GPSFun: geometry-aware protein sequence function predictions with language models.

Knowledge of protein function is essential for elucidating disease mechanisms and discovering new drug targets. However, there is a widening gap between the exponential growth of protein sequences and their limited function annotations. In our prior studies, we have developed a series of methods including GraphPPIS, GraphSite, LMetalSite and SPROF-GO for protein function annotations at residue or protein level. To further enhance their applicability and performance, we now present GPSFun, a versatile web server for Geometry-aware Protein Sequence Function annotations, which equips our previous tools with language models and geometric deep learning. Specifically, GPSFun employs large language models to efficiently predict 3D conformations of the input protein sequences and extract informative sequence embeddings. Subsequently, geometric graph neural networks are utilized to capture the sequence and structure patterns in the protein graphs, facilitating various downstream predictions including protein-ligand binding sites, gene ontologies, subcellular locations and protein solubility. Notably, GPSFun achieves superior performance to state-of-the-art methods across diverse tasks without requiring multiple sequence alignments or experimental protein structures. GPSFun is freely available to all users at https://bio-web1.nscc-gz.cn/app/GPSFun with user-friendly interfaces and rich visualizations.

Accurately identifying nucleic-acid-binding sites through geometric graph learning on language model predicted structures.

The interactions between nucleic acids and proteins are important in diverse biological processes. The high-quality prediction of nucleic-acid-binding sites continues to pose a significant challenge. Presently, the predictive efficacy of sequence-based methods is constrained by their exclusive consideration of sequence context information, whereas structure-based methods are unsuitable for proteins lacking known tertiary structures. Though protein structures predicted by AlphaFold2 could be used, the extensive computing requirement of AlphaFold2 hinders its use for genome-wide applications. Based on the recent breakthrough of ESMFold for fast prediction of protein structures, we have developed GLMSite, which accurately identifies DNA- and RNA-binding sites using geometric graph learning on ESMFold predicted structures. Here, the predicted protein structures are employed to construct protein structural graph with residues as nodes and spatially neighboring residue pairs for edges. The node representations are further enhanced through the pre-trained language model ProtTrans. The network was trained using a geometric vector perceptron, and the geometric embeddings were subsequently fed into a common network to acquire common binding characteristics. Finally, these characteristics were input into two fully connected layers to predict binding sites with DNA and RNA, respectively. Through comprehensive tests on DNA/RNA benchmark datasets, GLMSite was shown to surpass the latest sequence-based methods and be comparable with structure-based methods. Moreover, the prediction was shown useful for inferring nucleic-acid-binding proteins, demonstrating its potential for protein function discovery. The datasets, codes, and trained models are available at https://github.com/biomed-AI/nucleic-acid-binding.

Fast and accurate protein intrinsic disorder prediction by using a pretrained language model.

Determining intrinsically disordered regions of proteins is essential for elucidating protein biological functions and the mechanisms of their associated diseases. As the gap between the number of experimentally determined protein structures and the number of protein sequences continues to grow exponentially, there is a need for developing an accurate and computationally efficient disorder predictor. However, current single-sequence-based methods are of low accuracy, while evolutionary profile-based methods are computationally intensive. Here, we proposed a fast and accurate protein disorder predictor LMDisorder that employed embedding generated by unsupervised pretrained language models as features. We showed that LMDisorder performs best in all single-sequence-based methods and is comparable or better than another language-model-based technique in four independent test sets, respectively. Furthermore, LMDisorder showed equivalent or even better performance than the state-of-the-art profile-based technique SPOT-Disorder2. In addition, the high computation efficiency of LMDisorder enabled proteome-scale analysis of human, showing that proteins with high predicted disorder content were associated with specific biological functions. The datasets, the source codes, and the trained model are available at https://github.com/biomed-AI/LMDisorder.

Highly Dispersed Pt Catalysts on Hierarchically Mesoporous Organosilica@Silica Nanoparticles with a Core-Shell Structure for Polycyclic Aromatic Hydrogenation.

Hydrogenation of naphthalene can effectively reduce the content of aromatics in oil and generate high-value products. A series of Pt-based aluminum-modified core-shell-structured hierarchically periodic mesoporous organosilica@mesoporous silica nanoparticles (Pt/Al-x-PMOs@MSNs) were successfully synthesized and tested for the hydrogenation properties, with preferable mass transfer of macromolecular reactants in the pores and increasing the total acidity of the catalysts. Moreover, the physicochemical properties of the core-shell-structured Pt-based catalysts were systematically analyzed using various characterization techniques. At 300 °C, the naphthalene conversion on the Pt/Al-10-PMOs@MSNs catalyst reached up to 100%, the selectivity of trans-decalin reached 83.9%, and the rate constants (k1, k2) and TOF were 13.2 × 10-6 mol·g-1·s-1, 1.7 × 10-7 mol·g-1·s-1, and 218.8 h-1, respectively. In the presence of sulfur, the naphthalene hydrogenation over the Pt/Al-10-PMOs@MSN catalyst first decreased to around 40% and then recovered to the original level, which originated from the synergistic effect of the texture and chemical properties over the Pt/Al-10-PMOs@MSNs with an excellent performance.

Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy.

OBJECTIVES: Recent studies have revealed the change of molecular subtypes in breast cancer (BC) after neoadjuvant therapy (NAT). This study aims to construct a non-invasive model for predicting molecular subtype alteration in breast cancer after NAT. METHODS: Eighty-two estrogen receptor (ER)-negative/ human epidermal growth factor receptor 2 (HER2)-negative or ER-low-positive/HER2-negative breast cancer patients who underwent NAT and completed baseline MRI were retrospectively recruited between July 2010 and November 2020. Subtype alteration was observed in 21 cases after NAT. A 2D-DenseUNet machine-learning model was built to perform automatic segmentation of breast cancer. 851 radiomic features were extracted from each MRI sequence (T2-weighted imaging, ADC, DCE, and contrast-enhanced T1-weighted imaging), both in the manual and auto-segmentation masks. All samples were divided into a training set (n = 66) and a test set (n = 16). XGBoost model with 5-fold cross-validation was performed to predict molecular subtype alterations in breast cancer patients after NAT. The predictive ability of these models was subsequently evaluated by the AUC of the ROC curve, sensitivity, and specificity. RESULTS: A model consisting of three radiomics features from the manual segmentation of multi-sequence MRI achieved favorable predictive efficacy in identifying molecular subtype alteration in BC after NAT (cross-validation set: AUC = 0.908, independent test set: AUC = 0.864); whereas an automatic segmentation approach of BC lesions on the DCE sequence produced good segmentation results (Dice similarity coefficient = 0.720). CONCLUSIONS: A machine learning model based on baseline MRI is proven useful for predicting molecular subtype alterations in breast cancer after NAT. KEY POINTS: • Machine learning models using MRI-based radiomics signature have the ability to predict molecular subtype alterations in breast cancer after neoadjuvant therapy, which subsequently affect treatment protocols. • The application of deep learning in the automatic segmentation of breast cancer lesions from MRI images shows the potential to replace manual segmentation..

The Influence of Pore Structure and Acidity on the Hydrodesulfurization of Dibenzothiophene over NiMo-Supported Catalysts.

A series of mesoporous materials of SBA-16 were in situ incorporated into ZSM-5 crystallites via a two-step self-assemble method, and hydrodesulfurization (HDS) catalysts were prepared on the corresponding ZSM-5/SBA-16 (ZS) composites. The characterization results indicated that ZSM-5 nanoseeds were fabricated into the silica framework of the ZS composites, and the three-dimensional Im3m cubic structure of SBA-16 was retained simultaneously. In addition, the ZS series materials possessed open pores and large surfaces, which would facilitate the diffusion of reactants in the mesoporous channels. Moreover, the introduction of ZSM-5 seeds into composites could enhance the acidities of supports. As a result, the NiMo/ZS series catalysts exhibited high activities for DBT HDS processes. The NiMo/ZS-160 catalyst exhibited the highest catalytic efficiency (96.5%), which was apparently attributed to the synergistic contributions of the physicochemical properties of ZS supports and the dispersion states of active metals. Correspondingly, DBT HDS reactions over the NiMo/ZS series catalysts mainly proceeded via a hydrogenation desulfurization route that benefitted from the enhanced acidities especially the total Brønsted acid.