Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future.

Artificial intelligence (AI) is the use of mathematical algorithms to mimic human cognitive abilities and to address difficult healthcare challenges including complex biological abnormalities like cancer. The exponential growth of AI in the last decade is evidenced to be the potential platform for optimal decision-making by super-intelligence, where the human mind is limited to process huge data in a narrow time range. Cancer is a complex and multifaced disorder with thousands of genetic and epigenetic variations. AI-based algorithms hold great promise to pave the way to identify these genetic mutations and aberrant protein interactions at a very early stage. Modern biomedical research is also focused to bring AI technology to the clinics safely and ethically. AI-based assistance to pathologists and physicians could be the great leap forward towards prediction for disease risk, diagnosis, prognosis, and treatments. Clinical applications of AI and Machine Learning (ML) in cancer diagnosis and treatment are the future of medical guidance towards faster mapping of a new treatment for every individual. By using AI base system approach, researchers can collaborate in real-time and share knowledge digitally to potentially heal millions. In this review, we focused to present game-changing technology of the future in clinics, by connecting biology with Artificial Intelligence and explain how AI-based assistance help oncologist for precise treatment.

Studies on the chemopreventive effect of carnitine on tumorigenesis in vivo, using two experimental murine models of colon cancer.

Carnitine is known for its essential role in intermediary metabolism. In vitro studies suggest that its antioxidant and anti-inflammatory properties are potentially beneficial toward cancer prevention. This study tested effects of carnitine on the development of colon cancer in vivo using 2 murine models: azoxymethane (AOM) treatment as a model of carcinogen-induced colon cancer and a genetically induced model using Apc (Min/+) mice. AOM and Apc (Min/+) mice divided into dietary groups varying in lipid content, with or without carnitine supplementation (0.08%). AOM-exposed mice on a high butterfat diet had significantly increased aberrant crypts (ACF) (9.3 ± 0.88 vs. 6.3 ± 0.65), and macroscopic tumors (3.8 ± 0.95 vs. 2.0 ± 0.25) compared to mice on a control diet. In AOM mice fed the high butterfat diet, carnitine supplementation inhibited ACF (4.9 ± 0.7 vs. 9.3 ± 0.88, P < 0.001), crypt multiciplicity (1.6 ± 0.08 vs. 1.92 ± 0.1, P < 0.01) and tumors (1.5 ± 0.38 vs. 3.8 ± 0.95, P < 0.001). Carnitine supplementation resulted in significantly increased tissue carnitine and acylcarnitine levels. Carnitine inhibited the development of precancerous lesions and macroscopic colonic tumors in AOM-treated mice. However, carnitine did not exert protective effects on intestinal tumors in Apc (Min/+) mice.

L-Carnitine transport in human placental brush-border membranes is mediated by the sodium-dependent organic cation transporter OCTN2.

Maternofetal transport of l-carnitine, a molecule that shuttles long-chain fatty acids to the mitochondria for oxidation, is thought to be important in preparing the fetus for its lipid-rich postnatal milk diet. Using brush-border membrane (BBM) vesicles from human term placentas, we showed that l-carnitine uptake was sodium and temperature dependent, showed high affinity for carnitine (apparent K(m) = 11.09 +/- 1.32 microM; V(max) = 41.75 +/- 0.94 pmol.mg protein(-1).min(-1)), and was unchanged over the pH range from 5.5 to 8.5. l-Carnitine uptake was inhibited in BBM vesicles by valproate, verapamil, tetraethylammonium, and pyrilamine and by structural analogs of l-carnitine, including d-carnitine, acetyl-d,l-carnitine, and propionyl-, butyryl-, octanoyl-, isovaleryl-, and palmitoyl-l-carnitine. Western blot analysis revealed that OCTN2, a high-affinity, Na(+)-dependent carnitine transporter, was present in placental BBM but not in isolated basal plasma membrane vesicles. The reported properties of OCTN2 resemble those observed for l-carnitine uptake in placental BBM vesicles, suggesting that OCTN2 may mediate most maternofetal carnitine transport in humans.

A heterozygote phenotype is present in the jvs +/- mutant mouse livers.

The juvenile visceral steatosis (jvs) mouse, having a mutation in the carnitine transporter gene Octn2, is a model of primary systemic carnitine deficiency in humans (SCD, OMIM 212140). Like humans with SCD, homozygous jvs -/- mice have hepatic and cardiac steatoses, reduced plasma and tissue carnitines, and increased urinary carnitine clearance. Because symptomatic heterozygotes have been reported for some fatty acid oxidation disorders, including SCD, we compared the jvs heterozygotes to normal control mice. We measured the free and esterified carnitine, total cholesterol, and triglycerides in adult liver samples, myocardium, and skeletal muscle. Our results indicate significant differences between the livers of nonfasting adult normal (n = 8) vs jvs heterozygotes (n = 8) (means +/- SEM, p < 0.01) for the following parameters: free carnitine, 2.28 +/- 0.36 nmol/mg protein vs 0.41 +/- 0.13; total carnitine, 3.48 +/- 0.36 vs 1.27 +/- 0.25; triglycerides, 0.14 +/- 0.04 vs 0.39 +/- 0.02; and total cholesterol, 0.21 +/- 0.02 vs 0.39 +/- 0.04, but not for esterified carnitine, 1.18 +/- 0.17 vs 0.90 +/- 0.17 (p > 0.05). There is also a negative correlation between hepatic free carnitine and triglycerides from jvs heterozygotes (p < 0.05). Similar results were obtained with myocardium and skeletal muscle. We conclude that free and total carnitine levels are significantly lower in the heterozygote mouse liver and heart while triglyceride and total cholesterol levels are significantly higher. We speculate that in situations of lipolytic stress, some SCD heterozygotes might develop clinical symptoms of carnitine deficiency.

L-Carnitine transport in mouse renal and intestinal brush-border and basolateral membrane vesicles.

We characterized the uptake of carnitine in brush-border membrane (BBM) and basolateral membrane (BLM) vesicles, isolated from mouse kidney and intestine. In kidney, carnitine uptake was Na(+)-dependent, showed a definite overshoot and was saturable for both membranes, but for intestine, it was Na(+)-dependent only in BLM. The uptake was temperature-dependent in BLM of both kidney and intestine. The BBM transporter in kidney had a high affinity for carnitine: apparent K(m)=18.7 microM; V(max)=7.85 pmol/mg protein/s. In kidney BLM, similar characteristics were obtained: apparent K(m)=11.5 microM and V(max)=3.76 pmol/mg protein/s. The carnitine uptake by both membranes was not affected within the physiological pH 6.5-8.5. Tetraethylammonium, verapamil, valproate and pyrilamine significantly inhibited the carnitine uptake by BBM but not by BLM. By Western blot analysis, the OCTN2 (a Na(+)-dependent high-affinity carnitine transporter) was localized in the kidney BBM, and not in BLM. Strong OCTN2 expression was observed in kidney and skeletal muscle, with no expression in intestine in accordance with our functional study. We conclude that different polarized carnitine transporters exist in kidney BBM and BLM. L-Carnitine uptake by mouse renal BBM vesicles involves a carrier-mediated system that is Na(+)-dependent and is inhibited significantly by specific drugs. The BBM transporter is likely to be OCTN2 as indicated by a strong reactivity with the anti-OCTN2 polyclonal antibody.