Antifreeze proteins (AFPs), known as thermal hysteresis proteins, are ice-binding proteins. AFPs have been found in many fields such as in vertebrates, invertebrates, plants, bacteria, and fungi. Although the function of AFPs is common, the sequences and structures of them show a high degree of diversity. AFPs can be adsorbed in ice crystal surface and inhibit the growth of ice crystals in solution. However, the interaction between AFPs and ice crystal is not completely known for human beings. It is vitally significant to propose an automated means as a high-throughput tool to timely identify the AFPs. Analyzing physicochemical characteristics of AFPs sequences is very significant to understand the ice-protein interaction. In this manuscript, a predictor called "iAFP-Ense" was developed. The operation engine to run the AFPs prediction is an ensemble classifier formed by a voting system to fuse eleven different random forest classifiers based on feature extraction. We also compare our predictor with the AFP-PseAAC via the tenfold cross-validation on the same benchmark dataset. The comparison with the existing methods indicates the new predictor is very promising, meaning that many important key features which are deeply hidden in complicated protein sequences. The predictor used in this article is freely available at http://www.jci-bioinfo.cn/iAFP-Ense .
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00232-016-9935-9 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Utility of word embeddings from large language models in medical diagnosis.
J Am Med Inform Assoc
January 2025
Kennewick, WA 99338, United States.
Objective: This study evaluates the utility of word embeddings, generated by large language models (LLMs), for medical diagnosis by comparing the semantic proximity of symptoms to their eponymic disease embedding ("eponymic condition") and the mean of all symptom embeddings associated with a disease ("ensemble mean").
Materials And Methods: Symptom data for 5 diagnostically challenging pediatric diseases-CHARGE syndrome, Cowden disease, POEMS syndrome, Rheumatic fever, and Tuberous sclerosis-were collected from PubMed. Using the Ada-002 embedding model, disease names and symptoms were translated into vector representations in a high-dimensional space.
Utility of Candidate Genes From an Algorithm Designed to Predict Genetic Risk for Opioid Use Disorder.
JAMA Netw Open
January 2025
Mental Illness Research, Education and Clinical Center, Crescenz Veterans Affairs Medical Center, Philadelphia, Pennsylvania.
Importance: Recently, the US Food and Drug Administration gave premarketing approval to an algorithm based on its purported ability to identify individuals at genetic risk for opioid use disorder (OUD). However, the clinical utility of the candidate genetic variants included in the algorithm has not been independently demonstrated.
Objective: To assess the utility of 15 genetic variants from an algorithm intended to predict OUD risk.
Background: Predicting amyloid and tau status in nondemented older adults with AD pathologies using more affordable and accessible measures can facilitate clinical trials by reducing the screen failure rate. The goal of the present study was to develop tree-based ensemble models to predict PET-based amyloid and tau burden using non-invasive measures.
Method: Two datasets, amyloid (Aβ; n = 1062) and tau (n = 410), from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were used to predict the biomarker load in the subjects with normal cognition and mild cognitive impairment.
Background: The increasing prevalence of cognitive impairment and dementia threatens global health, necessitating the development of accessible tools for detection of cognitive impairment. This study explores using a transformer-based approach to detect cognitive impairment using acoustic markers of spontaneous speech.
Method: Recordings of unstructured interviews from baseline visits were obtained from participants of The 90+ Study, a longitudinal study of individuals older than 90 years.
Background: This study aimed to apply deep learning for various stages of dementia classification.
Methods: The ADNI database and OASIS database were used, where ADNI 21 centers with total 406 images (69AD, 202MCI and 135HC) were used as training and validation, and ADNI 4 centers with 176 images (28AD, 91MCI and 57HC) were used as testing, and another 176 images (28AD, 91MCI and 57HC) from local memory clinic were used as local testing. The 39 brain regional volumes were segmented and calculated using Freesurfer.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!