Accurate prediction of drug-target interactions (DTIs) plays a pivotal role in drug discovery, facilitating optimization of lead compounds, drug repurposing and elucidation of drug side effects. However, traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features. In this study, we proposed KG-CNNDTI, a novel knowledge graph-enhanced framework for DTI prediction, which integrates heterogeneous biological information to improve model generalizability and predictive performance. The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm, which were further enriched with contextualized sequence representations obtained from ProteinBERT. For compound representation, multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated. The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor. Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods, particularly in terms of Precision, Recall, F1-Score and area under the precision-recall curve (AUPR). Ablation analysis highlighted the substantial contribution of knowledge graph-derived features. Moreover, KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease, resulting in 40 candidate compounds. 5 were supported by literature evidence, among which 3 were further validated in vitro assays.
Alzheimer Disease/drug therapy* ; Biological Products/therapeutic use* ; Humans ; Neural Networks, Computer ; Machine Learning ; Drug Discovery/methods* ; Algorithms ; Drug Evaluation, Preclinical/methods*

More than 100 genes located on the X chromosome have been found to be associated with X-linked intellectual disability (XLID) to date, and NEXMIF is a pathogenic gene for XLID. In addition to intellectual disability, patients with NEXMIF gene mutation can also have other neurological symptoms, such as epilepsy, abnormal behavior, and hypotonia, as well as abnormalities of other systems. Two children with intellectual disability and epilepsy caused by NEXMIF gene mutation were treated in the Department of Pediatrics, Xiangya Hospital, Central South University from March 8, 2017 to June 20, 2020. Patient 1, a 7 years and 8 months old girl, visited our department because of the delayed psychomotor development. Physical examination revealed strabismus (right eye), hyperactivity, and loss of concentration. Intelligence test showed a developmental quotient of 43.6. Electroencephalogram showed abnormal discharge, and cranial imaging appeared normal. Whole exome sequencing revealed a de novo heterozygous mutation, c.2189delC (p.S730Lfs*17) in the NEXMIF gene (NM_001008537). During the follow-up period, the patient developed epileptic seizures, mainly manifested as generalized and absent seizures. She took the medicine of levetiracetam and lamotrigine, and the seizures were under control. Patient 2, a 6-months old boy, visited our department due to developmental regression and seizures. He showed poor reactions to light and sound, and was not able to raise head without aid. Hypotonia was also noticed. The electroencephalogram showed intermittent hyperarrhythmia, and spasms were monitored. He was given topiramate and adrenocorticotrophic hormone (ACTH). Whole exome sequencing detected a de novo c.592C>T (Q198X) mutation in NEXMIF gene. During the follow-up period, the seizures were reduced with vigabatrin. He had no obvious progress in the psychomotor development, and presented strabismus. There were 91 cases reported abroad, 1 case reported in China, and 2 patients were included in this study. A total of 85 variants in NEXMIF gene were found, involving 83 variants reported in PubMed and HGMD, and the 2 new variants presented in our patients. The patients with variants in NEXMIF gene all had mild to severe intellectual disability. Behavioral abnormalities, epilepsy, hypotonia, and other neurological symptoms are frequently presented. The phenotype of male partially overlaps with that of female. Male patients often have more severe intellectual disability, impaired language, and autistic features, while female patients often have refractory epilepsy. Most of the variants reported so far were loss-of-function resulted in the reduced protein expression of NEXMIF. The degree of NEXMIF loss appears to correlate with the severity of the phenotype.
Child ; Epilepsy/genetics* ; Female ; Humans ; Intellectual Disability/genetics* ; Male ; Muscle Hypotonia/complications* ; Mutation ; Phenotype ; Seizures/genetics* ; Strabismus/complications*

Cardio-facio-cutaneous (CFC) syndrome is an extremely rare autosomal dominant genetic disease due to BRAF and other gene mutations. The main characteristics of the patients are craniofacial deformities, cardiac malformations, skin abnormalities, delay of language and motor development, gastrointestinal dysfunction, intellectual disability, and epilepsy. In this case, the child has a typical CFC syndrome face and developmental delay. The gene results of the second-generation sequencing technology showed that there was a mutation site c.1741A>G (p. Asn581Asp) (heterozygous) in exon 14 of the BRAF (NM_004333.5) gene. The mutation was not observed in the child's parents. The above-mentioned mutation may be a de novo mutation. There is no effective therapy for this disease so far.
Abnormalities, Multiple ; Child ; Ectodermal Dysplasia/genetics* ; Facies ; Failure to Thrive ; Heart Defects, Congenital/genetics* ; Humans ; Mutation ; Proto-Oncogene Proteins B-raf/genetics*

OBJECTIVETo analyze the sequence of a novel human leukocyte antigen (HLA)-A*33:44 allele.

METHODSA novel HLA-A allele was found by double-stranded sequencing combined with single-stranded sequencing. The frequency of the novel allele was determined by population survey.

RESULTSGenomic sequence of this novel HLA-A*33:44 allele (accession No. HQ873871) has differed from HLA-B*33:03:01 by one nucleotide in exon 4, which resulted in nt 866 G→ A substitution, which results in an amino acid substitution from Gly(GGT) to Asp(GAT) at codon 265. This alternation is a new single nucleotide polymorphism compared with other HLA-A alleles. The frequency of this new allele is less than 0.0003 in Chinese Han population.

CONCLUSIONA mutation has been found in exon 4 of the novel HLA-A*33:44 allele, which may provide more information for HLA gene study.

Adult ; Alleles ; Amino Acid Substitution ; Asian Continental Ancestry Group ; genetics ; Female ; HLA-A Antigens ; genetics ; Humans ; Male ; Polymorphism, Single Nucleotide ; Sequence Analysis, DNA ; methods

OBJECTIVETo confirm a new allele HLA-B*13:01:06 and analyze its nucleotide sequence.

METHODSGenomic DNA was extracted using a Qiagen DNA extraction kit. Nucleotide sequences of HLA-A, HLA-B, HLA-C and HLA-DRB1 were analyzed by polymerase chain reaction-sequence based typing (PCR-SBT). HLA high-resolution results were assigned, and the nucleotide sequences of HLA-B locus was compared with that of HLA-B*13:01:01.

RESULTSThe nucleotide sequence of the new allele shows a strong similarity to that of HLA-B*13:01:01. One nucleotide in exon 2 has changed from G to A at position 219 (codon 49 GCG>GCA), which however did not result in amino acid change.

CONCLUSIONThe novel allele verified by sequencing has been submitted to GenBank and officially named as HLA-B*13:01:06 by the World Health Organization HLA Nomenclature Committee.

Alleles ; Amino Acid Sequence ; Base Sequence ; Exons ; HLA-B Antigens ; genetics ; Humans ; Male ; Middle Aged ; Molecular Sequence Data ; Sequence Analysis, DNA