Flux regulation through glycolysis and respiration is balanced by inositol pyrophosphates in yeast.

Although many prokaryotes have glycolysis alternatives, it's considered as the only energy-generating glucose catabolic pathway in eukaryotes. Here, we managed to create a hybrid-glycolysis yeast. Subsequently, we identified an inositol pyrophosphatase encoded by OCA5 that could regulate glycolysis and respiration by adjusting 5-diphosphoinositol 1,2,3,4,6-pentakisphosphate (5-InsP7) levels. 5-InsP7 levels could regulate the expression of genes involved in glycolysis and respiration, representing a global mechanism that could sense ATP levels and regulate central carbon metabolism. The hybrid-glycolysis yeast did not produce ethanol during growth under excess glucose and could produce 2.68 g/L free fatty acids, which is the highest reported production in shake flask of Saccharomyces cerevisiae. This study demonstrated the significance of hybrid-glycolysis yeast and determined Oca5 as an inositol pyrophosphatase controlling the balance between glycolysis and respiration, which may shed light on the role of inositol pyrophosphates in regulating eukaryotic metabolism.

Unveil the origin of voltage oscillation for sodium-ion batteries operating at -40 °C.

Voltage oscillation at subzero in sodium-ion batteries (SIBs) has been a common but overlooked scenario, almost yet to be understood. For example, the phenomenon seriously deteriorates the performance of Na3V2(PO4)3 (NVP) cathode in PC (propylene carbonate)/EC (ethylene carbonate)-based electrolyte at -20 °C. Here, the correlation between voltage oscillation, structural evolution, and electrolytes has been revealed based on theoretical calculations, in-/ex-situ techniques, and cross-experiments. It is found that the local phase transition of the Na3V2(PO4)3 (NVP) cathode in PC/EC-based electrolyte at -20 °C should be responsible for the oscillatory phenomenon. Furthermore, the low exchange current density originating from the high desolvation energy barrier in NVP-PC/EC system also aggravates the local phase transformation, resulting in severe voltage oscillation. By introducing the diglyme solvent with lower Na-solvent binding energy, the voltage oscillation of the NVP can be eliminated effectively at subzero. As a result, the high capacity retentions of 98.3% at -20 °C and 75.3% at -40 °C are achieved. The finding provides insight into the abnormal SIBs degradation and brings the voltage oscillation behavior of rechargeable batteries into the limelight.

Identification of 67 histone marks and histone lysine crotonylation as a new type of histone modification.

We report the identification of 67 previously undescribed histone modifications, increasing the current number of known histone marks by about 70%. We further investigated one of the marks, lysine crotonylation (Kcr), confirming that it represents an evolutionarily-conserved histone posttranslational modification. The unique structure and genomic localization of histone Kcr suggest that it is mechanistically and functionally different from histone lysine acetylation (Kac). Specifically, in both human somatic and mouse male germ cell genomes, histone Kcr marks either active promoters or potential enhancers. In male germinal cells immediately following meiosis, Kcr is enriched on sex chromosomes and specifically marks testis-specific genes, including a significant proportion of X-linked genes that escape sex chromosome inactivation in haploid cells. These results therefore dramatically extend the repertoire of histone PTM sites and designate Kcr as a specific mark of active sex chromosome-linked genes in postmeiotic male germ cells.

The Evf2 Ultraconserved Enhancer lncRNA Functionally and Spatially Organizes Megabase Distant Genes in the Developing Forebrain.

Gene regulation requires selective targeting of DNA regulatory enhancers over megabase distances. Here we show that Evf2, a cloud-forming Dlx5/6 ultraconserved enhancer (UCE) lncRNA, simultaneously localizes to activated (Umad1, 1.6 Mb distant) and repressed (Akr1b8, 27 Mb distant) chr6 target genes, precisely regulating UCE-gene distances and cohesin binding in mouse embryonic forebrain GABAergic interneurons (INs). Transgene expression of Evf2 activates Lsm8 (12 Mb distant) but fails to repress Akr1b8, supporting trans activation and long-range cis repression. Through both short-range (Dlx6 antisense) and long-range (Akr1b8) repression, the Evf2-5'UCE links homeodomain and mevalonate pathway-regulated enhancers to IN diversity. The Evf2-3' end is required for long-range activation but dispensable for RNA cloud localization, functionally dividing the RNA into 3'-activator and 5'UCE repressor and targeting regions. Together, these results support that Evf2 selectively regulates UCE interactions with multi-megabase distant genes through complex effects on chromosome topology, linking lncRNA-dependent topological and transcriptional control with interneuron diversity and seizure susceptibility.

An intranasal influenza virus vector vaccine protects against Helicobacter pylori in mice.

Helicobacter pylori is a human pathogen that infects almost half of the population. Antibiotic resistance in H. pylori threatens health and increases the demand for prophylactic and therapeutic vaccines. Traditional oral vaccine research faces considerable challenges because of the epithelial barrier, potential enterotoxicity of adjuvants, and the challenging conditions of the gastric environment. We developed an intranasal influenza A virus (IAV) vector vaccine based on two live attenuated influenza viruses with modified acidic polymerase protein (PA) genes encoding the A subunit of H. pylori neutrophil-activating protein (NapA), named IAV-NapA, including influenza virus A/WSN/33 (WSN)-NapA and A/Puerto Rico/8/34 (PR8)-NapA. These recombinant influenza viruses were highly attenuated and exhibited strong immunogenicity in mice. Vaccination with IAV-NapA induced antigen-specific humoral and mucosal immune responses while stimulating robust Th1 and Th17 cell immune responses in mice. Our findings suggest that prophylactic and therapeutic vaccination with influenza virus vector vaccines significantly reduces colonization of H. pylori and inflammation in the stomach of mice.IMPORTANCEHelicobacter pylori is the most common cause of chronic gastritis and leads to severe gastroduodenal pathology in some patients. Many studies have shown that Th1 and Th17 cellular and gastric mucosal immune responses are critical in reducing H. pylori load. IAV vector vaccines can stimulate these immune responses while overcoming potential adjuvant toxicity and antigen dosing issues. To date, no studies have demonstrated the role of live attenuated IAV vector vaccines in preventing and treating H. pylori infection. Our work indicates that vaccination with IAV-NapA induces antigen-specific humoral, cellular, and mucosal immunity, producing a protective and therapeutic effect against H. pylori infection in BALB/c mice. This undescribed H. pylori vaccination approach may provide valuable information for developing vaccines against H. pylori infection.

Learning with uncertainty to accelerate the discovery of histone lysine-specific demethylase 1A (KDM1A/LSD1) inhibitors.

Machine learning including modern deep learning models has been extensively used in drug design and screening. However, reliable prediction of molecular properties is still challenging when exploring out-of-domain regimes, even for deep neural networks. Therefore, it is important to understand the uncertainty of model predictions, especially when the predictions are used to guide further experiments. In this study, we explored the utility and effectiveness of evidential uncertainty in compound screening. The evidential Graphormer model was proposed for uncertainty-guided discovery of KDM1A/LSD1 inhibitors. The benchmarking results illustrated that (i) Graphormer exhibited comparative predictive power to state-of-the-art models, and (ii) evidential regression enabled well-ranked uncertainty estimates and calibrated predictions. Subsequently, we leveraged time-splitting on the curated KDM1A/LSD1 dataset to simulate out-of-distribution predictions. The retrospective virtual screening showed that the evidential uncertainties helped reduce false positives among the top-acquired compounds and thus enabled higher experimental validation rates. The trained model was then used to virtually screen an independent in-house compound set. The top 50 compounds ranked by two different ranking strategies were experimentally validated, respectively. In general, our study highlighted the importance to understand the uncertainty in prediction, which can be recognized as an interpretable dimension to model predictions.

DoriC 12.0: an updated database of replication origins in both complete and draft prokaryotic genomes.

DoriC was first launched in 2007 as a database of replication origins (oriCs) in bacterial genomes and has since been constantly updated to integrate the latest research progress in this field. The database was subsequently extended to include the oriCs in archaeal genomes as well as those in plasmids. This latest release, DoriC 12.0, includes the oriCs in both draft and complete prokaryotic genomes. At the same time, the number of oriCs in the database has also increased significantly and currently contains over 200 000 bacterial entries distributed in more than 40 phyla. Among them, a large number are from bacteria in new phyla whose oriCs were not explored before. Additionally, new oriC features and improvements have been introduced, especially in the visualization and analysis of oriCs. Currently, DoriC is considered as an important database in the fields of bioinformatics, microbial genomics, and even synthetic biology, providing a valuable resource as well as a comprehensive platform for the research on oriCs. DoriC 12.0 can be accessed at https://tubic.org/doric/ and http://tubic.tju.edu.cn/doric/.

An analgesic peptide H-20 attenuates chronic pain via the PD-1 pathway with few adverse effects.

The lack of effective and safe analgesics for chronic pain management has been a health problem associated with people's livelihoods for many years. Analgesic peptides have recently shown significant therapeutic potential, as they are devoid of opioid-related adverse effects. Programmed cell death protein 1 (PD-1) is widely expressed in neurons. Activation of PD-1 by PD-L1 modulates neuronal excitability and evokes significant analgesic effects, making it a promising target for pain treatment. However, the research and development of small molecule analgesic peptides targeting PD-1 have not been reported. Here, we screened the peptide H-20 using high-throughput screening. The in vitro data demonstrated that H-20 binds to PD-1 with micromolar affinity, evokes Src homology 2 domain-containing tyrosine phosphatase 1 (SHP-1) phosphorylation, and diminishes nociceptive signals in dorsal root ganglion (DRG) neurons. Preemptive treatment with H-20 effectively attenuates perceived pain in naïve WT mice. Spinal H-20 administration displayed effective and longer-lasting analgesia in multiple preclinical pain models with a reduction in or absence of tolerance, abuse liability, constipation, itch, and motor coordination impairment. In summary, our findings reveal that H-20 is a promising candidate drug that ameliorates chronic pain in the clinic.

Sox2-Evf2 lncRNA-mediated mechanisms of chromosome topological control in developing forebrain.

The Evf2 long non-coding RNA directs Dlx5/6 ultraconserved enhancer(UCE)-intrachromosomal interactions, regulating genes across a 27 Mb region on chromosome 6 in mouse developing forebrain. Here, we show that Evf2 long-range gene repression occurs through multi-step mechanisms involving the transcription factor Sox2. Evf2 directly interacts with Sox2, antagonizing Sox2 activation of Dlx5/6UCE, and recruits Sox2 to the Dlx5/6eii shadow enhancer and key Dlx5/6UCE interaction sites. Sox2 directly interacts with Dlx1 and Smarca4, as part of the Evf2 ribonucleoprotein complex, forming spherical subnuclear domains (protein pools, PPs). Evf2 targets Sox2 PPs to one long-range repressed target gene (Rbm28), at the expense of another (Akr1b8). Evf2 and Sox2 shift Dlx5/6UCE interactions towards Rbm28, linking Evf2/Sox2 co-regulated topological control and gene repression. We propose a model that distinguishes Evf2 gene repression mechanisms at Rbm28 (Dlx5/6UCE position) and Akr1b8 (limited Sox2 availability). Genome-wide control of RNPs (Sox2, Dlx and Smarca4) shows that co-recruitment influences Sox2 DNA binding. Together, these data suggest that Evf2 organizes a Sox2 PP subnuclear domain and, through Sox2-RNP sequestration and recruitment, regulates chromosome 6 long-range UCE targeting and activity with genome-wide consequences.

Impact of COVID-19 pandemic on depression incidence and healthcare service use among patients with depression: an interrupted time-series analysis from a 9-year population-based study.

BACKGROUND: Most studies on the impact of the COVID-19 pandemic on depression burden focused on the earlier pandemic phase specific to lockdowns, but the longer-term impact of the pandemic is less well-studied. In this population-based cohort study, we examined the short-term and long-term impacts of COVID-19 on depression incidence and healthcare service use among patients with depression. METHODS: Using the territory-wide electronic medical records in Hong Kong, we identified all patients aged ≥ 10 years with new diagnoses of depression from 2014 to 2022. We performed an interrupted time-series (ITS) analysis to examine changes in incidence of medically attended depression before and during the pandemic. We then divided all patients into nine cohorts based on year of depression incidence and studied their initial and ongoing service use patterns until the end of 2022. We applied generalized linear modeling to compare the rates of healthcare service use in the year of diagnosis between patients newly diagnosed before and during the pandemic. A separate ITS analysis explored the pandemic impact on the ongoing service use among prevalent patients with depression. RESULTS: We found an immediate increase in depression incidence (RR = 1.21, 95% CI: 1.10-1.33, p < 0.001) in the population after the pandemic began with non-significant slope change, suggesting a sustained effect until the end of 2022. Subgroup analysis showed that the increases in incidence were significant among adults and the older population, but not adolescents. Depression patients newly diagnosed during the pandemic used 11% fewer resources than the pre-pandemic patients in the first diagnosis year. Pre-existing depression patients also had an immediate decrease of 16% in overall all-cause service use since the pandemic, with a positive slope change indicating a gradual rebound over a 3-year period. CONCLUSIONS: During the pandemic, service provision for depression was suboptimal in the face of increased demand generated by the increasing depression incidence during the COVID-19 pandemic. Our findings indicate the need to improve mental health resource planning preparedness for future public health crises.

In Situ Symbiosis of Cerium Oxide Nanophase for Enhancing the Oxygen Electrocatalysis Performance of Single-Atom Fe─N─C Catalyst with Prolonged Stability for Zinc-Air Batteries.

The Fenton reaction, induced by the H2O2 formed during the oxygen reduction reaction (ORR) process leads to significant dissolution of Fe, resulting in unsatisfactory stability of the iron-nitrogen-doped carbon catalysts (Fe-NC). In this study, a strategy is proposed to improve the ORR catalytic activity while eliminating the effect of H2O2 by introducing CeO2 nanoparticles. Transmission electron microscopy and subsequent characterizations reveal that CeO2 nanoparticles are uniformly distributed on the carbon substrate, with atomically dispersed Fe single-atom catalysts (SACs) adjacent to them. CeO2@Fe-NC achieves a half-wave potential of 0.89 V and a limiting current density of 6.2 mA cm-2, which significantly outperforms Fe-NC and commercial Pt/C. CeO2@Fe-NC also shows a half-wave potential loss of only 1% after 10 000 CV cycles, which is better than that of Fe-NC (7%). Further, H2O2 elimination experiments show that the introduction of CeO2 significantly accelerate the decomposition of H2O2. In situ Raman spectroscopy results suggest that CeO2@Fe-NC significantly facilitates the formation of ORR intermediates compared with Fe-NC. The Zn-air batteries utilizing CeO2@Fe-NC cathodes exhibit satisfactory peak power density and open-circuit voltage. Furthermore, theoretical calculations show that the introduction of CeO2 enhances the ORR activity of Fe-NC SAC. This study provides insights for optimizing SAC-based electrocatalysts with high activity and stability.

4D Printed Soft Microactuator for Particle Manipulation via Surrounding Medium Variation.

Soft actuators have assumed vital roles in a diverse number of research and application fields, driving innovation and transformative advancements. Using 3D molding of smart materials and combining these materials through structural design strategies, a single soft actuator can achieve multiple functions. However, it is still challenging to realize soft actuators that possess high environmental adaptability while capable of different tasks. Here, the response threshold of a soft actuator is modulated by precisely tuning the ratio of stimulus-responsive groups in hydrogels. By combining a heterogeneous bilayer membrane structure and in situ multimaterial printing, the obtained soft actuator deformed in response to changes in the surrounding medium. The response medium is suitable for both biotic and abiotic environments, and the response rate is fast. By changing the surrounding medium, the precise capture, manipulation, and release of micron-sized particles of different diameters in 3D are realized. In addition, static capture of a single red blood cell is realized using biologically responsive medium changes. Finally, the experimental results are well predicted using finite element analysis. It is believed that with further optimization of the structure size and autonomous navigation platform, the proposed soft microactuator has significant potential to function as an easy-to-manipulate multifunctional robot.

A long-term growth stable Halomonas sp. deleted with multiple transposases guided by its metabolic network model Halo-ecGEM.

Microbial instability is a common problem during bio-production based on microbial hosts. Halomonas bluephagenesis has been developed as a chassis for next generation industrial biotechnology (NGIB) under open and unsterile conditions. However, the hidden genomic information and peculiar metabolism have significantly hampered its deep exploitation for cell-factory engineering. Based on the freshly completed genome sequence of H. bluephagenesis TD01, which reveals 1889 biological process-associated genes grouped into 84 GO-slim terms. An enzyme constrained genome-scale metabolic model Halo-ecGEM was constructed, which showed strong ability to simulate fed-batch fermentations. A visible salt-stress responsive landscape was achieved by combining GO-slim term enrichment and CVT-based omics profiling, demonstrating that cells deploy most of the protein resources by force to support the essential activity of translation and protein metabolism when exposed to salt stress. Under the guidance of Halo-ecGEM, eight transposases were deleted, leading to a significantly enhanced stability for its growth and bioproduction of various polyhydroxyalkanoates (PHA) including 3-hydroxybutyrate (3HB) homopolymer PHB, 3HB and 3-hydroxyvalerate (3HV) copolymer PHBV, as well as 3HB and 4-hydroxyvalerate (4HB) copolymer P34HB. This study sheds new light on the metabolic characteristics and stress-response landscape of H. bluephagenesis, achieving for the first time to construct a long-term growth stable chassis for industrial applications. For the first time, it was demonstrated that genome encoded transposons are the reason for microbial instability during growth in flasks and fermentors.

Long-range, high-precision optical calibration path based on an optoelectronic oscillator.

We propose a laser ranging calibration optical path system using multiple optoelectronic oscillators (OEOs) that provides long range, high precision, low cost and high stability. A phase locked loop is used to control the length of the calibration optical path, which is measured with high precision by alternating the oscillations between the measurement loop and the reference loop. The calibration optical path length exceeds 9000 m with the stability of 6.8 µm during 3 minutes, and the relative measurement accuracy of the calibration optical path reaches 6.9 × 10-10.

Velocity of cerebrospinal fluid in the aqueduct measured by phase-contrast MRI in rat.

Cerebrospinal fluid (CSF) circulation plays a key role in cerebral waste clearance via the glymphatic system. Although CSF flow velocity is an essential component of CSF dynamics, it has not been sufficiently characterized, and particularly, in studies of the glymphatic system in rat. To investigate the relationship between the flow velocity of CSF in the brain aqueduct and the glymphatic waste clearance rate, using phase-contrast MRI we performed the first measurements of CSF velocity in rats. Phase-contrast MRI was performed using a 7 T system to map mean velocity of CSF flow in the aqueduct in rat brain. The effects of age (3 months old versus 18 months old), gender, strain (Wistar, RNU, Dark Agouti), anesthetic agents (isoflurane versus dexmedetomidine), and neurodegenerative disorder (Alzheimer' disease in Fischer TgF344-AD rats, males and females) on CSF velocity were investigated in eight independent groups of rats (12 rats per group). Our results demonstrated that quantitative velocities of CSF flow in the aqueduct averaged 5.16 ± 0.86 mm/s in healthy young adult male Wistar rats. CSF flow velocity in the aqueduct was not altered by rat gender, strain, and the employed anesthetic agents in all rats, also age in the female rats. However, aged (18 months) Wistar male rats exhibited significantly reduced the CSF flow velocity in the aqueduct (4.31 ± 1.08 mm/s). In addition, Alzheimer's disease further reduced the CSF flow velocity in the aqueduct of male and female rats.

InSb all-dielectric metasurface for ultrahigh efficient Si-based mid-infrared detection.

Mid-infrared (MIR) Si-based optoelectronics has wide potential applications, and its design requires simultaneous consideration of device performance optimization and the feasibility of heterogeneous integration. The emerging interest in all-dielectric metasurfaces for optoelectronic applications stems from their exceptional ability to manipulate light. In this Letter, we present our research on an InSb all-dielectric metasurface designed to achieve ultrahigh absorptivity within the 5-5.5 µm wavelength range. By integrating an InSb nanodisk array layer on a Si platform using wafer bonding and heteroepitaxial growth, we demonstrate three kinds of metasurface with high absorptivity of 98.36%, 99.28%, and 99.18%. The enhanced absorption is mainly contributed by the Kerker effect and the anapole state and the peak, with the added flexibility of tuning both the peak and bandwidth of absorption by altering the metasurface parameters. Our findings provide an alternative scheme to develop high-performance detectors and absorbers for MIR silicon photonics.

Synthesis and Evaluation of Novel 99mTc-Labeled FGFR2-Targeting Peptides.

To develop radiolabeled FGFR2-targeting probes for visualizing fibroblast growth factor receptor (FGFR) expression levels in the tumor microenvironment, four novel 99mTc-labeled FGFR2-targeting peptides ([99mTc]Tc-FGFR2-1, [99mTc]Tc-FGFR2-2, [99mTc]Tc-FGFR2-3, and [99mTc]Tc-FGFR2-4) with different amino acid linkers between the targeted peptide moiety and the 99mTc chelating group were designed and synthesized. The in vitro cellular inhibition, internalization, and efflux results demonstrated that the four 99mTc complexes exhibited FGFR2-specific binding and prolonged cellular retention in DU145 human prostate cancer cells, which indicated that modification from the glycine side (N-terminal) of CH02 was feasible. Among them, [99mTc]Tc-FGFR2-1 exhibited the highest in vitro cellular uptake and in vivo tumor uptake at 30 min postinjection, and tumor uptake could be significantly inhibited by the competitor CH02 (53% inhibited, p < 0.05), suggesting the tumor-specific targeting ability of [99mTc]Tc-FGFR2-1. The DU145-xenografted tumor lesions were clearly visualized by single photon emission computed tomography (SPECT)/CT at 30 min postinjection of [99mTc]Tc-FGFR2-1, highlighting its potential as a SPECT imaging probe for tumor FGFR2 detection.

LncRNA PSR Regulates Vascular Remodeling Through Encoding a Novel Protein Arteridin.

RATIONALE: Vascular smooth muscle cells (VSMCs) phenotype switch from contractile to proliferative phenotype is a pathological hallmark in various cardiovascular diseases. Recently, a subset of long noncoding RNAs was identified to produce functional polypeptides. However, the functional impact and regulatory mechanisms of long noncoding RNAs in VSMCs phenotype switching remain to be fully elucidated. OBJECTIVES: To illustrate the biological function and mechanism of a VSMC-enriched long noncoding RNA and its encoded peptide in VSMC phenotype switching and vascular remodeling. RESULTS: We identified a VSMC-enriched transcript encoded by a previously uncharacterized gene, which we called phenotype switching regulator (PSR), which was markedly upregulated during vascular remodeling. Although PSR was annotated as a long noncoding RNA, we demonstrated that the lncPSR (PSR transcript) also encoded a protein, which we named arteridin. In VSMCs, both arteridin and lncPSR were necessary and sufficient to induce phenotype switching. Mechanistically, arteridin and lncPSR regulate downstream genes by directly interacting with a transcription factor YBX1 (Y-box binding protein 1) and modulating its nuclear translocation and chromatin targeting. Intriguingly, the PSR transcription was also robustly induced by arteridin. More importantly, the loss of PSR gene or arteridin protein significantly attenuated the vascular remodeling induced by carotid arterial injury. In addition, VSMC-specific inhibition of lncPSR using adeno-associated virus attenuated Ang II (angiotensin II)-induced hypertensive vascular remodeling. CONCLUSIONS: PSR is a VSMC-enriched gene, and its transcript IncPSR and encoded protein (arteridin) coordinately regulate transcriptional reprogramming through a shared interacting partner, YBX1. This is a previously uncharacterized regulatory circuit in VSMC phenotype switching during vascular remodeling, with lncPSR/arteridin as potential therapeutic targets for the treatment of VSMC phenotype switching-related vascular remodeling.

TransfIGN: A Structure-Based Deep Learning Method for Modeling the Interaction between HLA-A*02:01 and Antigen Peptides.

The intricate interaction between major histocompatibility complexes (MHCs) and antigen peptides with diverse amino acid sequences plays a pivotal role in immune responses and T cell activity. In recent years, deep learning (DL)-based models have emerged as promising tools for accelerating antigen peptide screening. However, most of these models solely rely on one-dimensional amino acid sequences, overlooking crucial information required for the three-dimensional (3-D) space binding process. In this study, we propose TransfIGN, a structure-based DL model that is inspired by our previously developed framework, Interaction Graph Network (IGN), and incorporates sequence information from transformers to predict the interactions between HLA-A*02:01 and antigen peptides. Our model, trained on a comprehensive data set containing 61,816 sequences with 9051 binding affinity labels and 56,848 eluted ligand labels, achieves an area under the curve (AUC) of 0.893 on the binary data set, better than state-of-the-art sequence-based models trained on larger data sets such as NetMHCpan4.1, ANN, and TransPHLA. Furthermore, when evaluated on the IEDB weekly benchmark data sets, our predictions (AUC = 0.816) are better than those of the recommended methods like the IEDB consensus (AUC = 0.795). Notably, the interaction weight matrices generated by our method highlight the strong interactions at specific positions within peptides, emphasizing the model's ability to provide physical interpretability. This capability to unveil binding mechanisms through intricate structural features holds promise for new immunotherapeutic avenues.

DrugFlow: An AI-Driven One-Stop Platform for Innovative Drug Discovery.

Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern drug discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, an AI-driven one-stop platform that offers a clean, convenient, and cloud-based interface to streamline early drug discovery workflows. By seamlessly integrating a range of innovative AI algorithms, covering molecular docking, quantitative structure-activity relationship modeling, molecular generation, ADMET (absorption, distribution, metabolism, excretion and toxicity) prediction, and virtual screening, DrugFlow can offer effective AI solutions for almost all crucial stages in early drug discovery, including hit identification and hit/lead optimization. We hope that the platform can provide sufficiently valuable guidance to aid real-word drug design and discovery. The platform is available at https://drugflow.com.