An Improved Machine Learning Model for Diagnostic Cancer Recognition Using Artificial Intelligence.

In the medical field, some specialized applications are currently being used to treat various ailments. These activities are being carried out with extra care, especially for cancer patients. Physicians are seeking the help of technology to help diagnose cancer, its dosage, its current status, cancer classification, and appropriate treatment. The machine learning method developed by an artificial intelligence is proposed here in order to effectively assist the doctors in that regard. Its design methods obtain highly complex cancerous inputs and clearly describe its type and dosage. It is also recommending the effects of cancer and appropriate medical procedures to the doctors. This method ensures that a lot of doctors' time is saved. In a saturation point, the proposed model achieved 93.31% of image recognition, 6.69% of image rejection, 94.22% accuracy, 92.42% of precision, 93.94% of recall rate, 92.6% of F1-score, and 2178 ms of computational speed. This shows that the proposed model performs well while compared with the existing methods.

Identification of high-risk Dukes B colorectal cancer by microRNA expression profiling: a preliminary study.

AIM: MicroRNAs (miRNAs) from tumour tissue and common gene mutations were studied to determine whether they predict the development of metastasis in patients with Dukes B colorectal cancer. METHOD: Patients who underwent curative resection for Dukes B colorectal cancer who subsequently developed distant metastatic disease at some stage in the following 5 years ('high-risk B') were compared with case-matched controls of Dukes A, Dukes B (no metastases, 'low-risk B') and Dukes C patients without any detectable metastasis at 5 years of follow-up. MiRNAs from tumour and adjacent normal tissue and common gene mutations (KRAS, BRAF, PIK3CA) in primary cancer tissue were analysed to identify prognostic tissue markers for the development of metastasis in patients with Dukes B colorectal cancer. RESULTS: Expression of miR-15b and miR-135b was significantly downregulated (P < 0.001) in 'high-risk B' tumours compared with Dukes A, 'low-risk B' and C without metastasis. No significant differences were noted for mutation status and the development of metastasis. CONCLUSION: The study suggests that the development of metastasis in Dukes B tumours may be predictable based on the miRNA expression of miR-15b and miR-135b. This requires further study on a much larger cohort.

Role of liquid membrane phenomenon in the anti-bacterial activity of Cefuroxime Sodium.

The role of liquid membrane phenomenon has been studied in the anti bacterial activity of cephalosporins i.e. Cefuroxime sodium. In our earlier publication [1] it was reported that hydraulic permeability data obtained to demonstrate the existence of liquid membrane in series with supporting membrane generated by Cefuroxime sodium. Transport of selected permeants (glucose, PABA, glycine, and ions like Mg(++), NH4 (+), PO4 (-), Ca(++), Na(+), K(+) and Cl(-)) through liquid membrane generated by Cefuroxime sodium in series with supporting membrane has been studied. The results indicated that the liquid membrane generated by Cefuroxime sodium inhibit the transport of various essential bio-molecules and permeants in to the cell. This modification in permeability of different permeants in the presence of the liquid membranes is likely to play significant role in the biological actions of Cefuroxime sodium. The anti-bacterial activity of Cefuroxime sodium further confirmed that the generation of liquid membrane by Cefuroxime sodium is also contributing for the antibacterial activity of them.

Structure of Mycobacterium tuberculosis single-stranded DNA-binding protein. Variability in quaternary structure and its implications.

Single-stranded DNA-binding protein (SSB) is an essential protein necessary for the functioning of the DNA replication, repair and recombination machineries. Here we report the structure of the DNA-binding domain of Mycobacterium tuberculosis SSB (MtuSSB) in four different crystals distributed in two forms. The structure of one of the forms was solved by a combination of isomorphous replacement and anomalous scattering. This structure was used to determine the structure of the other form by molecular replacement. The polypeptide chain in the structure exhibits the oligonucleotide binding fold. The globular core of the molecule in different subunits in the two forms and those in Escherichia coli SSB (EcoSSB) and human mitochondrial SSB (HMtSSB) have similar structure, although the three loops exhibit considerable structural variation. However, the tetrameric MtuSSB has an as yet unobserved quaternary association. This quaternary structure with a unique dimeric interface lends the oligomeric protein greater stability, which may be of significance to the functioning of the protein under conditions of stress. Also, as a result of the variation in the quaternary structure the path adopted by the DNA to wrap around MtuSSB is expected to be different from that of EcoSSB.

Crystallization and preliminary X-ray studies of the single-stranded DNA-binding protein from Mycobacterium tuberculosis.

Single-stranded DNA-binding proteins play an important role in DNA replication, repair and recombination. The protein from Mycobacterium tuberculosis (MtSSB) is a tetramer with 164 amino-acid residues in each subunit. The protein readily crystallizes in space group P3(1)21 (or P3(2)21) at pH 7.4 under appropriate conditions. Under different conditions, but at the same pH, orthorhombic crystals belonging to space group I222 or I2(1)2(1)2(1) were obtained after several months. Similar orthorhombic crystals were obtained when protein samples stored for several months were used for crystallization. The orthorhombic crystals obtained in different experiments, though similar to one another, exhibited variations in unit-cell parameters, presumably on account of different extents of proteolytic cleavage of the C-terminal region. Molecular-replacement calculations using different search models did not yield the structure. As part of attempts to solve the structure using isomorphous replacement, a good mercury derivative of the trigonal crystal has been prepared.

Differential effects of single-stranded DNA binding proteins (SSBs) on uracil DNA glycosylases (UDGs) from Escherichia coli and mycobacteria.

Deamination of cytosines results in accumulation of uracil residues in DNA, which unless repaired lead to GC-->AT transition mutations. Uracil DNA glyco-sylase excises uracil residues from DNA and initiates the base excision repair pathway to safeguard the genomic integrity. In this study, we have investigated the effect of single-stranded DNA binding proteins (SSBs) from Escherichia coli (Eco SSB) and Mycobacterium tuberculosis (Mtu SSB) on uracil excision from synthetic substrates by uracil DNA glycosylases (UDGs) from E. coli, Mycobacterium smegmatis and M.tuberculosis (referred to as Eco -, Msm - and Mtu UDGs respectively). Presence of SSBs with all the three UDGs resulted in decreased efficiency of uracil excision from a single-stranded 'unstructured' oligonucleo-tide, SS-U9. On the other hand, addition of Eco SSB to Eco UDG, or Mtu SSB to Mtu UDG reactions resulted in increased efficiency of uracil excision from a hairpin oligonucleotide containing dU at the second position in a tetraloop (Loop-U2). Interestingly, the efficiency of uracil excision by Msm UDG from the same substrate was decreased in the presence of either Eco- or Mtu SSBs. Furthermore, Mtu SSB also decreased uracil excision from Loop-U2 by Eco UDG. Our studies using surface plasmon resonance technique demonstrated interactions between the homologous combinations of SSBs and UDGs. Heterologous combinations either did not show detectable interaction (Eco SSB with Mtu UDG) or showed a relatively weaker interaction (Mtu SSB with Eco UDG). Taken together, our studies suggest differential interactions between the two groups (SSBs and UDGs) of the highly conserved proteins. Such studies may provide important clues to design selective inhibitors against this important class of DNA repair enzymes.

A molecular weight study of adenosine deaminase.

Adenosine deaminase exists in its smallest molecular form (ADA-S) of < 42 kDa in primate and rodent brain, intestine and liver, human erythrocytes, avian liver and in bovine spleen and intestine. The enzyme exhibits molecular heterogeneity in monkey and chicken liver and human erythrocytes. The large form of adenosine deaminase is seen in monkey liver and intermediary forms of the enzyme in chicken liver and human erythrocytes. Large forms of the enzyme predominate in rabbit intestine. Molecular weights of adenosine deaminase molecular forms were determined by gel filtration and by non denaturing gel electrophoresis with construction of Ferguson plots. Anomalous migration of the enzyme on SDS-PAGE possibly due to charge, disulfide bonds and proline content, did not allow for molecular weight determination on denaturing gels.

Molecular forms of adenosine deaminase do not aid the diagnosis of tuberculosis.

To investigate the diagnostic utility of adenosine deaminase as a test for tuberculosis, molecular forms of the enzyme indicative of cell-mediated immunity were studied in tuberculosis pleural effusion, peritonitis and meningitis. Twenty-six pleural, 21 peritoneal, and 24 cerebrospinal tuberculous and non-tuberculous fluids were examined for adenosine deaminase and the large and small forms of the enzyme were differentiated on immunoblots. Adenosine deaminase levels ranged from zero to 81 units/L, zero to 31 units/L and zero to 31 units/L in the pleural, peritoneal and cerebrospinal fluids, respectively. The large form of adenosine deaminase (280 kDa) was detected in one of 14 proved tuberculous cases, a peritoneal fluid. The small form of the enzyme (35-39 kDa) was seen in both tuberculous and non-tuberculous conditions in 6 pleural, 7 peritoneal and 8 cerebrospinal fluids. Molecular forms of adenosine deaminase did not appear to help in the diagnosis of tuberculosis in this patient population and may not be suited for analysis in fluids with low enzyme activity.