Biology subjects

Urban, G.

Publications and source records attributed to Urban, G..

3 recordsLinked to original sources

bioRxiv2020

Deep Semi-Supervised Learning Improves Universal Peptide Identification of Shotgun Proteomics Data

Semi-supervised machine learning post-processors critically improve peptide identification of shot-gun proteomics data. Such post-processors accept the peptide-spectrum matches (PSMs) and feature vectors resulting from a database search, train a machine learning classifier, and recalibrate PSMs using the trained parameters, often yielding significantly more identified peptides across q-value thresholds. However, current state-of-the-art post-processors rely on shallow machine learning methods, such as support vector machines. In contrast, the powerful training capabilities of deep learning models have displayed superior performance to shallow models in an ever-growing number of other fields. In this work, we show that deep models significantly improve the recalibration of PSMs compared to the most accurate and widely-used post-processors, such as Percolator and PeptideProphet. Furthermore, we show that deep learning is able to adaptively analyze complex datasets and features for more accurate universal post-processing, leading to both improved Prosit analysis and markedly better recalibration of recently developed database-search functions.

bioinformatics↗

bioRxiv2020

Protein Profiles: Biases and Protocols

The use of evolutionary profiles to predict protein secondary structure, as well as other protein structural features, has been standard practice since the 1990s. Using profiles in the input of such predictors, in place or in addition to the sequence itself, leads to significantly more accurate predictors. While profiles can enhance structural signals, their role remains somewhat surprising as proteins do not use profiles when folding in vivo. Furthermore, the same sequence-based redundancy reduction protocols initially derived to train and evaluate sequence-based predictors, have been applied to train and evaluate profile-based predictors. This can lead to unfair comparisons since profile may facilitate the bleeding of information between training and test sets. Here we use the extensively studied problem of secondary structure prediction to better evaluate the role of profiles and show that: (1) high levels of profile similarity between training and test proteins are observed when using standard sequence-based redundancy protocols; (2) the gain in accuracy for profile-based predictors, over sequence-based predictors, strongly relies on these high levels of profile similarity between training and test proteins; and (3) the overall accuracy of a profile-based predictor on a given protein dataset provides a biased measure when trying to estimate the actual accuracy of the predictor, or when comparing it to other predictors. We show, however, that this bias can be avoided by implementing a new protocol (EVALpro) which evaluates the accuracy of profile-based predictors as a function of the profile similarity between training and test proteins. Such a protocol not only allows for a fair comparison of the predictors on equally hard or easy examples, but also completely removes the need for selecting arbitrary similarity cutoffs when selecting test proteins. The EVALpro program is available for download from the SCRATCH suite (http://scratch.proteomics.ics.uci.edu).

bioinformatics↗

bioRxiv2020

Long-term in vivo Monitoring of Gliotic Sheathing of Ultrathin Entropic Coated Brain Microprobes with Fiber-based Optical Coherence Tomography

Microfabricated neuroprosthetic devices have made possible important observations on neuron activity; however, long-term high-fidelity recording performance of these devices has yet to be realized. Tissue-device interactions appear to be a primary source of lost recording performance. The current state of the art for visualizing the tissue response surrounding brain implants in animals is Immunohistochemistry + Confocal Microscopy, which is mainly performed after sacrificing the animal. Monitoring the tissue response as it develops could reveal important features of the response which may inform improvements in electrode design. Optical Coherence Tomography (OCT), an imaging technique commonly used in ophthalmology, has already been adapted for imaging of brain tissue. Here, we use OCT to achieve real-time, in vivo monitoring of the tissue response surrounding chronically implanted neural devices. The employed tissue-response-provoking implants are coated with a plasma-deposited nanofilms, which have been demonstrated as a biocompatible and anti-inflammatory interface for indwelling devices. We evaluate the method by comparing the OCT results to traditional histology qualitatively and quantitatively. The differences in OCT signal across the implantation period between the plasma group and the control reveal that the Parylene-type coating of otherwise rigid brain probes (glass and silicon) does not improve the glial encapsulation in the brain parenchyma.

bioengineering↗