Skip to main content

Refining mutanome-based individualised immunotherapy of melanoma using artificial intelligence


Using the particular nature of melanoma mutanomes to develop medicines that activate the immune system against specific mutations is a game changer in immunotherapy individualisation. It offers a viable solution to the recent rise in resistance to accessible immunotherapy alternatives, with some patients demonstrating innate resistance to these drugs despite past sensitisation to these agents. However, various obstacles stand in the way of this method, most notably the practicality of sequencing each patient's mutanome, selecting immunotherapy targets, and manufacturing specific medications on a large scale. With the robustness and advancement in research techniques, artificial intelligence (AI) is a potential tool that can help refine the mutanome-based immunotherapy for melanoma. Mutanome-based techniques are being employed in the development of immune-stimulating vaccines, improving current options such as adoptive cell treatment, and simplifying immunotherapy responses. Although the use of AI in these approaches is limited by data paucity, cost implications, flaws in AI inference capabilities, and the incapacity of AI to apply data to a broad population, its potential for improving immunotherapy is limitless. Thus, in-depth research on how AI might help the individualisation of immunotherapy utilising knowledge of mutanomes is critical, and this should be at the forefront of melanoma management.


Melanoma is a rare type of skin tumour, accounting for 1.1% of cancer deaths per year [1]. The annual incidence of melanoma has rapidly increased worldwide [2]. However, there has been a reduction in the mortality rate due to advancements in immunotherapy [3]. There are significant regional melanoma variations around the world that are attributed to racial skin phenotypes and sun exposure [4], which is the most implicated cause of melanoma globally [5]. Moreover, melanoma occurs mainly in young and middle-aged people, with an increasing incidence after age 25 and decreasing after 50, particularly in females [6].

The pathophysiology of melanoma involves mutations in genes regulating proteins, tight junctions, the cell cycle, deoxyribonucleic acid (DNA) damage, and remodelling of chromatin related to the melanocytes [5]. BRAF and NRAS are the most implicated genes, contributing 54.4% and 30.7% due to mutations at the V600 codon and Q61 codon, respectively [5]. Various treatment approaches have been developed in the management of melanoma, and these approaches have been continually refined, with new modalities added to better streamline the available options and increase survival rates. Available treatment options include surgical excision, chemotherapy, targeted therapy using BRAF, NRAS, and C-Kit inhibitors, radiation, and immunotherapy [1].

With the advent of immunotherapy, the median survival rate of advanced melanoma has improved from 9 months to 6 years [7]. Due to the variability in mutations in melanoma, knowledge of the status of individual mutations can help in patient stratification and aid targeted immunotherapy. In recent times, understanding individual mutations known as mutanomes has gained traction as a potential means for managing advanced cancers refractory to known therapies [8]. Advancement in artificial intelligence (AI) has sparked the debate that rapid sequencing of the mutanome and streamlining therapy options that trigger the immune system to target individual mutations will significantly improve therapy outcomes [9]. Particularly in melanoma, where adoptive cell therapy is proving to be a promising option for mutation-targeted immunotherapy, interest in artificial intelligence for refining this approach is increasing. One of the main reasons why AI is becoming more prominent in refining available immunotherapy options for melanoma is the increasing rate of reported resistance and refraction experienced by patients [10]. It is becoming apparent that finding approaches that utilise the differences in individual mutations and targeting these mutations on a personalised basis will help reduce the rate at which treatment failure occurs. However, due to the heterogeneity of melanoma, developing vaccines or personalising therapy for each patient is a tedious and expensive endeavour. Thus, this review seeks to highlight the applicability of AI in refining melanoma immunotherapy through exploring the differences in individual mutations.


This narrative review systematically investigates the potential applications of artificial intelligence in advancing research on mutanome-based individualisation of immunotherapy for melanoma management. Employing a rigorous methodology, the review encompasses a diverse range of study designs, including observational, case–control, cohort, and randomised controlled trials, with consideration for both paediatric and adult populations. The inclusion criteria, meticulously formulated, strictly adhere to English-language publications, spanning the period from 2001 to 2023 to align with contemporary practices.

To ensure a thorough exploration of the subject matter, the literature search utilised reputable databases such as ScienceDirect and PubMed. A thoughtfully selected set of search terms, including “mutanome”, “melanoma”, “immunotherapy”, and “artificial intelligence”, tailored the search to the specific focus of interest. Additionally, a manual search enriched the review by identifying references related to recently published, disease-specific reviews. Notably, stand-alone abstracts and unpublished studies were deliberately excluded.

Through this comprehensive and meticulous approach, the review aims to provide a scholarly assessment of the integration of AI technology in refining current research on mutanome-based individualisation of immunotherapy for melanoma management. The employed methodology is summarised in Table 1 for clarity and reference.

Table 1 Summary of the methodology employed in the study


Aetiology of malignant melanoma

Melanoma is caused by multifactorial interactions between the body and the environment [11]. Melanoma is mainly derived from the accumulation of several mutations in melanocyte genes. NRAS, BRAF, and PTEN are some of the most significant genes in the development of melanoma [12,13,14,15, 17, 17]. There are also various genes for which mutations can be inherited, resulting in hereditary melanoma, such as CDKN2A, CDK4, TP53, BRCA1, BRCA2, and PTEN [18].

Environmental factors such as exposure to ultraviolet rays, which is considered the leading risk factor for melanoma [19] can disrupt melanocytes either directly by causing oxidative stress [20, 21] or indirectly by causing several mutations that induce carcinogenesis [22, 23]. Moreover, the risk of developing melanoma rises substantially with overexposure to sun and ultraviolet (UV) rays in addition to recurring sunburns, particularly in younger age groups [24, 25]. It is also influenced by the skin phototype, as among the six skin phototypes, those with fair skin, blue eyes, and blond or red hair (Phototypes I and II) are the most vulnerable to developing skin melanoma due to their high sensitivity to UVB rays [26].

Another environmental factor is the geographical location, as melanoma incidence shows various rates in different regions, with the highest incidence rates in Australia and New Zealand [27]. More interestingly, it was found that acral melanoma on the hands' palms and the feet soles is more prevalent in people working with herbicides such as dichlorprop, atrazine, propanil, and paraquat, and it has a higher incidence in those using these herbicides at home than in those who do not [28]. Also, the susceptibility to skin melanoma is significantly influenced by the status of immunity, as immunosuppressive diseases such as Acquired Immunodeficiency Syndrome (AIDS) increase the risk of developing skin melanoma due to the inability of compromised immunity to effectively protect the body against the formation and development of solid tumours [29, 30].

Clinical manifestation of melanoma

Melanoma can manifest in different forms depending on the primary location of melanocyte transformation. They broadly occur from mutations in the skin melanocytes known as cutaneous melanoma; the iris, choroid, and ciliary body melanocytes collectively referred to as uveal melanomas; and the mucosal melanocytes leading to mucosal melanoma [31]. Of the three, cutaneous melanoma is the most predominant, accounting for 91.2% of all melanoma cases. The National Comprehensive Cancer Network (NCCN) set a new standard in 2017 to classify cutaneous melanoma into 4 types: chronic sun damage (CSD), non-chronic sun damage (non-CSD), acral, and mucosal melanomas. CSD-melanomas are asymmetric, flat, yellowish-brown, brown, or black macules with irregular borders. Non-CSD melanomas are divided mainly into superficial spreading melanoma (SSM), which begins as an asymptomatic tan to black macules that then grow radically, and nodular melanoma (NM), which commonly appears as blue or black, but sometimes pink to red nodules that lack Asymmetry, Border, Colour, Diameter and Evolving (ABCDE) features and can turn into elevated nodules, ulcers, or bleeding. Acral melanoma (AM) is characterised by irregular pigmentation, parallel ridges, and multicomponent lesions on hairless areas such as the palms, fingernails, soles, and toenails. Mucosal melanoma can be found in the lips, eyelids, oral cavity, intestinal mucosa, vulva, and many other sites. It appears as structureless, grey areas in early dermoscopic diagnosis and as lesions with a multicomponent pattern in advanced dermoscopic diagnosis [32].

Limitations and challenges in the management of malignant melanoma

The surgical removal option is primarily used for localised melanoma [33]. It can be used in some metastatic melanoma cases as well, but it is not considered to be curative, and other treatment options are still needed, such as chemotherapy. Although chemotherapy was the only curative option for metastatic melanoma until recently, its usage has decreased since the appearance of immunotherapies and targeted therapies [34]. To treat melanoma, numerous targeted therapies have been developed, among which the BRAF inhibitors vemurafenib and dabrafenib are the most promising [35, 36]. Despite their high efficacy, secondary resistance within a short time has been observed in most of the patients with BRAF-mutated melanomas [35,36,37]. Because of the high expense and severe side effects of the current treatments, research is still ongoing to overcome the limitations and complications, improve safety, and find other drug options [34].

The use of targeted therapy in malignant melanoma

A variety of cancer inhibitors are used in targeted therapy, including mitogen-activated protein kinase (MEK) inhibitors (trametinib), BRAF inhibitors (vemurafenib and dabrafenib), cyclin-dependent kinase (CDK) inhibitors (ribociclib, abemaciclib, and palbociclib), and c-Kit inhibitors (imatinib) [38]. Trametinib is a monotherapy-approved MEK1/MEK2 inhibitor used to treat BRAF V600-mutant metastatic melanoma [39]. Although vemurafenib is a BRAF mutant inhibitor with high selectivity and efficacy against metastatic melanoma with BRAF V600 and non-V600E mutations [38], treatment resistance develops in most patients [40]. Dabrafenib is a subsequent-generation BRAF mutant inhibitor. The Food and Drug Administration (FDA) approved it for the treatment of unresectable or metastatic BRAF V600E-mutated melanomas [41, 42]. Ribociclib, abemaciclib, and palbociclib are a new class of specific CDK4/6 inhibitors that are more effective and have fewer side effects [38]. Imatinib is a c-Kit inhibitor found to be effective against c-Kit-mutated metastatic melanomas [43].

Immunotherapy options available for malignant melanoma

Substantial advances have been made in immunotherapy treatments for metastatic melanoma over the last three decades. Cancer vaccines, adoptive cell therapies, and immunomodulatory approaches are the primary three types of immunotherapy options [34]. Interleukin-2 treatment was one of the first immune therapies for metastatic melanoma [35, 44]. Unfortunately, it was found to be highly toxic [34]. Cancer vaccines are therapeutic vaccines designed to stimulate the immune system against cancer cells. Due to the various evasion mechanisms cancer cells have, creating these vaccines has been challenging, so the early vaccines were not effective, and none have been approved for clinical application yet [45,46,47].

Up to date, the most effective treatment is immune checkpoint inhibitors [44, 48, 49]. Antibodies against the immune checkpoint receptors, such as programmed cell death protein 1 (PD-1), PD-1 ligand (PD-L1/2), and cytotoxic T-lymphocyte-associated protein 4 (CTLA-4), can be used to counteract the immune checkpoint modulation in melanoma. These antibodies disrupt binding to the corresponding ligands and tolerance signals, ultimately leading to the activation of the immune system [49,50,51,52]. The anti-CTLA-4 antibody ipilimumab and the anti-PD-1 antibodies nivolumab and pembrolizumab are currently the approved immune checkpoint inhibitor drugs for melanoma treatment [51]. Despite the benefits of checkpoint inhibitors, they have serious side effects mainly related to immunity because they inhibit the tolerance of immune mechanisms [53, 54]. Corticosteroids can neutralise their toxicity in some cases, but others continue to struggle with these side effects. In addition, a majority of patients still show no response, and others may even acquire secondary resistance [34, 55]. Overview of malignant melanoma with its newer therapeutic targets is summarised in Fig. 1.

Fig. 1
figure 1

Overview of malignant melanoma along with its new therapeutic targets. CTLA-4, cytotoxic T-lymphocyte associated protein-4; PD-1, programmed cell death protein 1; TCR, T cell receptor; PDL-1, programmed death ligand 1; MHC, major histocompatibility complex; DC, dendritic cell; BRAF, v-Raf murine sarcoma viral oncogene homolog B1; MEK, mitogen-activated protein kinase; ERK, extracellular signal-regulated kinase; RAF, rapidly activated fibrosarcoma; RAS, rat sarcoma; RTK, receptor tyrosine kinase; GTP, guanosine triphosphate; NRAS, neuroblastoma RAS viral oncogene homolog; PTEN, phosphatase and tensin homolog; TP53, tumour protein 53; BRCA, breast cancer gene; CDK, Cyclin dependent kinase

Mutanome-based individualised immunotherapy for malignant melanoma

Individualisation of melanoma immunotherapy represents a shifting paradigm in the field of oncology towards personalised medicine [7, 56, 57]. This transformation relies on various factors such as biomarker expression [58,59,60,61,62,63,64], immune system profiling [65], tumour microenvironment [66], patients' well-being [67, 68], and preferences [69]. However, tumour characteristics, which encompass the patient's mutanome and respective molecular profile, are the most important factor. The role of mutanomes in immunotherapy for malignant melanoma is summarised in Fig. 2. This holds a promising and powerful tool, as most melanoma mutations are unique and rarely shared, even among the same type [9, 70].

Fig. 2
figure 2

Overview of mutanome-based immunotherapy for malignant melanoma. DNA, deoxyribonucleic acid; RNA, ribonucleic acid; T-VEC, talimogene laherparepvec; GM-CSF, granulocyte macrophage colony stimulating factor; HSV-1, herpes simplex virus-1; NGS, Next Genome Sequencing; BAM, binary alignment map; VCF, variant cell format; SNP, single nucleotide polymorphism; shRNA, small hairpin RNA; cDNA, complementary DNA

The “mutanome” or “mutation-genome” reflects the tumour genetic mutational signature [71], while the molecular profile includes the ribonucleic acids (RNAs) [72], encoded neoantigens [73, 74], and neo-epitopes [15]. This concept emerged thanks to sequencing technologies, especially after publishing the first complete set of mutations in Saccharomyces cerevisiae yeast in 2002 [75]. One of the pioneering studies, which was done by Krauthammer and his team, was the first to unveil melanomas' mutational landscape using exosome sequencing [76].

As time progressed, significant advancements in sequencing technologies propelled us from traditional and exosome-only sequencing to embracing more sophisticated approaches, such as whole genome and next-generation sequencing [77]. These advancements have allowed for a more comprehensive exploration of all types of mutations, ranging from single nucleotide polymorphisms (SNPs) and insertions to deletions and frameshifts, regardless of their effect as driver or passenger mutations and irrespective of whether they occur in coding or non-coding regions [77, 78]. This way, we can catch mutations even with low mutational burden melanomas [79, 80].

Moreover, the integration of additional fields such as transcriptomics, immunogenicity testing [81], and computational biology pushed the concept to its extreme limits [82,83,84]. This enabled us to leverage individualisation by decoding the patient's tumour mutanome using NGS according to the health human genome atlas, predicting neoantigens [85], and identifying epitopes with strong human leukocyte antigen (HLA) binding affinity [83, 86]. That precious information can later be used in different types of immunotherapies.

In the context of adoptive cell therapy, research utilising this knowledge showed that tumour-infiltrating lymphocytes (TIL) prepared based on predicted neoantigens and neo-epitopes exhibited enhanced T cell expansion and response [87, 88]. But like other passive immunotherapies, despite their potential benefits, they lack long-term effectiveness due to challenges like T cell specificity loss [89] and research still trying to solve them [90].

A multimodal immunotherapy that makes use of both passive and active approaches is oncolytic virus therapy. Studies demonstrated that genetically modified viruses, like herpes [91], adenoma, and vaccinia, have the ability to directly lyse virus-infected melanoma cells and release tumour neoantigens, stimulating anti-tumour immunity [2, 93]. In recent studies, scientists have further enhanced active immunotherapy by coating viruses with predicted tumour neoantigens, Peptide-coated Conditionally Replicating Adenovirus (PeptiCRAd) [94]. This innovative technique holds great promise for future research.

However, vaccines continue to remain the primary research focus of active melanoma immunotherapy [95,96,97]. Mutanome-based individualisation approaches have been employed to develop on-demand vaccine manufacturing pipelines and conduct thorough testing. Various vaccine types, including peptide, RNA, and dendritic cell vaccines, have been studied.

For instance, autologous dendritic cells loaded ex vivo with patient-specific neoantigens demonstrated good tolerance and an increase in the breadth and diversity of T cell responses [98,99,100]. Subsequently, custom messenger ribonucleic acid (mRNA) liposomal vaccines capable of neoantigen encoding were developed and tested, resulting in the expansion of preexisting T cells and the induction of new T cell responses against the neo-epitopes [101,102,103,104]. Other studies explored a custom peptide vaccine synthesis approach using patients' neoantigen structures [105, 106].

This approach to melanoma treatment ensures that the treatment is tailored to the individual profile, maximising the chances of a successful immune response and reducing the risk of treatment resistance. This can also directly or indirectly target cancer cells and kill them. Overall, the integration of mutanome knowledge in individualised immunotherapy holds promise for revolutionising melanoma treatment, offering patients the potential for better responses, prolonged remissions, and a step closer to achieving the goal of precision oncology.

Despite our advancing knowledge of the mutanome, several limitations remain when implementing this research for individualised immunotherapy of malignant melanoma. One of the biggest limitations is the impact physiological differences in the body have on the absorption, distribution, metabolism, and elimination of drugs [107,108,109]. Immune checkpoint inhibitors (ICI) have revolutionised the treatment of malignant melanoma; however, the response rate is approximately one-third [110,111,112]. A lack of research into the pharmacokinetic responses of ethnicity, age, sex, and disease stage, however, limits the effectiveness of individualised immunotherapy [113]. Targeting this area of research remains challenging due to the large genetic variations that exist within these subpopulations [114]. Effectively targeting and utilising such data could allow individualised immunotherapy for malignant melanoma to reach its full potential [70].

AI and cancer immunotherapy

AI techniques of importance in cancer immunotherapy

In the field of cancer treatment, immunotherapy has made significant advancements and is now widely used. However, a challenge that has arisen is the identification of suitable individuals who can benefit from this therapy and who should receive it. To address this challenge, AI has been developed to aid in performing tasks that typically require human intelligence. These tasks include interpretation of language, perception of visual materials, and decision-making [115]. The utilisation of AI technologies has resulted in enhanced precision and effectiveness in the diagnosis and prediction of cancer treatment responses. AI has enabled the classification of patients into two groups: those who will respond positively to cancer immunotherapy and those who will not, thereby ensuring that only suitable patients receive the treatment [116]. With the aid of neural-based models, the tumour immune microenvironment of solid tumours such as colorectal, breast, lung, and pancreatic cancer, which plays a crucial role in patients' responses to cancer immunotherapy, has been accurately characterised by integrating RNA sequencing (RNA-Seq) and imaging data in a clinical setting [117].

Currently, numerous research groups and companies are dedicated to creating programmes that can enhance the efficiency, precision, and affordability of cancer screening. By acting as a supplementary visual aid, AI can aid medical professionals in identifying and diagnosing cancer in images with greater precision than would be possible otherwise. This results in improved accuracy and, consequently, insight for patients [117]. The application of deep learning (DL) methods enables the precise and automated identification of changes in tumour size and gene status, which can serve as an assisting tool for monitoring the efficacy of immunotherapy [115].

As biotechnology continues to develop and our understanding of the molecular mechanisms of tumours expands, immunotherapy has become an effective method of training the immune system to recognise and target specific cancer cells. This treatment modality can enhance the immune cells' ability to identify and eliminate cancer cells while also providing the body with supplementary components to augment the immune response. There are different types of cancer immunotherapy available, including targeted antibodies, cancer vaccines, adoptive cell transfer, tumour-infecting viruses, checkpoint inhibitors, cytokines, and adjuvants. In the prediction of immunotherapy responses, AI has been employed in the evaluation of immune signatures, medical imaging, and histologic analysis [117].

Current application of AI in the individualisation of cancer immunotherapy

The utilisation of AI, a cutting-edge technology, has made it possible to provide personalised treatment to patients with tumours by automating the prediction of the effects of tumour immunotherapy through the construction of models [118]. The use of AI in immunotherapy is concentrated on three main themes. The first theme concerns tumour neoantigens, which form the foundation of immunotherapy. A key unresolved issue in this area is the rapid and precise prediction of immunogenic tumour antigens using AI, which would minimise the need for experimental screening and validation [119]. Machine learning (ML) techniques have the potential to identify the factors that determine tumour immunogenicity and the peptides presented by major histocompatibility complex class I (MHC-I), which can be utilised to assess neoantigen binding and/or treatment response predictions in cancer immunotherapy [115]. Artificial neural networks enable the observation of tumour antigen T cell epitopes in patients with melanoma, which can be utilised for personalised cancer immunotherapy [117]. The second theme of AI application in immunotherapy pertains to the scope for improvement in tumour therapeutic monoclonal antibodies, despite their notable success. This has spurred much innovation in antibody design, with AI-augmented antibodies holding immense potential for further advancements in cancer treatment. The advent of DL has opened up new avenues for therapeutic antibody design, including the prediction of structure, screening for target binding, affinity maturation, and pharmaceutical property prediction.

The third theme pertains to the challenges associated with predicting the response to immunotherapy. This includes the identification of patients who are most likely to respond to immunotherapy using multimodal and multi-scale biomarkers, as well as the characterisation of the tumour immune microenvironment [119]. AI-based techniques like imaging and histopathology analysis both ML-based and DL-based approaches have demonstrated efficacy in interpreting tumour microenvironment (TME) in combination with immunohistochemistry. These methods reveal disparities in the expression and localisation of biomarkers among various histological subtypes, which can be leveraged to predict responses to immunotherapies or other targeted therapies [115].

To predict the effectiveness of immunotherapy using AI, a general approach involves creating a training cohort and a validation cohort. The multi-scale medical data from the training cohort are collected, filtered, segmented, and features extracted and selected. This data is then used to train and model AI. The validation cohort is used to verify the results of the AI's learning. The multi-scale medical data may include genomics, proteomics, pathological tissue, computed tomography / magnetic resonance (CT/MR) imaging, and more. The goal is for the AI to predict whether a patient will benefit from immunotherapy or suggest further evaluation, such as whole genome sequencing. Additionally, AI can predict which immunotherapy drug will be most effective for the patient. This approach can improve the accuracy of immunotherapy treatment and potentially lead to better patient outcomes [118].

Radiomics is an emerging AI technique that is gaining increasing attention in cancer management. It is an algorithm-based method that extracts patterns from images obtained from computed tomography, magnetic resonance imaging, positron emission tomography or a combination of two of these [120, 121]. These patterns serve as the basis for response rate monitoring [122], individualisation of therapy [122], risk stratification [121, 123], survival analysis [123], metastatic capability predictions [121, 124] and patient monitoring [122]. In the individualisation of therapy, this is especially useful as it can discern little differences in obtained images, thereby forming patterns that can be used in correlation generation, thus influencing therapy choices. One of such is its application as a predictive signature generator for better correlation with immune markers. CD8+ expression in melanoma was found to be inversely proportional to the mean of positive pixel (MPP) and standard deviation (SD) using radiomics which also correlates with prognostic outcomes in patients [125]. It has similarly been applied in signature–immune marker correlations in other types of cancers like non-small-cell lung [126] and renal cancers [127]. Furthermore, signature correlations have also been used in evaluating survival in melanoma patients treated with pembrolizumab [123].

Advantages and limitations of the use of AI in cancer immunotherapy

AI has emerged as a highly advanced tool in the field of computer-assisted cancer immunotherapy. As clinical data and AI methodologies continue to advance, AI has the potential to play an even greater role in predicting immunotherapy responses. One of the greatest strengths of AI is its ability to learn from large sets of data and identify patterns that can be applied to specific tasks, such as mutation annotation or diagnosis [128].

The incorporation of AI in cancer immunotherapy has been recognised as a developing computer-assisted approach that can enhance the predictive abilities and functional roles of personalised therapy. Nonetheless, there are discrepancies in the application of AI techniques for widespread use in clinical practice. AI-based algorithms have the potential to be a promising strategy for optimising individualised immunotherapy and ultimately improving the healthcare quality and prognosis of patients [115].

The application of AI in cancer immunotherapy has demonstrated some limitations. These include a shortage of available data, data biases, insufficient data sharing, a lack of code sharing, and difficulties in interpreting the models. Also, there is a gap between the ease of gathering data from various platforms and the ease of access by external agencies for independent use, especially for private or controlled-access datasets. The absence of data sharing hinders the effective validation of AI models across multiple medical centres. Additionally, the variability of data presents a significant challenge in implementing DL for immunotherapy, whereby incongruities in data batches and quality issues often lead to unsuccessful external validation [119].

The intricate nature of predicting immunotherapy outcomes necessitates collaboration between scientific researchers, enterprises, and clinicians to construct databases and establish industry standards. This collaborative effort should aim to eliminate technical obstacles and foster the development of AI-assisted systems that can precisely identify the target population for immunotherapy, accurately forecast treatment efficacy and prognosis, and promote the implementation of AI-assisted treatment while earning the trust of both physicians and patients [118].

AI in refining mutanome-based immunotherapy of malignant melanoma

AI is a tool that can potentially change outcomes in malignant melanoma. With advances in AI, the sequencing of melanoma mutations quickly, the development of individualised vaccines, the determination of the response rate to individualised immunotherapy, patient stratification based on predicted outcomes, and modifying the use of adoptive cell therapy can be refined to meet the increasing needs of melanoma patients. The use of AI in refining mutanome-based immunotherapy is summarised in Fig. 3.

Fig. 3
figure 3

Application of AI refining in mutanome-based immunotherapy. ACT, adoptive cell therapy; AI, artificial intelligence; ML, machine learning

AI in understanding melanoma mutanome

AI has the potential to advance comprehension of the melanoma mutanome and its significance for immunotherapy. Melanoma harbours an exceptionally high mutational burden, which produces tumour-particular neoantigens that can be targeted by the immune system [21, 130]. Nevertheless, completely exploiting the mutanome necessitates the identification of immunogenic mutations from whole genome and transcriptome data [131]. AI methods employing deep finding algorithms can promote mutanome examination, and this has been used to advance rapid technology-based identification and validation of individual mutanomes by individualised vaccines against cancer (IVAC) in the individualisation of immunotherapy for malignant melanoma [132]. Also, neural networks can recognise mutation-derived neoantigens by incorporating genomic, epigenomic, and immunogenicity information at an unprecedented scale and swiftness [133]. This will empower exhaustive mining of the melanoma mutanome to develop personalised mutanome vaccines [134]. AI can also uncover mutations related to immunotherapy response or resistance, guiding individual categorisation and combination tactics [129].

By accelerating mutanome profiling, AI has the potential to boost comprehension of how the mutational landscape influences immunotherapy efficacy in melanoma. This may reveal new pathways to conquer resistance by targeting special mutational signatures [135]. AI-driven multi-omic relationships with clinical outcomes could also supply insights into optimising mutanome-focused methods through rational drug combinations impacting ribosome biogenesis or epigenetics [136, 137]. Thus, AI is well-positioned to revolutionise understanding of the melanoma mutanome's benefits for immunotherapy through thorough assessment of its tumour-particular abnormalities.

AI in the development of melanoma vaccines

Personalising melanoma vaccines based on mutanomes is an up-and-coming application of AI [95,96,97]. With machine learning algorithms able to learn from large amounts of omics data and make inferences that can be applied to new situations, the identification of neoantigens can be optimised, leading to the development of individualised vaccines for different mutational variants [128]. Aside from this, machine learning can streamline vaccines suited to individual immune profiles and hasten the development of large amounts of vaccines for different individuals in a short period of time due to swift algorithms and inherent decision-making capabilities [128]. An mRNA vaccine, mRNA-4157, in a phase 3 clinical trial for melanoma by Moderna and Merck utilises proprietary algorithms in the identification of mutanomes as targets of the vaccine [138]. Advancements in these algorithms are also predicted to shorten the production time from 6 weeks to 30 days, thus increasing the turnaround time, which is one of the major issues identified with the individualisation of immunotherapy [138]. As is known, neoantigens result from mutations in tumours, which can vary among melanoma patients [56]. The identification of immunogenic neoantigens has been challenging so far [139]. However, AI advancements in next-generation sequencing (NGS) have made it possible to identify neoantigens, which are ideal vaccine targets [56]. An AI tool developed by Evaxion (EVX) named Pioneer Technology has been used to identify specific neoantigens for individualised melanoma vaccines like EVX-01 and EVX-02, which are novel molecules at various stages of clinical trials [140].

AI in refining adoptive cell therapy immunotherapy option

In addition to vaccines, AI can refine the adoptive cell therapy (ACT) immunotherapy option. It is known that melanoma mutations are unique and rarely shared [9, 70]. Thus, AI can build on this knowledge to enhance the modulations of T cells, having greater specificity for individual mutations. Also, with deep learning algorithms, AI can simulate what happens when ACT is used, thus limiting resource waste and identifying major lapses and potential adverse effects early on in the drug discovery process [141]. A major problem with ACT is T cell specificity loss, which can be optimised by T cell receptor (TCR) deep sequencing. However, TCRs of significance are rare to come across. With AI, TCR can easily be identified compared to previous experiences via machine learning algorithms that can predict TCR–target interactions specific to every individual [89]. Another issue with ACT is that T cells cannot recognise all mutanomes in tumours. Rather than using peptide-binding algorithms to identify immunogenic mutations, advancements in predictive algorithms have made it possible for minigenes to analyse T cell reactivity in tumours, thus making it possible to develop novel ACTs that recognise individual neoantigens [142].

AI in determining prediction capacities

AI presents an advancing approach that can achieve things that were previously deemed resource-intensive in melanoma. This can help improve prediction capacities, thus increasing the drug discovery pipeline efficiency [143]. In particular, AI can improve predictions in patients that are at a higher risk of metastasis based on their mutanome [141], thus allowing for early preventive measures that can increase patient survival rates. Different melanoma mutanomes are associated with varying levels of serum biomarkers [144]. Some predictive biomarkers, like dermcidin, interferon-gamma, interleukin-4, and granulocyte macrophage colony stimulating factor (GM-CSF), are associated with metastatic melanoma in early-stage patients [141]. Using an AI algorithm to streamline metastatic risk assessment can help improve immunotherapy options that will best reduce the risk of metastasis at an early stage. Machine learning can also increase the speed of determining the probability of survival in melanoma patients. This was demonstrated in research where a combination of machine learning and radiomics was used to assess the survival rates of advanced melanoma patients treated with the immune checkpoint blocker pembrolizumab [123]. This approach can benefit from machine learning’s ability to automate how lesions are identified and segmented in melanoma. AI has also been used to predict the specific type of mutations that initiated a particular cancer in an individual via a noninvasive method [145]. The detailing of the BRAF mutation underlying the melanoma brain metastasis using machine learning-assisted radiomics technique was achieved in contrast to the norm where tissue biopsy is required to determine the genetic aspect of brain metastasis [145]. This noninvasive approach presents a novel technique that can be utilised to predict the exact mutanome in melanoma, thus facilitating better immunotherapy selection [145]. However, this method cannot predict the development of metastasis in specific patients. Table 2 provides a summary of the potential impact of AI on the enhancement of mutanome-based immunotherapy for malignant melanoma.

Table 2 Summary of the role of AI in refining mutanome-based immunotherapy of malignant melanoma

Future prospects and potential limitations of AI in advancing and refining mutanome-based immunotherapy for malignant melanoma

AI is a powerful tool that can change the future management and outcomes associated with malignant melanoma. In light of rising concerns about the development of resistance to available immunotherapy options, exploring the mutanome-based immunotherapy approach refined by AI is gaining traction. Limited research has been carried out on how understanding individual mutations can benefit therapy outcomes due to the diverse nature of the mutations underlying the development of melanomas [9, 70]. Also, the use of AI in melanoma management is not without drawbacks. Notably, imprecisions in AI’s ability to adequately detect lesions in people outside the dataset used in developing the AI algorithm have been cited [146], thus raising concerns about AI’s inference applicability in a larger population [146]. However, AI still remains a game changer that can effectively turn the tide on melanoma management.

A futuristic utility of AI is its ability to swiftly through large sets of mutanomes in a short time. One major problem often cited in the development of individualised immunotherapy is the time and resource intensiveness of sequencing individual mutanomes and modulating immunotherapy options specific to the mutanomes. ML can process large amounts of data in a relatively short time, carry out gene-treatment pairing for best fit, determine the chances of toxicity and efficacy, and also use this data as a pattern for future predictions [143].

Exploring AI to improve individualised immunotherapy options based on mutanomes remains an aspect of the cancer drug discovery process requiring much attention. The growing resistance to multiple immunotherapies available for melanoma continues to dash the hopes of discovering immunotherapy ignited in the scientific world. Worse still, other therapy options like chemotherapy are ineffective in achieving the cure rates obtained from immunotherapies. Thus, it is important to improve and facilitate research that seeks to enhance the application of AI in individualising therapy best suited for the specific genetic mutations in every patient. With improvements in technologies and newer AI algorithms developing, individualised immunotherapy is becoming a possibility. This will help increase the efficiency of the drug discovery process, reduce adverse drug events, and increase survival rates in melanoma patients.

While AI shows promise for optimising mutanome-based immunotherapy, certain limitations must be addressed. Accurately predicting immunogenic neoantigens from tumour sequencing data remains challenging due to tumour heterogeneity and the complexity of antigen presentation [21, 137]. DL models require vast amounts of high-quality immunogenomic training data, which are difficult to obtain, potentially limiting generalisability [131, 133].

Additional barriers include the dynamic interplay between mutations, epigenetic modifications, and cellular signalling pathways influencing immunogenicity, which are challenging to fully incorporate into static AI models [135, 137]. Mutational signatures associated with endogenous and exogenous DNA damage involve complex biological processes not easily defined by current machine learning algorithms [135]. There are also ethical concerns around explaining “black box” AI predictions to patients and difficulties validating models using prospective clinical trial data [129, 131].

Overcoming these limitations requires multidisciplinary collaborations between clinicians, immunologists, geneticists, and AI specialists. Larger pan-cancer immunogenomic databases with linked multi-omic profiles and treatment outcomes could improve generalisability but represent a major undertaking [133]. Combining unsupervised and supervised machine learning with mechanistic modelling may help capture tumour biology dynamics not evident from bulk sequencing alone [133, 137]. With refinements, AI has the potential to optimise mutanome-based therapies if technical challenges around data, modelling complexity, and clinical integration are addressed.


AI is a tool with vast potential in melanoma, as demonstrated by numerous studies on how to optimise its use to simplify management approaches. Although it is not without lapses, its application in rapidly sequencing mutanomes to enhance the ease of individualising therapy in all stages of melanoma is revolutionary. Thus, exploring AI to refine mutanome-based individualisation of therapy can strengthen current predictions of response and toxicity in melanoma patients at all stages. Owing to its robustness, it can also be used to predict the kind of mutation underlying a cancer type, thus easing the ease of patient stratification for immunotherapy and helping future prevention of metastasis. However, more research is required to address the shortcomings of AI in its multiple distinguishing capabilities, large-scale application, and data porosity in order to aid its future outcomes in melanoma.

Availability of data and materials

No data available.



Cytotoxic T-lymphocyte associated protein-4


Programmed cell death protein 1


T cell receptor


Programmed death ligand 1


Major histocompatibility complex


Dendritic cell


V-raf murine sarcoma viral oncogene homolog B1


Mitogen-activated protein kinase


Extracellular signal-regulated kinase


Rapidly activated fibrosarcoma


Rat sarcoma


Receptor tyrosine kinase


Guanosine triphosphate


Neuroblastoma ras viral oncogene homolog


Phosphatase and tensin homolog


Tumour protein 53


Breast cancer gene


Cyclin dependent kinase


Deoxyribonucleic acid


Ribonucleic acid


Talimogene laherparepvec


Granulocyte macrophage colony stimulating factor


Herpes simplex virus-1; NGS: Next Genome Sequencing


Binary alignment map


Variant cell format


Tyrosine-protein kinase kit


Single nucleotide polymorphism


Small hairpin RNA


Complementary DNA


Adoptive cell therapy


Artificial Intelligence


Machine Learning


Individualised vaccines against cancer


Cyclin dependent kinase inhibitor 2A


Messenger RNA; UV: Ultra violet


Acquired immunodeficiency syndrome


National Comprehensive Cancer Network


Chronic sun damage


Superficial spreading melanoma


Nodular melanoma


Asymmetry, border, colour, diameter, and evolving


Acral melanoma


Human leukocyte antigen


Tumour-infiltrating lymphocyte




Peptide-coated Conditionally Replicating Adenovirus


Immune checkpoint inhibitors

RNA Seq:

RNA sequencing


Deep learning


Tumour microenvironment


Computed tomography


Magnetic resonance


Mean of positive pixel


Standard deviation


  1. Kalkan Z. Evaluation of Immunotherapy and Targeted Therapies in the Treatment of Metastatic Malignant Melanoma. Eurasian J Med Invest. 2022.

    Article  Google Scholar 

  2. Ali Z, Yousaf N, Larkin J. Melanoma epidemiology, biology and prognosis. EJC Suppl. 2013;11(2):81–91.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Islami F, Ward EM, Sung H, et al. Annual report to the nation on the status of cancer, part 1: national cancer statistics. J Natl Cancer Inst. 2021;113(12):1648–69.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Leonardi GC, Falzone L, Salemi R, et al. Cutaneous melanoma: from pathogenesis to therapy (review). Int J Oncol. 2018;52(4):1071–80.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Ticha I, Hojny J, Michalkova R, et al. A comprehensive evaluation of pathogenic mutations in primary cutaneous melanomas, including the identification of novel loss-of-function variants. Sci Rep. 2019;9(1):17050.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Rastrelli M, Tropea S, Rossi CR, Alaibac M. Melanoma: epidemiology, risk factors, pathogenesis, diagnosis and classification. In Vivo. 2014;28(6):1005–11.

    PubMed  Google Scholar 

  7. Knight A, Karapetyan L, Kirkwood JM. Immunotherapy in melanoma: recent advances and future directions. Cancers. 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Overwijk WW, Wang E, Marincola FM, Rammensee HG, Restifo NP. Mining the mutanome: developing highly personalized Immunotherapies based on mutational analysis of tumors. J Immunother Cancer. 2013;1:11.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Vormehr M, Tureci O, Sahin U. Harnessing Tumor Mutations for Truly Individualized Cancer Vaccines. Annu Rev Med. 2019;70:395–407.

    Article  CAS  PubMed  Google Scholar 

  10. Lim SY, Shklovskaya E, Lee JH, et al. The molecular and functional landscape of resistance to immune checkpoint blockade in melanoma. Nat Commun. 2023;14(1):1516.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Strashilov S, Yordanov A. Aetiology and pathogenesis of cutaneous melanoma: current concepts and advances. Int J Mol Sci. 2021.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Ko JM, Velez NF, Tsao H. Pathways to melanoma. Semin Cutan Med Surg. 2010;29(4):210–7.

    Article  CAS  PubMed  Google Scholar 

  13. Munoz-Couselo E, Adelantado EZ, Ortiz C, Garcia JS, Perez-Garcia J. NRAS-mutant melanoma: current challenges and future prospect. Onco Targets Ther. 2017;10:3941–7.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Pons M, Quintanilla M. Molecular biology of malignant melanoma and other cutaneous tumors. Clin Transl Oncol. 2006;8(7):466–74.

    Article  CAS  PubMed  Google Scholar 

  15. Alcazer V, Bonaventura P, Tonon L, Wittmann S, Caux C, Depil S. Neoepitopes-based vaccines: challenges and perspectives. Eur J Cancer. 2019;108:55–60.

    Article  CAS  PubMed  Google Scholar 

  16. Kim M. Cooperative interactions of PTEN deficiency and RAS activation in melanoma metastasis. Small GTPases. 2010;1(3):161–4.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Romano C, Schepis C. PTEN gene: a model for genetic diseases in dermatology. ScientificWorldJournal. 2012;2012: 252457.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Abdo JF, Sharma A, Sharma R. Role of heredity in melanoma susceptibility: a primer for the practicing surgeon. Surg Clin North Am. 2020;100(1):13–28.

    Article  PubMed  Google Scholar 

  19. Kozmin S, Slezak G, Reynaud-Angelin A, et al. UVA radiation is highly mutagenic in cells that are unable to repair 7,8-dihydro-8-oxoguanine in Saccharomyces cerevisiae. Proc Natl Acad Sci U S A. 2005;102(38):13538–43.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Obrador E, Liu-Smith F, Dellinger RW, Salvador R, Meyskens FL, Estrela JM. Oxidative stress and antioxidants in the pathophysiology of malignant melanoma. Biol Chem. 2019;400(5):589–612.

    Article  CAS  PubMed  Google Scholar 

  21. Douki T. Oxidative stress and genotoxicity in melanoma induction: impact on repair rather than formation of dna damage? Photochem Photobiol. 2020;96(5):962–72.

    Article  CAS  PubMed  Google Scholar 

  22. Khan AQ, Travers JB, Kemp MG. Roles of UVA radiation and DNA damage responses in melanoma pathogenesis. Environ Mol Mutagen. 2018;59(5):438–60.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  23. Trucco LD, Mundra PA, Hogan K, et al. Ultraviolet radiation-induced DNA damage is prognostic for outcome in melanoma. Nat Med. 2019;25(2):221–4.

    Article  CAS  PubMed  Google Scholar 

  24. Hausauer AK, Swetter SM, Cockburn MG, Clarke CA. Increases in melanoma among adolescent girls and young women in California: trends by socioeconomic status and UV radiation exposure. Arch Dermatol. 2011;147(7):783–9.

    Article  PubMed  Google Scholar 

  25. Raimondi S, Suppa M, Gandini S. Melanoma Epidemiology and Sun Exposure. Acta Derm Venereol. 2020;100(11):adv00136.

    Article  CAS  PubMed  Google Scholar 

  26. Trakatelli M, Bylaite-Bucinskiene M, Correia O, et al. Clinical assessment of skin phototypes: watch your words! Eur J Dermatol. 2017;27(6):615–9.

    Article  PubMed  Google Scholar 

  27. Karimkhani C, Green AC, Nijsten T, et al. The global burden of melanoma: results from the Global Burden of Disease Study 2015. Br J Dermatol. 2017;177(1):134–40.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Stanganelli I, De Felici MB, Mandel VD, et al. The association between pesticide use and cutaneous melanoma: a systematic review and meta-analysis. J Eur Acad Dermatol Venereol. 2020;34(4):691–708.

    Article  CAS  PubMed  Google Scholar 

  29. Kubica AW, Brewer JD. Melanoma in immunosuppressed patients. Mayo Clin Proc. 2012;87(10):991–1003.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Konsoulova A. Principles of cancer immunobiology and immunotherapy of solid tumors. Intech Open. 2015.

    Article  Google Scholar 

  31. Varrone F, Mandrich L, Caputo E. Melanoma immunotherapy and precision medicine in the era of tumor micro-tissue engineering: where are we now and where are we going? Cancer. 2021.

    Article  Google Scholar 

  32. Liu J, Zou X. Melanoma. In: Liu J, Zou X, editors. Practical Dermoscopy. Singapore: Springer; 2022. p. 57–69.

    Chapter  Google Scholar 

  33. Lee C, Collichio F, Ollila D, Moschos S. Historical review of melanoma treatment and outcomes. Clin Dermatol Mar-Apr. 2013;31(2):141–7.

    Article  Google Scholar 

  34. Davis LE, Shalin SC, Tackett AJ. Current state of melanoma diagnosis and treatment. Cancer Biol Ther. 2019;20(11):1366–79.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Rebecca VW, Sondak VK, Smalley KS. A brief history of melanoma: from mummies to mutations. Melanoma Res. 2012;22(2):114–22.

    Article  PubMed  PubMed Central  Google Scholar 

  36. Chapman PB, Hauschild A, Robert C, et al. Improved survival with vemurafenib in melanoma with BRAF V600E mutation. N Engl J Med. 2011;364(26):2507–16.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Scolyer RA, Long GV, Thompson JF. Evolving concepts in melanoma classification and their relevance to multidisciplinary melanoma patient care. Mol Oncol. 2011;5(2):124–36.

    Article  PubMed  PubMed Central  Google Scholar 

  38. Rahimi A, Esmaeili Y, Dana N, et al. A comprehensive review on novel targeted therapy methods and nanotechnology-based gene delivery systems in melanoma. Eur J Pharm Sci. 2023;187:106476.

    Article  CAS  PubMed  Google Scholar 

  39. Liu Y, Sheikh MS. Melanoma: molecular pathogenesis and therapeutic management. Mol Cell Pharmacol. 2014;6(3):228.

    PubMed  PubMed Central  Google Scholar 

  40. Swaika A, Crozier JA, Joseph RW. Vemurafenib: an evidence-based review of its clinical utility in the treatment of metastatic melanoma. Drug Des Devel Ther. 2014;8:775–87.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Ballantyne AD, Garnock-Jones KP. Dabrafenib: first global approval. Drugs. 2013;73(12):1367–76.

    Article  CAS  PubMed  Google Scholar 

  42. Livingstone E, Zimmer L, Vaubel J, Schadendorf D. BRAF, MEK and KIT inhibitors for melanoma: adverse events and their management. Chin Clin Oncol. 2014;3(3):29.

    Article  PubMed  Google Scholar 

  43. Hodi FS, Corless CL, Giobbie-Hurder A, et al. Imatinib for melanomas harboring mutationally activated or amplified KIT arising on mucosal, acral, and chronically sun-damaged skin. J Clin Oncol. 2013;31(26):3182–90.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Byrne EH, Fisher DE. Immune and molecular correlates in melanoma treated with immune checkpoint blockade. Cancer. 2017;123(S11):2143–53.

    Article  PubMed  Google Scholar 

  45. Berd D, Sato T, Cohn H, Maguire HC Jr, Mastrangelo MJ. Treatment of metastatic melanoma with autologous, hapten-modified melanoma vaccine: regression of pulmonary metastases. Int J Cancer. 2001;94(4):531–9.

    Article  CAS  PubMed  Google Scholar 

  46. Guo C, Manjili MH, Subjeck JR, Sarkar D, Fisher PB, Wang XY. Therapeutic cancer vaccines: past, present, and future. Adv Cancer Res. 2013;119:421–75.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Baars A, van Riel JM, Cuesta MA, Jaspars EH, Pinedo HM, van den Eertwegh AJ. Metastasectomy and active specific immunotherapy for a large single melanoma metastasis. Hepatogastroenterology May-Jun. 2002;49(45):691–3.

    CAS  Google Scholar 

  48. Weber J. Immunotherapy for melanoma. Curr Opin Oncol. 2011;23(2):163–9.

    Article  CAS  PubMed  Google Scholar 

  49. Lee N, Zakka LR, Mihm MC Jr, Schatton T. Tumour-infiltrating lymphocytes in melanoma prognosis and cancer immunotherapy. Pathology. 2016;48(2):177–87.

    Article  PubMed  Google Scholar 

  50. Koller KM, Wang W, Schell TD, et al. Malignant melanoma-The cradle of anti-neoplastic immunotherapy. Crit Rev Oncol Hematol. 2016;106:25–54.

    Article  PubMed  Google Scholar 

  51. Topalian SL, Drake CG, Pardoll DM. Immune checkpoint blockade: a common denominator approach to cancer therapy. Cancer Cell. 2015;27(4):450–61.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  52. Prieto PA, Yang JC, Sherry RM, et al. CTLA-4 blockade with ipilimumab: long-term follow-up of 177 patients with metastatic melanoma. Clin Cancer Res. 2012;18(7):2039–47.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  53. Sharma P, Allison JP. Immune checkpoint targeting in cancer therapy: toward combination strategies with curative potential. Cell. 2015;161(2):205–14.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  54. Fellner C. Ipilimumab (yervoy) prolongs survival in advanced melanoma: serious side effects and a hefty price tag may limit its use. P T. 2012;37(9):503–30.

    PubMed  PubMed Central  Google Scholar 

  55. Brahmer JR, Lacchetti C, Schneider BJ, et al. Management of immune-related adverse events in patients treated with immune checkpoint inhibitor therapy: American society of clinical oncology clinical practice guideline. J Clin Oncol. 2018;36(17):1714–68.

    Article  CAS  PubMed  Google Scholar 

  56. D’Alise AM, Scarselli E. Getting personal in metastatic melanoma: neoantigen-based vaccines as a new therapeutic strategy. Curr Opin Oncol. 2023;35(2):94–9.

    Article  PubMed  PubMed Central  Google Scholar 

  57. Spiliopoulou P, Vornicova O, Genta S, Spreafico A. Shaping the future of immunotherapy targets and biomarkers in melanoma and non-melanoma cutaneous cancers. Int J Mol Sci. 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  58. Friedman CF, Postow MA. Emerging tissue and blood-based biomarkers that may predict response to immune checkpoint inhibition. Curr Oncol Rep. 2016;18(4):21.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  59. Cristescu R, Mogg R, Ayers M, et al. Pan-tumor genomic biomarkers for PD-1 checkpoint blockade-based immunotherapy. Science. 2018.

    Article  PubMed  PubMed Central  Google Scholar 

  60. Namikawa K, Mori T, Muto Y, et al. 346O - PD-L1 expression and clinical outcome after nivolumab monotherapy in various subtypes of melanoma: A single-institutional retrospective study. Ann Oncol. 2018;29:ix105.

    Article  Google Scholar 

  61. Nebhan CA, Johnson DB. Predictive biomarkers of response to immune checkpoint inhibitors in melanoma. Expert Rev Anticancer Ther. 2020;20(2):137–45.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  62. Doroshow DB, Bhalla S, Beasley MB, et al. PD-L1 as a biomarker of response to immune-checkpoint inhibitors. Nat Rev Clin Oncol. 2021;18(6):345–62.

    Article  CAS  PubMed  Google Scholar 

  63. Wang C, Wang HN, Wang L. Biomarkers for predicting the efficacy of immune checkpoint inhibitors. J Cancer. 2022;13(2):481–95.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  64. Sorroche BP, Teixeira RJ, Pereira CAD, et al. PD-L1 tumor expression as a predictive biomarker of immune checkpoint inhibitors’ response and survival in advanced melanoma patients in Brazil. Diagnostics. 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  65. Huang L, Chen H, Xu Y, Chen J, Liu Z, Xu Q. Correlation of tumor-infiltrating immune cells of melanoma with overall survival by immunogenomic analysis. Cancer Med. 2020;9(22):8444–56.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  66. Bai X, Quek C. Unravelling tumour microenvironment in melanoma at single-cell level and challenges to checkpoint immunotherapy. Genes. 2022.

    Article  PubMed  PubMed Central  Google Scholar 

  67. Balch CM. Decreased survival rates of older-aged patients with melanoma: biological differences or undertreatment? Ann Surg Oncol. 2015;22(7):2101–3.

    Article  PubMed  Google Scholar 

  68. Gulati N, Celen A, Johannet P, et al. Preexisting immune-mediated inflammatory disease is associated with improved survival and increased toxicity in melanoma patients who receive immune checkpoint inhibitors. Cancer Med. 2021;10(21):7457–65.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  69. Garrett SB, Abramson CM, Rendle KA, Dohan D. Approaches to decision-making among late-stage melanoma patients: a multifactorial investigation. Support Care Cancer. 2019;27(3):1059–70.

    Article  PubMed  Google Scholar 

  70. Krzyszczyk P, Acevedo A, Davidoff EJ, et al. The growing role of precision and personalized medicine for cancer treatment. Technology. 2018;6(3–4):79–100.

    Article  PubMed  Google Scholar 

  71. Yang TT, Yu S, Ke CK, Cheng ST. The genomic landscape of melanoma and its therapeutic implications. Genes. 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  72. Raimondo TM, Reed K, Shi D, Langer R, Anderson DG. Delivering the next generation of cancer immunotherapies with RNA. Cell. 2023;186(8):1535–40.

    Article  CAS  PubMed  Google Scholar 

  73. Verdegaal EM, de Miranda NF, Visser M, et al. Neoantigen landscape dynamics during human melanoma-T cell interactions. Nature. 2016;536(7614):91–5.

    Article  CAS  PubMed  Google Scholar 

  74. Lang F, Schrors B, Lower M, Tureci O, Sahin U. Identification of neoantigens for individualized therapeutic cancer vaccines. Nat Rev Drug Discov. 2022;21(4):261–82.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  75. Giaever G, Chu AM, Ni L, et al. Functional profiling of the Saccharomyces cerevisiae genome. Nature. 2002;418(6896):387–91.

    Article  CAS  PubMed  Google Scholar 

  76. Krauthammer M, Kong Y, Ha BH, et al. Exome sequencing identifies recurrent somatic RAC1 mutations in melanoma. Nat Genet. 2012;44(9):1006–14.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  77. Scatena C, Murtas D, Tomei S. Cutaneous Melanoma Classification: The Importance of High-Throughput Genomic Technologies. Front Oncol. 2021;11: 635488.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  78. Timar J, Ladanyi A. Molecular pathology of skin melanoma: epidemiology, differential diagnostics, prognosis and therapy prediction. Int J Mol Sci. 2022.

    Article  PubMed  PubMed Central  Google Scholar 

  79. Kang K, Xie F, Mao J, Bai Y, Wang X. Significance of tumor mutation burden in immune infiltration and prognosis in cutaneous melanoma. Front Oncol. 2020;10: 573141.

    Article  PubMed  PubMed Central  Google Scholar 

  80. Ning B, Liu Y, Wang M, Li Y, Xu T, Wei Y. The predictive value of tumor mutation burden on clinical efficacy of immune checkpoint inhibitors in melanoma: a systematic review and meta-analysis. Front Pharmacol. 2022;13: 748674.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  81. Xu S, Wang X, Fei C. A highly effective system for predicting MHC-II epitopes with immunogenicity. Front Oncol. 2022;12: 888556.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  82. Kiyotani K, Chan HT, Nakamura Y. Immunopharmacogenomics towards personalized cancer immunotherapy targeting neoantigens. Cancer Sci. 2018;109(3):542–9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  83. Sahin U, Tureci O. Personalized vaccines for cancer immunotherapy. Science. 2018;359(6382):1355–60.

    Article  CAS  PubMed  Google Scholar 

  84. Ping H, Yu W, Gong X, et al. Analysis of melanoma tumor antigens and immune subtypes for the development of mRNA vaccine. Invest New Drugs. 2022;40(6):1173–84.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  85. Lazdun Y, Si H, Creasy T, et al. A new pipeline to predict and confirm tumor neoantigens predict better response to immune checkpoint blockade. Mol Cancer Res. 2021;19(3):498–506.

    Article  CAS  PubMed  Google Scholar 

  86. Sahin U, Derhovanessian E, Miller M, et al. Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer. Nature. 2017;547(7662):222–6.

    Article  CAS  PubMed  Google Scholar 

  87. van den Berg JH, Heemskerk B, van Rooij N, et al. Tumor infiltrating lymphocytes (TIL) therapy in metastatic melanoma: boosting of neoantigen-specific T cell reactivity and long-term follow-up. J Immunother Cancer. 2020.

    Article  PubMed  PubMed Central  Google Scholar 

  88. Kristensen NP, Heeke C, Tvingsholm SA, et al. Neoantigen-reactive CD8+ T cells affect clinical outcome of adoptive cell therapy with tumor-infiltrating lymphocytes in melanoma. J Clin Invest. 2022.

    Article  PubMed  PubMed Central  Google Scholar 

  89. Poschke IC, Hassel JC, Rodriguez-Ehrenfried A, et al. The outcome of ex vivo TIL expansion is highly influenced by spatial heterogeneity of the tumor T-cell repertoire and differences in intrinsic in vitro growth capacity between T-cell clones. Clin Cancer Res. 2020;26(16):4289–301.

    Article  CAS  PubMed  Google Scholar 

  90. Tas L, Jedema I, Haanen J. Novel strategies to improve efficacy of treatment with tumor-infiltrating lymphocytes (TILs) for patients with solid cancers. Curr Opin Oncol. 2023;35(2):107–13.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  91. Chesney JA, Ribas A, Long GV, et al. Randomized, double-blind, placebo-controlled, global phase III trial of talimogene laherparepvec combined with pembrolizumab for advanced melanoma. J Clin Oncol. 2023;41(3):528–40.

    Article  CAS  PubMed  Google Scholar 

  92. Cui C, Wang X, Lian B, et al. OrienX010, an oncolytic virus, in patients with unresectable stage IIIC-IV melanoma: a phase Ib study. J Immunother Cancer. 2022.

    Article  PubMed  PubMed Central  Google Scholar 

  93. Robinson C, Xu MM, Nair SK, Beasley GM, Rhodin KE. Oncolytic viruses in melanoma. Front Biosci. 2022;27(2):63.

    Article  CAS  Google Scholar 

  94. Feola S, Russo S, Martins B, et al. Peptides-coated oncolytic vaccines for cancer personalized medicine. Front Immunol. 2022;13: 826164.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  95. Maurer DM, Butterfield LH, Vujanovic L. Melanoma vaccines: clinical status and immune endpoints. Melanoma Res. 2019;29(2):109–18.

    Article  PubMed  PubMed Central  Google Scholar 

  96. Fritah H, Rovelli R, Chiang CL, Kandalaft LE. The current clinical landscape of personalized cancer vaccines. Cancer Treat Rev. 2022;106: 102383.

    Article  CAS  PubMed  Google Scholar 

  97. Chang R, Gulley JL, Fong L. Vaccinating against cancer: getting to prime time. J Immunother Cancer. 2023.

    Article  PubMed  PubMed Central  Google Scholar 

  98. Carreno BM, Magrini V, Becker-Hapak M, et al. Cancer immunotherapy. A dendritic cell vaccine increases the breadth and diversity of melanoma neoantigen-specific T cells. Science. 2015;348(6236):803–8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  99. Geskin LJ, Damiano JJ, Patrone CC, Butterfield LH, Kirkwood JM, Falo LD. Three antigen-loading methods in dendritic cell vaccines for metastatic melanoma. Melanoma Res. 2018;28(3):211–21.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  100. Dillman RO, Nistor GI, Keirstead HS. Autologous dendritic cells loaded with antigens from self-renewing autologous tumor cells as patient-specific therapeutic cancer vaccines. Hum Vaccin Immunother. 2023;19(1):2198467.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  101. Miller M, Sahin U, Derhovanessian E, et al. 6O - IVAC MUTANOME: A first-in-human phase I clinical trial targeting individual mutant neoantigens for the treatment of melanoma. Ann Oncol. 2017;28:xi1–2.

    Article  Google Scholar 

  102. Lopez JS, Camidge R, Iafolla M, et al. Abstract CT301: A phase Ib study to evaluate RO7198457, an individualized Neoantigen Specific immunoTherapy (iNeST), in combination with atezolizumab in patients with locally advanced or metastatic solid tumors. Cancer Res. 2020;80(16_Supplement):CT-301-CT−301.

    Article  Google Scholar 

  103. Sahin U, Oehm P, Derhovanessian E, et al. An RNA vaccine drives immunity in checkpoint-inhibitor-treated melanoma. Nature. 2020;585(7823):107–12.

    Article  CAS  PubMed  Google Scholar 

  104. Khattak A, Carlino M, Meniawy T, et al. Abstract CT001: a personalized cancer vaccine, mRNA-4157, combined with pembrolizumab versus pembrolizumab in patients with resected high-risk melanoma: efficacy and safety results from the randomized, open-label Phase 2 mRNA-4157-P201/Keynote-942 trial. Cancer Res. 2023;83(8_Supplemen):CT-001-CT−001.

    Article  Google Scholar 

  105. Ott PA, Hu-Lieskovan S, Chmielowski B, et al. A phase Ib trial of personalized neoantigen therapy plus anti-PD-1 in patients with advanced melanoma, non-small cell lung cancer, or bladder cancer. Cell. 2020;183(2):347-362 e24.

    Article  CAS  PubMed  Google Scholar 

  106. Hu Z, Leet DE, Allesoe RL, et al. Personal neoantigen vaccines induce persistent memory T cell responses and epitope spreading in patients with melanoma. Nat Med. 2021;27(3):515–25.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  107. Kesisoglou F, Chung J, van Asperen J, Heimbach T. Physiologically based absorption modeling to impact biopharmaceutics and formulation strategies in drug development—industry case studies. J Pharm Sci. 2016;105(9):2723–34.

    Article  CAS  PubMed  Google Scholar 

  108. Kesisoglou F, Mitra A. Application of absorption modeling in rational design of drug product under quality-by-design paradigm. AAPS J. 2015;17:1224–36.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  109. Rowland M, Peck C, Tucker G. Physiologically-based pharmacokinetics in drug development and regulatory science. Annu Rev Pharmacol Toxicol. 2011;51:45–73.

    Article  CAS  PubMed  Google Scholar 

  110. Brahmer JR, Tykodi SS, Chow LQ, et al. Safety and activity of anti-PD-L1 antibody in patients with advanced cancer. N Engl J Med. 2012;366(26):2455–65.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  111. Hamid O, Robert C, Daud A, et al. Safety and tumor responses with lambrolizumab (anti-PD-1) in melanoma. N Engl J Med. 2013;369(2):134–44.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  112. Topalian SL, Hodi FS, Brahmer JR, et al. Safety, activity, and immune correlates of anti-PD-1 antibody in cancer. N Engl J Med. 2012;366(26):2443–54.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  113. Hartmanshenn C, Scherholz M, Androulakis IP. Physiologically-based pharmacokinetic models: approaches for enabling personalized medicine. J Pharmacokinet Pharmacodyn. 2016;43(5):481–504.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  114. Khalil F, Laer S. Physiologically based pharmacokinetic modeling: methodology, applications, and limitations with a focus on its role in pediatric drug development. J Biomed Biotechnol. 2011;2011: 907461.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  115. Yang Y, Zhao Y, Liu X, Huang J. Artificial intelligence for prediction of response to cancer immunotherapy. Semin Cancer Biol. 2022;87:137–47.

    Article  CAS  PubMed  Google Scholar 

  116. Damane BP, Mkhize-Kwitshana ZL, Kgokolo MC, Luvhengo T, Dlamini Z. Applying artificial intelligence prediction tools for advancing precision oncology in immunotherapy: future perspectives in personalized care. In: Dlamini Z, editor. Artificial intelligence and precision oncology: bridging cancer research and clinical decision support. Springer: Berlin; 2023. p. 239–58.

    Chapter  Google Scholar 

  117. Afkham SA, Khormali E, Dorigo T. A new look at cancer immunotherapy via artificial intelligence. In: Rezaei N, editor. Handbook of Cancer and Immunology. Springer International Publishing; 2022. p. 1–18.

    Google Scholar 

  118. Xie J, Luo X, Deng X, et al. Advances in artificial intelligence to predict cancer immunotherapy efficacy. Front Immunol. 2022;13:1076883.

    Article  CAS  PubMed  Google Scholar 

  119. Li T, Li Y, Zhu X, et al. Artificial intelligence in cancer immunotherapy: Applications in neoantigen recognition, antibody design and immunotherapy response prediction. Semin Cancer Biol. 2023;91:50–69.

    Article  CAS  PubMed  Google Scholar 

  120. Amorim BJ, Torrado-Carvajal A, Esfahani SA, et al. PET/MRI radiomics in rectal cancer: a pilot study on the correlation between PET- and MRI-derived image features with a clinical interpretation. Mol Imag Biol. 2020;22(5):1438–45.

    Article  CAS  Google Scholar 

  121. Ferro M, Crocetto F, Barone B, Del Giudice F, Maggi M, Lucarelli G, Busetto GM, Autorino R, Marchioni M, Cantiello F, Crocerossa F, Luzzago S, Piccinelli M, Mistretta FA, Tozzi M, Schips L, Falagario UG, Veccia A, Vartolomei MD, Musi G, Tătaru OS. Artificial intelligence and radiomics in evaluation of kidney lesions: a comprehensive literature review. Ther Adv Urol. 2023;15:17562872231164804.

    Article  PubMed  PubMed Central  Google Scholar 

  122. Cook GJR, Siddique M, Taylor BP, Yip C, Chicklore S, Goh V. Radiomics in PET: principles and applications. Clin Transl Imag. 2014;2(3):269–76.

    Article  Google Scholar 

  123. Dercle L, Zhao B, Gonen M, et al. Early readout on overall survival of patients with melanoma treated with immunotherapy using a novel imaging analysis. JAMA Oncol. 2022;8(3):385–92.

    Article  PubMed  PubMed Central  Google Scholar 

  124. Coroller TP, Grossmann P, Hou Y, et al. CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol. 2015;114(3):345–50.

    Article  PubMed  PubMed Central  Google Scholar 

  125. Aoude LG, Wong BZY, Bonazzi VF, et al. Radiomics Biomarkers Correlate with CD8 Expression and Predict Immune Signatures in Melanoma Patients. Mol Cancer Res. 2021;19(6):950–6.

    Article  CAS  PubMed  Google Scholar 

  126. Miles KA, Ganeshan B, Rodriguez-Justo M, et al. Multifunctional imaging signature for V-KI-RAS2 Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations in colorectal cancer. J Nucl Med. 2014;55(3):386–91.

    Article  CAS  PubMed  Google Scholar 

  127. Ferro M, Musi G, Marchioni M, et al. Radiogenomics in Renal Cancer Management—Current Evidence and Future Prospects. Int J Mol Sci. 2023;24(5):4615.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  128. Xu Z, Wang X, Zeng S, Ren X, Yan Y, Gong Z. Applying artificial intelligence for cancer immunotherapy. Acta Pharm Sin B. 2021;11(11):3393–405.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  129. Schumacher TN, Schreiber RD. Neoantigens in cancer immunotherapy. Science. 2015;348(6230):69–74.

    Article  CAS  PubMed  Google Scholar 

  130. Samstein RM, Lee CH, Shoushtari AN, et al. Tumor mutational load predicts survival after immunotherapy across multiple cancer types. Nat Genet. 2019;51(2):202–6.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  131. Robbins PF, Lu YC, El-Gamil M, et al. Mining exomic sequencing data to identify mutated antigens recognized by adoptively transferred tumor-reactive T cells. Nat Med. 2013;19(6):747–52.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  132. Kloke B-P, Britten CM, Loquai C, et al. Abstract CT202: IVAC MUTANOME: individualized vaccines for the treatment of cancer. Cancer Res. 2015;75(15_Supplement):CT202–CT202.

    Article  Google Scholar 

  133. Hartmaier RJ, Charo J, Fabrizio D, et al. Genomic analysis of 63,220 tumors reveals insights into tumor uniqueness and targeted cancer immunotherapy strategies. Genome Med. 2017;9(1):16.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  134. Zhang X, Sharma PK, Peter Goedegebuure S, Gillanders WE. Personalized cancer vaccines: targeting the cancer mutanome. Vaccine. 2017;35(7):1094–100.

    Article  CAS  PubMed  Google Scholar 

  135. Alexandrov LB, Nik-Zainal S, Wedge DC, et al. Signatures of mutational processes in human cancer. Nature. 2013;500(7463):415–21.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  136. Xue S, Barna M. Specialized ribosomes: a new frontier in gene regulation and organismal biology. Nat Rev Mol Cell Biol. 2012;13(6):355–69.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  137. Pelletier J, Thomas G, Volarevic S. Ribosome biogenesis in cancer: new players and therapeutic avenues. Nat Rev Cancer. 2018;18(1):51–63.

    Article  CAS  PubMed  Google Scholar 

  138. Carvalho T. Personalized anti-cancer vaccine combining mRNA and immunotherapy tested in melanoma trial. New York: Nature News; 2023.

    Book  Google Scholar 

  139. Bidram M, Zhao Y, Shebardina NG, et al. mRNA-based cancer vaccines: a therapeutic strategy for the treatment of melanoma patients. Vaccines. 2021.

    Article  PubMed  PubMed Central  Google Scholar 

  140. Evaxion. Using AI to create a vaccine revolution. New York: Nature; 2023.

    Google Scholar 

  141. Mancuso F, Lage S, Rasero J, et al. Serum markers improve current prediction of metastasis development in early-stage melanoma patients: a machine learning-based study. Mol Oncol. 2020;14(8):1705–18.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  142. Lu YC, Yao X, Crystal JS, et al. Efficient identification of mutated cancer antigens recognized by T cells associated with durable tumor regressions. Clin Cancer Res. 2014;20(13):3401–10.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  143. Goussault R, Frénard C, Maubec E, et al. Machine learning models to predict the response to anti-cancer therapy in metastatic melanoma patients. J Clin Oncol. 2020;38:e4071–e4071.

    Article  Google Scholar 

  144. Wang X, Montoyo-Pujol YG, Bermudez S, et al. Serum cytokine profiles of melanoma patients and their association with tumor progression and metastasis. J Oncol. 2021;2021:6610769.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  145. Shofty B, Artzi M, Shtrozberg S, et al. Virtual biopsy using MRI radiomics for prediction of BRAF status in melanoma brain metastasis. Sci Rep. 2020;10(1):6623.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  146. Wen D, Khan SM, Ji XuA, et al. Characteristics of publicly available skin cancer image datasets: a systematic review. Lancet Digit Health. 2022;4(1):e64–74.

    Article  CAS  PubMed  Google Scholar 

Download references


We acknowledge the Icormed Research Collaborative for facilitating this project.


Authors have no funding to declare.

Author information

Authors and Affiliations



Conceptualisation of topic and coordination of reading, writing, and editing: FZ; reading, writing, and editing of the original draft: FZ, FKS, AAA, ZGB, JKT, VS, MH, RH; critical revision of the manuscript: FZ, HH, WAA; figures and tables: VS, JKT, FZ; final approval of manuscript: all authors.

Corresponding author

Correspondence to Wireko Andrew Awuah.

Ethics declarations


Ethics approval and consent to participate.

Not applicable.

Competing interests

Authors have no competing interests to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit The Creative Commons Public Domain Dedication waiver ( applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zakariya, F., Salem, F.K., Alamrain, A.A. et al. Refining mutanome-based individualised immunotherapy of melanoma using artificial intelligence. Eur J Med Res 29, 25 (2024).

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: