CSM-peptides: A computational approach to rapid identification of therapeutic peptides

Characterisation of defensins across the marsupial family tree

Defensins are antimicrobial peptides involved in innate immunity, and gene number differs amongst eutherian mammals. Few studies have investigated defensins in marsupials, despite their potential involvement in immunological protection of altricial young. Here we use recently sequenced marsupial genomes and transcriptomes to annotate defensins in nine species across the marsupial family tree. We characterised 35 alpha and 286 beta defensins; gene number differed between species, although Dasyuromorphs had the largest repertoire. Defensins were encoded in three gene clusters within the genome, syntenic to eutherians, and were expressed in the pouch and mammary gland. Marsupial beta defensins were closely related to eutherians, however marsupial alpha defensins were more divergent. We identified marsupial orthologs of human DEFB3 and 6, and several marsupial-specific beta defensin lineages which may have novel functions. Marsupial predicted mature peptides were highly variable in length and sequence composition. We propose candidate peptides for future testing to elucidate the function of marsupial defensins.

piscesCSM: prediction of anticancer synergistic drug combinations

While drug combination therapies are of great importance, particularly in cancer treatment, identifying novel synergistic drug combinations has been a challenging venture. Computational methods have emerged in this context as a promising tool for prioritizing drug combinations for further evaluation, though they have presented limited performance, utility, and interpretability. Here, we propose a novel predictive tool, piscesCSM, that leverages graph-based representations to model small molecule chemical structures to accurately predict drug combinations with favourable anticancer synergistic effects against one or multiple cancer cell lines. Leveraging these insights, we developed a general supervised machine learning model to guide the prediction of anticancer synergistic drug combinations in over 30 cell lines. It achieved an area under the receiver operating characteristic curve (AUROC) of up to 0.89 on independent non-redundant blind tests, outperforming state-of-the-art approaches on both large-scale oncology screening data and an independent test set generated by AstraZeneca (with more than a 16% improvement in predictive accuracy). Moreover, by exploring the interpretability of our approach, we found that simple physicochemical properties and graph-based signatures are predictive of chemotherapy synergism. To provide a simple and integrated platform to rapidly screen potential candidate pairs with favourable synergistic anticancer effects, we made piscesCSM freely available online at https://biosig.lab.uq.edu.au/piscescsm/ as a web server and API. We believe that our predictive tool will provide a valuable resource for optimizing and augmenting combinatorial screening libraries to identify effective and safe synergistic anticancer drug combinations. SCIENTIFIC CONTRIBUTION: This work proposes piscesCSM, a machine-learning-based framework that relies on well-established graph-based representations of small molecules to identify and provide better predictive accuracy of syngenetic drug combinations. Our model, piscesCSM, shows that combining physiochemical properties with graph-based signatures can outperform current architectures on classification prediction tasks. Furthermore, implementing our tool as a web server offers a user-friendly platform for researchers to screen for potential synergistic drug combinations with favorable anticancer effects against one or multiple cancer cell lines.

Engineering G protein-coupled receptors for stabilization

G protein-coupled receptors (GPCRs) are one of the most important families of targets for drug discovery. One of the limiting steps in the study of GPCRs has been their stability, with significant and time-consuming protein engineering often used to stabilize GPCRs for structural characterization and drug screening. Unfortunately, computational methods developed using globular soluble proteins have translated poorly to the rational engineering of GPCRs. To fill this gap, we propose GPCR-tm, a novel and personalized structurally driven web-based machine learning tool to study the impacts of mutations on GPCR stability. We show that GPCR-tm performs as well as or better than alternative methods, and that it can accurately rank the stability changes of a wide range of mutations occurring in various types of class A GPCRs. GPCR-tm achieved Pearson's correlation coefficients of 0.74 and 0.46 on 10-fold cross-validation and blind test sets, respectively. We observed that the (structural) graph-based signatures were the most important set of features for predicting destabilizing mutations, which points out that these signatures properly describe the changes in the environment where the mutations occur. More specifically, GPCR-tm was able to accurately rank mutations based on their effect on protein stability, guiding their rational stabilization. GPCR-tm is available through a user-friendly web server at https://biosig.lab.uq.edu.au/gpcr_tm/.

CAPTURE: Comprehensive anti-cancer peptide predictor with a unique amino acid sequence encoder

Anticancer peptides (ACPs) key properties including bioactivity, high efficacy, low toxicity, and lack of drug resistance make them ideal candidates for cancer therapies. To deeply explore the potential of ACPs and accelerate development of cancer therapies, although 53 Artificial Intelligence supported computational predictors have been developed for ACPs and non ACPs classification but only one predictor has been developed for ACPs functional types annotations. Moreover, these predictors extract amino acids distribution patterns to transform peptides sequences into statistical vectors that are further fed to classifiers for discriminating peptides sequences and annotating peptides functional classes. Overall, these predictors remain fail in extracting diverse types of amino acids distribution patterns from peptide sequences. The paper in hand presents a unique CARE encoder that transforms peptides sequences into statistical vectors by extracting 4 different types of distribution patterns including correlation, distribution, composition, and transition. Across public benchmark dataset, proposed encoder potential is explored under two different evaluation settings namely; intrinsic and extrinsic. Extrinsic evaluation indicates that 12 different machine learning classifiers achieve superior performance with the proposed encoder as compared to 55 existing encoders. Furthermore, an intrinsic evaluation reveals that, unlike existing encoders, the proposed encoder generates more discriminative clusters for ACPs and non-ACPs classes. Across 8 public benchmark ACPs and non-ACPs classification datasets, proposed encoder and Adaboost classifier based CAPTURE predictor outperforms existing predictors with an average accuracy, recall and MCC score of 1%, 4%, and 2% respectively. In generalizeability evaluation case study, across 7 benchmark anti-microbial peptides classification datasets, CAPTURE surpasses existing predictors by an average AU-ROC of 2%. CAPTURE predictive pipeline along with label powerset method outperforms state-of-the-art ACPs functional types predictor by 5%, 5%, 5%, 6%, and 3% in terms of average accuracy, subset accuracy, precision, recall, and F1 respectively. CAPTURE web application is available at https://sds_genetic_analysis.opendfki.de/CAPTURE.

Roasted yerba mate (Ilex paraguariensis) infusions in bovine milk model before and after in vitro digestion: Bioaccessibility of phenolic compounds, antioxidant activity, protein-polyphenol interactions and bioactive peptides

Yerba mate is increasingly acknowledged for its bioactive properties and is currently being incorporated into various food and pharmaceutical products. When roasted, yerba mate transforms into mate tea, consumed as a hot aqueous infusion, and has gained popularity. This study investigated the bioaccessibility of phenolic compounds, protein-polyphenol interactions, antioxidant activity, and bioactive peptides in roasted yerba mate infusions, utilizing whole, semi-skimmed, and skimmed bovine milk models. The phytochemical profile of roasted yerba mate was analyzed in infusions with water and milk (whole, semi-skimmed, and skimmed), before and after in vitro digestion, identifying 18 compounds that exhibited variations in composition and presence among the samples. Bioavailability varied across different milk matrices, with milk being four times more efficient as a solvent for extraction. Gastric digestion significantly impacted (p < 0.05) the release of phenolic compounds, such as chlorogenic acid and rutin, with only chlorogenic acid remaining 100 % bioavailable in the infusion prepared with skimmed milk. Protein-polyphenol interaction did not influence protein digestion in different infusions, as there was a similarity in the hydrolysis pattern during the digestive process. Changes in antioxidant activity during digestion phases, especially after intestinal digestion in milk infusions, were related to alterations in protein structures and digestive interactions. The evaluation of total phenolic compounds highlighted that skimmed milk infusion notably preserved these compounds during digestion. Peptidomic analysis identified 253, 221, and 191 potentially bioactive peptides for whole, semi-skimmed, and skimmed milk-digested infusions, respectively, with a focus on anti-inflammatory and anticancer activities, presenting a synergistic approach to promote health benefits. The selection of milk type is crucial for comprehending the effects of digestion and interactions in bioactive compound-rich foods, highlighting the advantages of consuming plant infusions prepared with milk.

Food peptidomic analysis of bovine milk fermented by Lacticaseibacillus casei LBC 237: In silico prediction of bioactive peptides and anticancer potential

Bioactive peptides, which exhibited diverse biological activities such as anti-cancer, anti-inflammatory, bactericidal, antiviral, and quorum sensing properties, were considered promising alternative therapeutic agents. Sourced from various raw materials, particularly foods, these peptides garnered significant interest. In this context, the study focused on exploring bioactive peptides derived from bovine whole milk fermentation by Lacticaseibacillus casei LBC 237. Comprehensive peptidomic analysis and in silico predictions, with a specific emphasis on anti-cancer properties, were conducted. The study categorized peptides into BP-LBC, originating from the metabolism of L. casei LBC 237 and not matching any sequence in the Bos taurus database, and BP-MILK, matching a sequence in the Bos taurus database. Among the 143 identified peptides with potential biological activity, 33.56% were attributed to BP-LBC, while 66.43% originated from BP-MILK, demonstrating the important contribution of proteins in bovine milk in the generation of bioactive peptides. Hydrophobic peptides, enriched in Leucine, Lysine, and Proline, dominated both fractions, significantly influencing their functional properties. Pearson correlation analysis revealed inverse relationships between bioactive peptides, molecular weight, and anti-tumor activity in BP-MILK. The DGKVWEESLK peptide exhibited in silico activity against 10 different cancer cell lines. Studying the bioactive properties of peptides from familiar sources enhances the connection between food science and human health. In addition, in silico studies have been crucial in deepening our understanding of the bioactive potential of these peptides and their mode of action.

An Integrated Comprehensive Peptidomics and In Silico Analysis of Bioactive Peptide-Rich Milk Fermented by Three Autochthonous Cocci Strains

Bioactive peptides (BPs) are molecules of paramount importance with great potential for the development of functional foods, nutraceuticals or therapeutics for the prevention or treatment of various diseases. A functional BP-rich dairy product was produced by lyophilisation of bovine milk fermented by the autochthonous strains Lactococcus lactis subsp. lactis ZGBP5-51, Enterococcus faecium ZGBP5-52 and Enterococcus faecalis ZGBP5-53 isolated from the same artisanal fresh cheese. The efficiency of the proteolytic system of the implemented strains in the production of BPs was confirmed by a combined high-throughput mass spectrometry (MS)-based peptidome profiling and an in silico approach. First, peptides released by microbial fermentation were identified via a non-targeted peptide analysis (NTA) comprising reversed-phase nano-liquid chromatography (RP nano-LC) coupled with matrix-assisted laser desorption/ionisation-time-of-flight/time-of-flight (MALDI-TOF/TOF) MS, and then quantified by targeted peptide analysis (TA) involving RP ultrahigh-performance LC (RP-UHPLC) coupled with triple-quadrupole MS (QQQ-MS). A combined database and literature search revealed that 10 of the 25 peptides identified in this work have bioactive properties described in the literature. Finally, by combining the output of MS-based peptidome profiling with in silico bioactivity prediction tools, three peptides (75QFLPYPYYAKPA86, 40VAPFPEVFGK49, 117ARHPHPHLSF126), whose bioactive properties have not been previously reported in the literature, were identified as potential BP candidates.

AI-Driven Enhancements in Drug Screening and Optimization

The greatest challenge in drug discovery remains the high rate of attrition across the different phases of the process, which cost the industry billions of dollars every year. While all phases remain crucial to ensure pharmaceutical-level safety, quality, and efficacy of the end product, streamlining these efforts toward compounds with success potential is pivotal for a more efficient and cost-effective process. The use of artificial intelligence (AI) within the pharmaceutical industry aims at just this, and has applications in preclinical screening for biological activity, optimization of pharmacokinetic properties for improved drug formulation, early toxicity prediction which reduces attrition, and pre-emptively screening for genetic changes in the biological target to improve therapeutic longevity. Here, we present a series of in silico tools that address these applications in small molecule development and describe how they can be embedded within the current pharmaceutical development pipeline.

Tuna trimmings (Thunnas albacares) hydrolysate alleviates immune stress and intestinal mucosal injury during chemotherapy on mice and identification of potentially active peptides

In this study, Tuna trimmings (Thunnas albacares) protein hydrolysate (TPA) was produced by alcalase. The anti-tumor synergistic effect and intestinal mucosa protective effect of TPA on S180 tumor-bearing mice treated with 5-fluorouracil (5-FU) chemotherapy were investigated. The results showed that TPA can enhance the anti-tumor effect of 5-FU chemotherapy, as evident by a significant reduction in tumor volume observed in the medium and high dose TPA+5-FU groups compared to the 5-FU group (p < 0.001). Moreover, TPA significantly elevated the content of total protein and albumin in all TPA dose groups (p < 0.01, p < 0.001), indicating its ability to regulate the nutritional status of the mice. Furthermore, histopathological studies revealed a significant increase in the height of small intestinal villi, crypt depth, mucosal thickness, and villi area in the TPA+5-FU groups compared to the 5-FU group (p < 0.05), suggesting that TPA has a protective effect on the intestinal mucosa. Amino acid analysis revealed that TPA had a total amino acid content of 66.30 g/100 g, with essential amino acids accounting for 30.36 g/100 g. Peptide molecular weight distribution analysis of TPA indicated that peptides ranging from 0.25 to 1 kDa constituted 64.54%. LC-MS/MS analysis identified 109 peptide sequences, which were predicted to possess anti-cancer and anti-inflammatory activities through database prediction. Therefore, TPA has the potential to enhance the antitumor effects of 5-FU, mitigate immune depression and intestinal mucosal damage induced by 5-FU. Thus, TPA could be serve as an adjuvant nutritional support for malnourished patients undergoing chemotherapy.

Aggregation Limiting Cell-Penetrating Peptides Derived from Protein Signal Sequences

Alzheimer's disease (AD) is the most common neurodegenerative disease (ND) and the leading cause of dementia. It is characterized by non-linear, genetic-driven pathophysiological dynamics with high heterogeneity in the biological alterations and the causes of the disease. One of the hallmarks of the AD is the progression of plaques of aggregated amyloid-β (Aβ) or neurofibrillary tangles of Tau. Currently there is no efficient treatment for the AD. Nevertheless, several breakthroughs in revealing the mechanisms behind progression of the AD have led to the discovery of possible therapeutic targets. Some of these include the reduction in inflammation in the brain, and, although highly debated, limiting of the aggregation of the Aβ. In this work we show that similarly to the Neural cell adhesion molecule 1 (NCAM1) signal sequence, other Aβ interacting protein sequences, especially derived from Transthyretin, can be used successfully to reduce or target the amyloid aggregation/aggregates in vitro. The modified signal peptides with cell-penetrating properties reduce the Aβ aggregation and are predicted to have anti-inflammatory properties. Furthermore, we show that by expressing the Aβ-EGFP fusion protein, we can efficiently assess the potential for reduction in aggregation, and the CPP properties of peptides in mammalian cells.