Biology subjects

Balewski, J.

Publications and source records attributed to Balewski, J..

3 recordsLinked to original sources

bioRxiv2021

Deeplasmid: Deep learning accurately separates plasmids from bacterial chromosomes

Plasmids are mobile genetic elements that play a key role in microbial ecology and evolution by mediating horizontal transfer of important genes, such as antimicrobial resistance genes. Many microbial genomes have been sequenced by short read sequencers and have resulted in a mix of contigs that derive from plasmids or chromosomes. New tools that accurately identify plasmids are needed to elucidate new plasmid-borne genes of high biological importance. We have developed Deeplasmid, a deep learning tool for distinguishing plasmids from bacterial chromosomes based on the DNA sequence and its encoded biological data. It requires as input only assembled sequences generated by any sequencing platform and assembly algorithm and its runtime scales linearly with the number of assembled sequences. Deeplasmid achieves an AUC-ROC of over 93%, and it was much more precise than the state-of-the-art methods. Finally, as a proof of concept, we used Deeplasmid to predict new plasmids in the fish pathogen Yersinia ruckeri ATCC 29473 that has no annotated plasmids. Deeplasmid predicted with high reliability that a long assembled contig is part of a plasmid. Using long read sequencing we indeed validated the existence of a 102 Kbp long plasmid, demonstrating Deeplasmids ability to detect novel plasmids. AvailabilityThe software is available with a BSD license: deeplasmid.sourceforge.io. A Docker container is available on DockerHub under: billandreo/deeplasmid. Contactwandreopoulos@lbl.gov alevy@mail.huji.ac.il

bioinformatics↗

bioRxiv2019

Inferring neuronal ionic conductances from membrane potentials using CNNs

The neuron is the fundamental unit of computation in the nervous system, and different neuron types produce different temporal patterns of voltage fluctuations in response to input currents. Understanding the mechanism of single neuron firing patterns requires accurate knowledge of the spatial densities of diverse ion channels along the membrane. However, direct measurements of these microscopic variables are difficult to obtain experimentally. Alternatively, one can attempt to infer those microscopic variables from the membrane potential (a mesoscopic variable), or features thereof, which are more experimentally tractable. One approach in this direction is to infer the ionic densities as parameters of a neuronal model. Traditionally this is done using a Multi-Objective Optimization (MOO) method to minimize the differences between features extracted from a simulated neurons membrane potential and the same features extracted from target data. Here, we use Convolutional Neural Networks (CNNs) to directly regress generative parameters (e.g., ionic conductances, membrane resistance, etc.,) from simulated time-varying membrane potentials in response to an input stimulus. We simulated diverse neuron models of increasing complexity (Izikivich: 4 parameters; Hodgkin-Huxley: 7 parameters; Mainen-Sejnowski: 10 parameters) with a large range of variation in the underlying parameter values. We show that hyperparameter optimized CNNs can accurately infer the values of generative variables for these neuron models, and that these results far surpass the previous state-of-the-art method (MOO). We discuss the benefits of optimizing the CNN architecture, improvements in accuracy with additional training data, and some observed limitations. Based on these results, we propose that CNNs may be able to infer the spatial distribution of diverse ionic densities from spatially resolved measurements of neuronal membrane potentials (e.g. voltage imaging).

neuroscience↗

bioRxiv2019

Accurate prediction of bacterial two-component signaling with a deep recurrent neural network ORAKLE

Two-component systems (2CS) are a primary method that bacteria use to detect and respond to environmental stimuli. Receptor histidine kinases (HK) detect an environmental signal, activating the appropriate response regulator (RR). Genes for such cognate HK-RR pairs are often located proximally on the chromosome, allowing easier identification of the target for a particular signal. However, almost half of all HK and RR proteins are orphans, with no nearby partner, complicating identification of the proteins that respond to a particular signal. To address this problem, we trained a neural network on the amino acid sequences of known 2CS pairs. Next, we developed a recommender algorithm that ranks a set of HKs for an arbitrary fixed RR and arbitrary species whose amino acid sequences are known. The recommender strongly favors known 2CS pairs, and correctly selects orphan pairs in Escherichia coli. We expect that use of these results will permit rapid discovery of orphan HK-RR pairs.

bioinformatics↗