Deep learning in drug design and discovery / 药学学报

Among various technologies used in drug design and discovery, deep learning is still in its infancy. Recently, deep learning approaches have been rapidly developed and applied to address various problems in drug discovery, including generation of virtual compound library, prediction of compound activity, metabolism and toxicity, and prediction of organic synthesis routes. Compared with the traditional machine learning methods, the prediction power of deep learning did not show significant improvement. However, proactively learning and automatically feature extraction bring advantages for deep learning approaches. Compared to first principle-based computational chemistry methods, deep learning can not be generalized because it depends on large-scale and high-quality annotated data sets. But its molecular representation with single-atom atomic environment vectors could be useful for computational chemists. As an emerging technology, deep learning, especially the unsupervised learning method that does not rely on large datasets with labels, is gradually improving. It is expected that someday deep learning method will become practical for drug discovery.

Clinical effects of percutaneous endoscopic transforaminal decompression for the treatment of lumbar spinal stenosis / 中国骨伤

<p><b>OBJECTIVE</b>To evaluate clinical effects of lumbar spinal stenosis by endoscopic transforaminal decompression, and to provide a theory basis for selection of surgical candidates.</p><p><b>METHODS</b>From June 2014 to January 2016, clinical data of 87 patients with lumbar spinal stenosis were retrospectively analyzed, including 45 males and 42 females, aged from 25 to 81 years old with an average of 55.14 years old; 8 cases on L₃,₄, 61 cases on L₄,₅, 18 cases on L₅S₁. All patients underwent percutaneous edoscopic transforaminal decompression. Clinical symptoms and nerve functions were evaluated by VAS, ODI before operation, 3 and 6 months after operation, MacNab scoring was used to evaluate clinical effects.</p><p><b>RESULTS</b>Postoperative incision of 87 patients healed well without complications, and obtained more than 6 months follow-up. VAS score before operation, 3 and 6 months after operation respectively were 63.88±8.56, 13.22±8.24, 6.83±9.43 respectively;ODI score before operation, 3 and 6 months after operation were 59.96±12.60, 9.08±10.55, 5.64±6.84 respectively. There was statistical significance in VAS and ODI score compared before operation and 3 and 6 months after operation. According to MacNab scoring, 41 cases obtained excellent results, 30 good, 7 moderate and 9 poor.</p><p><b>CONCLUSIONS</b>Percutenous endoscopic transforaminal decompression for lumbar spinal stenosis could reach good clinical effects if choosing appropriate indications. For patients with yellow ligament hypertrophy or combined with some ossified stenosis, insufficient decompression may result in poor therapeutic effects.</p>

Load rate of facet joints at the adjacent segment increased after fusion / 中华医学杂志(英文版)

<p><b>BACKGROUND</b>The cause of the adjacent segment degeneration (ASD) after fusion remains unknown. It is reported that adjacent facet joint stresses increase after anterior cervical discectomy and fusion. This increase of stress rate may lead to tissue injury. Thus far, the load rate of the adjacent segment facet joint after fusion remains unclear.</p><p><b>METHODS</b>Six C2-C7 cadaveric spine specimens were loaded under four motion modes: Flexion, extension, rotation, and lateral bending, with a pure moment using a 6° robot arm combined with an optical motion analysis system. The Tecscan pressure test system was used for testing facet joint pressure.</p><p><b>RESULTS</b>The contact mode of the facet joints and distributions of the force center during different motions were recorded. The adjacent segment facet joint forces increased faster after fusion, compared with intact conditions. While the magnitude of pressures increased, there was no difference in distribution modes before and after fusion. No pressures were detected during flexion. The average growth velocity during extension was the fastest and was significantly faster than lateral bending.</p><p><b>CONCLUSIONS</b>One of the reasons for cartilage injury was the increasing stress rate of loading. This implies that ASD after fusion may be related to habitual movement before and after fusion. More and faster extension is disadvantageous for the facet joints and should be reduced as much as possible.</p>

Device implanted complications of Coflex interspinous dynamic stabilization / 中华外科杂志

<p><b>OBJECTIVE</b>To investigate device implanted complications and corresponding therapeutic strategies of Coflex interspinous dynamic stabilization system for lumbar spine intraoperatively and postoperatively.</p><p><b>METHODS</b>From September 2008 to August 2010, 133 cases of degenerative disease of lumbar spine including 62 males and 71 females, ranging from 35 to 81 years of age (mean 60.8 years), underwent or planed to be underwent decompression with Coflex interspinous dynamic stabilization system were reviewed retrospectively, and 13 cases including 6 males and 7 females, ranging from 41 to 71 years of age (mean 58.6 years), occurred device implanted complications. The Coflex implanted complications were analyzed, and therapeutic strategies according to different character were carried out, scores of visual analogue scale (VAS), Oswestry disability index(ODI) and effect-related data preoperatively, postoperatively, after conservative treatment and in final follow-up were evaluated with paired-samples t test.</p><p><b>RESULTS</b>Thirteen cases of Coflex implanted complications and treatment applied included: 3 cases occurred fracture of spinous processes intraoperatively were treated by pedicle screws instead; 2 cases occurred fracture of spinous processes postoperatively or during follow-up, including 1 case underwent revision with pedicle screws, another 1 case treated with conservative treatment; 4 cases with degenerative coronal spondylolysis in surgical segments, 1 case with sagittal instability preoperatively, and 1 case with device dislodgment in follow-up all suffered aggravated pain and received conservative treatment; 1 case suffered implanted malposition intraoperatively was underwent internal fixation with pedicle screws instead; at length, 1 case with aggravated pain postoperatively and without definite reason received revision with internal fixation of pedicle screws demolishing the Coflex. The follow-up time of 13 cases ranged from 20 to 38 months (mean 27.6 months); and 7 cases implanted Coflex with aggravated pain of lumbar and lower limb, but the position of device can still maintained, were received conservative treatment, and whose score of VAS and ODI in the final follow-up were 1.9 ± 0.7 and 23.2 ± 3.4, and comparing to 6.1 ± 1.1 and 58.1 ± 3.0 preoperatively, evident improvement was got finally (t = 8.2 and 18.2, P < 0.01). Scores of VAS and ODI of 2 cases with Coflex implanted complications underwent revision with pedicle screws were also improved correspondingly.</p><p><b>CONCLUSIONS</b>Coflex interspinous dynamic stabilization system implanted should be avoided to cases who suffered with osteoporosis, too narrow interspinous space and intervertebral coronal spondylolysis or sagittal instability; and choice of device, depth of implantation and intensity of clumping should be appropriate. For patients with symptom but device still in right position, conservative treatment can be carried out; but for patients subjected to malposition of device, failure of implantation intraoperatively or intolerance to device, revisions and salvages should be underwent with internal fixation of pedicle screws.</p>