulator of PTI against Botrytis cinerea and Pseudomonas syringae pv. tomato DC3000 (Pst). Notably, overexpression of ERF19 increased plant susceptibility to these pathogens and repressed MAMP-induced PTI outputs. In contrast, expression of the chimeric dominant repressor ERF19-SRDX boosted PTI activation, conferred increased resistance to B. cinerea, and enhanced elf18-triggered immunity against Pst. Consistent with a negative role of ERF19 in PTI, MAMP-mediated growth inhibition was respectively weakened or augmented in lines overexpressing ERF19 or expressing ERF19-SRDX. Moreover, we demonstrate that the transcriptional repressor Novel INteractor of JAZ (NINJA) associates with and represses the function of ERF19. Our work reveals ERF19 as a key player in a buffering mechanism to avoid defects imposed by over-activation of PTI and a potential role for NINJA in fine-tuning ERF19-mediated regulation.

plant biology↗

bioRxiv2017

Toward D-Peptide Biosynthesis: Elongation Factor P Enables Ribosomal Incorporation Of Consecutive D-Amino Acids

To maintain stereospecific biochemistry in cells, living organisms have evolved mechanisms to exclude D-amino acids (DAA) in their protein synthesis machinery, which also limits our exploration of the realm of mirror-image molecules. Here, we show that high affinity between EF-Tu and aminoacyl-tRNA promotes D-amino acid incorporation. More strikingly, Elongation Factor P efficiently resolves peptidyl transferase stalling between two consecutive D-amino acids, and hence enables the translation of D-peptides.

biochemistry↗