A5090775265- Genomics and Phylogenetic Studies
- Microbial Natural Products and Biosynthesis
- RNA and protein synthesis mechanisms
- Machine Learning in Bioinformatics
- Antimicrobial Peptides and Activities
- Bioinformatics and Genomic Networks
- Probiotics and Fermented Foods
- Biochemical and Structural Characterization
- Gene expression and cancer classification
- Blockchain Technology Applications and Security
- Transportation and Mobility Innovations
- Mass Spectrometry Techniques and Applications
- Antibiotics Pharmacokinetics and Efficacy
- Sharing Economy and Platforms
- Ferroptosis and cancer prognosis
- Genetics, Bioinformatics, and Biomedical Research
- Antibiotic Resistance in Bacteria
- Biomedical Text Mining and Ontologies
- FinTech, Crowdfunding, Digital Finance
- Pneumonia and Respiratory Infections
- Machine Learning in Materials Science
Iowa State University
2017-2020
Ames National Laboratory
2018
Abstract Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation protein function. Results Here, we report on results third CAFA challenge, CAFA3, that featured expanded analysis over previous rounds, both in terms volume data analyzed types performed. In a novel major new development, predictions assessment goals drove some experimental assays, resulting functional annotations for...
Antibiotic resistance constitutes a major public health crisis, and finding new sources of antimicrobial drugs is crucial to solving it. Bacteriocins, which are bacterially produced peptide products, candidates for broadening the available choices antimicrobials. However, discovery bacteriocins by genomic mining hampered their sequences' low complexity high variance, frustrates sequence similarity-based searches.
Bacteriocins, the ribosomally produced antimicrobial peptides of bacteria, represent an untapped source promising antibiotic alternatives. However, bacteriocins display diverse mechanisms action, a narrow spectrum activity, and inherent challenges in natural product isolation making vitro verification putative difficult. A subset exert their effects through favorable biophysical interactions with bacterial membrane mediated by charge, hydrophobicity, conformation peptide. We have developed...
Abstract The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation protein function. Here we report on results third CAFA challenge, CAFA3, that featured expanded analysis over previous rounds, both in terms volume data analyzed types performed. In a novel major new development, predictions assessment goals drove some experimental assays, resulting functional annotations for more than 1000...
Abstract Antibiotic resistance constitutes a major public health crisis, and finding new sources of antimicrobial drugs is crucial to solving it. Bacteriocins, which are bacterially-produced peptide products, candidates for broadening the available choices an-timicrobials. However, discovery bacteriocins by genomic mining hampered their sequences’ low complexity high variance, frustrates sequence similarity-based searches. Here we use word embeddings protein sequences represent bacteriocins,...
Abstract Motivation Antibiotic resistance is a growing public health problem, which affects millions of people worldwide, and if left unchecked expected to upend many aspects healthcare as it practiced today. Identifying the type antibiotic resistant genes in genome metagenomic sample utmost importance prevention, diagnosis, treatment infections. Today there are multiple tools available that predict class from DNA protein sequences, yet lack benchmarks on performances these tools. Results We...
Abstract Ribosomally synthesized and post-translationally modified peptides (RiPPs) are an important class of natural products that include many antibiotics a variety other bioactive compounds. While recent breakthroughs in RiPP discovery raised the challenge developing new algorithms for their analysis, peptidogenomic-based identification RiPPs by combining genome/metagenome mining with analysis tandem mass spectra remains open problem. We present here MetaRiPPquest, software tool...
Abstract Bacteriocins are ribosomally produced antimicrobial peptides that represent an untapped source of promising antibiotic alternatives. However, inherent challenges in isolation and identification natural bacteriocins substantial yield have limited their potential use as viable compounds. In this study, we developed overall pipeline for bacteriocin-derived compound design testing combines sequence-free prediction using a machine-learning algorithm simple biophysical trait filter to...
Antibiotic resistance monitoring is of paramount importance in the face this on-going global epidemic. Deep learning models trained with traditional optimization algorithms (e.g. Adam, SGD) provide poor posterior estimates when tested against out-of-distribution (OoD) antibiotic resistant/non-resistant genes. In paper, we introduce a deep model Stochastic Gradient Langevin Dynamics (SGLD) to classify resistant The provides better uncertainty OoD data compared methods such as Adam.
We performed a gene co-expression analysis on Lung Squamous Cell Carcinoma data to find modules (groups) of genes that may highly impact the growth these type tumors. Additionally, we used cancer survival relate prognostic significance in terms time. Analysis RNA-seq revealed which are significant enrichment analysis. Specifically, two - RFC4 and ECT2 have been found be also second dataset microarray data, many this could implying might indeed play crucial role Cancer. All R code for can at:...
Abstract Antibiotic resistance monitoring is of paramount importance in the face this ongoing global epidemic. Using traditional alignment based methods to detect antibiotic resistant genes results huge number false negatives. In paper, we introduce a deep learning model on self-attention architecture that can classify into correct classes with high precision and recall by just using protein sequences as input. Additionally, models trained optimization algorithms (e.g. Adam, SGD) provide...