The objective of our work was to develop deep learning methods for extracting and normalizing pat... more The objective of our work was to develop deep learning methods for extracting and normalizing patient-reported free-text side effects in a cancer chemotherapy side effect remote monitoring web application. The F-measure was 0.79 for the medical concept extraction model and 0.85 for the negation extraction model (Bi-LSTM-CRF). The next step was the normalization. Of the 1040 unique concepts in the dataset, 62, 3% scored 1 (corresponding to a perfect match with an UMLS CUI). These methods need to be improved to allow their integration into home telemonitoring devices for automatic notification of the hospital oncologists.
Biosurfactants are amphiphilic compounds produced by bacteria either extracellularly or as a part... more Biosurfactants are amphiphilic compounds produced by bacteria either extracellularly or as a part of the cell membrane. Biosurfactants have had a profound impact on medical and pharmaceutical biotechnology. In our previous work, we isolated a new biosurfactant produced by Acinetobacter indicus M6 which reduces the surface tension of water from 72.0 to 39.8 mN/m and which showed thermophilic, halophytic and acidophilic stability. The chemical nature was found to be a class of glycolipoprotein. Here, our research presents the extracted biosurfactant's antiproliferative activity against lung cancer cells (A549), and anti-microbial and anti-biofilm activity against MRSA. The anti-tumour activity of biosurfactant against lung cancer cells was evaluated interms of cell viability at different concentrations. The results showed a decrease in the percentage of lung cancer viable cells with increasing biosurfactant concentrations and incubation time, with a significant decrease being observed at 200 µg/ml concentration leading to cell proliferation inhibition at G1 phase. Treatment of biofilms for seven days at 500 µg/ml resulted in up to 82.5% biofilm disruption.
The objective of our work was to develop deep learning methods for extracting and normalizing pat... more The objective of our work was to develop deep learning methods for extracting and normalizing patient-reported free-text side effects in a cancer chemotherapy side effect remote monitoring web application. The F-measure was 0.79 for the medical concept extraction model and 0.85 for the negation extraction model (Bi-LSTM-CRF). The next step was the normalization. Of the 1040 unique concepts in the dataset, 62, 3% scored 1 (corresponding to a perfect match with an UMLS CUI). These methods need to be improved to allow their integration into home telemonitoring devices for automatic notification of the hospital oncologists.
Biosurfactants are amphiphilic compounds produced by bacteria either extracellularly or as a part... more Biosurfactants are amphiphilic compounds produced by bacteria either extracellularly or as a part of the cell membrane. Biosurfactants have had a profound impact on medical and pharmaceutical biotechnology. In our previous work, we isolated a new biosurfactant produced by Acinetobacter indicus M6 which reduces the surface tension of water from 72.0 to 39.8 mN/m and which showed thermophilic, halophytic and acidophilic stability. The chemical nature was found to be a class of glycolipoprotein. Here, our research presents the extracted biosurfactant's antiproliferative activity against lung cancer cells (A549), and anti-microbial and anti-biofilm activity against MRSA. The anti-tumour activity of biosurfactant against lung cancer cells was evaluated interms of cell viability at different concentrations. The results showed a decrease in the percentage of lung cancer viable cells with increasing biosurfactant concentrations and incubation time, with a significant decrease being observed at 200 µg/ml concentration leading to cell proliferation inhibition at G1 phase. Treatment of biofilms for seven days at 500 µg/ml resulted in up to 82.5% biofilm disruption.
Uploads
Papers by Nada Salah