Application of cluster repeated mini-batch training method to classify electroencephalography for grab and lift tasks.

Modern deep neural network training is based on mini-batch stochastic gradient optimization. While using extensive mini-batches improves the computational parallelism, the small batch training proved that it delivers improved generalization performance and allows a significantly smaller memory, which might also improve machine throughput. However, mini-batch size and characteristics, a key factor for training deep neural networks, has not been sufficiently investigated in training correlated group features and looping with highly complex ones. In addition, the unsupervised learning method clusters the data into different groups with similar properties to make the training process more stable and faster. Then, the supervised learning algorithm was applied with the cluster repeated mini-batch training (CRMT) methods. The CRMT algorithm changed the random minibatch characteristics in the training step into training in order of clusters. Specifically, the self-organizing maps (SOM) were used to cluster the information into n groups based on the dataset's labels Then, neural network models (ANN) were trained with each cluster using the cluster repeated mini-batch training method. Experiments conducted on EEG datasets demonstrate the survey of the proposed method and optimize it. In addition, the results in our research outperform other state-of-the-art methods.

Extract antibody and antigen names from biomedical literature.

BACKGROUND: The roles of antibody and antigen are indispensable in targeted diagnosis, therapy, and biomedical discovery. On top of that, massive numbers of new scientific articles about antibodies and/or antigens are published each year, which is a precious knowledge resource but has yet been exploited to its full potential. We, therefore, aim to develop a biomedical natural language processing tool that can automatically identify antibody and antigen entities from articles. RESULTS: We first annotated an antibody-antigen corpus including 3210 relevant PubMed abstracts using a semi-automatic approach. The Inter-Annotator Agreement score of 3 annotators ranges from 91.46 to 94.31%, indicating that the annotations are consistent and the corpus is reliable. We then used the corpus to develop and optimize BiLSTM-CRF-based and BioBERT-based models. The models achieved overall F1 scores of 62.49% and 81.44%, respectively, which showed potential for newly studied entities. The two models served as foundation for development of a named entity recognition (NER) tool that automatically recognizes antibody and antigen names from biomedical literature. CONCLUSIONS: Our antibody-antigen NER models enable users to automatically extract antibody and antigen names from scientific articles without manually scanning through vast amounts of data and information in the literature. The output of NER can be used to automatically populate antibody-antigen databases, support antibody validation, and facilitate researchers with the most appropriate antibodies of interest. The packaged NER model is available at https://github.com/TrangDinh44/ABAG_BioBERT.git .

Studying the characteristics of nanobody CDR regions based on sequence analysis in combination with 3D structures.

BACKGROUND: Single-domain antibodies or nanobodies have recently attracted much attention in research and applications because of their great potential and advantage over conventional antibodies. However, isolation of candidate nanobodies in the lab has been costly and time-consuming. Screening of leading nanobody candidates through synthetic libraries is a promising alternative, but it requires prior knowledge to control the diversity of the complementarity-determining regions (CDRs) while still maintaining functionality. In this work, we identified sequence characteristics that could contribute to nanobody functionality by analyzing three datasets, CDR1, CDR2, and CDR3. RESULTS: By classification of amino acids based on physicochemical properties, we found that two different amino acid groups were sufficient for CDRs. The nonpolar group accounted for half of the total amino acid composition in these sequences. Observation of the highest occurrence of each amino acid revealed that the usage of some important amino acids such as tyrosine and serine was highly correlated with the length of the CDR3. Amino acid repeat motifs were also under-represented and highly restricted as 3-mers. Inspecting the crystallographic data also demonstrated conservation in structural coordinates of dominant amino acids such as methionine, isoleucine, valine, threonine, and tyrosine and certain positions in the CDR1, CDR2, and CDR3 sequences. CONCLUSIONS: We identified sequence characteristics that contributed to functional nanobodies including amino acid groups, the occurrence of each kind of amino acids, and repeat patterns. These results provide a simple set of rules to make it easier to generate desired candidates by computational means; also, they can be used as a reference to evaluate synthetic nanobodies.