Artificial intelligence and amniotic fluid multiomics: prediction of perinatal outcome in asymptomatic women with short cervix.

OBJECTIVE: To evaluate the application of artificial intelligence (AI), i.e. deep learning and other machine-learning techniques, to amniotic fluid (AF) metabolomics and proteomics, alone and in combination with sonographic, clinical and demographic factors, in the prediction of perinatal outcome in asymptomatic pregnant women with short cervical length (CL). METHODS: AF samples, which had been obtained in the second trimester from asymptomatic women with short CL (< 15 mm) identified on transvaginal ultrasound, were analyzed. CL, funneling and the presence of AF 'sludge' were assessed in all cases close to the time of amniocentesis. A combination of liquid chromatography coupled with mass spectrometry and proton nuclear magnetic resonance spectroscopy-based metabolomics, as well as targeted proteomics analysis, including chemokines, cytokines and growth factors, was performed on the AF samples. To determine the robustness of the markers, we used six different machine-learning techniques, including deep learning, to predict preterm delivery < 34 weeks, latency period prior to delivery < 28 days after amniocentesis and requirement for admission to a neonatal intensive care unit (NICU). Omics biomarkers were evaluated alone and in combination with standard sonographic, clinical and demographic factors to predict outcome. Predictive accuracy was assessed using the area under the receiver-operating characteristics curve (AUC) with 95% CI, sensitivity and specificity. RESULTS: Of the 32 patients included in the study, complete omics, demographic and clinical data and outcome information were available for 26. Of these, 11 (42.3%) patients delivered ≥ 34 weeks, while 15 (57.7%) delivered < 34 weeks. There was no statistically significant difference in CL between these two groups (mean ± SD, 11.2 ± 4.4 mm vs 8.9 ± 5.3 mm, P = 0.31). Using combined omics, demographic and clinical data, deep learning displayed good to excellent performance, with an AUC (95% CI) of 0.890 (0.810-0.970) for delivery < 34 weeks' gestation, 0.890 (0.790-0.990) for delivery < 28 days post-amniocentesis and 0.792 (0.689-0.894) for NICU admission. These values were higher overall than for the other five machine-learning methods, although each individual machine-learning technique yielded statistically significant prediction of the different perinatal outcomes. CONCLUSIONS: This is the first study to report use of AI with AF proteomics and metabolomics and ultrasound assessment in pregnancy. Machine learning, particularly deep learning, achieved good to excellent prediction of perinatal outcome in asymptomatic pregnant women with short CL in the second trimester. Copyright © 2018 ISUOG. Published by John Wiley & Sons Ltd.

Metabolomic identification of diagnostic serum-based biomarkers for advanced stage melanoma.

INTRODUCTION: Melanoma is a highly aggressive malignancy and is currently one of the fastest growing cancers worldwide. While early stage (I and II) disease is highly curable with excellent prognosis, mortality rates rise dramatically after distant spread. We sought to identify differences in the metabolome of melanoma patients to further elucidate the pathophysiology of melanoma and identify potential biomarkers to aid in earlier detection of recurrence. METHODS: Using 1H NMR and DI-LC-MS/MS, we profiled serum samples from 26 patients with stage III (nodal metastasis) or stage IV (distant metastasis) melanoma and compared their biochemical profiles with 46 age- and gender-matched controls. RESULTS: We accurately quantified 181 metabolites in serum using a combination of 1H NMR and DI-LC-MS/MS. We observed significant separation between cases and controls in the PLS-DA scores plot (permutation test p-value = 0.002). Using the concentrations of PC-aa-C40:3, DL-carnitine, octanoyl-L-carnitine, ethanol, and methylmalonyl-L-carnitine we developed a diagnostic algorithm with an AUC (95% CI) = 0.822 (0.665-0.979) with sensitivity and specificity of 100 and 56%, respectively. Furthermore, we identified arginine, proline, tryptophan, glutamine, glutamate, glutathione and ornithine metabolism to be significantly perturbed due to disease (p < 0.05). CONCLUSION: Targeted metabolomic analysis demonstrated significant differences in metabolic profiles of advanced stage (III and IV) melanoma patients as compared to controls. These differences may represent a potential avenue for the development of multi-marker serum-based assays for earlier detection of recurrences, allow for newer, more effective targeted therapy when tumor burden is less, and further elucidate the pathophysiologic changes that occur in melanoma.

Metabolomic profiling of brain from infants who died from Sudden Infant Death Syndrome reveals novel predictive biomarkers.

OBJECTIVE: Sudden Infant Death Syndrome (SIDS) is defined as the sudden death of an infant <1 year of age that cannot be explained following a thorough investigation. Currently, no reliable clinical biomarkers are available for the prediction of infants who will die of SIDS. STUDY DESIGN: This study aimed to profile the medulla oblongata from postmortem human brain from SIDS victims (n=16) and compare their profiles with that of age-matched controls (n=7). RESULTS: Using LC-Orbitrap-MS, we detected 12 710 features in electrospray ionization positive (ESI+) mode and 8243 in ESI- mode from polar extracts of brain. Five features acquired in ESI+ mode produced a predictive model for SIDS with an area under the receiver operating characteristic curve (AUC) of 1 (confidence interval (CI): 0.995-1) and a predictive power of 97.4%. Three biomarkers acquired in ESI- mode produced a predictive model with an AUC of 0.866 (CI: 0.767-0.942) and a predictive power of 77.6%. We confidently identified 5 of these features (l-(+)-ergothioneine, nicotinic acid, succinic acid, adenosine monophosphate and azelaic acid) and putatively identify another 4 out of the 15 in total. CONCLUSIONS: This study underscores the potential value of metabolomics for studying SIDS. Further characterization of the metabolome of postmortem SIDS brains could lead to the identification of potential antemortem biomarkers for novel prevention strategies for SIDS.

Metabolomics reveals novel biomarkers of illegal 5-nitromimidazole treatment in pigs. Further evidence of drug toxicity uncovered.

The aim of the study was to investigate the potential of a metabolomics platform to distinguish between pigs treated with ronidazole, dimetridazole and metronidazole and non-medicated animals (controls), at two withdrawal periods (day 0 and 5). Livers from each animal were biochemically profiled using UHPLC-QTof-MS in ESI+ mode of acquisition. Several Orthogonal Partial Least Squares-Discriminant Analysis models were generated from the acquired mass spectrometry data. The models classified the two groups control and treated animals. A total of 42 ions of interest explained the variation in ESI+. It was possible to find the identity of 3 of the ions and to positively classify 4 of the ionic features, which can be used as potential biomarkers of illicit 5-nitroimidazole abuse. Further evidence of the toxic mechanisms of 5-nitroimidazole drugs has been revealed, which may be of substantial importance as metronidazole is widely used in human medicine.

New insights into the causes of human illness due to consumption of azaspiracid contaminated shellfish.

Azaspiracid (AZA) poisoning was unknown until 1995 when shellfish harvested in Ireland caused illness manifesting by vomiting and diarrhoea. Further in vivo/vitro studies showed neurotoxicity linked with AZA exposure. However, the biological target of the toxin which will help explain such potent neurological activity is still unknown. A region of Irish coastline was selected and shellfish were sampled and tested for AZA using mass spectrometry. An outbreak was identified in 2010 and samples collected before and after the contamination episode were compared for their metabolite profile using high resolution mass spectrometry. Twenty eight ions were identified at higher concentration in the contaminated samples. Stringent bioinformatic analysis revealed putative identifications for seven compounds including, glutarylcarnitine, a glutaric acid metabolite. Glutaric acid, the parent compound linked with human neurological manifestations was subjected to toxicological investigations but was found to have no specific effect on the sodium channel (as was the case with AZA). However in combination, glutaric acid (1 mM) and azaspiracid (50 nM) inhibited the activity of the sodium channel by over 50%. Glutaric acid was subsequently detected in all shellfish employed in the study. For the first time a viable mechanism for how AZA manifests itself as a toxin is presented.

Association of fodrin with brain microtubules.

We have compared the polypeptide composition of microtubules isolated from bovine brain by the conventional in vitro reassembly method with those obtained by direct isolation of brain microtubules into a stabilizing buffer. The stabilizing buffer included 6.7 M glycerol to limit the rate of subunit exchange between assembled and unassembled states. The microtubule-associated proteins normally found by in vitro reassembly are also found in the stabilized preparation, but in smaller proportions. Fodrin, a brain membrane-associated protein believed to be homologous to spectrin, was found to be the most abundant component after tubulin in the stabilized microtubules. The ratio of tubulin to fodrin, 16:1 by mass, was almost constant at each stage of the preparation. Some actin was initially present in the stabilized microtubules, but was gradually lost during purification. When stabilized microtubules were diluted into cold aqueous buffer, they depolymerized and the recovered microtubule protein could then be purified by in vitro reassembly. The composition after this treatment resembled that of microtubules prepared initially by reassembly in vitro. The missing fodrin was found to be removed in the preliminary centrifugation and was unavailable for incorporation into growing microtubules during the in vitro assembly step. This suggests that the standard in vitro reassembly procedure for purification of microtubules may distort the composition of microtubule-associated proteins.