The Protein Journal最新文献

{"title":"Unraveling the interaction between a glycolytic regulator protein EhPpdk and an anaphase promoting complex protein EhApc10: yeast two hybrid screening, in vitro binding assays and molecular simulation study","authors":"Suchetana Pal,&nbsp;Pinaki Biswas,&nbsp;Raktim Ghosh,&nbsp;Somasri Dam","doi":"10.1007/s10930-024-10238-5","DOIUrl":"10.1007/s10930-024-10238-5","url":null,"abstract":"<div><p>The anaphase promoting complex (APC or cyclosome) is a major ubiquitin ligase that coordinates mitotic and G1 progression, acting as a major regulator of chromosome segregation. While the human APC contains fourteen subunits, it is yet to be explored in the pathogen <i>Entamoeba histolytica</i>. Our study reveals the existence of a single functional Apc10 homolog in <i>E</i>. <i>histolytica</i>, which acts as a processivity factor of ubiquitin ligase activity in human. A cDNA library generated from HM1:IMSS strain of <i>E</i>. <i>histolytica</i> was screened for interaction partners of EhApc10 in yeast two hybrid study. The novel interactor, a glycolytic enzyme, pyruvate phosphate dikinase (Ppdk) was found to interact with EhApc10 and further validated by in vitro assay. A comprehensive in silico study has emphasized the structural and functional aspects, encompassing physicochemical traits, predictive 3D structure modelling, validation of EhApc10-EhPpdk interaction through molecular docking and simulation. The interplay between a cell cycle protein and a glycolytic enzyme highlights the connection between cellular metabolism and the cell cycle regulatory mechanism. The study serves as the groundwork for future research on the non-mitotic role of APC beyond cell cycle.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 6","pages":"1104 - 1119"},"PeriodicalIF":1.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unravelling the Significance of Seed Proteomics: Insights into Seed Development, Function, and Agricultural Applications","authors":"Jameel R. Al-Obaidi,&nbsp;Su-Ee Lau,&nbsp;Yvonne Jing Mei Liew,&nbsp;Boon Chin Tan,&nbsp;Norasfaliza Rahmad","doi":"10.1007/s10930-024-10240-x","DOIUrl":"10.1007/s10930-024-10240-x","url":null,"abstract":"<div><p>Seeds are essential for plant reproduction, ensuring species survival and dispersal while adapting to diverse environments throughout a plant’s life. Proteomics has emerged as a powerful tool for deciphering the complexities of seed growth, germination, and stress responses. Advanced proteomic technologies enable the analysis of protein changes during germination, dormancy, and ageing, enhancing our understanding of seed lifespan and vitality. Recent studies have revealed detailed insights into metabolic processes and storage protein profiles across various plant species. This knowledge is crucial for improving seed storage, conserving quality, and maintaining viability. Additionally, it contributes to sustainable agriculture by identifying stress-responsive proteins and signalling pathways that can mitigate stress and enhance farming practices. This review highlights significant advancements in seed proteomics over the past decade, discussing critical discoveries related to storage proteins, protein interactions, and proteome modifications due to stress. It illustrates how these insights transform seed biology, boosting productivity, food security, and environmentally friendly practices. The review also identifies existing knowledge gaps and provides direction for future research, underscoring the need for continued interdisciplinary collaboration in this dynamic field.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 6","pages":"1083 - 1103"},"PeriodicalIF":1.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Influence of Cataract Causing Mutations on αA-Crystallin: A Computational Approach","authors":"Kajal Abrol,&nbsp;Jayarani Basumatari,&nbsp;Jupita Handique,&nbsp;Muthukumaran Rajagopalan,&nbsp;Amutha Ramaswamy","doi":"10.1007/s10930-024-10239-4","DOIUrl":"10.1007/s10930-024-10239-4","url":null,"abstract":"<div><p>The αA-crystallin protein plays a vital role in maintaining the refractive index and transparency of the eye lens. Significant clinical studies have emerged as the αA-crystallin is prone to aggregation, resulting in the formation of cataracts with varied etiologies due to mutations. This work aims to comprehend the structural and functional role of cataract-causing mutations in αA-crystallin, particularly at N-Terminal and α-Crystallin Domains, using in-silico approaches including molecular dynamics simulation. About 19 mutants of αA-crystallin along with native structure were simulated for 100 ns and the post-simulations analyses reveal pronounced dynamics of αA-crystallin due to the enhanced structure flexibility as its native compactness was lost and is witnessed mainly by the mutants R12L, R21L, R21Q, R54L, R65Q, R116C and R116H. It is observed that αA-crystallin discloses the NTD motions as the dominant one and the same was endorsed by the linear variation between Rg and the center-of-mass of αA-crystallin. Interestingly, such enhanced dynamics of αA-crystallin mutants associated with the structure flexibility is internally modulated by the dynamic exchange of secondary structure elements β-sheets and coils (R² = 0.619) during simulation. Besides, the observed pronounced dynamics of dimer interface region (β3-L6-β4 segment) of ACD along with CTD dynamics also gains importance. Particularly, the highly dynamic mutants are also characterized by enhanced non-covalent and hydrophobic interactions which renders detrimental effects towards its stability, and favours possible protein unfolding mechanisms. Overall, this study highlights the mutation-mediated structural distortions in αA-crystallin and demands the need for further potential development of inhibitors against cataract formation.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 6","pages":"1045 - 1069"},"PeriodicalIF":1.9,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142562972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HaloClass: Salt-Tolerant Protein Classification with Protein Language Models","authors":"Kush Narang,&nbsp;Abhigyan Nath,&nbsp;William Hemstrom,&nbsp;Simon K. S. Chu","doi":"10.1007/s10930-024-10236-7","DOIUrl":"10.1007/s10930-024-10236-7","url":null,"abstract":"<div><p>Salt-tolerant proteins, also known as halophilic proteins, have unique adaptations to function in high-salinity environments. These proteins have naturally evolved in extremophilic organisms, and more recently, are being increasingly applied as enzymes in industrial processes. Due to an abundance of salt-tolerant sequences and a simultaneous lack of experimental structures, most computational methods to predict stability are sequence-based only. These approaches, however, are hindered by a lack of structural understanding of these proteins. Here, we present HaloClass, an SVM classifier that leverages ESM-2 protein language model embeddings to accurately identify salt-tolerant proteins. On a newer and larger test dataset, HaloClass outperforms existing approaches when predicting the stability of never-before-seen proteins that are distal to its training set. Finally, on a mutation study that evaluated changes in salt tolerance based on single- and multiple-point mutants, HaloClass outperforms existing approaches, suggesting applications in the guided design of salt-tolerant enzymes.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 6","pages":"1035 - 1044"},"PeriodicalIF":1.9,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10930-024-10236-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142484790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exosomes with Engineered Brain Derived Neurotrophic Factor on Their Surfaces Can Proliferate Menstrual Blood Derived Mesenchymal Stem Cells: Targeted Delivery for a Protein Drug","authors":"Fatemeh Siamian Gorji,&nbsp;Seyedeh Farzaneh Mahdavian,&nbsp;Shabanali Khodashenas,&nbsp;Zeinab Rezaee Kiasari,&nbsp;Reza Valadan,&nbsp;Saeed Khalili,&nbsp;Mohammad Reza Mahdavi","doi":"10.1007/s10930-024-10234-9","DOIUrl":"10.1007/s10930-024-10234-9","url":null,"abstract":"<div><p>Despite the efficacy of brain derived neurotrophic factor (BDNF) in neuro-regenerative medicine, it can’t pass the blood–brain barrier. Recently, exosomes have been harnessed for targeted delivery of therapeutics into brain. Given these facts, an engineered exosome capable of BDNF expression on the surface would be an amenable tool for drug delivery. The BDNF gene was cloned into a plex-lamp lentiviral vector and virus particles were packaged using the Torano method. HEK293T cells were transduced by the purified viruses to produce and purify recombinant exosomes displaying the fusion protein on their surfaces. Western blot, Zeta sizer, TEM, and ELISA methods were used for exosome characterization. The effect of engineered exosomes on menstrual blood-derived mesenchymal stem cells (Mens-MSCs) proliferation was evaluated by cell counting assay, MTT assay, and qPCR on the <i>bcl2</i> and <i>nestin</i> genes. Approximately, 1.8 × 10⁸ TdU/ml of the viral particles was purified from the transfected cells and transduced into the HEK293T. Western blot and ELISA methods confirmed the surface display of the LAMP-BDNF fusion. TEM graphs and Zeta sizer results confirmed the morphology and the size of purified exosomes. Treatment of Mens-MSCs with the targeted exosomes augmented the expression level of <i>bcl2</i> and <i>nestin</i> genes, increased the cell proliferation, and elevated the cell number. Chimeric BDNF on the exosome surface could retain its biological activity and elevate the expression of <i>bcl2</i> and <i>nestin</i> genes. Moreover, these exosomes are capable of elevating the Mens-MSCs proliferation.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 6","pages":"1070 - 1082"},"PeriodicalIF":1.9,"publicationDate":"2024-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142484789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sulfonylhydrazide Derivatives as Potential Anti-cancer Agents: Synthesis, In Vitro and In Silico Studies","authors":"Kholoud M. Ibrahim,&nbsp;Doaa M. Elsisi,&nbsp;Yousry A. Ammar,&nbsp;Fivian F. M. Araki,&nbsp;Jehane A. A. Micky","doi":"10.1007/s10930-024-10232-x","DOIUrl":"10.1007/s10930-024-10232-x","url":null,"abstract":"<div><p>The synthesis of new agents for cancer treatment persists due to its global lethality. A series of thirteen derivatives, namely salicylic acid-5-sulfohydrazide (SA-SH) analogs, were designed and synthesized from 5-(chlorosulfonyl)-2-hydroxybenzoic acid via nucleophilic substitution reaction with different acid hydrazides, thiocarbohydrazide &amp; thiosemicarbazide scaffolds. Confirmation of the designed derivative’s structures employed various spectroscopic techniques (FT-IR and NMR) and elemental analysis. The newly synthesized synthons were evaluated for cytotoxic activity against HepG-2 and HCT-116 cell lines in comparison to Doxorubicin. Notably, SA-SH derivatives (5, 7, 8a, 8b and 11) exhibited significantly higher efficacy against HepG-2 and HCT-116 cell lines than other analogs. Furthermore, compound (8a) demonstrated a superior activity against HepG-2 cell lines with IC₅₀ values of 3.99 ± 0.2 μM than the reference drug, Doxorubicin, (IC₅₀ HepG-2 = 4.50 ± 0.2 µM). The molecular docking simulation of the most active SA-SH derivatives and the reference drug doxorubicin into the active site of FGFR4 (fibroblast growth factor receptor, the predominant isoform expressed in human hepatocytes) (PDB ID: 6V9C) proved the usefulness of hybridizing salicylic scaffold with SO₂ and hydrazide moieties as a promising approach in designing new anticancer agents. Finally, ADME and drug-likeness features of the most active compounds compared to positive controls were investigated to increase the success possibilities in clinical trials and they were found to be promising candidates for further investigation and development as drugs.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 5","pages":"949 - 966"},"PeriodicalIF":1.9,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142305338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of Cationic Amino Acid Binding Protein from Candidatus Liberibacter Asiaticus and in Silico Study to Identify Potential Inhibitor Molecules","authors":"Sapna Lonare,&nbsp;Deena Nath Gupta,&nbsp;Harry Kaur,&nbsp;Surabhi Rode,&nbsp;Shalja Verma,&nbsp;Mrugendra Gubyad,&nbsp;Dilip Kumar Ghosh,&nbsp;Pravindra Kumar,&nbsp;Ashwani Kumar Sharma","doi":"10.1007/s10930-024-10233-w","DOIUrl":"10.1007/s10930-024-10233-w","url":null,"abstract":"<div><p>Cationic amino acid binding protein (CLasArgBP), one of the two amino acid binding receptor in <i>Candidatus</i> Liberibacter asiaticus (CLas), is predominately expressed in citrus psyllids as a part of ATP-binding cassette transport system. The present study describes characterization of CLasArgBP by various biophysical techniques and in silico study, to identify potential inhibitor molecules against CLasArgBP through virtual screening and MD simulations. Further, <i>in planta</i> study was carried out to assess the effect of selected inhibitors on Huanglongbing infected Mosambi plants. The results showed that CLasArgBP exhibits pronounced specificity for arginine, histidine and lysine. Surface plasmon resonance (SPR) study reports highest binding affinity for arginine (Kd, 0.14 µM), compared to histidine and lysine (Kd, 15 µΜ and 26 µΜ, respectively). Likewise, Differential Scanning Calorimetry (DSC) study showed higher stability of CLasArgBP for arginine, compared to histidine and lysine. N(omega)-nitro-L-arginine, Gamma-hydroxy-L-arginine and Gigartinine emerged as lead compounds through in silico study displaying higher binding energy and stability compared to arginine. SPR reports elevated binding affinities for N(omega)-nitro-L-arginine and Gamma-hydroxy-L-arginine (Kd, 0.038 µΜ and 0.061 µΜ, respectively) relative to arginine. DSC studies showed enhanced thermal stability for CLasArgBP in complex with selected inhibitors. Circular dichroism and fluorescence studies showed pronounced conformational changes in CLasArgBP with selected inhibitors than with arginine. <i>In planta</i> study demonstrated a substantial decrease in CLas titer in treated plants as compared to control plants. Overall, the study provides the first comprehensive characterization of cationic amino acid binding protein from CLas, as a potential drug target to manage HLB disease.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 5","pages":"967 - 982"},"PeriodicalIF":1.9,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142305337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Solubility of Proteins in Escherichia coli Based on Functional and Structural Features Using Machine Learning Methods","authors":"Feiming Huang,&nbsp;Qian Gao,&nbsp;XianChao Zhou,&nbsp;Wei Guo,&nbsp;KaiYan Feng,&nbsp;Lin Zhu,&nbsp;Tao Huang,&nbsp;Yu-Dong Cai","doi":"10.1007/s10930-024-10230-z","DOIUrl":"10.1007/s10930-024-10230-z","url":null,"abstract":"<div><p>Protein solubility is a critical parameter that determines the stability, activity, and functionality of proteins, with broad and far-reaching implications in biotechnology and biochemistry. Accurate prediction and control of protein solubility are essential for successful protein expression and purification in research and industrial settings. This study gathered information on soluble and insoluble proteins. In characterizing the proteins, they were mapped to STRING and characterized by functional and structural features. All functional/structural features were integrated to create a 5768-dimensional binary vector to encode proteins. Seven feature-ranking algorithms were employed to analyze the functional/structural features, yielding seven feature lists. These lists were subjected to the incremental feature selection, incorporating four classification algorithms, one by one to build effective classification models and identify functional/structural features with classification-related importance. Some essential functional/structural features used to differentiate between soluble and insoluble proteins were identified, including GO:0009987 (intercellular communication) and GO:0022613 (ribonucleoprotein complex biogenesis). The best classification model using support vector machine as the classification algorithm and 295 optimized functional/structural features generated the F1 score of 0.825, which can be a powerful tool to differentiate soluble proteins from insoluble proteins.</p></div>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 5","pages":"983 - 996"},"PeriodicalIF":1.9,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142147269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring Acyl Thiotriazinoindole Based Pharmacophores: Design, Synthesis, and SAR Studies with Molecular Docking and Biological Activity Profiling against Urease, α-amylase, α-glucosidase, Antimicrobial, and Antioxidant Targets","authors":"Mian Bilal Haider,&nbsp;Aamer Saeed,&nbsp;Atteeque Ahmed,&nbsp;Muhammad Azeem,&nbsp;Hammad Ismail,&nbsp;Sabba Mehmood,&nbsp;Parham Taslimi,&nbsp;Syed Adnan Ali Shah,&nbsp;Madiha Irfan,&nbsp;Hesham R. El-Seedi","doi":"10.1007/s10930-024-10229-6","DOIUrl":"10.1007/s10930-024-10229-6","url":null,"abstract":"&lt;div&gt;&lt;p&gt;A diminutive chemical library of acyl thiotriazinoindole (ATTI) based bioactive scaffolds was synthesized, instigated by taking the economical starting material Isatin, through a series of five steps. Isatin was first nitrated followed by the attachment of pentyl moiety via nucleophilic substitution reaction. The obtained compound was reacted with thiosemicarbazide to obtain thiosemicarbazone derivative, which was eventually cyclized using basic conditions in water as solvent. Finally, the reported series was obtained through reaction of nitrated thiotriazinoindole moiety with differently substituted phenacyl bromides. The synthesized compounds were characterized using NMR spectroscopy and elemental analysis. Finally, the synthesized motifs were scrutinized for their potential to impede urease, &lt;i&gt;α&lt;/i&gt;-glucosidase, DPPH, and &lt;i&gt;α&lt;/i&gt;-amylase. Compound &lt;b&gt;5 h&lt;/b&gt; with &lt;i&gt;para&lt;/i&gt; cyano group manifested the most pivotal biological activity among all, displaying IC&lt;sub&gt;50&lt;/sub&gt; values of 29.7 ± 0.8, 20.5 ± 0.5 and 36.8 ± 3.9 µM against urease, &lt;i&gt;α&lt;/i&gt;-glucosidase, and DPPH assay, respectively. Simultaneously, for &lt;i&gt;α-&lt;/i&gt;amylase compound &lt;b&gt;5 g&lt;/b&gt; possessing a &lt;i&gt;p&lt;/i&gt;-CH&lt;sub&gt;3&lt;/sub&gt; at phenyl ring unfolded as most active, with calculated IC&lt;sub&gt;50&lt;/sub&gt; values 90.3 ± 1.1 µM. The scaffolds were additionally gauged for their antifungal and antibacterial activity. Among the tested strains, &lt;b&gt;5d&lt;/b&gt; having bromo as substituent exhibited the most potent antibacterial activity, while it also demonstrated the highest potency against &lt;i&gt;Aspergillus fumigatus&lt;/i&gt;. Other derivatives &lt;b&gt;5b&lt;/b&gt;, &lt;b&gt;5e, 5i,&lt;/b&gt; and &lt;b&gt;5j&lt;/b&gt; also exhibited dual inhibition against both antibacterial and antifungal strains. The interaction pattern of derivatives clearly displayed their SAR, and their docking scores were correlated with their IC&lt;sub&gt;50&lt;/sub&gt; values. In molecular docking studies, the importance of interactions like hydrogen bonding was further asserted. The electronic factors of various substituents engendered variety of interactions between the ligands and targets implying their importance in the structures of the synthesized heterocyclic scaffolds. To conclude, the synthesized compounds had satisfactory biological activity against various important targets. Further studies are therefore encouraged by attachment of different substitutions in the structure at various positions to enhance the activity of these compounds.&lt;/p&gt;&lt;h3&gt;Graphical Abstract&lt;/h3&gt;&lt;p&gt;Exploring Acyl Thiotriazinoindole based Pharmacophores: Design, Synthesis, and SAR studies with Molecular Docking and Biological Activity Profiling against Urease, &lt;i&gt;α&lt;/i&gt;-amylase, &lt;i&gt;α&lt;/i&gt;-glucosidase, Antimicrobial, and Antioxidant Targets&lt;/p&gt;&lt;p&gt;An updated synthetic pathway to furnish acyl thiotriazinoindole based scaffolds was developed starting from Isatin and the novel compounds were assessed for various biological applications.&lt;/p&gt;\u0000&lt;div&gt;&lt;figure&gt;&lt;div&gt;&lt;div&gt;&lt;picture&gt;&lt;source&gt;&lt;img&gt;&lt;/source&gt;&lt;/picture&gt;&lt;/","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"43 5","pages":"1009 - 1024"},"PeriodicalIF":1.9,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142116712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuropsychological test using machine learning for cognitive impairment screening.","authors":"Chanda Simfukwe, SangYun Kim, Seong Soo An, Young Chul Youn","doi":"10.1080/23279095.2022.2078210","DOIUrl":"10.1080/23279095.2022.2078210","url":null,"abstract":"<p><strong>Objectives: </strong>Neuropsychological tests (NPTs) are widely used tools to evaluate cognitive functioning. The interpretation of these tests can be time-consuming and requires a specialized clinician. For this reason, we trained machine learning models that detect normal controls (NC), cognitive impairment (CI), and dementia among subjects.</p><p><strong>Patients and methods: </strong>A total number of 14,927 subject datasets were collected from the formal neuropsychological assessments Seoul Neuropsychological Screening Battery (SNSB) by well-qualified neuropsychologists. The dataset included 44 NPTs of SNSB, age, education level, and diagnosis of each participant. The dataset was preprocessed and classified according to three different classes NC, CI, and dementia. We trained machine-learning with a supervised machine learning classifier algorithm support vector machine (SVM) 30 times with classification from scikit-learn (https://scikit-learn.org/stable/) to distinguish the prediction accuracy, sensitivity, and specificity of the models; NC <i>vs.</i> CI, NC <i>vs.</i> dementia, and NC <i>vs.</i> CI <i>vs.</i> dementia. Confusion matrixes were plotted using the testing dataset for each model.</p><p><strong>Results: </strong>The trained model's 30 times mean accuracies for predicting cognitive states were as follows; NC <i>vs.</i> CI model was 88.61 ± 1.44%, NC <i>vs.</i> dementia model was 97.74 ± 5.78%, and NC <i>vs.</i> CI <i>vs.</i> dementia model was 83.85 ± 4.33%. NC <i>vs.</i> dementia showed the highest accuracy, sensitivity, and specificity of 97.74 ± 5.78, 97.99 ± 5.78, and 96.08 ± 4.33% in predicting dementia among subjects, respectively.</p><p><strong>Conclusion: </strong>Based on the results, the SVM algorithm is more appropriate in training models on an imbalanced dataset for a good prediction accuracy compared to natural network and logistic regression algorithms. The NC <i>vs.</i> dementia machine-learning trained model with SVM based on NPTs SNSB dataset could assist neuropsychologists in classifying the cognitive function of subjects.</p>","PeriodicalId":793,"journal":{"name":"The Protein Journal","volume":"35 1","pages":"825-830"},"PeriodicalIF":1.4,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41306657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}