Machine Learning-Based Integrated Multiomics Characterization of Colorectal Cancer Reveals Distinctive Metabolic Signatures.

The metabolic signature identification of colorectal cancer is critical for its early diagnosis and therapeutic approaches that will significantly block cancer progression and improve patient survival. Here, we combined an untargeted metabolic analysis strategy based on internal extractive electrospray ionization mass spectrometry and the machine learning approach to analyze metabolites in 173 pairs of cancer samples and matched normal tissue samples to build robust metabolic signature models for diagnostic purposes. Screening and independent validation of metabolic signatures from colorectal cancers via machine learning methods (Logistic Regression_L1 for feature selection and eXtreme Gradient Boosting for classification) was performed to generate a panel of seven signatures with good diagnostic performance (the accuracy of 87.74%, sensitivity of 85.82%, and specificity of 89.66%). Moreover, seven signatures were evaluated according to their ability to distinguish between cancer and normal tissues, with the metabolic molecule PC (30:0) showing good diagnostic performance. In addition, genes associated with PC (30:0) were identified by multiomics analysis (combining metabolic data with transcriptomic data analysis) and our results showed that PC (30:0) could promote the proliferation of colorectal cancer cell SW480, revealing the correlation between genetic changes and metabolic dysregulation in cancer. Overall, our results reveal potential determinants affecting metabolite dysregulation, paving the way for a mechanistic understanding of altered tissue metabolites in colorectal cancer and design interventions for manipulating the levels of circulating metabolites.

Predicting effect of anti-PD-1/PD-L1 inhibitors therapy for hepatocellular carcinoma by detecting plasma metabolite based on UHPLC-MS.

Introduction: Anti-PD-1/PD-L1 inhibitors therapy has become a promising treatment for hepatocellular carcinoma (HCC), while the therapeutic efficacy varies significantly among effects for individual patients are significant difference. Unfortunately, specific predictive biomarkers indicating the degree of benefit for patients and thus guiding the selection of suitable candidates for immune therapy remain elusive.no specific predictive biomarkers are available indicating the degree of benefit for patients and thus screening the preferred population suitable for the immune therapy. Methods: Ultra-high-pressure liquid chromatography-mass spectrometry (UHPLC-MS) considered is an important method for analyzing biological samples, since it has the advantages of high rapid, high sensitivity, and high specificity. Ultra-high-pressure liquid chromatography-mass spectrometry (UHPLC-MS) has emerged as a pivotal method for analyzing biological samples due to its inherent advantages of rapidity, sensitivity, and specificity. In this study, potential metabolite biomarkers that can predict the therapeutic effect of HCC patients receiving immune therapy were identified by UHPLC-MS. Results: A partial least-squares discriminant analysis (PLS-DA) model was established using 14 glycerophospholipid metabolites mentioned above, and good prediction parameters (R2 = 0.823, Q2 = 0.615, prediction accuracy = 0.880 and p < 0.001) were obtained. The relative abundance of glycerophospholipid metabolite ions is closely related to the survival benefit of HCC patients who received immune therapy. Discussion: This study reveals that glycerophospholipid metabolites play a crucial role in predicting the efficacy of immune therapy for HCC.

PCBP1 interacts with the HTLV-1 Tax oncoprotein to potentiate NF-κB activation.

Human T-cell leukemia virus type 1 (HTLV-1) is the etiological agent of adult T-cell leukemia/lymphoma. The HTLV-1 Tax constitutively activates nuclear factor-κB (NF-κB) to promote the survival and transformation of HTLV-1-infected T cells. Despite extensive study of Tax, how Tax interacts with host factors to regulate NF-κB activation and HTLV-1-driven cell proliferation is not entirely clear. Here, we showed that overexpression of Poly (rC)-binding protein 1 (PCBP1) promoted Tax-mediated IκB kinase (IKK)-NF-κB signaling activation, whereas knockdown of PCBP1 attenuated Tax-dependent IKK-NF-κB activation. However, Tax activation of HTLV-1 long terminal repeat was unaffected by PCBP1. Furthermore, depletion of PCBP1 led to apoptosis and reduced proliferation of HTLV-1-transformed cells. Mechanistically, PCBP1 interacted and co-localized with Tax in the cytoplasm, and PCBP1 KH3 domain was indispensable for the interaction between PCBP1 and Tax. Moreover, PCBP1 facilitated the assembly of Tax/IKK complex. Collectively, our results demonstrated that PCBP1 may exert an essential effect in Tax/IKK complex combination and subsequent NF-κB activation, which provides a novel insight into the pathogenetic mechanisms of HTLV-1.

8-Cl-Ado and 8-NH2-Ado synergize with venetoclax to target the methionine-MAT2A-SAM axis in acute myeloid leukemia.

Targeting the metabolic dependencies of acute myeloid leukemia (AML) cells is a promising therapeutical strategy. In particular, the cysteine and methionine metabolism pathway (C/M) is significantly altered in AML cells compared to healthy blood cells. Moreover, methionine has been identified as one of the dominant amino acid dependencies of AML cells. Through RNA-seq, we found that the two nucleoside analogs 8-chloro-adenosine (8CA) and 8-amino-adenosine (8AA) significantly suppress the C/M pathway in AML cells, and methionine-adenosyltransferase-2A (MAT2A) is one of most significantly downregulated genes. Additionally, mass spectrometry analysis revealed that Venetoclax (VEN), a BCL-2 inhibitor recently approved by the FDA for AML treatment, significantly decreases the intracellular level of methionine in AML cells. Based on these findings, we hypothesized that combining 8CA or 8AA with VEN can efficiently target the Methionine-MAT2A-S-adenosyl-methionine (SAM) axis in AML. Our results demonstrate that VEN and 8CA/8AA synergistically decrease the SAM biosynthesis and effectively target AML cells both in vivo and in vitro. These findings suggest the promising potential of combining 8CA/8AA and VEN for AML treatment by inhibiting Methionine-MAT2A-SAM axis and provide a strong rationale for our recently activated clinical trial.

Noninvasive tests maintain high accuracy for advanced fibrosis in chronic hepatitis B patients with different nomenclatures of steatotic liver disease.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a new nomenclature proposed in 2023. We aimed to compare the diagnostic efficacy of noninvasive tests (NITs) for advanced fibrosis under different nomenclatures in patients with chronic hepatitis B (CHB). A total of 844 patients diagnosed with CHB and concurrent steatotic liver disease (SLD) by liver biopsy were retrospectively enrolled and divided into four groups. The performances of fibrosis-4 (FIB-4), gamma-glutamyl transpeptidase to platelet ratio index (GPRI), aspartate aminotransferase to platelet ratio index (APRI), and liver stiffness measurement (LSM) were compared among the four groups. The four NITs showed similar diagnostic efficacy for nonalcoholic fatty liver disease (NAFLD), MASLD, and metabolic dysfunction-associated fatty liver disease (MAFLD) in patients with CHB with advanced fibrosis. LSM showed the most stable accuracy for NAFLD (AUC = 0.842), MASLD (AUC = 0.846), and MAFLD (AUC = 0.863) compared with other NITs (p < 0.05). Among the four NITs, APRI (AUC = 0.841) and GPRI (AUC = 0.844) performed best in patients with CHB & MetALD (p < 0.05). The cutoff value for GPRI in patients with CHB & MetALD was higher than that in the other three groups, while further comparisons of NITs at different fibrosis stages showed that the median GPRI of CHB & MetALD (1.113) at F3-4 was higher than that in the CHB & MASLD group (0.508) (p < 0.05). Current NITs perform adequately in patients with CHB and SLD; however, alterations in cutoff values for CHB & MetALD need to be noted.

Internal m 6 A and m 7 G RNA modifications in hematopoietic system and acute myeloid leukemia.

ABSTRACT: Epitranscriptomics focuses on the RNA-modification-mediated post-transcriptional regulation of gene expression. The past decade has witnessed tremendous progress in our understanding of the landscapes and biological functions of RNA modifications, as prompted by the emergence of potent analytical approaches. The hematopoietic system provides a lifelong supply of blood cells, and gene expression is tightly controlled during the differentiation of hematopoietic stem cells (HSCs). The dysregulation of gene expression during hematopoiesis may lead to severe disorders, including acute myeloid leukemia (AML). Emerging evidence supports the involvement of the mRNA modification system in normal hematopoiesis and AML pathogenesis, which has led to the development of small-molecule inhibitors that target N6-methyladenosine (m 6 A) modification machinery as treatments. Here, we summarize the latest findings and our most up-to-date information on the roles of m 6 A and N7-methylguanine in both physiological and pathological conditions in the hematopoietic system. Furthermore, we will discuss the therapeutic potential and limitations of cancer treatments targeting m 6 A.

METTL16 promotes liver cancer stem cell self-renewal via controlling ribosome biogenesis and mRNA translation.

BACKGROUND: While liver cancer stem cells (CSCs) play a crucial role in hepatocellular carcinoma (HCC) initiation, progression, recurrence, and treatment resistance, the mechanism underlying liver CSC self-renewal remains elusive. We aim to characterize the role of Methyltransferase 16 (METTL16), a recently identified RNA N6-methyladenosine (m6A) methyltransferase, in HCC development/maintenance, CSC stemness, as well as normal hepatogenesis. METHODS: Liver-specific Mettl16 conditional KO (cKO) mice were generated to assess its role in HCC pathogenesis and normal hepatogenesis. Hydrodynamic tail-vein injection (HDTVi)-induced de novo hepatocarcinogenesis and xenograft models were utilized to determine the role of METTL16 in HCC initiation and progression. A limiting dilution assay was utilized to evaluate CSC frequency. Functionally essential targets were revealed via integrative analysis of multi-omics data, including RNA-seq, RNA immunoprecipitation (RIP)-seq, and ribosome profiling. RESULTS: METTL16 is highly expressed in liver CSCs and its depletion dramatically decreased CSC frequency in vitro and in vivo. Mettl16 KO significantly attenuated HCC initiation and progression, yet only slightly influenced normal hepatogenesis. Mechanistic studies, including high-throughput sequencing, unveiled METTL16 as a key regulator of ribosomal RNA (rRNA) maturation and mRNA translation and identified eukaryotic translation initiation factor 3 subunit a (eIF3a) transcript as a bona-fide target of METTL16 in HCC. In addition, the functionally essential regions of METTL16 were revealed by CRISPR gene tiling scan, which will pave the way for the development of potential inhibitor(s). CONCLUSIONS: Our findings highlight the crucial oncogenic role of METTL16 in promoting HCC pathogenesis and enhancing liver CSC self-renewal through augmenting mRNA translation efficiency.

Therapeutic targeting Tudor domains in leukemia via CRISPR-Scan Assisted Drug Discovery.

Epigenetic dysregulation has been reported in multiple cancers including leukemias. Nonetheless, the roles of the epigenetic reader Tudor domains in leukemia progression and therapy remain unexplored. Here, we conducted a Tudor domain-focused CRISPR screen and identified SGF29, a component of SAGA/ATAC acetyltransferase complexes, as a crucial factor for H3K9 acetylation, ribosomal gene expression, and leukemogenesis. To facilitate drug development, we integrated the CRISPR tiling scan with compound docking and molecular dynamics simulation, presenting a generally applicable strategy called CRISPR-Scan Assisted Drug Discovery (CRISPR-SADD). Using this approach, we identified a lead inhibitor that selectively targets SGF29's Tudor domain and demonstrates efficacy against leukemia. Furthermore, we propose that the structural genetics approach used in our study can be widely applied to diverse fields for de novo drug discovery.

EnAMP: A novel deep learning ensemble antibacterial peptide recognition algorithm based on multi-features.

Antimicrobial peptides (AMPs), as the preferred alternatives to antibiotics, have wide application with good prospects. Identifying AMPs through wet lab experiments remains expensive, time-consuming and challenging. Many machine learning methods have been proposed to predict AMPs and achieved good results. In this work, we combine two kinds of word embedding features with the statistical features of peptide sequences to develop an ensemble classifier, named EnAMP, in which, two deep neural networks are trained based on Word2vec and Glove word embedding features of peptide sequences, respectively, meanwhile, we utilize statistical features of peptide sequences to train random forest and support vector machine classifiers. The average of four classifiers is the final prediction result. Compared with other state-of-the-art algorithms on six datasets, EnAMP outperforms most existing models with similar computational costs, even when compared with high computational cost algorithms based on Bidirectional Encoder Representation from Transformers (BERT), the performance of our model is comparable. EnAMP source code and the data are available at https://github.com/ruisue/EnAMP.

Efficient catalyst-free N2 fixation by water radical cations under ambient conditions.

The growth and sustainable development of humanity is heavily dependent upon molecular nitrogen (N2) fixation. Herein we discover ambient catalyst-free disproportionation of N2 by water plasma which occurs via the distinctive HONH-HNOH+• intermediate to yield economically valuable nitroxyl (HNO) and hydroxylamine (NH2OH) products. Calculations suggest that the reaction is prompted by the coordination of electronically excited N2 with water dimer radical cation, (H2O)2+•, in its two-center-three-electron configuration. The reaction products are collected in a 76-needle array discharge reactor with product yields of 1.14 µg cm-2 h-1 for NH2OH and 0.37 µg cm-2 h-1 for HNO. Potential applications of these compounds are demonstrated to make ammonia (for NH2OH), as well as to chemically react and convert cysteine, and serve as a neuroprotective agent (for HNO). The conversion of N2 into HNO and NH2OH by water plasma could offer great profitability and reduction of polluting emissions, thus giving an entirely look and perspectives to the problem of green N2 fixation.

Combination of histological and metabolomic assessments to evaluate the potential pharmacological efficacy of saikosaponin D.

Saikosaponin D (SsD), a natural triterpenoid saponin compound, exhibits notable potential in suppressing tumor growth and inhibiting metastasis, particularly in breast cancer. However, its underlying mechanism of action for SsD remains unclear. In this study, a combination strategy to reveal the metabolism modulation of SsD on breast cancer was performed by integration of histopathological assessments and untargeted metabolomics analysis. Pathological evaluation of the efficacy of SsD from a visual and intuitive perspective. Accordingly, a non-targeted metabolomics study was used to investigate the pharmacological efficacy using a set of serum samples from mice before and after (0-30 days) modulated with SsD based on ultra-high performance liquid chromatography tandem orbitrap mass spectrometry to discover metabolite biomarkers for finding the key metabolic mechanism in a molecular perspective. As a result, 20 metabolites were selected as potential biomarkers for SsD efficacy evaluation with high sensitivity and specificity. These metabolites changes were involved in sphingolipid metabolism, glycerophospholipid metabolism, phenylalanine and tryptophan metabolism, and phenylalanine, tyrosine and tryptophan biosynthesis pathways, suggesting that SsD exerted anti-breast cancer effects through the regulation of the underlying metabolism. In conclusion, we developed a new analysis strategy that effectively discovers tumor-progressing related metabolite biomarkers in serum for pharmacological efficacy evaluation.

Targeting PRMT9-mediated arginine methylation suppresses cancer stem cell maintenance and elicits cGAS-mediated anticancer immunity.

Current anticancer therapies cannot eliminate all cancer cells, which hijack normal arginine methylation as a means to promote their maintenance via unknown mechanisms. Here we show that targeting protein arginine N-methyltransferase 9 (PRMT9), whose activities are elevated in blasts and leukemia stem cells (LSCs) from patients with acute myeloid leukemia (AML), eliminates disease via cancer-intrinsic mechanisms and cancer-extrinsic type I interferon (IFN)-associated immunity. PRMT9 ablation in AML cells decreased the arginine methylation of regulators of RNA translation and the DNA damage response, suppressing cell survival. Notably, PRMT9 inhibition promoted DNA damage and activated cyclic GMP-AMP synthase, which underlies the type I IFN response. Genetically activating cyclic GMP-AMP synthase in AML cells blocked leukemogenesis. We also report synergy of a PRMT9 inhibitor with anti-programmed cell death protein 1 in eradicating AML. Overall, we conclude that PRMT9 functions in survival and immune evasion of both LSCs and non-LSCs; targeting PRMT9 may represent a potential anticancer strategy.

NRAS Mutant Dictates AHCYL1-Governed ER Calcium Homeostasis for Melanoma Tumor Growth.

Calcium homeostasis is critical for cell proliferation, and emerging evidence shows that cancer cells exhibit altered calcium signals to fulfill their need for proliferation. However, it remains unclear whether there are oncogene-specific calcium homeostasis regulations that can expose novel therapeutic targets. Here, from RNAi screen, we report that adenosylhomocysteinase like protein 1 (AHCYL1), a suppressor of the endoplasmic reticulum (ER) calcium channel protein inositol trisphosphate receptor (IP3R), is selectively upregulated and critical for cell proliferation and tumor growth potential of human NRAS-mutated melanoma, but not for melanoma expressing BRAF V600E. Mechanistically, AHCYL1 deficiency results in decreased ER calcium levels, activates the unfolded protein response (UPR), and triggers downstream apoptosis. In addition, we show that AHCYL1 transcription is regulated by activating transcription factor 2 (ATF2) in NRAS-mutated melanoma. Our work provides evidence for oncogene-specific calcium regulations and suggests AHCYL1 as a novel therapeutic target for RAS mutant-expressing human cancers, including melanoma. IMPLICATIONS: Our findings suggest that targeting the AHCYL1-IP3R axis presents a novel therapeutic approach for NRAS-mutated melanomas, with potential applicability to all cancers harboring RAS mutations, such as KRAS-mutated human colorectal cancers.

New sights of low dose IL-2: Restoration of immune homeostasis for viral infection.

Viral infection poses a significant threat to human health. In addition to the damage caused by viral replication, the immune response it triggers often leads to more serious adverse consequences. After the occurrence of viral infection, in addition to the adverse consequences of infection, chronic infections can also lead to virus-related autoimmune diseases and tumours. At the same time, the immune response triggered by viral infection is complex, and dysregulated immune response may lead to the occurrence of immune pathology and macrophage activation syndrome. In addition, it may cause secondary immune suppression, especially in patients with compromised immune system, which could lead to the occurrence of secondary infections by other pathogens. This can often result in more severe clinical outcomes. Therefore, regarding the treatment of viral infections, restoring the balance of the immune system is crucial in addition to specific antiviral medications. In recent years, scientists have made an interesting finding that low dose IL-2 (ld-IL-2) could potentially have a crucial function in regulating the immune system and reducing the chances of infection, especially viral infection. Ld-IL-2 exerts immune regulatory effects in different types of viral infections by modulating CD4+ T subsets, CD8+ T cells, natural killer cells, and so on. Our review summarised the role of IL-2 or IL-2 complexes in viral infections. Ld-IL-2 may be an effective strategy for enhancing host antiviral immunity and preventing infection from becoming chronic; additionally, the appropriate use of it can help prevent excessive inflammatory response after infection. In the long term, it may reduce the occurrence of infection-related autoimmune diseases and tumours by promoting the restoration of early immune homeostasis. Furthermore, we have also summarised the application of ld-IL-2 in the context of autoimmune diseases combined with viral infections; it may be a safe and effective strategy for restoring immune homeostasis without compromising the antiviral immune response. In conclusion, focusing on the role of ld-IL-2 in viral infections may provide a new perspective for regulating immune responses following viral infections and improving prognosis.

RNA m6A reader YTHDF2 facilitates precursor miR-126 maturation to promote acute myeloid leukemia progression.

As the most common internal modification of mRNA, N6-methyladenosine (m6A) and its regulators modulate gene expression and play critical roles in various biological and pathological processes including tumorigenesis. It was reported previously that m6A methyltransferase (writer), methyltransferase-like 3 (METTL3) adds m6A in primary microRNAs (pri-miRNAs) and facilitates its processing into precursor miRNAs (pre-miRNAs). However, it is unknown whether m6A modification also plays a role in the maturation process of pre-miRNAs and (if so) whether such a function contributes to tumorigenesis. Here, we found that YTHDF2 is aberrantly overexpressed in acute myeloid leukemia (AML) patients, especially in relapsed patients, and plays an oncogenic role in AML. Moreover, YTHDF2 promotes expression of miR-126-3p (also known as miR-126, as it is the main product of precursor miR-126 (pre-miR-126)), a miRNA that was reported as an oncomiRNA in AML, through facilitating the processing of pre-miR-126 into mature miR-126. Mechanistically, YTHDF2 recognizes m6A modification in pre-miR-126 and recruits AGO2, a regulator of pre-miRNA processing, to promote the maturation of pre-miR-126. YTHDF2 positively and negatively correlates with miR-126 and miR-126's downstream target genes, respectively, in AML patients, and forced expression of miR-126 could largely rescue YTHDF2/Ythdf2 depletion-mediated suppression on AML cell growth/proliferation and leukemogenesis, indicating that miR-126 is a functionally important target of YTHDF2 in AML. Overall, our studies not only reveal a previously unappreciated YTHDF2/miR-126 axis in AML and highlight the therapeutic potential of targeting this axis for AML treatment, but also suggest that m6A plays a role in pre-miRNA processing that contributes to tumorigenesis.

Variations in the oral microbiome and metabolome of methamphetamine users.

Drug addiction can seriously damage human physical and mental health, while detoxification is a long and difficult process. Although studies have reported changes in the oral microbiome of methamphetamine (METH) users, the role that the microbiome plays in the process of drug addiction is still unknown. This study aims to explore the function of the microbiome based on analysis of the variations in the oral microbiome and metabolome of METH users. We performed the 16S rRNA sequencing analysis based on the oral saliva samples collected from 278 METH users and 105 healthy controls (CTL). In addition, the untargeted metabolomic profiling was conducted based on 220 samples. Compared to the CTL group, alpha diversity was reduced in the group of METH users and the relative abundances of Peptostreptococcus and Gemella were significantly increased, while the relative abundances of Campylobacter and Aggregatibacter were significantly decreased. Variations were also detected in oral metabolic pathways, including enhanced tryptophan metabolism, lysine biosynthesis, purine metabolism, and steroid biosynthesis. Conversely, the metabolic pathways of porphyrin metabolism, glutathione metabolism, and pentose phosphate were significantly reduced. It was speculated that four key microbial taxa, i.e., Peptostreptococcus, Gemella, Campylobacter, and Aggregatibacter, could be involved in the toxicity and addiction mechanisms of METH by affecting the above metabolic pathways. It was found that with the increase of drug use years, the content of tryptamine associated with neuropsychiatric disorders was gradually increased. Our study provides novel insights into exploring the toxic damage and addiction mechanisms underlying the METH addiction.IMPORTANCEIt was found that with the increase of drug use years, the content of tryptamine associated with neuropsychiatric disorders gradually increased. The prediction models based on oral microbiome and metabolome could effectively predict the methamphetamine (METH) smoking. Our study provides novel insights into the exploration of the molecular mechanisms regulating the toxic damage and addiction of METH as well as new ideas for early prevention and treatment strategies of METH addiction.

RNA Modifications in Cancer Metabolism and Tumor Microenvironment.

RNA modifications have recently been recognized as essential posttranscriptional regulators of gene expression in eukaryotes. Investigations over the past decade have revealed that RNA chemical modifications have profound effects on tumor initiation, progression, refractory, and recurrence. Tumor cells are notorious for their robust plasticity in response to the stressful microenvironment and undergo metabolic adaptations to sustain rapid cell proliferation, which is termed as metabolic reprogramming. Meanwhile, cancer-associated metabolic reprogramming leads to substantial alterations of intracellular and extracellular metabolites, which further reshapes the tumor microenvironment (TME). Moreover, cancer cells compete with tumor-infiltrating immune cells for the limited nutrients to maintain their proliferation and function in the TME. In this chapter, we review recent interesting findings on the engagement of epitranscriptomic pathways, especially the ones associated with N6-methyladenosine (m6A), in the regulation of cancer metabolism and the surrounding microenvironment. We also discuss the promising therapeutic approaches targeting RNA modifications for anti-tumor therapy.

π Bridge Engineering-Boosted Dual Enhancement of Type-I Photodynamic and Photothermal Performance for Mitochondria-Targeting Multimodal Phototheranostics of Tumor.

Designing mitochondria-targeting phototheranostic agents (PTAs), which can simultaneously possess exceptional and balanced type-I photodynamic therapy (PDT) and photothermal therapy (PTT) performance, still remains challenging. Herein, benzene, furan, and thiophene were utilized as π bridges to develop multifunctional PTAs. STB with thiophene as a π bridge, in particular, benefiting from stronger donor-accepter (D-A) interactions, reduced the singlet-triplet energy gap (ΔES1-T1), allowed more free intramolecular rotation, and exhibited outstanding near-infrared (NIR) emission, effective type-I reactive oxygen species (ROS) generation, and relatively high photothermal conversion efficiency (PCE) of 51.9%. In vitro and in vivo experiments demonstrated that positive-charged STB not only can actively target the mitochondria of tumor cells but also displayed strong antitumor effects and excellent in vivo imaging ability. This work subtly established a win-win strategy by π bridge engineering, breaking the barrier of making a balance between ROS generation and photothermal conversion, boosting a dual enhancement of PDT and PTT performance, and stimulating the development of multimodal imaging-guided precise cancer phototherapy.

EnILs: A General Ensemble Computational Approach for Predicting Inducing Peptides of Multiple Interleukins.

Interleukins (ILs) are a group of multifunctional cytokines, which play important roles in immune regulations and inflammatory responses. Recently, IL-6 has been found to affect the development of COVID-19, and significantly elevated levels of IL-6 cytokines have been reported in patients with severe COVID-19. IL-10 and IL-17 are anti-inflammatory and proinflammatory cytokines, respectively, which play multiple protective roles in host defense against pathogens. At present, a number of machine learning methods have been proposed to predict ILs inducing peptides, but their predictive performance needs to be further improved, and the inducing peptides of different ILs are predicted separately, rather than using a general approach. In our work, we combine the statistical features of peptide sequence with word embedding to design a general ensemble model named EnILs to predict inducing peptides of different ILs, in which the predictive probabilities of random forest, eXtreme Gradient Boosting and neural network are integrated in an average way. Compared with the state-of-the-art machine learning methods, EnILs shows considerable performance in the prediction of IL-6, IL-10, and IL-17 inducing peptides. In addition, we predict the most promising IL-6 inducing peptides in Severe Acute Respiratory Syndrome Coronavirus 2 spike protein in the case study for further experimental verification.