From Lipid Signatures to Cellular Responses: Unraveling the Complexity of Melanoma and Furthering Its Diagnosis and Treatment

Recent advancements in mass spectrometry have significantly enhanced our understanding of complex lipid profiles, opening new avenues for oncological diagnostics. This review highlights the importance of lipidomics in the comprehension of certain metabolic pathways and its potential for the detection and characterization of various cancers, in particular melanoma. Through detailed case studies, we demonstrate how lipidomic analysis has led to significant breakthroughs in the identification and understanding of cancer types and its potential for detecting unique biomarkers that are instrumental in its diagnosis. Additionally, this review addresses the technical challenges and future perspectives of these methodologies, including their potential expansion and refinement for clinical applications. The discussion underscores the critical role of lipidomic profiling in advancing cancer diagnostics, proposing a new paradigm in how we approach this devastating disease, with particular emphasis on its application in comparative oncology.


Introduction
Cancer is one of the major causes of demise in developed countries, only second to cardiovascular disease [1].The types of malignancies most prevalent vary with country and year.However, breast cancer and melanoma are frequently found among the ones showing the greatest incidence worldwide [2][3][4].Furthermore, in the USA, it is predicted that they will become the major types by the year 2040 [5].This roughly coincides with the prevalence of spontaneous malignancies in other mammals, such as cats and dogs.Nevertheless, in the former species, lymphoma is the most common, while in the latter case, mastocytoma, lymphomas, and hemangiosarcoma show very similar numbers to melanoma [6][7][8][9].
Early, accurate diagnosis is paramount to success in any medical intervention, and this is especially true for cancer.In the case of Non-White individuals, delayed diagnosis of melanoma is more common than in Caucasians and is associated with worse survival rates [10].A similar situation may occur in the case of vulvar melanoma in women [11].Recently, the use of dermoscopy has significantly enhanced the early detection and diagnosis of melanoma, providing detailed visualization of pigmented skin lesions [12,13].Additionally, oxidation markers such as malondialdehyde (MDA) have been highlighted as important biomarkers in melanoma patients.Elevated MDA levels, indicative of lipid peroxidation and oxidative stress, have been consistently reported across various studies (e.g., [14][15][16]), underscoring their potential role in melanoma pathogenesis and progression.metabolism is one of the recipients of these alterations [27].Concomitantly, it has long been known that the lipid composition of melanoma cells can be quite distinct, making them identifiable from healthy tissue [28].
Being hydrophobic molecules, lipids are not found in significant concentrations in solution in plasma; rather, they are present in colloidal form.In order to form colloids, they need to associate to specific lipid transport systems (LDL, HDL, chylomicrons) or form microvesicles. Variations exist in lipid profiles between the different types of lipoproteins, as a reflection of physiology.Thus, phospholipids are more abundant in HDL than in VLDL, while the reverse is true for triglycerides [29], in accordance with those lipoproteins belonging to two different lipid transport systems [30].On the other hand, tissue cells, either normal or tumoral, release microvesicles into the extracellular medium and, eventually, they reach the blood plasma.These vesicles are known as exosomes or extracellular vesicles (EVs).In the case of tumor-derived exosomes, these are known to be quite different from other exosomes and are involved in intercellular crosstalk, with multiple consequences.For example, they may induce changes in healthy tissue favoring metastatic colonization [31,32].Being biomembrane-based secreted vesicular structures, they carry proteins, nucleic acids, and several other molecules that can be used as cancer biomarkers [33].Naturally, they can also be a source of lipids that can contribute to lipid biomarker signatures in plasma.
Finally, a constant creation of new membranes and cells, together with the increasing need to maintain activated signaling routes that rely on lipid rafts, make tumor cells avid for certain types of lipids, such as cholesterol.The uptake of this lipid through LDL receptor overexpression and increased internalization leads, on the one hand, to a greater flux of LDL along the tumor cell endocytic pathway [34].On the other hand, it leads to blood hypocholesterolemia, as observed in various types of cancer, including hematopoietic, bowel, lung, prostate and head and neck cancers [35].This situation is by no means particular for cholesterol; rather, it is common for many types of lipids, with natural variations among them [36].Accordingly, plasma lipids are considered as a cancer-specific biomarker source with diagnostic value for some time now [37].

Interplay between Lipid Metabolism and Cellular Respiration in Cancer
The metabolic signature of cancer cells encompasses alterations in glycolysis, mitochondrial respiration, and lipid and amino acid metabolism.Mitochondria play a crucial role in bioenergetic regulation, metabolism, and apoptosis [38,39].Moreover, they are interconnected with lipid metabolism pathways, suggesting their involvement in metastatic progression and cancer phenotype, such as the carnitine shuttle system, lipoic acid biosynthesis, and sterol modifications (cholesterol) [40].Specific studies on melanoma have revealed that alterations in lipid metabolism are closely linked to mitochondrial dysfunction.In melanoma cells, dysregulated lipid metabolism contributes to changes in the mitochondrial membrane composition, impacting bioenergetics and promoting survival and proliferation under stress conditions [41,42].For instance, increased fatty acid oxidation and elevated levels of certain phospholipids have been observed, which correlate with enhanced mitochondrial activity and resistance to apoptosis [43].
The lipid composition of mitochondrial membranes (MMs) primarily comprises glycerophospholipids at 75-95%, of which 80% are phosphatidylethanolamines (PEs) and phosphatidylcholines (PCs), and 10-15% are cardiolipins (CLs) [44,45].CLs account for 20% of the lipid mass in the inner mitochondrial membrane (IMM) [46,47], being essential for the electron transport chain and oxidative phosphorylation (OXPHOS), which is an indispensable process for bioenergetics [48].Abnormal CL metabolism is associated with various pathologies, including cancer, affecting the structural and functional stability of mitochondria.Abnormal levels of CL interfere with mitochondrial metabolism by altering binding sites in the OXPHOS complexes I, III, and IV, which are necessary for the stability of supercomplexes and the synthesis of acetyl-CoA.Acetyl-CoA is essential for the Krebs cycle, being involved in metastasis and cell migration [47,49].Additionally, CL participates in mitochondrial quality control through mitophagy.Mitochondrial dysfunction, resulting from increased oxidative stress due to OXPHOS, leads to cellular protection mechanisms, such as apoptosis.In turn, increased OXPHOS leads to lipid oxidation, with the translocation of oxidized CL from the IMM to the outer mitochondrial membrane (OMM), where it is recognized by the mitophagy machinery [45,47,49].This acts as a survival mechanism, promoting the elimination of damaged mitochondria and preventing apoptosis (Figure 1a).mitochondria.Abnormal levels of CL interfere with mitochondrial metabolism by alte binding sites in the OXPHOS complexes I, III, and IV, which are necessary for the stab of supercomplexes and the synthesis of acetyl-CoA.Acetyl-CoA is essential for the K cycle, being involved in metastasis and cell migration [47,49].Additionally, CL par pates in mitochondrial quality control through mitophagy.Mitochondrial dysfunct resulting from increased oxidative stress due to OXPHOS, leads to cellular protec mechanisms, such as apoptosis.In turn, increased OXPHOS leads to lipid oxidation, w the translocation of oxidized CL from the IMM to the outer mitochondrial membr (OMM), where it is recognized by the mitophagy machinery [45,47,49].This acts as a vival mechanism, promoting the elimination of damaged mitochondria and preven apoptosis (Figure 1a).Cholesterol, which is present in all cellular membranes and is associated with gl sphingolipids in lipid rafts, constitutes approximately 3% of mitochondrial membra mainly in the IMM [50,51].In cancer cells, there is an accumulation of mitochondrial c lesterol, which is correlated with tumor growth and malignancy [52].This alters the idity of MM, affecting transmembrane proteins and increasing the production of reac oxygen species (ROS) [50,52].As a result, oxidative phosphorylation is promoted, cha ing energy metabolism and contributing to chemotherapy resistance by altering m chondrial apoptosis [51] (Figure 1b).
Carnitine is a key cofactor in metabolism, regulating the acyl-CoA/CoA bala modulating lipid biosynthesis and degradation, as well as gene expression.It particip in the synthesis of trimethylamine-N-oxide (TMAO), inflammatory processes and f acid oxidation (FAO) in the mitochondria [53][54][55].Carnitine facilitates the transfer of groups across mitochondrial membranes for FAO and ATP production.In cancer, alt tions in the expression or activity of carnitine transport are observed, especially in n plasms with dysregulated fatty acid utilization [54].Under hypoxia, cancer cells ob energy from fatty acid oxidation, demonstrating carnitine's involvement in metab plasticity [54].Furthermore, the rate-limiting enzyme in fatty acid oxidation (FAO) in Cholesterol, which is present in all cellular membranes and is associated with glycosphingolipids in lipid rafts, constitutes approximately 3% of mitochondrial membranes, mainly in the IMM [50,51].In cancer cells, there is an accumulation of mitochondrial cholesterol, which is correlated with tumor growth and malignancy [52].This alters the fluidity of MM, affecting transmembrane proteins and increasing the production of reactive oxygen species (ROS) [50,52].As a result, oxidative phosphorylation is promoted, changing energy metabolism and contributing to chemotherapy resistance by altering mitochondrial apoptosis [51] (Figure 1b).
Carnitine is a key cofactor in metabolism, regulating the acyl-CoA/CoA balance, modulating lipid biosynthesis and degradation, as well as gene expression.It participates in the synthesis of trimethylamine-N-oxide (TMAO), inflammatory processes and fatty acid oxidation (FAO) in the mitochondria [53][54][55].Carnitine facilitates the transfer of acyl groups across mitochondrial membranes for FAO and ATP production.In cancer, alterations in the expression or activity of carnitine transport are observed, especially in neoplasms with dysregulated fatty acid utilization [54].Under hypoxia, cancer cells obtain energy from fatty acid oxidation, demonstrating carnitine's involvement in metabolic plasticity [54].Furthermore, the rate-limiting enzyme in fatty acid oxidation (FAO) in the metabolic adaptation of cancer is carnitine palmitoyltransferase I (CPTI), which is overexpressed in cancer cells, promoting FAO and the adaptation to metabolic stress [53,54].This increases NADPH production, facilitating acetyl-CoA generation and providing redox power, which counteracts oxidative stress and promotes cell survival [54][55][56] (Figure 1c).
Lipoic acid (LA) is a mitochondrial cofactor with therapeutic effects, inhibiting tumor proliferation, migration, and invasion, acting as a metal chelator and antioxidant [40,57].However, studies show that in colon cancer cell lines, LA administration increases OXPHOS, acting as a pro-oxidant and triggering apoptosis by increasing mitochondrial ROS in cancer cells [58,59].Besides promoting apoptosis, LA modulates mitochondrial metabolism and circulating lipid levels, activating the MAPK signaling pathway and inhibiting mTOR, thereby hindering cell proliferation [40,59] (Figure 1d).
To sum up, lipid metabolism plays a fundamental role in the regulation of mitochondrial function within the context of cancer.Alterations in the lipid composition of mitochondrial membranes, the handling of lipids such as cholesterol and phospholipids, and the modulation of key metabolic pathways such as fatty acid oxidation directly influence mitochondrial bioenergetics and cell signaling.These interactions not only affect the survival and proliferation of cancer cells but also their ability to resist treatments and adapt to adverse environments.

Lipid Profile in Melanoma
Lipids play crucial roles in cell biology, functioning as structural components of membranes, signaling molecules, and energy reservoirs.Among the various lipid classes, sphingolipids and glycerolipids are particularly significant in the development and progression of melanoma.
The sphingolipid family is involved in melanoma cell adhesion, metabolic plasticity and aggressiveness [60].Levels of S-1-P produced by downregulated acid ceramidase induce the loss of E-cadherin in melanoma cells, along with an increase in gangliosides, promoting epithelial-mesenchymal transition (EMT) processes and adhesion to the extracellular matrix, which characterizes the aggressive phenotype of melanoma [60][61][62].
In melanoma cells, the low activity of enzymes responsible for ceramide production has been reported, favoring the consumption of ceramides towards the production of sphingosine-1-phosphate and gangliosides [28,60,63].Sphingomyelin (SM) synthase activity is notably reduced in melanoma cells compared to melanocytes, resulting in a significant decrease in SM species [64].This reduction is critical because SM plays a vital role in cell membrane structure and signaling.The decreased levels of SM disrupt membrane integrity and facilitate the production of pro-tumorigenic molecules such as ceramide and sphingosine-1-phosphate, which promote cell proliferation, migration and survival, contributing to melanoma progression and metastasis [65].Moreover, in stage II patients and proliferative melanoma cells, an increased hydrolysis of ceramide to sphingosine-1-phosphate has been observed [63].Additionally, a poorer prognosis has been correlated with the downregulation of sphingomyelin synthase 1, which catalyzes the transformation of ceramide to sphingomyelin in patients with metastasis.The lipid profiling of melanocytes, primary melanoma cells, and metastatic melanoma using mass spectrometry has reported a drastic reduction in SM species in melanoma cells compared to melanocytes [66].
Phospholipids encompass various lipid classes derived from phosphatidic acid (PA): phosphatidylethanolamine (PE), phosphatidylcholine (PC), phosphatidylinositol and its phosphorylated derivatives (PI, PIP), phosphatidylserine (PS), and phosphatidylglycerol (PG).Abnormalities in glycerophospholipid metabolism, leading to increased levels of PC and PA, favor cell survival by inhibiting apoptosis and inducing EMT and cellular invasion processes.In primary melanoma tumor tissue samples, a significant increase in total PC and PG was revealed compared to nevus melanocytes [67].Furthermore, mass spectrometry analysis determined that PC, PG, PA, and PI species show increased signals in primary and metastatic melanoma cells [66].
Lipid metabolism is crucial in melanoma due to its role in maintaining cellular membrane integrity, signaling, and energy production [68].Distinct lipidomic profiles differentiate melanoma from melanocytic nevi, with melanoma cells showing increased levels of specific phospholipids and sphingolipids, which promote tumorigenesis [66].Lipids such as ceramides and sphingosine-1-phosphate are involved in cell proliferation, migration, and survival, facilitating melanoma expansion and metastasis [69,70].Understanding these lipid alterations provides insights into melanoma biology and identifies potential therapeutic targets.

Canine Models in Comparative Melanoma Research
Comparative oncology models, such as canine melanoma, provide significant insights into the role of lipids in tumor biology, helping to elucidate mechanisms that support melanoma development and progression.The lipidomic profiles of canine models of disease show significant parallels with humans [71,72], providing insights into the role of lipids in tumor biology [73].In the case of melanoma, the similarities between canine and human disease include genetic mutations, histopathological features, and lipidomic profiles [74,75].Etiologically, both species exhibit mutations in key oncogenes and tumor suppressors such as TP53 and NRAS.Histologically, melanoma in dogs and humans displays similar cellular morphologies and patterns of invasion [75].
The canine models of disease, including spontaneous cancer, offer unique advantages for translational research, leading swiftly to new or improved methods.For instance, the development of hematopoietic cell transplantation for malignant and non-malignant blood diseases in humans and dogs has gained from a parallel development with two-way inputs [76].Further, other preclinical studies have shown that therapies that are successful in canine models, such as immunotherapies and targeted inhibitors, often translate well to human clinical trials, thereby accelerating the development of effective treatments and improving patient outcomes [77,78].On the other hand, the study of melanoma in classical murine systems finds difficulties in modelling human tumor heterogeneity and faces important differences in melanocyte locations between species (epidermis in humans and dermis in mice) [75,79].Additionally, the low efficacy for pharmacological response studies in phase III is well-known [75].Therefore, better and spontaneous tumor models are of great interest for studying innovative therapies in vivo, their effects on the tumor and the patient, and the interactions between tumor cells and the microenvironment [75,80,81].
In dogs, melanoma accounts for 7% of spontaneous neoplasms [75,82], 14-45% of all oral neoplasms [75], and 9-20% of cutaneous tumors [75].The most common locations include the mouth (62%), skin (27%), digits (6%), and eyes (1%), among others [83].Notably, there is a predisposition in males for developing oral (mucosal) melanomas [84].Despite histological and etiological similarities, canine melanomas also show some differences in humans.The most important may be that the primary risk factor for cutaneous melanomas in humans is UV radiation, with a higher risk in individuals with fair skin, or more specifically, those with very low melanin concentrations [85].In dogs, the reverse is true, and cutaneous melanoma in dogs increases in breeds with dark skin tones (e.g., Schnauzers, Scottish Terriers, Poodles) [75,85].Additionally, UV radiation is not a risk factor of the same magnitude as it is in humans, as fur acts as a protective factor [85].Nevertheless, the canine model may be especially appropriate in the case of mucosal melanoma [86].Around 30% of melanoma cases in dogs and 50% of mucosal melanomas in humans are amelanotic, making diagnosis challenging due to the lack of melanin [87].Both exhibit high aggressiveness and metastatic potential, primarily affecting lymph nodes and lungs [75,85,86].This type of melanoma also has the worst prognosis in dogs, with a median survival of 3 months to 2 years, depending on the stage and treatment choice [75,85,86].
Currently, the prognostic method for oral melanoma in dogs, according to the WHO, is based on tumor size and the presence of distal or regional metastasis.Furthermore, as in humans, prognostic parameters include nuclear atypia, mitotic count, the presence of lymphatic invasion, and the Ki-67 index [86,[88][89][90].Therefore, there are no validated biomarkers capable of providing a reliable prognosis.
The relevance of using domestic animals for comparative oncology studies has increased over the past decade, primarily due to the rise of the One Health movement, but also because of the advantages they present over conventional in vivo models [79,91].In 2005, the dog genome was sequenced, marking the beginning of comparative studies of various diseases [92,93].It has been demonstrated that the canine genome has high homology with the human genome.Despite the existence of specific mutations in human melanoma that are absent in canine melanoma, and vice versa, the genomic similarities suggest that the evolutionary lines of dogs and humans are more similar in terms of nucleotide divergence and reorganization than those of humans and rodents [92].Not surprisingly then, lipidomic analyses also reveal comparable alterations in lipid species, particularly in phospholipids and sphingolipids, underscoring the similarities in the alterations in the metabolic pathways involved in melanoma progression [74].However, there is clearly room for more studies on canine lipidomics in the different subtypes of melanoma.Given the critical role of lipid metabolism in cancer progression, invasion, and metastasis, this field warrants more extensive investigation.

Lipidomics and Machine Learning
In chemical terms, lipids are usually divided in classes, including phosphatidylcholines (PC) or sterol esters.For many purposes, such as understanding the overall biomembrane structure, this level of detail is enough.However, each variation in the molecule resulting from inclusion of a different fatty acid or an ether bond, for example, results in a different species, which is chemically and physiologically different, with some species being more abundant than others.For instance, the most abundant phospholipid species in the plasma membrane tends to be 1-stearoyl-2-oleoyl-sn-phosphatidylcholine (abbreviated PC 18:0/18:1, or often simply, PC 36:1).However, its analogous plasmalogen, 1-O-1 ′ -(Z)-octadecenyl-2-oleoyl-sn-glycero-3-phosphocholine (PC 36:1; O), is less abundant and shows patently different membrane behaviors [94].Untargeted lipidomics is the individual identification and quantitation of the whole set of lipid species in a sample.This is usually attained using direct mass spectrometry approaches, such as MALDI-TOF or ESI [67,95,96] (Figure 2).Alternatively, lipid-class separation techniques, such as UHPLC, may be associated to MS to improve identification of isobaric species [66,97,98].also because of the advantages they present over conventional in vivo models [79,91].In 2005, the dog genome was sequenced, marking the beginning of comparative studies of various diseases [92,93].It has been demonstrated that the canine genome has high homology with the human genome.Despite the existence of specific mutations in human melanoma that are absent in canine melanoma, and vice versa, the genomic similarities suggest that the evolutionary lines of dogs and humans are more similar in terms of nucleotide divergence and reorganization than those of humans and rodents [92].Not surprisingly then, lipidomic analyses also reveal comparable alterations in lipid species, particularly in phospholipids and sphingolipids, underscoring the similarities in the alterations in the metabolic pathways involved in melanoma progression [74].However, there is clearly room for more studies on canine lipidomics in the different subtypes of melanoma.Given the critical role of lipid metabolism in cancer progression, invasion, and metastasis, this field warrants more extensive investigation.

Lipidomics and Machine Learning
In chemical terms, lipids are usually divided in classes, including phosphatidylcholines (PC) or sterol esters.For many purposes, such as understanding the overall biomembrane structure, this level of detail is enough.However, each variation in the molecule resulting from inclusion of a different fatty acid or an ether bond, for example, results in a different species, which is chemically and physiologically different, with some species being more abundant than others.For instance, the most abundant phospholipid species in the plasma membrane tends to be 1-stearoyl-2-oleoyl-sn-phosphatidylcholine (abbreviated PC 18:0/18:1, or often simply, PC 36:1).However, its analogous plasmalogen, 1-O-1′-(Z)-octadecenyl-2-oleoyl-sn-glycero-3-phosphocholine (PC 36:1; O), is less abundant and shows patently different membrane behaviors [94].Untargeted lipidomics is the individual identification and quantitation of the whole set of lipid species in a sample.This is usually attained using direct mass spectrometry approaches, such as MALDI-TOF or ESI [67,95,96] (Figure 2).Alternatively, lipid-class separation techniques, such as UHPLC, may be associated to MS to improve identification of isobaric species [66,97,98].Needless to say, the vast number of lipid species that can be identified from complex samples, such as blood plasma, require solid, multivariate statistical processing to reach meaningful conclusions.It is out of the scope of this review to describe the plethora of Needless to say, the vast number of lipid species that can be identified from complex samples, such as blood plasma, require solid, multivariate statistical processing to reach meaningful conclusions.It is out of the scope of this review to describe the plethora of different mathematical approaches employed by lipidomics researchers.Nevertheless, we will try to provide some simple descriptions when possible.The reader is referred to more authoritative works published elsewhere for both multivariate statistics and machine learning algorithms [99][100][101][102].The reader is also advised that there exists a plethora of method modifications that can increase the difficulties of precisely identifying the actual methods used.
The present relatively easy use of computer-aided multivariate statistics makes the analysis of large sets of data amenable and, as a consequence, attractive.Not surprisingly, the first analysis of data obtained from lipidomic studies is usually conducted utilizing dimension reduction methods, such as Principal Component Analysis (PCA), Partial Least Squares (PLS), Maximum Margin Criterion (MMC), or their derivatives.This simplifies the analysis of a large number of variables (the levels of individual lipid species) obtained from a single experimental case and permits clustering by graphical means.In many studies, this is enough to show useful differences in lipid composition between healthy and pathological tissues.For example, in a case of hepatocellular carcinoma, the exploratory analysis was performed using PCA, but later, PLS-DA (Partial Least Square Discriminant Analysis, a variant based on PLS) and SIMCA (Soft Independent Modelling of Class Analogy) clustering models were constructed [103].Similarly, OPLS-DA (Orthogonal PLS-DA) was used to successfully cluster healthy individual plasma from that of patients suffering from pancreatic [104] or papillary thyroid cancer [105].PLS also helped in the discovery of possible lipid biomarkers in melanoma using cell lines [106] and separated grades in meningioma biopsies [107].In dogs, OPLS was found superior to PCA in distinguishing mammary tumors [108].Likewise, OPLS and PCA were used successfully in a more recent study to create models discriminating nevi from primary and metastatic human melanoma [66].
However, it has been the recent development of algorithms capable of autonomously deciding the tests and parameters to be used in mathematical modelling (machine learning, ML) that has set a different ball in motion.A PubMed search using "machine learning", "diagnosis", and "cancer" as keywords for papers published since January 2020 offered 8927 results in June 2024, but only 2821 in the previous twenty years (2000-2020).ML algorithms used in lipidomics are nearly exclusively supervised and aim at clustering.Supervised algorithms need the data sets to be divided into training and validating groups.The first group is fed to the chosen ML algorithm to obtain the parameters necessary to construct a second algorithm, a mathematical model able to classify individual cases into different groups on the basis of their associated data.The second data group measures how successful the constructed algorithm is in its predictions when facing an unknowntype case.A list with several lipidomics studies published between 2021 and 2024, using different ML algorithms can be found in Table 1.
ML algorithms may be separated into linear and non-linear types.Linear algorithms assume, at some stage, that the variation relationship between variables is due to a constant factor.Non-linear ones do not make that assumption.Linear algorithms, such as Multiple Linear Regression (MLR) or Logistic Regression (LR) are mathematically simpler.LR is a dichotomic popular algorithm and has been successfully used when classifying gastric lesions using plasma biopsies [117,118] (Table 1).In the case of the 2021 study, the figures for specificity (true negative rate) and sensitivity (true positive rate) obtained were 93.8% and 95.0%, respectively.Moreover, the Receiver Operating Characteristic Area Under the Curve (ROC AUC, or diagnostic accuracy) reached a remarkable 94.4% [117].Similar figures were observed for several of the models built using LR in the 2022 study too [118].Other linear approaches have been successfully applied to renal carcinoma [112] and mammary cancer [98].In this last case, solid biopsies were used to train ML Support Vector Machine (SVM) and LR algorithms, with similar results: values for ROC AUC above 95% were obtained.It must be noted that SVM algorithms can be used under linear and non-linear assumptions, but the actual strategy is seldom stated in the manuscripts.Another case of successful use of SVM comes from a study on meningioma [109].The authors were able to separate three different types of lesions with a diagnostic accuracy of 87%.Other non-linear algorithms are also widely used.The most common ones include k-Nearest Neighbor (KNN) and Naïve Bayes (NB), among others (e.g., [67,95,97,109,114]).In any case, it is difficult to predict which ML algorithm will best cluster the cases available from a study.For this reason, and due to their ease of implementation, it is usual to test several algorithms and opt for the best performing one.In several cases, the data provided similar results using a panel of ML algorithms, such as in small cell lung cancer [110] and an ovarian cancer model [97].Although non-linear algorithms can be considered more general, they do not necessarily fit better in all cases.For example, in melanoma solid biopsies, the linear ML model constructed using LR was found superior to non-linear models constructed using NB and KNN, with the former achieving a perfect classification of the samples [67].

From Bench to Market
Translation of academic work into diagnostic tools that can be used in the clinics is an arduous and lengthy process.This is due not only to technical difficulties, such as lack of standardization or lipid fragmentation [119,120], but also to the administrative and legal burden associated with such delicate matters.However, lipidomics clearly shows the potential to differentiate between healthy and tumoral tissue for several cancer types [121].Accordingly, some early examples of success can be found.For instance, in the field of pancreatic cancer, it has been reported that serum lipidomics could be used in the early detection of this pathology [104], and this served as the basis for a patent claim [122].More directly relevant to melanoma, UHPLC-lipidomics has already shown its potential to provide biomarkers [66].Lipidomics was also shown to be useful in histological differentiation between healthy tissue, nevi, and melanoma through imaging mass spectrometry [67,123].As a consequence, a patent was filed for these methods [124].It is foreseeable that more and further developments will occur in the near future.

Perspectives
There are several aspects that present opportunities for cancer lipidomics.Some have been known for some time, such as the necessity for normalization and quality control of lipidomic data to ease interpretation [125].In this respect, several efforts have been made, and the lipidomics community is close to a consensus [119,[126][127][128][129][130].Related to this, shotgun mass spectrometry techniques are widely used for the identification of pathogens in clinical environments, both as an in-house analytical service and as a contract one [131].Therefore, if shotgun lipidomic approaches are standardized, there is an opportunity to reach the same level of industry development as other omics, such as genomics or proteomics.As an example of the existing gap, a search in LinkedIn in June 2024 showed 4400 companies using genomics in their description, but only three mentioned lipidomics.
Up to this point, most reports have made use of machine learning algorithms.The inclusion of more advanced artificial intelligence algorithms, such as deep learning, is possibly the next step in this area [132][133][134].Actually, some attempts have already been made in cancer, albeit not in lipidomics [135,136].In any case, the present state of the art makes the discrimination of certain types of cancer from healthy individuals easy in a dichotomic way.This may suffice in the case of imaging lipidomics, such as in the already mentioned example in breast cancer [95], since, in these cases, the suspected cancer type is known, and healthy tissue from the same individual may be available for a comparison.Possibly, a closer example to implementation is melanoma, since biopsies from lesions are easy to obtain, but their analysis still suffers from a lack of consensus antigenic markers [17], which can be addressed by lipidomics imaging [67].However, in more ambitious endeavors, such as making use of liquid biopsies for oncological testing, it will be necessary to implement lipidomic strategies that are able to distinguish between several types of cancer and healthy individuals at the same time.To the best of the authors' knowledge, no work has dealt with this issue yet, and the question remains on whether lipidomics will be able to distinguish between healthy individuals and oncological patients beyond the current capabilities.Be that as it may, proposals exist for the combined use of multi-omics as a plausible solution to the limitations of single-approach strategies [137].On the other hand, even if limited to a dichotomic answer, an opportunity is clear for liquid biopsy-based lipidomics as a follow up technique, making post-intervention control tests easier, faster, and less invasive.
Lipidomics can be integrated with other 'omic' sciences such as genomics, proteomics, and metabolomics to provide a comprehensive understanding of cancer biology [138,139].Predictive models that combine data from multiple omic layers have demonstrated enhanced accuracy in characterizing tumor subtypes and predicting patient outcomes.For instance, a multi-omic approach has successfully identified biomarkers for the early diagnosis and metastasis potential by incorporating lipidomic data with metabolic markers and protein expression profiles in the serum from prostate cancer patients [140].In that study, authors reported a ROC AUC of 89% for a Logistic Regression model using just four biomarkers (two proteins, one metabolite, and one lipid) and two pathological variables (T stage and Gleason score).To date, these studies are just emerging, and it still remains to be applied to melanoma.Nevertheless, no doubt that such integrative models will leverage machine learning algorithms to analyze complex datasets, offering a holistic view of cancer pathogenesis and treatment response.
Finally, a natural tendency is seen to employ the power of lipidomics to gain insight into the mechanistical aspects in cancer.For example, alterations in metabolism related to prostate cancer were identified [141] and the actual influence of PIK3CA mutations on lipid metabolism clarified [142] by lipidomic approaches.Nonetheless, more work and efforts are needed to exploit the full potential of lipidomics in cancer research.
Lipidomics holds significant potential in clinical practice, particularly in the context of translational research.By identifying lipid biomarkers specific to melanoma, lipidomics can aid in early diagnosis, prognosis, and personalized treatment strategies.In the future, lipidomic profiling could become part of routine clinical assessments, enabling noninvasive monitoring of disease progression and response to therapy through liquid biopsies.Moreover, targeting lipid metabolic pathways offers novel therapeutic avenues, making lipidomics a valuable tool in precision oncology.
In conclusion, lipidomics, together with machine learning/artificial intelligence approaches, are a promising tool in cancer research and diagnostics.Breakthroughs are expected to occur in the immediate future.

Figure 1 .
Figure 1.Lipids and mitochondrial metabolism in cancer.(a) Cardiolipin involvement in mitoc drial quality control and induction of mitophagy.(b) Increased cholesterol levels in tumor m chondria and the regulation of membrane characteristics.(c) Carnitine in cancer; involvemen Warburg effect, Tricarboxylic acid (TCA), and β-oxidation pathways.(d) Regulation of m through lipoic acid in cancer.

Figure 1 .
Figure 1.Lipids and mitochondrial metabolism in cancer.(a) Cardiolipin involvement in mitochondrial quality control and induction of mitophagy.(b) Increased cholesterol levels in tumor mitochondria and the regulation of membrane characteristics.(c) Carnitine in cancer; involvement in Warburg effect, Tricarboxylic acid (TCA), and β-oxidation pathways.(d) Regulation of mTOR through lipoic acid in cancer.

Figure 2 .
Figure 2. Graphic representation of the process of using mass spectrometry for untargeted lipidomic analysis in the early diagnosis of cancer.(a) Sample collection.(b) Lipid profile analysis using mass spectrometry.(c) Data analysis using machine learning algorithms.(d) Early diagnosis of cancer.

Figure 2 .
Figure 2. Graphic representation of the process of using mass spectrometry for untargeted lipidomic analysis in the early diagnosis of cancer.(a) Sample collection.(b) Lipid profile analysis using mass spectrometry.(c) Data analysis using machine learning algorithms.(d) Early diagnosis of cancer.

Table 1 .
Lipidomics studies and machine learning algorithms used.