Daneshmand, A. | bioRxiv Science

bioRxiv2022

Identification and prediction of Parkinson's disease subtypes and progression using machine learning in two cohorts.

BackgroundThe clinical manifestations of Parkinsons disease (PD) are characterized by heterogeneity in age at onset, disease duration, rate of progression, and the constellation of motor versus non-motor features. There is an unmet need for the characterization of distinct disease subtypes as well as improved, individualized predictions of the disease course. The emergence of machine learning to detect hidden patterns in complex, multi-dimensional datasets provides unparalleled opportunities to address this critical need. Methods and FindingsWe used unsupervised and supervised machine learning methods on comprehensive, longitudinal clinical data from the Parkinsons Disease Progression Marker Initiative (PPMI) (n = 294 cases) to identify patient subtypes and to predict disease progression. The resulting models were validated in an independent, clinically well-characterized cohort from the Parkinsons Disease Biomarker Program (PDBP) (n = 263 cases). Our analysis distinguished three distinct disease subtypes with highly predictable progression rates, corresponding to slow, moderate, and fast disease progression. We achieved highly accurate projections of disease progression five years after initial diagnosis with an average area under the curve (AUC) of 0.92 (95% CI: 0.95 {+/-} 0.01 for the slower progressing group (PDvec1), 0.87 {+/-} 0.03 for moderate progressors, and 0.95 {+/-} 0.02 for the fast progressing group (PDvec3). We identified serum neurofilament light (Nfl) as a significant indicator of fast disease progression among other key biomarkers of interest. We replicated these findings in an independent validation cohort, released the analytical code, and developed models in an open science manner. ConclusionsOur data-driven study provides insights to deconstruct PD heterogeneity. This approach could have immediate implications for clinical trials by improving the detection of significant clinical outcomes that might have been masked by cohort heterogeneity. We anticipate that machine learning models will improve patient counseling, clinical trial design, allocation of healthcare resources, and ultimately individualized patient care.

bioinformatics↗

bioRxiv2019

Effects of cLFchimera, a recombinant antimicrobial peptide, on intestinal morphology, microbiota, and gene expression of immune cells and tight junctions in broiler chickens challenged with C. perfringens

The current study was conducted to investigate the effects of cLFchimera, a recombinant antimicrobial peptide (AMP), on various productive performance and gut health attributes of broilers experimentally challenged with Clostridium perfringens (Cp). Three hundred and sixty 1-day-old chickens were randomly allocated to 4 treatments of 6 replicates as follows: T1) unchallenged group fed with corn-soybean meal (CSM) without Cp challenge and additives; T2) challenge group fed with CSM and challenged with Cp without any additives; T3) peptide group challenged with NE supplemented with 20 mg cLF36/kg diet (AMP); T4) antibiotic group challenged with NE and supplemented with 45 mg antibiotic (bacitracin methylene disalicylate)/kg diet (antibiotic). Birds had free access to feed and water, sampling for villi morphology and ileal microbiota were performed on days 10 and 22, while jejunal section was sampled for gene expression of cytokines, tight junctions proteins, and mucin only on day 22. Results showed that AMP ameliorated NE-related lesion in the jejunum and ileum and reduced mortality in challenged birds compared to challenge group with Cp without any additives. Also, supplementing challenged birds with AMP improved growth performance and reconstructed villi morphology. While antibiotic non-selectively reduced the count of bacteria, AMP positively restored ileal microflora in favor of good bacteria (i.e. Bifidobacteria spp. and Lactobacillus spp.). AMP beneficially regulated the expression of cytokines, junctional proteins, and mucin in the jejunum of challenged birds with Cp. Since cLFchimera ameliorated NE lesion score, reduced mortality, improved productive performance and gut health attributes in chickens compared to challenged group and also were mostly similar with those of antibiotics and therefore, it could be concluded that this chimeric peptide can be a worthy candidate to substitute growth promoter antibiotics, while more research is required to unveil the exact mode of action of this synthetic peptide. Author summaryNecrotic enteritis (NE) is a detrimental enteric disease in the poultry industry worldwide. The etiological factor of this disease is Clostridium perfringens, which is gram-positive anaerobic bacterium. This bacterium is common inhabitant of the intestine in lower counts (105), but it becomes pathogenic in higher counts and can secrete NetB toxin, which is the main cause of inducing NE in broilers. Due to the emergence of antibiotic-resistant bacteria, new generation of antimicrobial additives such as antimicrobial peptides (AMPs) has been introduced to the poultry industry. AMPs are small molecules with 12-50 amino acids having antibacterial activity. Recently, we extracted new AMP from camel milk, expressed in E. coli, refined and lyophilized to produce purified peptides. The current study investigated the effects of this peptide on prevention of NE in broilers. Results showed that AMP ameliorated lesion scores in the intestine and reduced mortality in challenged birds. AMP improved growth performance and reconstructed villi morphology in NE-challenged broilers. While antibiotic non-selectively reduced the count of bacteria, AMP positively restored ileal microflora. AMP beneficially regulated the expression of cytokines, junctional proteins, and mucin in the jejunum of NE-challenged birds.

pathology↗