Biology subjects

Si, D.

Publications and source records attributed to Si, D..

5 recordsLinked to original sources

bioRxiv2019

Automated Threshold Selection for Cryo-EM Density Maps

Recent advances in cryo-EM have made it possible to create protein density maps with a near-atomic resolution. This has contributed to its wide popularity, resulting in a rapidly growing number of available cryo-EM density maps. In order to computationally process them, an electron density threshold level is required which defines a lower bound for density values. In the context of this paper the threshold level is required in a pre-processing step of the backbone structure prediction project which predicts the location of C atoms of the backbone of a protein based on its cryo-EM density map using deep learning techniques. A custom threshold level has to be selected for each prediction in order to reduce noise that could irritate the deep learning model. Automatizing this threshold selection process makes it easier to run predictions as well as it removes the dependency of the prediction accuracy to the ability of someone to choose the right threshold value. This paper presents a method to automatize the threshold selection for the previously mentioned project as well as for other problems which require a density threshold level. The method uses the surface area to volume ratio and the ratio of voxels that lie above the threshold level to non-zero voxels as metrics to derive characteristics about suitable threshold levels based on a training dataset. The threshold level selection was tested by integrating it in the backbone prediction project and evaluating the accuracy of predictions using automatically as well as manually selected thresholds. We found that there was no loss in accuracy using the automatically selected threshold levels indicating that they are equally good as manually selected ones. The source code related to this paper can be found at https://github.com/DrDongSi/Auto-Thresholding.

bioinformatics↗

bioRxiv2019

Toward Broad Spectrum DHFR inhibitors Targeting Trimethoprim Resistant Enzymes Identified in Clinical Isolates of Methicillin-Resistant Staphylococcus aureus

The spread of plasmid borne resistance enzymes in clinical Staphylococcus aureus isolates is rendering trimethoprim and iclaprim, both inhibitors of dihydrofolate reductase (DHFR), ineffective. Continued exploitation of these targets will require compounds that can broadly inhibit these resistance-confering isoforms. Using a structure-based approach, we have developed a novel class of ionized non-classical antifolates (INCAs) that capture the molecular interactions that have been exclusive to classical antifolates. These modifications allow for a greatly expanded spectrum of activity across these pathogenic DHFR isoforms, while maintaining the ability to penetrate the bacterial cell wall. Using biochemical, structural and computational methods, we are able to optimize these inhibitors to the conserved active sites of the endogenous and trimethoprim resistant DHFR enzymes. Here, we report a series of INCA compounds that exhibit low nanomolar enzymatic activity and potent cellular activity with human selectivity against a panel of clinically relevant TMPR MRSA isolates.

biochemistry↗

bioRxiv2019

Cascaded-CNN: Deep Learning to Predict Protein Backbone Structure from High-Resolution Cryo-EM Density Maps

Cryo-electron microscopy (cryo-EM) has become a leading technology for determining protein structures. Recent advances in this field have allowed for atomic resolution. However, predicting the backbone trace of a protein has remained a challenge on all but the most pristine density maps (< 2.5[A] resolution). Here we introduce a deep learning model that uses a set of cascaded convolutional neural networks (CNNs) to predict C atoms along a proteins backbone structure. The cascaded-CNN (C-CNN) is a novel deep learning architecture comprised of multiple CNNs, each predicting a specific aspect of a proteins structure. This model predicts secondary structure elements (SSEs), backbone structure, and C atoms, combining the results of each to produce a complete prediction map. The cascaded-CNN is a semantic segmentation image classifier and was trained using thousands of simulated density maps. This method is largely automatic and only requires a recommended threshold value for each evaluated protein. A specialized tabu-search path walking algorithm was used to produce an initial backbone trace with C placements. A helix-refinement algorithm made further improvements to the -helix SSEs of the backbone trace. Finally, a novel quality assessment-based combinatorial algorithm was used to effectively map C traces to obtain full-atom protein structures. This method was tested on 50 experimental maps between 2.6[A] and 4.4[A] resolution. It outperformed several state-of-the-art prediction methods including RosettaES, MAINMAST, and a Phenix based method by producing the most complete prediction models, as measured by percentage of found C atoms. This method accurately predicted 88.5% (mean) of the C atoms within 3[A] of a proteins backbone structure surpassing the 66.8% mark achieved by the leading alternate method (Phenix based fully automatic method) on the same set of density maps. The C-CNN also achieved an average RMSD of 1.23[A] for all 50 experimental density maps which is similar to the Phenix based fully automatic method. The source code and demo of this research has been published at https://github.com/DrDongSi/Ca-Backbone-Prediction.

molecular biology↗

bioRxiv2019

Artificial Intelligence for Bioinformatics: Applications in Protein Folding Prediction

AI recently shows great promise in the field of bioinformatics, such as protein structure prediction. The Critical Assessment of protein Structure Prediction (CASP) is a nationwide experiment that takes place biannually, which centered around analyzing the best current systems for predicting protein tertiary structures. In this paper, we research on available AI methods and features, and then explore novel methods based on reinforcement learning. Such method will have profound implications for R&D in bioinformatics and add an additional platform to the management of innovation in biotechnology.

bioinformatics↗

bioRxiv2019

AngularQA: Protein Model Quality Assessment with LSTM Networks

Quality Assessment (QA) plays an important role in protein structure prediction. Traditional protein QA methods suffer from searching databases or comparing with other models for making predictions, which usually fail. We propose a novel protein single-model QA method which is built on a new representation that converts raw atom information into a series of carbon-alpha (C) atoms with side-chain information, defined by their dihedral angles and bond lengths to the prior residue. An LSTM network is used to predict the quality by treating each amino acid as a time-step and consider the final value returned by the LSTM cells. To the best of our knowledge, this is the first time anyone has attempted to use an LSTM model on the QA problem; furthermore, we use a new representation which has not been studied for QA. In addition to angles, we make use of sequence properties like secondary structure at each time-step, without using any database. Our model achieves an overall correlation of 0.651 on the CASP12 testing dataset. Our experiment points out new directions for QA problem and our method could be widely used for protein structure prediction problem. The software is freely available at GitHub: https://github.com/caorenzhi/AngularQA

bioinformatics↗