Anticancer peptides as novel immunomodulatory therapeutic candidates for cancer treatment.

Cancer remains a concern after years of research in this field. Conventional therapies such as chemotherapy, radiation, and surgery are available for cancer treatment, but they are characterized by various side effects. There are several immunological challenges that make it difficult for the immune system and conventional therapies to treat cancer. Some of these challenges include heterogeneity, resistance to medicines, and cancer relapse. Even advanced treatments like immune checkpoint inhibitors (ICIs), which revolutionized cancer treatment, have associated toxicity and resistance further necessitate the exploration of alternative therapies. Anticancer peptides (ACPs) offer promising potential as cancer-fighting agents and address challenges such as treatment resistance, tumor heterogeneity, and metastasis. Although these peptides exist as components of the defense system in various plants, animals, fungi, etc., but can also be created synthetically and used as a new treatment measure. These peptides possess properties that make them appealing for cancer therapy, such as apoptosis induction, inhibition of angiogenesis, and cell membrane breakdown with low toxicity. Their capacity to specifically target cancer cells selectively holds promise for enhancing treatment environments as well as improving patients' quality of life. This review provides detailed insights into the different prospects of ACPs, including their characterization, use as immunomodulatory agents in cancer treatment, and their mechanistic details after addressing various immunological challenges in existing cancer treatment strategies. In conclusion, ACPs have promising potential as novel cancer therapeutics due to their target specificity and fewer side effects than conventional therapies.

ACP-CapsPred: an explainable computational framework for identification and functional prediction of anticancer peptides based on capsule network.

Cancer is a severe illness that significantly threatens human life and health. Anticancer peptides (ACPs) represent a promising therapeutic strategy for combating cancer. In silico methods enable rapid and accurate identification of ACPs without extensive human and material resources. This study proposes a two-stage computational framework called ACP-CapsPred, which can accurately identify ACPs and characterize their functional activities across different cancer types. ACP-CapsPred integrates a protein language model with evolutionary information and physicochemical properties of peptides, constructing a comprehensive profile of peptides. ACP-CapsPred employs a next-generation neural network, specifically capsule networks, to construct predictive models. Experimental results demonstrate that ACP-CapsPred exhibits satisfactory predictive capabilities in both stages, reaching state-of-the-art performance. In the first stage, ACP-CapsPred achieves accuracies of 80.25% and 95.71%, as well as F1-scores of 79.86% and 95.90%, on benchmark datasets Set 1 and Set 2, respectively. In the second stage, tasked with characterizing the functional activities of ACPs across five selected cancer types, ACP-CapsPred attains an average accuracy of 90.75% and an F1-score of 91.38%. Furthermore, ACP-CapsPred demonstrates excellent interpretability, revealing regions and residues associated with anticancer activity. Consequently, ACP-CapsPred presents a promising solution to expedite the development of ACPs and offers a novel perspective for other biological sequence analyses.

Investigation of therapeutic potential of the Il24-p20 fusion protein against breast cancer: an in-silico approach.

Targeted delivery of therapeutic anticancer chimeric molecules enhances drug efficacy. Numerous studies have focused on developing novel treatments by employing cytokines, particularly interleukins, to inhibit the growth of cancer cells. In the present study, we fused interleukin 24 with the tumor-targeting peptide P20 through a rigid linker to selectively target cancer cells. The secondary structure, tertiary structure, and physicochemical characteristics of the constructed chimeric IL-24-P20 protein were predicted by using bioinformatics tools. In-silico analysis revealed that the fusion construct has a basic nature with 175 amino acids and a molecular weight of 20 kDa. By using the Rampage and ERRAT2 servers, the validity and quality of the fusion protein were evaluated. The results indicated that 93% of the chimeric proteins contained 90.1% of the residues in the favoured region, resulting in a reliable structure. Finally, docking and simulation studies were conducted via ClusPro and Desmond Schrödinger, respectively. Our results indicate that the constructed fusion protein exhibits excellent quality, interaction capabilities, validity, and stability. These findings suggest that the fusion protein is a promising candidate for targeted cancer therapy.

mACPpred 2.0: Stacked Deep Learning for Anticancer Peptide Prediction with Integrated Spatial and Probabilistic Feature Representations.

Anticancer peptides (ACPs), naturally occurring molecules with remarkable potential to target and kill cancer cells. However, identifying ACPs based solely from their primary amino acid sequences remains a major hurdle in immunoinformatics. In the past, several web-based machine learning (ML) tools have been proposed to assist researchers in identifying potential ACPs for further testing. Notably, our meta-approach method, mACPpred, introduced in 2019, has significantly advanced the field of ACP research. Given the exponential growth in the number of characterized ACPs, there is now a pressing need to create an updated version of mACPpred. To develop mACPpred 2.0, we constructed an up-to-date benchmarking dataset by integrating all publicly available ACP datasets. We employed a large-scale of feature descriptors, encompassing both conventional feature descriptors and advanced pre-trained natural language processing (NLP)-based embeddings. We evaluated their ability to discriminate between ACPs and non-ACPs using eleven different classifiers. Subsequently, we employed a stacked deep learning (SDL) approach, incorporating 1D convolutional neural network (1D CNN) blocks and hybrid features. These features included the top seven performing NLP-based features and 90 probabilistic features, allowing us to identify hidden patterns within these diverse features and improve the accuracy of our ACP prediction model. This is the first study to integrate spatial and probabilistic feature representations for predicting ACPs. Rigorous cross-validation and independent tests conclusively demonstrated that mACPpred 2.0 not only surpassed its predecessor (mACPpred) but also outperformed the existing state-of-the-art predictors, highlighting the importance of advanced feature representation capabilities attained through SDL. To facilitate widespread use and accessibility, we have developed a user-friendly for mACPpred 2.0, available at https://balalab-skku.org/mACPpred2/.

ACP-ESM: A novel framework for classification of anticancer peptides using protein-oriented transformer approach.

Anticancer peptides (ACPs) are a class of molecules that have gained significant attention in the field of cancer research and therapy. ACPs are short chains of amino acids, the building blocks of proteins, and they possess the ability to selectively target and kill cancer cells. One of the key advantages of ACPs is their ability to selectively target cancer cells while sparing healthy cells to a greater extent. This selectivity is often attributed to differences in the surface properties of cancer cells compared to normal cells. That is why ACPs are being investigated as potential candidates for cancer therapy. ACPs may be used alone or in combination with other treatment modalities like chemotherapy and radiation therapy. While ACPs hold promise as a novel approach to cancer treatment, there are challenges to overcome, including optimizing their stability, improving selectivity, and enhancing their delivery to cancer cells, continuous increasing in number of peptide sequences, developing a reliable and precise prediction model. In this work, we propose an efficient transformer-based framework to identify ACPs for by performing accurate a reliable and precise prediction model. For this purpose, four different transformer models, namely ESM, ProtBERT, BioBERT, and SciBERT are employed to detect ACPs from amino acid sequences. To demonstrate the contribution of the proposed framework, extensive experiments are carried on widely-used datasets in the literature, two versions of AntiCp2, cACP-DeepGram, ACP-740. Experiment results show the usage of proposed model enhances classification accuracy when compared to the literature studies. The proposed framework, ESM, exhibits 96.45% of accuracy for AntiCp2 dataset, 97.66% of accuracy for cACP-DeepGram dataset, and 88.51% of accuracy for ACP-740 dataset, thence determining new state-of-the-art. The code of proposed framework is publicly available at github (https://github.com/mstf-yalcin/acp-esm).

Dual Antimicrobial and Anticancer Activity of Membrane-Active Peptide BP52.

The linear undecapeptide BP52 was previously reported to have antibacterial activity against phytopathogenic bacteria species. Due to the structural similarities to naturally occurring cationic helical antimicrobial peptides, it was speculated that this peptide could potentially target microbial pathogens and cancer cells found in mammals. Consequently, this study aims to further investigate the structural and biological properties of this peptide. Our findings indicate that BP52 exhibits strong antimicrobial and anticancer activity while displaying relatively low levels of hemolytic activity. Hence, this study suggests that BP52 could be a potential lead compound for drug discovery against infectious diseases and cancer. Besides, new insights into the relationships between the structure and the multifunctional properties of antimicrobial peptides were also explored.

Efficient prediction of anticancer peptides through deep learning.

Background: Cancer remains one of the leading causes of mortality globally, with conventional chemotherapy often resulting in severe side effects and limited effectiveness. Recent advancements in bioinformatics and machine learning, particularly deep learning, offer promising new avenues for cancer treatment through the prediction and identification of anticancer peptides. Objective: This study aimed to develop and evaluate a deep learning model utilizing a two-dimensional convolutional neural network (2D CNN) to enhance the prediction accuracy of anticancer peptides, addressing the complexities and limitations of current prediction methods. Methods: A diverse dataset of peptide sequences with annotated anticancer activity labels was compiled from various public databases and experimental studies. The sequences were preprocessed and encoded using one-hot encoding and additional physicochemical properties. The 2D CNN model was trained and optimized using this dataset, with performance evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). Results: The proposed 2D CNN model achieved superior performance compared to existing methods, with an accuracy of 0.87, precision of 0.85, recall of 0.89, F1-score of 0.87, and an AUC-ROC value of 0.91. These results indicate the model's effectiveness in accurately predicting anticancer peptides and capturing intricate spatial patterns within peptide sequences. Conclusion: The findings demonstrate the potential of deep learning, specifically 2D CNNs, in advancing the prediction of anticancer peptides. The proposed model significantly improves prediction accuracy, offering a valuable tool for identifying effective peptide candidates for cancer treatment. Future Work: Further research should focus on expanding the dataset, exploring alternative deep learning architectures, and validating the model's predictions through experimental studies. Efforts should also aim at optimizing computational efficiency and translating these predictions into clinical applications.

Novel peptides derived from S. hispanica seeds induce selective cytotoxicity on human cancer cells.

Cancer prevails as one of the major health concerns worldwide due to the consistent rise in incidence and lack of effective therapies. Previous studies identified the peptides KLKKNL, MLKSKR, and KKYRVF from Salvia hispanica seeds and stated their selective anticancer activity. Thus, this study aimed to determine the cell death pathway induced by these peptides on five cancer cell lines (MCF-7, Caco2, HepG2, DU145, and HeLa). Based on the results of this work, it is possible to suggest that KLKKNL primarily induces selective cancer cell death through the apoptotic pathway in the Caco2 and HeLa lines. On the other hand, the peptide KKYRVF reported the highest statistical (p < 0.05) selective cytotoxic effect on the MCF-7, Caco2, HepG2, and DU145 cancer cell lines by induction of the necrotic pathway. These findings offer some understanding of the selective anticancer effect of KLKKNL, MLKSKR, and KKYRVF.

ACP-PDAFF: Pretrained model and dual-channel attentional feature fusion for anticancer peptides prediction.

Anticancer peptides(ACPs) have attracted significant interest as a novel method of treating cancer due to their ability to selectively kill cancer cells without damaging normal cells. Many artificial intelligence-based methods have demonstrated impressive performance in predicting ACPs. Nevertheless, the limitations of existing methods in feature engineering include handcrafted features driven by prior knowledge, insufficient feature extraction, and inefficient feature fusion. In this study, we propose a model based on a pretrained model, and dual-channel attentional feature fusion(DAFF), called ACP-PDAFF. Firstly, to reduce the heavy dependence on expert knowledge-based handcrafted features, binary profile features (BPF) and physicochemical properties features(PCPF) are used as inputs to the transformer model. Secondly, aimed at learning more diverse feature informations of ACPs, a pretrained model ProtBert is utilized. Thirdly, for better fusion of different feature channels, DAFF is employed. Finally, to evaluate the performance of the model, we compare it with other methods on five benchmark datasets, including ACP-Mixed-80 dataset, Main and Alternate datasets of AntiCP 2.0, LEE and Independet dataset, and ACPred-Fuse dataset. And the accuracies obtained by ACP-PDAFF are 0.86, 0.80, 0.94, 0.97 and 0.95 on five datasets, respectively, higher than existing methods by 1% to 12%. Therefore, by learning rich feature informations and effectively fusing different feature channels, ACD-PDAFF achieves outstanding performance. Our code and the datasets are available at https://github.com/wongsing/ACP-PDAFF.

Cyclic tachyplesin I kills proliferative, non-proliferative and drug-resistant melanoma cells without inducing resistance.

Acquired drug resistance is the major cause for disease recurrence in cancer patients, and this is particularly true for patients with metastatic melanoma that carry a BRAF V600E mutation. To address this problem, we investigated cyclic membrane-active peptides as an alternative therapeutic modality to kill drug-tolerant and resistant melanoma cells to avoid acquired drug resistance. We selected two stable cyclic peptides (cTI and cGm), previously shown to have anti-melanoma properties, and compared them with dabrafenib, a drug used to treat cancer patients with the BRAF V600E mutation. The peptides act via a fast membrane-permeabilizing mechanism and kill metastatic melanoma cells that are sensitive, tolerant, or resistant to dabrafenib. Melanoma cells do not become resistant to long-term treatment with cTI, nor do they evolve their lipid membrane composition, as measured by lipidomic and proteomic studies. In vivo studies in mice demonstrated that the combination treatment of cTI and dabrafenib resulted in fewer metastases and improved overall survival. Such cyclic membrane-active peptides are thus well suited as templates to design new anticancer therapeutic strategies.

Glioma and Peptidergic Systems: Oncogenic and Anticancer Peptides.

Glioma cells overexpress different peptide receptors that are useful for research, diagnosis, management, and treatment of the disease. Oncogenic peptides favor the proliferation, migration, and invasion of glioma cells, as well as angiogenesis, whereas anticancer peptides exert antiproliferative, antimigration, and anti-angiogenic effects against gliomas. Other peptides exert a dual effect on gliomas, that is, both proliferative and antiproliferative actions. Peptidergic systems are therapeutic targets, as peptide receptor antagonists/peptides or peptide receptor agonists can be administered to treat gliomas. Other anticancer strategies exerting beneficial effects against gliomas are discussed herein, and future research lines to be developed for gliomas are also suggested. Despite the large amount of data supporting the involvement of peptides in glioma progression, no anticancer drugs targeting peptidergic systems are currently available in clinical practice to treat gliomas.

Extended dipeptide composition framework for accurate identification of anticancer peptides.

The identification of anticancer peptides (ACPs) is crucial, especially in the development of peptide-based cancer therapy. The classical models such as Split Amino Acid Composition (SAAC) and Pseudo Amino Acid Composition (PseAAC) lack the incorporation of feature representation. These advancements improve the predictive accuracy and efficiency of ACP identification. Thus, the effort of this research is to propose and develop an advanced framework based on feature extraction. Thus, to achieve this objective herein we propose an Extended Dipeptide Composition (EDPC) framework. The proposed EDPC framework extends the dipeptide composition by considering the local sequence environment information and reforming the CD-HIT framework to remove noise and redundancy. To measure the accuracy, we have performed several experiments. These experiments were employed using four famous machine learning (ML) algorithms named; Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and K Nearest Neighbor (KNN). For comparisons, we have used accuracy, specificity, sensitivity, precision, recall, and F1-Score as evaluation criteria. The reliability of the proposed framework is further evaluated using statistical significance tests. As a result, the proposed EDPC framework exhibited enhanced performance than SAAC and PseAAC, where the SVM model delivered the highest accuracy of 96. 6% and significant enhancements in specificity, sensitivity, precision, and F1-score over multiple datasets. Due to the incorporation of enhanced feature representation and the incorporation of local and global sequence profiles proposed EDPC achieves higher classification performance. The proposed frameworks can deal with noise and also duplicating features. These are accompanied by a wide range of feature representations. Finally, our proposed framework can be used for clinical applications where ACP identification is essential. Future works will include extending to a larger variety of datasets, incorporating tertiary structural information, and using deep learning techniques to improve the proposed EDPC.

Investigation of cytotoxic effect and action mechanism of a synthetic peptide derivative of rabbit cathelicidin against MDA-MB-231 breast cancer cell line.

Antimicrobial peptides (AMPs) have sparked significant interest as potential anti-cancer agents, thereby becoming a focal point in pursuing novel cancer-fighting strategies. These peptides possess distinctive properties, underscoring the importance of developing more potent and selectively targeted versions with diverse mechanisms of action against human cancer cells. Such advancements would offer notable advantages compared to existing cancer therapies. This research aimed to examine the toxicity and selectivity of the nrCap18 peptide in both cancer and normal cell lines. Furthermore, the rate of cellular death was assessed using apoptosis and acridine orange/ethidium bromide (AO/EB) double staining at three distinct incubation times. Additionally, the impact of this peptide on the cancer cell cycle and migration was evaluated, and ultimately, the expression of cyclin-dependent kinase 4/6 (CDK4/6) genes was investigated. The results obtained from the study demonstrated significant toxicity and selectivity in cancer cells compared to normal cells. Moreover, a strong progressive increase in cell death was observed over time. Furthermore, the peptide exhibited the ability to halt the progression of cancer cells in the G1 phase of the cell cycle and impede their migration by suppressing the expression of CDK4/6 genes.

Comparative Study of the Potential Cell-Penetrating Peptide ∆M4 on Apoptosis Cell Signaling in A375 and A431 Cancer Cell Lines.

In recent yearsjajajj, peptide-based therapeutics have attracted increasing interest as a potential approach to cancer treatment. Peptides are characterized by high specificity and low cytotoxicity, but they cannot be considered universal drugs for all types of cancer. Of the numerous anticancer-reported peptides, both natural and synthetic, only a few have reached clinical applications. However, in most cases, the mechanism behind the anticancer activity of the peptide is not fully understood. For this reason, in this work, we investigated the effect of the novel peptide ∆M4, which has documented anticancer activity, on two human skin cancer cell lines. A novel approach to studying the potential induction of apoptosis by anticancer peptides is the use of protein microarrays. The results of the apoptosis protein study demonstrated that both cell types, skin malignant melanoma (A375) and epidermoid carcinoma (A431), exhibited markers associated with apoptosis and cellular response to oxidative stress. Additionally, ∆M4 induced concentration- and time-dependent moderate ROS production, triggering a defensive response from the cells, which showed decreased activation of cytoplasmic superoxide dismutase. However, the studied cells exhibited a differential response in catalase activity, with A375 cells showing greater resistance to the peptide action, possibly mediated by the Nrf2 pathway. Nevertheless, both cell types showed moderate activity of caspases 3/7, suggesting that they may undergo partial apoptosis, although another pathway of programmed death cannot be excluded. Extended analysis of the mechanisms of action of anticancer peptides may help determine their effectiveness in overcoming chemoresistance in cancerous cells.

P18: Novel Anticancer Peptide from Induced Tumor-Suppressing Cells Targeting Breast Cancer and Bone Metastasis.

BACKGROUND: The skeletal system is a common site for metastasis from breast cancer. In our prior work, we developed induced tumor-suppressing cells (iTSCs) capable of secreting a set of tumor-suppressing proteins. In this study, we examined the possibility of identifying anticancer peptides (ACPs) from trypsin-digested protein fragments derived from iTSC proteomes. METHODS: The efficacy of ACPs was examined using an MTT-based cell viability assay, a Scratch-based motility assay, an EdU-based proliferation assay, and a transwell invasion assay. To evaluate the mechanism of inhibitory action, a fluorescence resonance energy transfer (FRET)-based GTPase activity assay and a molecular docking analysis were conducted. The efficacy of ACPs was also tested using an ex vivo cancer tissue assay and a bone microenvironment assay. RESULTS: Among the 12 ACP candidates, P18 (TDYMVGSYGPR) demonstrated the most effective anticancer activity. P18 was derived from Arhgdia, a Rho GDP dissociation inhibitor alpha, and exhibited inhibitory effects on the viability, migration, and invasion of breast cancer cells. It also hindered the GTPase activity of RhoA and Cdc42 and downregulated the expression of oncoproteins such as Snail and Src. The inhibitory impact of P18 was additive when it was combined with chemotherapeutic drugs such as Cisplatin and Taxol in both breast cancer cells and patient-derived tissues. P18 had no inhibitory effect on mesenchymal stem cells but suppressed the maturation of RANKL-stimulated osteoclasts and mitigated the bone loss associated with breast cancer. Furthermore, the P18 analog modified by N-terminal acetylation and C-terminal amidation (Ac-P18-NH2) exhibited stronger tumor-suppressor effects. CONCLUSIONS: This study introduced a unique methodology for selecting an effective ACP from the iTSC secretome. P18 holds promise for the treatment of breast cancer and the prevention of bone destruction by regulating GTPase signaling.

Advancing Peptide-Based Cancer Therapy with AI: In-Depth Analysis of State-of-the-Art AI Models.

Anticancer peptides (ACPs) play a vital role in selectively targeting and eliminating cancer cells. Evaluating and comparing predictions from various machine learning (ML) and deep learning (DL) techniques is challenging but crucial for anticancer drug research. We conducted a comprehensive analysis of 15 ML and 10 DL models, including the models released after 2022, and found that support vector machines (SVMs) with feature combination and selection significantly enhance overall performance. DL models, especially convolutional neural networks (CNNs) with light gradient boosting machine (LGBM) based feature selection approaches, demonstrate improved characterization. Assessment using a new test data set (ACP10) identifies ACPred, MLACP 2.0, AI4ACP, mACPred, and AntiCP2.0_AAC as successive optimal predictors, showcasing robust performance. Our review underscores current prediction tool limitations and advocates for an omnidirectional ACP prediction framework to propel ongoing research.

Synthesis and structural optimization of oncolytic peptide LTX-315.

Oncolytic peptides represented potential novel candidates for anticancer treatments especially drug-resistant cancer cell lines. One of the most promising and extensively studied is LTX-315, which is considered as the first in class oncolytic peptide and has entered phase I/II clinical trials. Nevertheless, the shortcomings including poor proteolytic stability, moderate anticancer durability and high synthesis costs may hinder the widespread clinical applications of LTX-315. In order to reduce the synthesis costs, as well as develop derivatives possessing both high protease-stability and durable anticancer efficiency, twenty LTX-315-based derived-peptides were designed and efficiently synthesized. Especially, through solid-phase S-alkylation, as well as the optimized peptide cleavage condition, the derived peptides could be prepared with drastically reduced synthesis cost. The in vitro anticancer efficiency, serum stability, anticancer durability, anti-migration activity, and hemolysis effect were systematically investigated. It was found that derived peptide MS-13 exhibited comparable anticancer efficiency and durability to those of LTX-315. Strikingly, the D-type peptide MS-20, which is the enantiomer of MS-13, was demonstrated to possess significantly high proteolytic stability and sustained anticancer durability. In general, the cost-effective synthesis and stability-guided structural optimizations were conducted on LTX-315, affording the highly hydrolysis resistant MS-20 which possessed durable anticancer activity. Meanwhile, this study also provided a reliable reference for the future optimization of anticancer peptides through the solid-phase S-alkylation and L-type to D-type amino acid substitutions.

Rational design of a new short anticancer peptide with good potential for cancer treatment.

Anticancer peptides (ACPs) have regarded as a new generation of promising antitumor drugs due to the unique mode of action. The main challenge is to develop potential anticancer peptides with satisfied antitumor activity and low toxicity. Here, a series of new α-helical anticancer peptides were designed and synthesized based on the regular repeat motif KLLK. The optimal peptides 14E and 14Aad were successfully derived from the new short α-helical peptide KL-8. Our results demonstrated that 14E and 14Aad had good antitumor activity and low toxicity, exhibiting excellent selectivity index. This result highlighted that the desirable modification position and appropriate hydrophobic side-chain structure of acidic amino acids played critical roles in regulating the antitumor activity/toxicity of new peptides. Further studies indicated that they could induce tumor cell death via the multiple actions of efficient membrane disruption and intracellular mechanisms, displaying apparent superiority in combination with PTX. In addition, the new peptides 14E and 14Aad showed excellent antitumor efficacy in vivo and low toxicity in mice compared to KL-8 and PTX. Particularly, 14Aad with the longer side chain at the 14th site exhibited the best therapeutic performance. In conclusion, our work provided a new avenue to develop promising anticancer peptides with good selectivity for tumor therapy.

ACP-ESM2: The prediction of anticancer peptides based on pre-trained classifier.

Anticancer peptides (ACPs) are a type of protein molecule that has anti-cancer activity and can inhibit cancer cell growth and survival. Traditional classification approaches for ACPs are expensive and time-consuming. This paper proposes a pre-trained classifier model, ESM2-GRU, for ACP prediction to make it easier to predict ACPs, gain a better understanding of the structural and functional differences of anti-cancer peptides, and optimize the design for the development of more effective anti-cancer treatment strategies. The model is made up of the ESM2 pre-trained model, a bidirectional GRU recurrent neural network, and a fully connected layer. ACP sequences are first fed into the ESM2 model, which then expands the dimensions before feeding the findings back into the bidirectional GRU recurrent neural network. Finally, the fully connected layer generates the ultimate output. Experimental validation demonstrates that the ESM2-GRU model greatly improves classification performance on the benchmark dataset ACP606, with AUC, ACC, and MCC values of 0.975, 0.852, and 0.738, respectively. This exceptional prediction potential helps to identify specific types of anti-cancer peptides, improving their targeting and selectivity and, therefore, furthering the development of tailored medicine and treatments.

ACP-DRL: an anticancer peptides recognition method based on deep representation learning.

Cancer, a significant global public health issue, resulted in about 10 million deaths in 2022. Anticancer peptides (ACPs), as a category of bioactive peptides, have emerged as a focal point in clinical cancer research due to their potential to inhibit tumor cell proliferation with minimal side effects. However, the recognition of ACPs through wet-lab experiments still faces challenges of low efficiency and high cost. Our work proposes a recognition method for ACPs named ACP-DRL based on deep representation learning, to address the challenges associated with the recognition of ACPs in wet-lab experiments. ACP-DRL marks initial exploration of integrating protein language models into ACPs recognition, employing in-domain further pre-training to enhance the development of deep representation learning. Simultaneously, it employs bidirectional long short-term memory networks to extract amino acid features from sequences. Consequently, ACP-DRL eliminates constraints on sequence length and the dependence on manual features, showcasing remarkable competitiveness in comparison with existing methods.