CodonBERT: a BERT-based architecture tailored for codon optimization using the cross-attention mechanism.

MOTIVATION: Due to the varying delivery methods of mRNA vaccines, codon optimization plays a critical role in vaccine design to improve the stability and expression of proteins in specific tissues. Considering the many-to-one relationship between synonymous codons and amino acids, the number of mRNA sequences encoding the same amino acid sequence could be enormous. Finding stable and highly expressed mRNA sequences from the vast sequence space using in silico methods can generally be viewed as a path-search problem or a machine translation problem. However, current deep learning-based methods inspired by machine translation may have some limitations, such as recurrent neural networks, which have a weak ability to capture the long-term dependencies of codon preferences. RESULTS: We develop a BERT-based architecture that uses the cross-attention mechanism for codon optimization. In CodonBERT, the codon sequence is randomly masked with each codon serving as a key and a value. In the meantime, the amino acid sequence is used as the query. CodonBERT was trained on high-expression transcripts from Human Protein Atlas mixed with different proportions of high codon adaptation index codon sequences. The result showed that CodonBERT can effectively capture the long-term dependencies between codons and amino acids, suggesting that it can be used as a customized training framework for specific optimization targets. AVAILABILITY AND IMPLEMENTATION: CodonBERT is freely available on https://github.com/FPPGroup/CodonBERT.

THPLM: a sequence-based deep learning framework for protein stability changes prediction upon point variations using pretrained protein language model.

MOTIVATION: Quantitative determination of protein thermodynamic stability is a critical step in protein and drug design. Reliable prediction of protein stability changes caused by point variations contributes to developing-related fields. Over the past decades, dozens of structure-based and sequence-based methods have been proposed, showing good prediction performance. Despite the impressive progress, it is necessary to explore wild-type and variant protein representations to address the problem of how to represent the protein stability change in view of global sequence. With the development of structure prediction using learning-based methods, protein language models (PLMs) have shown accurate and high-quality predictions of protein structure. Because PLM captures the atomic-level structural information, it can help to understand how single-point variations cause functional changes. RESULTS: Here, we proposed THPLM, a sequence-based deep learning model for stability change prediction using Meta's ESM-2. With ESM-2 and a simple convolutional neural network, THPLM achieved comparable or even better performance than most methods, including sequence-based and structure-based methods. Furthermore, the experimental results indicate that the PLM's ability to generate representations of sequence can effectively improve the ability of protein function prediction. AVAILABILITY AND IMPLEMENTATION: The source code of THPLM and the testing data can be accessible through the following links: https://github.com/FPPGroup/THPLM.

[Establishment of a fast discriminant model with electronic nose for Polygonati Rhizoma mildew based on odor variation].

The odor fingerprint of Pollygonati Rhizoma samples with different mildewing degrees was analyzed and the relationship between the odor variation and the mildewing degree was explored. A fast discriminant model was established according to the response intensity of electronic nose. The α-FOX3000 electronic nose was applied to analyze the odor fingerprint of Pollygonati Rhizoma samples with different mildewing degrees and the radar map was used to analyze the main contributors among the volatile organic compounds. The feature data were processed and analyzed by partial least squares discriminant analysis(PLS-DA), K-nearest neighbor(KNN), sequential minimal optimization(SMO), random forest(RF) and naive Bayes(NB), respectively. According to the radar map of the electronic nose, the response values of three sensors, namely T70/2, T30/1, and P10/2, increased with the mildewing, indicating that the Pollygonati Rhizoma produced alkanes and aromatic compounds after the mildewing. According to PLS-DA model, Pollygonati Rhizoma samples of three mildewing degrees could be well distinguished in three areas. Afterwards, the variable importance analysis of the sensors was carried out and then five sensors that contributed a lot to the classification were screened out: T70/2, T30/1, PA/2, P10/1 and P40/1. The classification accuracy of all the four models(KNN, SMO, RF, and NB) was above 90%, and KNN was most accurate(accuracy: 97.2%). Different volatile organic compounds were produced after the mildewing of Pollygonati Rhizoma, and they could be detected by electronic nose, which laid a foundation for the establishment of a rapid discrimination model for mildewed Pollygonati Rhizoma. This paper shed lights on further research on change pattern and quick detection of volatile organic compounds in moldy Chinese herbal medicines.

[Change pattern and correlation analysis of macroscopic characteristics, active components and rancidness degrees of Armeniacae Semen Amarum in deterioration process].

To discuss the effect of deterioration on the quality of Armeniacae Semen Amarum by observing the changes of macroscopic characteristics, active components and rancidness degrees of Armeniacae Semen Amarum in deterioration process. The traditional macroscopic identification was used to observe, identify and classify the morphologic and organleptic characteristics of Armeniacae Semen Amarum. The contents of amygdalin and fatty oil(two representatives of active components) were detected by HPLC and general rule 0713 in Chinese Pharmacopoeia, respectively. Acid value and peroxide value of the samples were selected as the representative indices of different rancidness degrees, and the general rule 2303 was adopted as the method for quantitative analysis. Then principal component analysis(PCA), partial least square analysis discrimination analysis(PLS-DA) were further utilized to establish the discriminative models of samples with different rancidness degrees, and also to screen out the largest contribution factors. In sensory evaluation, Armeniacae Semen Amarum samples were divided into three groups: non-rancid, slightly-rancid, and noticeably-rancid. The color of seed coat, cotyledon and surface of noticeably-rancid samples was deepened, and the odor differed much from non-rancid samples. Average content of amygdalin and fatty oil in non-rancid samples was 4.12% and 67.77%, respectively, both meeting the requirements of Chinese Pharmacopoeia; and decreased to some extent in slightly-rancid samples. However, the content of amygdalin sharply dropped to 0.074% in noticeably-rancid samples. The acid value and peroxide value were increased significantly with the intensifying of the rancidness degree, from only 1.363 and 0.016 74 in non-rancid samples to 1.865 and 0.023 70 in slightly-rancid samples, even doubled in noticeably-rancid samples(2.167 and 0.033 82). The discriminative models established by PCA and PLS-DA could complete the task of distinguishing the non-rancid samples from noticeably-rancid ones. The contribution degree of amygdalin content as one of the input attributes of discriminative model was higher than 1. Rancidness affected the quality of Armeniacae Semen Amarum, resulting in appearance changes, decrease in content of active components, and increase in acid value and peroxide value. Obviously, noticeably-rancid samples were non-conforming to Chinese Pharmacopoeia and no longer suitable for medicinal use. Rancidness can significantly reduce the quality of Armeniacae Semen Amarum, and even could possibly produce toxicity, which should attach more attention.

[Discrimination of Armeniacae Semen Amarum from different processed products and various rancidness degrees by electronic nose and support vector machine].

This study was aimed to develop a simple, rapid and reliable method for identifying Armeniacae Semen Amarum from different processed products and various rancidness degrees. The objective odor information of Armeniacae Semen Amarum was obtained by electronic nose. 105 batches of Armeniacae Semen Amarum samples were studied, including three processed products of Armeniacae Semen Amarum, fried Armeniacae Semen Amarum and peeled Armeniacae Semen Amarum, as well as the samples with various rancidness degrees: without rancidness, slight rancidness, and rancidness. The discriminant models of different processed products and rancidness degrees of Armeniacae Semen Amarum were established by Support Vector Machine(SVM), respectively, and the models were verified based on back estimation of blind samples. The results showed that there were differences in the characteristic response radar patterns of the sensor array of different processed products and the samples with different rancidness degrees. The initial identification rate was 95.90% and 92.45%, whilst validation recognition rate was 95.38% and 91.08% in SVM identification models. In conclusion, differentiation in odor of different processed and rancidness degree Armeniacae Semen Amarum was performed by the electronic nose technology, and different processed and rancidness degrees Armeniacae Semen Amarum were successfully discriminated by combining with SVM. This research provides ideas and methods for objective identification of odor of traditional Chinese medicine, conducive to the inheritance and development of traditional experience in odor identification.

[Identification of Curcuma herbs using XGBoost algorithm in electronic nose odor fingerprint].

This article aims to identify four commonly applied herbs from Curcuma genus of Zingiberaceae family,namely Curcumae Radix( Yujin),Curcumae Rhizoma( Ezhu),Curcumae Longae Rhizoma( Jianghuang) and Wenyujin Rhizoma Concisum( Pianjianghuang). The odor fingerprints of those four herbal medicines were collected by electronic nose,respectively. Meanwhile,XGBoost algorithm was introduced to data analysis and discriminant model establishment,with four indexes for performance evaluation,including accuracy,precision,recall,and F-measure. The discriminant model was established by XGBoost with positive rate of returning to 166 samples in the training set and 69 samples in the test set were 99. 39% and 95. 65%,respectively. The top four of the contribution to the discriminant model were LY2/g CT,P40/1,LY2/Gh and LY2/LG,the least contributing sensor was T70/2. Compared with support vector machine,random forest and artificial neural network,XGBoost algorithms shows better identification capacity with higher recognition efficiency. The accuracy,precision,recall and F-measure of the XGBoost discriminant model forecast set were 95. 65%,95. 25%,93. 07%,93. 75%,respectively. The superiority of XGBoost in the identification of Curcuma herbs was verified. Obviously,this new method could not only be suitable for digitization and objectification of traditional Chinese medicine( TCM) odor indicators,but also achieve the identification of different TCM based on their odor fingerprint in electronic nose system. The introduction of XGBoost algorithm and more excellent algorithms provide more ideas for the application of electronic nose in data mining for TCM studies.

[Rancidness of Armeniacae Semen Amarum involving Bianzhuang Lunzhi].

This article aims to compare the qualities of Armeniacae Semen Amarum before and after rancidness, in order to study the rancidness of Armeniacae Semen Amarum. In the experiment, content of fatty oil, acid value and peroxide value were determined before and after rancidness,respectively. Meanwhile, HPLC, GC-MS were utilized to analyze laetrile and fatty acid components. Besides, colorimeter and e-nose were introduced to quantify and compare "color and odor". A correlation analysis was conducted on the above results. The results showed that color of post-rancidness Armeniacae Semen Amarum changed from yellow to brown, with sour and lower content of laetrile. On the contrary, acid and peroxide values increased significantly, with changes in fatty acid component. There was a considerable correlation between appearance characteristics and changes in internal quality. The "sensory analysis-quality identification system" can provide a certain scientific basis for prediction of the content of chemical components in traditional Chinese medicine, preliminary judgment of quality of traditional Chinese medicine and real-time quality monitoring, which offers us novel ideas and reference for storage principles of traditional Chinese medicines of "pre-event prediction, during-event intervention and post-event identification".

A benchmark for evaluation of structure-based online tools for antibody-antigen binding affinity.

The prediction of binding affinity changes caused by missense mutations can elucidate antigen-antibody interactions. A few accessible structure-based online computational tools have been proposed. However, selecting suitable software for particular research is challenging, especially research on the SARS-CoV-2 spike protein with antibodies. Therefore, benchmarking of the mutation-diverse SARS-CoV-2 datasets is critical. Here, we collected the datasets including 1216 variants about the changes in binding affinity of antigens from 22 complexes for SARS-CoV-2 S proteins and 22 monoclonal antibodies as well as applied them to evaluate the performance of seven binding affinity prediction tools. The tested tools' Pearson correlations between predicted and measured changes in binding affinity were between -0.158 and 0.657, while accuracy in classification tasks on predicting increasing or decreasing affinity ranged from 0.444 to 0.834. These tools performed relatively better on predicting single mutations, especially at epitope sites, whereas poor performance on extremely decreasing affinity. The tested tools were relatively insensitive to the experimental techniques used to obtain structures of complexes. In summary, we constructed a list of datasets and evaluated a range of structure-based online prediction tools that will explicate relevant processes of antigen-antibody interactions and enhance the computational design of therapeutic monoclonal antibodies.

Prediction of protein stability changes upon single-point variant using 3D structure profile.

Identifying protein thermodynamic stability changes upon single-point variants is crucial for studying mutation-induced alterations in protein biophysics, genomic variants, and mutation-related diseases. In the last decade, various computational methods have been developed to predict the effects of single-point variants, but the prediction accuracy is still far from satisfactory for practical applications. Herein, we review approaches and tools for predicting stability changes upon the single-point variant. Most of these methods require tertiary protein structure as input to achieve reliable predictions. However, the availability of protein structures limits the immediate application of these tools. To improve the performance of a computational prediction from a protein sequence without experimental structural information, we introduce a new computational framework: MU3DSP. This method assesses the effects of single-point variants on protein thermodynamic stability based on point mutated protein 3D structure profile. Given a protein sequence with a single variant as input, MU3DSP integrates both sequence-level features and averaged features of 3D structures obtained from sequence alignment to PDB to assess the change of thermodynamic stability induced by the substitution. MU3DSP outperforms existing methods on various benchmarks, making it a reliable tool to assess both somatic and germline substitution variants and assist in protein design. MU3DSP is available as an open-source tool at https://github.com/hurraygong/MU3DSP.

Exploration on Varying Patterns of Morphological Features and Quality of Armeniacae Semen Amarum in Rancid Process Based on Colorimeter, Electronic Nose, and GC/MS Coupled With Human Panel.

In recent years, the domestic and international trade volumes of Chinese medicinal materials (CMMs) keep increasing. By the end of 2019, the total amount of exported CMMs reached as high as US $1.137 billion, while imported was US $2.155 billion. A stable and controllable quality system of CMMs apparently becomes the most important issue, which needs multifaceted collaboration from harvesting CMMs at a proper season to storing CMMs at a proper temperature. However, due to imperfect storage conditions, different kinds of deteriorations are prone to occur, for instance, get moldy or rancid, which not only causes a huge waste of CMM resources but also poses a great threat to clinical medication safety and public health. The key issue is to quickly and accurately distinguish deteriorated CMM samples so as to avoid consuming low-quality or even harmful CMMs. However, some attention has been paid to study the changing quality of deteriorated CMMs and a suitable method for identifying them. In this study, as a medicine and food material which easily becomes rancid, armeniacae semen amarum (ASA) was chosen as a research objective, and experimental ASA samples of different rancidness degrees were collected. Then, various kinds of analytical methods and technologies were applied to explore the changing rules of ASA quality and figure out the key indicators for the quality evaluation of ASA in the rancid process, including the human panel, colorimeter, electronic nose, and GC/MS. This study aims to analyze the correlation between the external morphological features and the inner chemical compounds, to find out the specific components from "quantitative change" to "qualitative change" in the process of "getting rancid," and to discover the dynamic changes in the aforementioned key indicators at different stages of rancidness. The results showed since ASA samples began to get rancid with the extension of storage time, morphological features, namely, surface color and smell, changed significantly, and the degree of rancidness further deepened at the same time. Based on macroscopic identification accomplished via the human panel, ASA samples with varying degrees of rancidness were divided into four groups. The result of colorimeter analysis was in agreement with that of the human panel, as well as the determination of the amygdalin content and peroxide value. Moreover, there were obvious differences in the amygdalin content and peroxide value among ASA samples with different rancidness degrees. With a higher degree of rancidness, the content of amygdalin decreased, while the peroxide value increased significantly. The rancidness degree of ASA has a negative correlation with the amygdalin content and a positive correlation with the peroxide value. The newly discovered nonanal and 2-bromopropiophenone in rancid ASA samples may be the key components of "rancidity smell," and these two components would be the exclusive components that trigger "quantitative change" to "qualitative change" in the process of rancidness of ASA. This study sheds light on studying the internal mechanism of "rancidness" of CMMs and provides an important basis for the effective storage and safe medication of easy-to-get rancid herbs, and it also plays an important foundation for the establishment of a stable and controllable quality system for CMMs.

scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses.

Single-cell RNA-sequencing (scRNA-Seq) is widely used to reveal the heterogeneity and dynamics of tissues, organisms, and complex diseases, but its analyses still suffer from multiple grand challenges, including the sequencing sparsity and complex differential patterns in gene expression. We introduce the scGNN (single-cell graph neural network) to provide a hypothesis-free deep learning framework for scRNA-Seq analyses. This framework formulates and aggregates cell-cell relationships with graph neural networks and models heterogeneous gene expression patterns using a left-truncated mixture Gaussian model. scGNN integrates three iterative multi-modal autoencoders and outperforms existing tools for gene imputation and cell clustering on four benchmark scRNA-Seq datasets. In an Alzheimer's disease study with 13,214 single nuclei from postmortem brain tissues, scGNN successfully illustrated disease-related neural development and the differential mechanism. scGNN provides an effective representation of gene expression and cell-cell relationships. It is also a powerful framework that can be applied to general scRNA-Seq analyses.

Understanding Membrane Protein Drug Targets in Computational Perspective.

Membrane proteins play crucial physiological roles in vivo and are the major category of drug targets for pharmaceuticals. The research on membrane protein is a significant part in the drug discovery. The biological process is a cycled network, and the membrane protein is a vital hub in the network since most drugs achieve the therapeutic effect via interacting with the membrane protein. In this review, typical membrane protein targets are described, including GPCRs, transporters and ion channels. Also, we conclude network servers and databases that are referring to the drug, drug-target information and their relevant data. Furthermore, we chiefly introduce the development and practice of modern medicines, particularly demonstrating a series of state-of-the-art computational models for the prediction of drug-target interaction containing network-based approach and machine-learningbased approach as well as showing current achievements. Finally, we discuss the prospective orientation of drug repurposing and drug discovery as well as propose some improved framework in bioactivity data, created or improved predicted approaches, alternative understanding approaches of drugs bioactivity and their biological processes.

Predicting siRNA efficacy based on multiple selective siRNA representations and their combination at score level.

Small interfering RNAs (siRNAs) may induce to targeted gene knockdown, and the gene silencing effectiveness relies on the efficacy of the siRNA. Therefore, the task of this paper is to construct an effective siRNA prediction method. In our work, we try to describe siRNA from both quantitative and qualitative aspects. For quantitative analyses, we form four groups of effective features, including nucleotide frequencies, thermodynamic stability profile, thermodynamic of siRNA-mRNA interaction, and mRNA related features, as a new mixed representation, in which thermodynamic of siRNA-mRNA interaction is introduced to siRNA efficacy prediction for the first time to our best knowledge. And then an F-score based feature selection is employed to investigate the contribution of each feature and remove the weak relevant features. Meanwhile, we encode the siRNA sequence and existed empirical design rules as a qualitative siRNA representation. These two kinds of siRNA representations are combined to predict siRNA efficacy by supported Vector Regression (SVR) at score level. The experimental results indicate that our method may select the features with powerful discriminative ability and make the two kinds of siRNA representations work at full capacity. The prediction results also demonstrate that our method can outperform other popular siRNA efficacy prediction algorithms.

Is it possible to rapidly and noninvasively identify different plants from Asteraceae using electronic nose with multiple mathematical algorithms?

Many plants originating from the Asteraceae family are applied as herbal medicines and also beverage ingredients in Asian areas, particularly in China. However, they may be confused due to their similar odor, especially when ground into powder, losing their typical macroscopic characteristics. In this paper, 11 different multiple mathematical algorithms, which are commonly used in data processing, were utilized and compared to analyze the electronic nose (E-nose) response signals of different plants from Asteraceae family. Results demonstrate that three-dimensional plot scatter figure of principal component analysis with less extracted components could offer the identification results more visually; simultaneously, all nine kinds of artificial neural network could give classification accuracies at 100%. This paper presents a rapid, accurate, and effective method to distinguish Asteraceae plants based on their response signals in E-nose. It also gives insights to further studies, such as to find unique sensors that are more sensitive and exclusive to volatile components in Chinese herbal medicines and to improve the identification ability of E-nose. Screening sensors made by other novel materials would be also an interesting way to improve identification capability of E-nose.