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.

Study on the dynamic effects of plateau hypoxic and cold environment on the thermal adaptation of short-term sojourners in Xizang.

The plateau hypoxic environment can affect the thermoregulation process of the human body, and due to the different acclimatization ability to the hypoxic environment, the thermal requirements among the people who enter Xizang at different times may be different. Accordingly, this study aims to clarify how plateau hypoxic environments influence the physiological and subjective responses of people entering Xizang at different times. And field experiments were conducted in Xi'an and Lhasa, respectively, to compare the thermal responses and oxygen responses of the subjects under different temperature conditions on the plain, the first day of entering Xizang and the 15th day of entering Xizang. The results showed that under the hypoxic environment, the thermal sensation of the subjects decreased. With the extension of the time entering Xizang, the influence of the hypoxic environment on thermal comfort was gradually weakened, but under the low temperature environment, the effect of hypoxia on thermal response was not significantly reduced. The results of this study can help to reveal how plateau hypoxic environments affect human thermal comfort and provide a theoretical basis for the design of indoor thermal environment parameters suitable for sojourners entering Xizang at different times.

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.

Modulation of HIV-1 capsid multimerization by sennoside A and sennoside B via interaction with the NTD/CTD interface in capsid hexamer.

Small molecules that bind to the pocket targeted by a peptide, termed capsid assembly inhibitor (CAI), have shown antiviral effects with unique mechanisms of action. We report the discovery of two natural compounds, sennoside A (SA) and sennoside B (SB), derived from medicinal plants that bind to this pocket in the C-terminal domain of capsid (CA CTD). Both SA and SB were identified via a drug-screening campaign that utilized a time-resolved fluorescence resonance energy transfer assay. They inhibited the HIV-1 CA CTD/CAI interaction at sub-micromolar concentrations of 0.18 µM and 0.08 µM, respectively. Mutation of key residues (including Tyr 169, Leu 211, Asn 183, and Glu 187) in the CA CTD decreased their binding affinity to the CA monomer, from 1.35-fold to 4.17-fold. Furthermore, both compounds induced CA assembly in vitro and bound directly to the CA hexamer, suggesting that they interact with CA beyond the CA CTD. Molecular docking showed that both compounds were bound to the N-terminal domain (NTD)/CTD interface between adjacent protomers within the CA hexamer. SA established a hydrogen-bonding network with residues N57, V59, Q63, K70, and N74 of CA1-NTD and Q179 of CA2-CTD. SB formed hydrogen bonds with the N53, N70, and N74 residues of CA1-NTD, and the A177and Q179 residues of CA2-CTD. Both compounds, acting as glue, can bring αH4 in the NTD and αH9 in the CTD of the NTD/CTD interface close to each other. Collectively, our research indicates that SA and SB, which enhance CA assembly, could serve as novel chemical tools to identify agents that modulate HIV-1 CA assembly. These natural compounds may potentially lead to the development of new antiviral therapies with unique mechanisms of action.

Comparison of Surgical Outcomes Between Short-Segment Open and Percutaneous Pedicle Screw Fixation Techniques for Thoracolumbar Fractures.

BACKGROUND This study aimed to compare the surgical outcomes between open pedicle screw fixation (OPSF) and percutaneous pedicle screw fixation (PPSF) for the treatment of thoracolumbar fractures, which has received scant research attention to date. MATERIAL AND METHODS Eight-four patients with acute and subacute thoracolumbar fractures who were treated with SSPSF from January 2013 to June 2014 at the Changzhou Hospital of Traditional Chinese Medicine (Changzhou, China) were retrospectively reviewed. The patients were divided into 4 groups: the OPSF with 4 basic screws (OPSF-4) group, the OPSF with 4 basic and 2 additional screws (OPSF-6) group, the PPSF with 4 basic screws (PPSF-4) group, and the PPSF with 4 basic and 2 additional screws (PPSF-6) group. The intraoperative, immediate postoperative, and over 1-year follow-up outcomes were evaluated and compared among these groups. RESULTS Blood loss in the PPSF-4 group and the PPSF-6 group was significantly less than in the OPSF-4 group and the OPSF-6 group (P<0.05). The OPSF-6 group exhibited significantly higher immediate postoperative correction percentage of anterior column height of fractured vertebra than the other 3 groups (P<0.05), and higher correction of sagittal regional Cobb angle and kyphotic angle of injured vertebra than in the PPSF-4 and -6 groups (P<0.05). In addition, there was no significant difference in the correction loss of percentage of anterior column height, and loss of sagittal Cobb angle and kyphotic angle of fractured vertebrae at final follow-up among the 4 groups (P>0.05). CONCLUSIONS OPSF with 6 screws had an advantage in the correction of injured vertebral height and kyphosis, and PPSF reduced the intraoperative blood loss of patients.