Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry. This task is of great importance for predicting structure-activity relationships for a wide variety of substances ranging from biomolecules to ubiquitous materials. Substantial computational resources are invested in Monte Carlo and Molecular Dynamics methods to generate diverse and representative conformer sets for medium to large molecules, which are yet intractable to chemoinformatic conformer search methods. We present TorsionNet, an efficient sequential conformer search technique based on reinforcement learning under the rigid rotor approximation. The model is trained via curriculum learning, whose theoretical benefit is explored in detail, to maximize a novel metric grounded in thermodynamics called the Gibbs Score. Our experimental results show that TorsionNet outperforms the highest scoring chemoinformatics method by 4x on large branched alkanes, and by several orders of magnitude on the previously unexplored biopolymer lignin, with applications in renewable energy.
BACKGROUND Surgical resection is the main stay treatment in oral cancer. Different techniques were used by the surgeons for reconstruction of the normal anatomy. With these, a study was conducted to evaluate the outcome and quality of life in terms of conventional forms of reconstruction and functional outcome in both genders for oral cavity reconstruction. METHODS It was a hospital based non randomized study, conducted in the department of surgical oncology, Vydehi Institute of Medical Sciences and research centre, Bangalore from January 2017 to June 2018. Individuals aged 20 – 70 years with confirmed oral carcinoma were included; poor vascular supply of donor area, distant metastasis proved by chest X ray or abdominal ultrasound were excluded. Pre-structured proforma was used to collect the baseline data. ANOVA tests were used. P <0.05 was considered statistically significant. RESULTS Majority (27.7 %) were in the age group 51 to 60 years and the male to female ratio was 0.56. Statistically, there was no significant association between gender and type of flaps. 60 % had carcinoma of left buccal mucosa and 40 % had right side carcinoma, statistically there was no significant difference. The mean number of nodes was 20.85 ± 9.52. Statistically, there was no significant association between type of flaps and number of lymph nodes. CONCLUSIONS PMMC flap reconstruction is reliable and an affordable procedure with high success rate in achieving treatment goals. However, studies on large sample size for long term is required. KEYWORDS Oral Carcinoma, Microvascular Techniques, Local Flaps, Regional Flaps
BACKGROUND Salivary gland (SG) neoplasms are rare, constitute of 3 - 4 % of head and neck tumours. 70 - 80 % of SG neoplasms occur in parotid gland. These are unique in the way they present, generally slow growing. A study was conducted to analyse various modes of presentation of SG tumours and to review the role of FNAC (Fine Needle Aspiration Cytology) in the diagnosis of SG tumours. METHODS This was a prospective study, conducted in the department of surgical oncology, October 2016 to July 2018. Individuals aged >18 years, came with swelling of the SGs were considered. Swellings that were not neoplasms, the individuals with inflammatory or infections of SGs, autoimmune diseases were excluded. Statistical analysis were performed by SPSS software version-21 and MS excel 2013. RESULTS Out of 40 participants, male female ratio was 2.07. The age was ranged between 31 – 70 years, maximum (80 %) members were in 41 – 60 group. Parotid gland was the most commonly followed by submandibular gland (20 %). Swelling alone was observed in 82.5 % (33) cases, two cases (5 %) presented with swelling along with pain with facial nerve involvement. CONCLUSIONS SG tumours occur in 4th to 6th decade, common among men. Parotid gland is most frequently involved, most often benign. FNAC had good accuracy in diagnosis and surgery is the main modality of treatment. KEYWORDS Salivary Gland, Tumour, Neoplasms, FNAC
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.