Entire Sequence Research Articles

Research on time-series financial data prediction and analysis based on deep recurrent neural network

Time series data is widely available in a variety of industries. By forecasting time series, decision-makers can better grasp future trends and make more effective decisions. Financial time series data exhibit non-stationarity and high volatility. High-frequency fluctuations in financial products such as exchange rates, bonds and equities may reflect external shocks and risks in global financial markets, which are potentially dangerous and may threaten national economic security or even trigger financial crises. For financial time series data, a deep recurrent neural network first progressively processes each data point in the time series through its recurrent unit. Each recurring unit can adjust its own weights to better predict or analyze future values. Over time, these recurrent units continuously update their internal state, resulting in a comprehensive understanding of the characteristics of the entire data sequence. In addition, we add a gating mechanism to further improve the network's ability to control the flow of information, so that the model is more effective when retaining long-term dependencies, so as to improve the accuracy of prediction and the stability of the model. Experimental results show that our recurrent neural network model shows higher prediction accuracy and stability than other baseline models on financial time series datasets.

PLMACPred prediction of anticancer peptides based on protein language model and wavelet denoising transformation

Anticancer peptides (ACPs) perform a promising role in discovering anti-cancer drugs. The growing research on ACPs as therapeutic agent is increasing due to its minimal side effects. However, identifying novel ACPs using wet-lab experiments are generally time-consuming, labor-intensive, and expensive. Leveraging computational methods for fast and accurate prediction of ACPs would harness the drug discovery process. Herein, a machine learning-based predictor, called PLMACPred, is developed for identifying ACPs from peptide sequence only. PLMACPred adopted a set of encoding schemes representing evolutionary-property, composition-property, and protein language model (PLM), i.e., evolutionary scale modeling (ESM-2)- and ProtT5-based embedding to encode peptides. Then, two-dimensional (2D) wavelet denoising (WD) was employed to remove the noise from extracted features. Finally, ensemble-based cascade deep forest (CDF) model was developed to identify ACP. PLMACPred model attained superior performance on all three benchmark datasets, namely, ACPmain, ACPAlter, and ACP740 over tenfold cross validation and independent dataset. PLMACPred outperformed the existing models and improved the prediction accuracy by 18.53%, 2.4%, 7.59% on ACPmain, ACPalter, ACP740 dataset, respectively. We showed that embedding from ProtT5 and ESM-2 was capable of capturing better contextual information from the entire sequence than the other encoding schemes for ACP prediction. For the explainability of proposed model, SHAP (SHapley Additive exPlanations) method was used to analyze the feature effect on the ACP prediction. A list of novel sequence motifs was proposed from the ACP sequence using MEME suites. We believe, PLMACPred will support in accelerating the discovery of novel ACPs as well as other activities of microbial peptides.

Possible involvement of three-stemmed pseudoknots in regulating translational initiation in human mRNAs.

RNA pseudoknots play a crucial role in various cellular functions. Established pseudoknots show significant variation in both size and structural complexity. Specifically, three-stemmed pseudoknots are characterized by an additional stem-loop embedded in their structure. Recent findings highlight these pseudoknots as bacterial riboswitches and potent stimulators for programmed ribosomal frameshifting in RNA viruses like SARS-CoV2. To investigate the possible presence of functional three-stemmed pseudoknots in human mRNAs, we employed in-house developed computational methods to detect such structures within a dataset comprising 21,780 full-length human mRNA sequences. Numerous three-stemmed pseudoknots were identified. A selected set of 14 potential instances are presented, in which the start codon of the mRNA is found in close proximity either upstream, downstream, or within the identified three-stemmed pseudoknot. These pseudoknots likely play a role in translational initiation regulation. The probability of their existence gains support from their ranking as the most stable pseudoknot identified in the entire mRNA sequence, structural conservation across homologous mRNAs, stereochemical feasibility as demonstrated by structural modeling, and classification as members of the CPK-1 pseudoknot family, which includes many well-established pseudoknots. Furthermore, in four of the mRNAs, two or three closely spaced or tandem three-stemmed pseudoknots were identified. These findings suggest the frequent occurrence of three-stemmed pseudoknots in human mRNAs. A stepwise co-transcriptional folding mechanism is proposed for the formation of a three-stemmed pseudoknot structure. Our results not only provide fresh insights into the structures and functions of pseudoknots but also unveil the potential to target pseudoknots for treating human diseases.

Interactive Character Control with Auto-Regressive Motion Diffusion Models

Real-time character control is an essential component for interactive experiences, with a broad range of applications, including physics simulations, video games, and virtual reality. The success of diffusion models for image synthesis has led to the use of these models for motion synthesis. However, the majority of these motion diffusion models are primarily designed for offline applications, where space-time models are used to synthesize an entire sequence of frames simultaneously with a pre-specified length. To enable real-time motion synthesis with diffusion model that allows time-varying controls, we propose A-MDM (Auto-regressive Motion Diffusion Model). Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on the previous frame. Despite its streamlined network architecture, which uses simple MLPs, our framework is capable of generating diverse, long-horizon, and high-fidelity motion sequences. Furthermore, we introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning (See Figure 1). These techniques enable a pre-trained A-MDM to be efficiently adapted for a variety of new downstream tasks. We conduct a comprehensive suite of experiments to demonstrate the effectiveness of A-MDM, and compare its performance against state-of-the-art auto-regressive methods.

Perseverance reduces whereas impulsivity increases the risk of reoffending

By law, every criminal verdict describes the norm violation in question. To date, the use of this information for prognostic purposes has been standardized only for sex offenses. This study presents a content-analytic approach to the material. A theory-based coding system allows for systematic tracing of the offender’s affective and regulatory processing during norm violation, targeting the entire action sequence: initial activation affect (positive vs. negative), impulsivity vs. intentionality, affect regulation, and coping with intention-implementation difficulties. In a sample of N = 304 males convicted of violent and/or sexual offenses, the processing variables were investigated with respect to (a) objective measurability, (b) relationships with established reoffending risk markers, and (c) their (incremental) performance in predicting reoffending. With respect to objectivity (a), the inter-rater agreement (n = 111) varied widely among the variables (intraclass correlation range 0.03–0.62). Regarding risk markers (b), significant associations were found with the Level of Service Inventory–Revised (LSI-R) subscales criminal history, alcohol/drugs, emotional/personal, and attitudes/orientation. The Crime Scene Behavior Risk Measure for sexual offenses (n = 106) correlated with psychological processing variables for the items multiple juvenile offenders and male victim. Two variables emerged as relevant for predicting recidivism (c): negatively motivated impulsivity predicted violent reoffending, while persistence when coping with implementation difficulties negatively predicted sexual and general reoffending. These relationships statistically mediated the predictive contribution of actuarial risk tools (LSI-R/crime scene behavior risk). Psychological processes during norm violation as reported in verdicts appear to represent underexploited information within risk assessment and beyond.

Actions chains and intention understanding in 3- to 6-year-old children

In intentional behavior, the final goal of an action is crucial in determining the entire sequence of motor acts. Neurons have been described in the inferior parietal lobule of monkeys, which besides encoding a specific motor act (e.g., grasping), have their discharge modulated by the final goal of the intended action (e.g., grasping-to-eat). Many of these "action-constrained" neurons have mirror properties responding to the observation of the motor act they encode, provided that this is embedded in a specific action. Thanks to this mechanism, the observers have an internal copy of the whole action before its execution and may, in this way, understand the agent's intention. The chained organization of motor acts has been demonstrated in schoolchildren. Here, we examined whether this organization is already present in very young children. To this purpose, we recorded EMG from the mylohyoid (MH) muscle in the children aged 3 to 6 y. The results showed that preschoolers, like older children, possess the chained organization of motor acts in execution. Interestingly, in comparison to older children, they have a delayed ability to use this mechanism to infer others' intentions by observation. Finally, we found a significant negative association between the children's age and the activation of the MH muscle during the grasp-to-eat phase in the observation condition. We, tentatively, interpreted it as a sign of an immature control of motor acts.

Luminescence dating of the MIS 6 glaciation of the Pamir mountains (Central Asia)

The Pamir Mountains are one of the highest mountain systems in the world; they act as sources of fresh water for the main rivers of Central Asia: the Amudaria and Syrdaria. Throughout the Quaternary, the Pamirs played a major role in controlling atmospheric circulation and land-surface processes, and provided great volumes of terrigenous sediments for transport by large rivers to the depressions in the Aral and Caspian regions. These ultimately provided broad aeolian cover in the sandy deserts, and finer dust for the widely distributed loess-palaeosol sequences. The glaciation history of this highly dynamic region provides an important basis for understanding climate change, sediment source and landscape evolution in Central Asia during the Quaternary. The question of the number, distribution, extent and timing of Pleistocene glaciations in the Pamir is debated. One of the main obstacles to research, together with difficulties of access and severity of current climate, is the varying degree of preservation of traces of previous glaciations in the western and eastern Pamir. As a result of a geological survey, we for the first time identified a thick lacustrine deposit at high altitudes in a tributary of the Panj – the valley of the Sary-Shitharv River – this records the damming of the Panj River valley by a large glacier. Luminescence measurements were undertaken to obtain the age of the Sary-Shitharv glacially-dammed lake. As often in mountain catchments the quartz OSL signal was unsuitable for dose estimation, and so the chronology of the Sary-Shitharv section is based entirely on post-IR IRSL signals from K-rich feldspar. We used pIRIR50,290 and pIRIR200,290 protocols and obtained indistinguishable ages from both protocols. Given the high sedimentation rates deduced from the structure of lacustrine deposits, the entire sequence must have been accumulated rather quickly, over a period of no more than a few thousand years. The average age over the whole series of dates is 165 ± 11 ka. This places the existence of the glacially-dammed lake at Sary-Shitharv in late MIS 6, a result that fits well with the general course of the glacial history of the Pamirs.

Complete combinatorial mutational enumeration of a protein functional site enables sequence-landscape mapping and identifies highly-mutated variants that retain activity.

Understanding how proteins evolve under selective pressure is a longstanding challenge. The immensity of the search space has limited efforts to systematically evaluate the impact of multiple simultaneous mutations, so mutations have typically been assessed individually. However, epistasis, or the way in which mutations interact, prevents accurate prediction of combinatorial mutations based on measurements of individual mutations. Here, we use artificial intelligence to define the entire functional sequence landscape of a protein binding site in silico, and we call this approach Complete Combinatorial Mutational Enumeration (CCME). By leveraging CCME, we are able to construct a comprehensive map of the evolutionary connectivity within this functional sequence landscape. As a proof of concept, we applied CCME to the ACE2 binding site of the SARS-CoV-2 spike protein receptor binding domain. We selected representative variants from across the functional sequence landscape for testing in the laboratory. We identified variants that retained functionality to bind ACE2 despite changing over 40% of evaluated residue positions, and the variants now escape binding and neutralization by monoclonal antibodies. This work represents a crucial initial stride toward achieving precise predictions of pathogen evolution, opening avenues for proactive mitigation.

Sparse transformer with local and seasonal adaptation for multivariate time series forecasting

Transformers have achieved remarkable performance in multivariate time series(MTS) forecasting due to their capability to capture long-term dependencies. However, the canonical attention mechanism has two key limitations: (1) its quadratic time complexity limits the sequence length, and (2) it generates future values from the entire historical sequence. To address this, we propose a Dozer Attention mechanism consisting of three sparse components: (1) Local, each query exclusively attends to keys within a localized window of neighboring time steps. (2) Stride, enables each query to attend to keys at predefined intervals. (3) Vary, allows queries to selectively attend to keys from a subset of the historical sequence. Notably, the size of this subset dynamically expands as forecasting horizons extend. Those three components are designed to capture essential attributes of MTS data, including locality, seasonality, and global temporal dependencies. Additionally, we present the Dozerformer Framework, incorporating the Dozer Attention mechanism for the MTS forecasting task. We evaluated the proposed Dozerformer framework with recent state-of-the-art methods on nine benchmark datasets and confirmed its superior performance. The experimental results indicate that excluding a subset of historical time steps from the time series forecasting process does not compromise accuracy while significantly improving efficiency. Code is available at https://github.com/GRYGY1215/Dozerformer.

Long-read sequencing identifies an SVA_D retrotransposon insertion deep within the intron of ATP7A as a novel cause of occipital horn syndrome

BackgroundSINE-VNTR-Alu (SVA) retrotransposons move from one genomic location to another in a ‘copy-and-paste’ manner. They continue to move actively and cause monogenic diseases through various mechanisms. Currently, disease-causing SVA retrotransposons...

Optimizing anterior urethral stricture assessment: leveraging AI-assisted three-dimensional sonourethrography in clinical practice.

This investigation sought to validate the clinical precision and practical applicability of AI-enhanced three-dimensional sonographic imaging for the identification of anterior urethral stricture. The study enrolled 63 male patients with diagnosed anterior urethral strictures alongside 10 healthy volunteers to serve as controls. The imaging protocol utilized a high-frequency 3D ultrasound system combined with a linear stepper motor, which enabled precise and rapid image acquisition. For image analysis, an advanced AI-based segmentation process using a modified U-net algorithm was implemented to perform real-time, high-resolution segmentation and three-dimensional reconstruction of the urethra. A comparative analysis was performed against the surgically measured stricture lengths. Spearman's correlation analysis was executed to assess the findings. The AI model completed the entire processing sequence, encompassing recognition, segmentation, and reconstruction, within approximately 5min. The mean intraoperative length of urethral stricture was determined to be 14.4 ± 8.4mm. Notably, the mean lengths of the urethral strictures reconstructed by manual and AI models were 13.1 ± 7.5mm and 13.4 ± 7.2mm, respectively. Interestingly, no statistically significant disparity in urethral stricture length between manually reconstructed and AI-reconstructed images was observed. Spearman's correlation analysis underscored a more robust association of AI-reconstructed images with intraoperative urethral stricture length than manually reconstructed 3D images (0.870 vs. 0.820). Furthermore, AI-reconstructed images provided detailed views of the corpus spongiosum fibrosis from multiple perspectives. The research heralds the inception of an innovative, efficient AI-driven sonographic approach for three-dimensional visualization of urethral strictures, substantiating its viability and superiority in clinical application.

Enhancing Landslide Prediction Through Advanced Transformer-Based Models: Integrating SAR Imagery and Environmental Data

Landslides, a significant natural hazard driven predominantly by rainfall infiltration, pose a continuous threat to the terrain, buildings, and ecosystem of Caiazzo, located in southern Italy (Caserta). This research undertakes a novel approach to predict and understand the complex patterns of landslide deformations in this region. Our study leverages the advanced capabilities of COSMO-SkyMed satellite imagery, integrating a comprehensive dataset that includes factors such as elevation, slope, Topographic Wetness Index, Stream Power Index, geology, flow direction, curvature, Normalized Difference Vegetation Index, and several other relevant indices. We employ Transformer-based models, renowned for their effectiveness in capturing long-range dependencies within sequential data. The Transformer models in our study are adept at analyzing the temporal sequences of environmental factors and their intricate interactions, thereby offering a more nuanced understanding of the temporal patterns leading to landslides. These Transformer models are designed to process the entire sequence of satellite data obtained by the Coherent Pixels - Temporal Phase Coherence within the SUBSOFT package to ensure data integrity and precision, encompassing 132 images in ascending geometry and 143 in descending geometry, spanning from 2013 to 2021. By doing so, they efficiently identify critical patterns and dependencies over time, such as the interplay between rainfall events and subsequent soil and vegetation changes. The models are fine-tuned to our specific dataset, ensuring high precision and accuracy in landslide deformation prediction. Our evaluation metrics, including Mean Absolute Error, Root Mean Square Error, and R^2 score, demonstrate the superior performance of the Transformer-based approach, with significant improvements over the conventional Deep Learning model. The visual correlation of our predictions with actual landslide occurrences further corroborates the effectiveness of this method. This transformative approach not only enhances our understanding and predictive capability for landslides in Caiazzo but also sets a benchmark for landslide prediction in geologically vulnerable regions worldwide.

Relationship between central banks’ activities and their profitability

Central banks across the world are facing a challenging situation related to their negative profitability. Even if the problem itself should not pose any threat to the viability of these banks, the whole issue related to negative profitability may be politically sensitive. Unlike commercial banks, central banks enjoy a uniqueness related to the link between them and society. This relationship comprises not only benefits to central banks, but also some obligations central banks must render to society. The whole sequence of events to be described in this article and clearly beyond the influence of central banks contributed to a situation where the aforementioned benefits started to decrease, while the scope of obligations began to rise. Such a combination had to affect their profitability, at least temporarily. The aim of this article is to explain the reasons behind the entire sequence of events which contributed to the current circumstances central banks are trying to defy. In order to understand the complexity of the entire story of central banks’ profitability, a brief analysis will be done containing both elements of history of central banking and, above all, elements related to the unique (but not homogenous) accounting rules pursued by central banks across the world.

Oligocene magmato-tectonic events influential in the development of Pb-Zn, Ag, and Au mineralization at the Plomosas deposit, southwestern Sierra Madre Occidental, Mexico

ABSTRACT The Plomosas deposit is the product of a sequence of overlapping events of Pb–Zn, Ag, and Au low sulfidation mineralization that occurred in Mexico’s southwestern Sierra Madre Occidental (SMO). Field observations, detailed petrography, and U–Pb age dating of the entire stratigraphic sequence were used to characterize the magmatic evolution of the district and to obtain new insights into the evolution of the SMO. The stratigraphy at Plomosas is distinct from other areas to the north as it lacks Jurassic marine units, Cretaceous continental volcanic successions as well as Cretaceous and Palaeocene batholiths. The local basement is composed of undeformed Late Jurassic volcaniclastic units and coeval felsic intrusions. Early to late Oligocene silicic ignimbrites, intermediate lava flows, and occasional basaltic flows unconformably overlie the Jurassic basement. Several Oligocene intermediate to felsic porphyry bodies and rhyolitic domes crosscut the stratigraphy. The upper volcanic sequence is separated into two packages by an angular unconformity. Mineralization produced an early Pb–Zn-mineralized hydrothermal fault breccia, followed by Cu–Ag veins and late Au veins. The Pb–Zn mineralized breccia is hosted by ~30 Ma Oligocene volcanic units that form the basal sequence. The Cu–Ag and Au-rich veins overlap and crosscut the early hydrothermal features and cut the late Oligocene volcanic cover that unconformably overlie the basal sequence. Our results highlight the importance of episodes of Oligocene magmatism to the genesis of mineralization in the southwestern SMO specifically through a genetic link between Pb–Zn veins and intermediate Oligocene intrusive bodies, and of Ag and Au veins with late Oligocene volcanism.

Molecular epizootiology of porcine reproductive and respiratory syndrome virus in the Xinjiang Uygur Autonomous Region of China.

Rapid evolution of porcine reproductive and respiratory syndrome virus (PRRSV) is the bottleneck for effective prevention and control of PRRS. Thus, understanding the prevalence and genetic background of PRRSV strains in swine-producing regions is important for disease prevention and control. However, there is only limited information about the epizootiological situation of PRRS in the Xinjiang Uygur Autonomous Region, China. In this study, blood or lung tissue samples were collected from 1,411 PRRS-suspected weaned pigs from 9 pig farms in Changji, Shihezi, and Wujiaqu cities between 2020 and 2022. The samples were first tested by RT-quantitative PCR, yielding a PRRSV-2 positive rate of 53.6%. Subsequently, 36 PRRSV strains were isolated through initial adaptation in bone marrow-derived macrophages followed by propagation in grivet monkey Marc-145 cells. Furthermore, 28 PRRSV-positive samples and 20 cell-adapted viruses were selected for high-throughput sequencing (HTS) to obtain the entire PRRSV genome sequences. Phylogenetic analysis based on the nucleotide sequences of the ORF5 gene of the PRRSV strains identified in this study grouped into sub-lineages 1.8 and 8.7 the former being the dominant strain currently circulating in Xinjiang. However, the NSP2 proteins of the Xinjiang PRRSV strains shared the same deletion patterns as sub-lineage 1.8 prototype strain NADC30 with the exception of 4 strains carrying 2-3 additional amino acid deletions. Further analysis confirmed that recombination events had occurred in 27 of 37 PRRSVs obtained here with the parental strains belonging to sub-lineages 1.8 and 8.7, lineages 3 and 5, with the recombination events having occurred most frequently in the 5' and 3' termini of ORF1a and 5' terminus of ORF1b.

Mitochondrial genome analysis reveals phylogenetic insights and gene rearrangements in Parupeneus (Syngnathiformes: Mullidae)

Despite the critical role of mitochondrial genomes (mitogenomes) in species identification and evolutionary studies in the genus Parupeneus, current resources are inadequate, given the species richness. Although previous studies have suggested a complex evolutionary history, the detailed mitogenomic variations and their implications remain largely unexplored. Therefore, we sequenced and assembled the mitogenomes of P. barberinoides, P. barberinus, P. biaculeatus, P. crassilabris, P. cyclostomus, P. heptacanthus, P. multifasciatus, and P. chrysopleuron, to enrich the molecular data and provide novel insights into the genetic diversity, evolutionary dynamics and phylogenetics of the family Mullidae. Our analysis revealed a novel gene rearrangement in P. chrysopleuron, Cytb-T-P-CR-Q-I-F-12S-V-16S-ND1-M-ND2, which differed from the conventional sequence of Cytb-T-P-CR-F-12S-V-16S-ND1-I-Q-M-ND2 observed in other species. In the novel rearrangement, four non-coding regions are inserted between ND1 and M, Q and I, I and ψM (tRNA-Met pseudogene), ψM and F. We assume that two tandem duplication/random loss events occur in the CR and IQM, making the entire sequence longer than that in other Parupeneus species. The phylogenetic results indicated that Mullidae formed a sister group relationship with the family Dactylopteridae, contradicting previous studies that identified a sister group relationship between Mullidae and Callionymoidei. The genera Parupeneus and Mullus formed a sister group, and discrepancies were found in the topological structure of the interspecies relationships within the genus Parupeneus compared with those reported by previous studies. Through combined phylogenetic and mitochondrial structural analysis, we found that phylogenetic topology is closely related to mitochondrial structural abnormalities. This study not only expands the mitogenomic dataset available for Mullidae but also underscores the importance of mitochondrial DNA studies in resolving taxonomic ambiguities and understanding the evolutionary history of marine fishes. Our study contributes to the ongoing research on marine fish taxonomy, mitogenomics, and evolutionary biology by providing new insights into the genetic diversity of marine ecosystems.

Complete genome sequence of a metallo-β-lactamase-producing Aeromonas dhakensis strain, RYU-Ah62, isolated from a patient with an abdominal abscess.

Aeromonas dhakensis is highly virulent but often misidentified in clinical settings. The entire genome sequence of a metallo-β-lactamase-producing A. dhakensis strain from a clinical specimen has been presented in this study. The genome comprised a single chromosome of 4.89 Mbp with 61.6% G + C content.

Identification and serological responses to a novel Plasmodium vivax merozoite surface protein 1 (PvMSP-1) derived synthetic peptide: a putative biomarker for malaria exposure.

The integration of diagnostic methods holds promise for advancing the surveillance of malaria transmission in both endemic and non-endemic regions. Serological assays emerge as valuable tools to identify and delimit malaria transmission, serving as a complementary method to rapid diagnostic tests (RDT) and thick smear microscopy. Here, we evaluate the potential of antibodies directed against peptides encompassing the entire amino acid sequence of the PvMSP-1 Sal-I strain as viable serological biomarkers for P. vivax exposure. We screened peptides encompassing the complete amino acid sequence of the Plasmodium vivax Merozoite Surface Protein 1 (PvMSP-1) Sal-I strain as potential biomarkers for P. vivax exposure. Here, immunodominant peptides specifically recognized by antibodies from individuals infected with P. vivax were identified using the SPOT-synthesis technique followed by immunoblotting. Two 15-mer peptides were selected based on their higher and specific reactivity in immunoblotting assays. Subsequently, peptides p70 and p314 were synthesized in soluble form using SPPS (Solid Phase Peptide Synthesis) and tested by ELISA (IgG, and subclasses). This study unveils the presence of IgG antibodies against the peptide p314 in most P. vivax-infected individuals from the Brazilian Amazon region. In silico B-cell epitope prediction further supports the utilization of p314 as a potential biomarker for evaluating malaria transmission, strengthened by its amino acid sequence being part of a conserved block of PvMSP-1. Indeed, compared to patients infected with P. falciparum and uninfected individuals never exposed to malaria, P. vivax-infected patients have a notably higher recognition of p314 by IgG1 and IgG3.

Improved prediction of anti-angiogenic peptides based on machine learning models and comprehensive features from peptide sequences

Angiogenesis is a key process for the proliferation and metastatic spread of cancer cells. Anti-angiogenic peptides (AAPs), with the capability of inhibiting angiogenesis, are promising candidates in cancer treatment. We propose AAPL, a sequence-based predictor to identify AAPs with machine learning models of improved prediction accuracy. Each peptide sequence was transformed to a vector of 4335 numeric values according to 58 different feature types, followed by a heuristic algorithm for feature selection. Next, the hyperparameters of six machine learning models were optimized with respect to the feature subset. We considered two datasets, one with entire peptide sequences and the other with 15 amino acids from peptide N-termini. AAPL achieved Matthew’s correlation coefficients of 0.671 and 0.756 for independent tests based on the two datasets, respectively, outperforming existing predictors by a range of 5.3% to 24.6%. Further analyses show that AAPL yields higher prediction accuracy for peptides with more hydrophobic residues, and fewer hydrophilic and charged residues. The source code of AAPL is available at https://github.com/yunzheng2002/Anti-angiogenic.

Comparative Study of Two Himalayan Snow Trouts, Schizothorax esocinus and Schizothorax curvifrons Within the Schizothoracinae and Other Nearest Relatives of Cyprinidae, Inferred from Mitochondrial Sequences of Cytochrome b (Cyt-b) and Cytochrome Oxidase I (Co-I) Gene.

The Himalayan region encompasses varied aquatic ecosystems, characterized by the presence of diverse ichthyofauna, particularly represented by members of the Schizothorax genus, commonly referred to as snow trout. The primary objective of this work was to examine the molecular phylogeny of Schizothoracinae, specifically focusing on the two species, Schizothorax esocinus and Schizothorax curvifrons, which are known to inhabit the northern and north-eastern regions of the Himalayas. This investigation was conducted by analyzing the entire mitochondrial Cyt-b and Co-I gene sequences. The aligned Cyt-b and Co-I sequences for S. esocinus, S. curvifrons, and related members within the subfamily Schizothoracinae, spanned 1130 to 1141 and 1536 to 1551 base pairs, respectively. Using these gene, phylogenetic trees were created to compare Schizothoracinae species to other subfamilies of the family Cyprinidae (Barbinae, Alburninae, Leuciscinae, Xenocyprinae, Cyprininae, and Cultrinae). Genetic distances for Cyt-b and Co-I sequence at three hierarchical levels shows significant disparities in their average score. For Cyt-b, average p-distances for intraspecies, intragenus, and intrafamily were 2.13%, 4.1%, and 15.23%, respectively. Similarly, for Co-I, average p-distances were 1.19%, 3.6%, and 13.8% for intraspecies, intragenus, and intrafamily, respectively. Total number of haplotypes (h) based on Cyt-b and Co-I gene were 6 and 12 within the target Schizothorax spp. In the present study, the observed range of haplotype diversity (hd) for the Cyt-b gene varied from 0.00 to 0.847, with an average haplotype diversity of 0.847 ± 0.034. Similarly, for the Co-I gene, the observed haplotype diversity ranged from 0.00 to 0.931, with an average value of haplotype diversity estimated to be 0.931 ± 0.024. The results of the present study clearly shows that the representative species exhibited close affinities with members of Barbinae and Cyprininae, while other subfamilies formed distinct groups. The findings of the study also indicated that the Cyt-b and Co-I gene exhibits polymorphism and has the potential to serve as a marker for identifying genetic differentiation among populations based on ecological habitats. Mitochondrial Cyt-b and Co-I have been established as a universally accepted and validated genetic marker within a comprehensive bio-identification system at the species level.