Structure-aware deep learning model for peptide toxicity prediction.

Antimicrobial resistance is a critical public health concern, necessitating the exploration of alternative treatments. While antimicrobial peptides (AMPs) show promise, assessing their toxicity using traditional wet lab methods is both time-consuming and costly. We introduce tAMPer, a novel multi-modal deep learning model designed to predict peptide toxicity by integrating the underlying amino acid sequence composition and the three-dimensional structure of peptides. tAMPer adopts a graph-based representation for peptides, encoding ColabFold-predicted structures, where nodes represent amino acids and edges represent spatial interactions. Structural features are extracted using graph neural networks, and recurrent neural networks capture sequential dependencies. tAMPer's performance was assessed on a publicly available protein toxicity benchmark and an AMP hemolysis data we generated. On the latter, tAMPer achieves an F1-score of 68.7%, outperforming the second-best method by 23.4%. On the protein benchmark, tAMPer exhibited an improvement of over 3.0% in the F1-score compared to current state-of-the-art methods. We anticipate tAMPer to accelerate AMP discovery and development by reducing the reliance on laborious toxicity screening experiments.

De novo synthetic antimicrobial peptide design with a recurrent neural network.

Antibiotic resistance is recognized as an imminent and growing global health threat. New antimicrobial drugs are urgently needed due to the decreasing effectiveness of conventional small-molecule antibiotics. Antimicrobial peptides (AMPs), a class of host defense peptides, are emerging as promising candidates to address this need. The potential sequence space of amino acids is combinatorially vast, making it possible to extend the current arsenal of antimicrobial agents with a practically infinite number of new peptide-based candidates. However, mining naturally occurring AMPs, whether directly by wet lab screening methods or aided by bioinformatics prediction tools, has its theoretical limit regarding the number of samples or genomic/transcriptomic resources researchers have access to. Further, manually designing novel synthetic AMPs requires prior field knowledge, restricting its throughput. In silico sequence generation methods are gaining interest as a high-throughput solution to the problem. Here, we introduce AMPd-Up, a recurrent neural network based tool for de novo AMP design, and demonstrate its utility over existing methods. Validation of candidates designed by AMPd-Up through antimicrobial susceptibility testing revealed that 40 of the 58 generated sequences possessed antimicrobial activity against Escherichia coli and/or Staphylococcus aureus. These results illustrate that AMPd-Up can be used to design novel synthetic AMPs with potent activities.

The development of a novel navigation system for reverse shoulder arthroplasty and its accuracy: a phantom and cadaveric study.

PURPOSE: Reverse shoulder arthroplasty has demonstrated excellent clinical efficacy for patients with shoulder joint diseases and is increasingly in demand. Traditional surgery faces challenges such as limited exposed surfaces and a narrow field of vision, leading to a shorter prosthesis lifespan and a higher risk of complications. In this study, an optical navigation system was proposed to assist surgeons in real-time tracking of the surgical scene. METHODS: Our optical navigation system was developed using the NDI Polaris Spectra device and several open-source platforms. The first step involved using the preoperative medical image to plan screw implantation paths. Real-time tracking of the patient phantom or cadaver and the surgical instrument was achieved through registration and calibration algorithms. Surgeons were guided on drilling through visualization methods. Postoperative results were compared with the planned implantation paths, and an algorithm was introduced to correct errors caused by the incorrect beginning points. RESULTS: Experiments involved three scapula cadavers and their corresponding phantoms with identical anatomy. For each experiment, three holes were completed with drills with diameters of 3.2 mm and 8.0 mm, respectively. Comparisons between the postoperative actual screw implantation paths and the preoperative planned implantation paths revealed an entry error of 1.05 ± 0.15 mm and an angle error of 2.47 ± 0.55° for phantom experiments. For cadaver experiments, the entry error was 1.53 ± 0.22 mm, and the angle error was 4.91 ± 0.78°. CONCLUSION: Our proposed optical navigation system successfully achieved real-time tracking of the surgical site, encompassing the patient phantom or cadaver and surgical instrument, thereby aiding surgeons in achieving precise surgical outcomes. Future study will explore the integration of robots to further enhance surgical efficiency and effectiveness.

A Novel growth guidance system for early onset scoliosis: a preliminary in vitro study.

PURPOSE: The purpose of the study was to describe a novel growth guidance system, which can avoid metal debris and reduce the sliding friction forces, and test the durability and glidability of the system by in vitro test. METHOD: Two major modifications were made to the traditional Shilla system, including the use of ultra-high molecular weight polyethylene (UHMWPE) gaskets to avoid direct contact between the screw and rod, and polishing the surface of the sliding part of the rod. We tested the durability of the system by a fatigue test, which the samples were test on the MTS system for a 10 million cycle of a constant displacement. Pre and post-testing involved weighing the UHMWPE gaskets and observing the wear conditions. The sliding ability were measured by a sliding displacement test. The maximum sliding displacement of the system was measured after a 300 cycles of dynamic compressive loads in a sinusoidal waveform. RESULTS: After the fatigue test, all the UHMWPE gaskets samples showed some of the fretting on the edge of the inner sides, but its still isolated and avoided the friction between the screws and rods. There was no production of metallic fretting around the sliding screws and rods. The average wear mass of the UHMWPE gaskets was 0.002 ± 0.001 g, less than 1.7% of the original mass. In the sliding test, the novel growth guidance system demonstrated the best sliding ability, with an average maximum sliding distance(AMSD) of 35.75 ± 5.73 mm, significantly better than the group of the traditional Shilla technique(AMSD 3.65 ± 0.46 mm, P < 0.0001). CONCLUSION: In conclusion, we modified the Shilla technique and designed a novel growth guidance system by changing the friction interface of sliding screw and rod, which may significantly reduce the metallic debris and promote spine growth. The fatigue test and sliding dislocation test demonstrated the better durability and glidability of the system. An in vivo animal experiment should be performed to further verify the system.

Adipose-derived stem cell-based optimization strategies for musculoskeletal regeneration: recent advances and perspectives.

Musculoskeletal disorders are the leading causes of physical disabilities worldwide. The poor self-repair capacity of musculoskeletal tissues and the absence of effective therapies have driven the development of novel bioengineering-based therapeutic approaches. Adipose-derived stem cell (ADSC)-based therapies are being explored as new regenerative strategies for the repair and regeneration of bone, cartilage, and tendon owing to the accessibility, multipotency, and active paracrine activity of ADSCs. In this review, recent advances in ADSCs and their optimization strategies, including ADSC-derived exosomes (ADSC-Exos), biomaterials, and genetic modifications, are summarized. Furthermore, the preclinical and clinical applications of ADSCs and ADSC-Exos, either alone or in combination with growth factors or biomaterials or in genetically modified forms, for bone, cartilage, and tendon regeneration are reviewed. ADSC-based optimization strategies hold promise for the management of multiple types of musculoskeletal injuries. The timely summary and highlights provided here could offer guidance for further investigations to accelerate the development and clinical application of ADSC-based therapies in musculoskeletal regeneration.

Metformin-loaded PLGA microspheres combined with an in situ-formed injectable SA/BG hydrogel alleviate rotator cuff muscle degeneration.

Rotator cuff tears are a prevalent musculoskeletal problem that affect many individuals and may result in substantial social and health-related expenses. Moreover, the muscular fat infiltration and dystrophy associated with rotator cuff tears have been persistent challenges in rotator cuff surgical repair and postoperative rehabilitation. In this study, an in situ-formed injectable sodium alginate (SA) and bioglass (BG) hydrogel consisting of poly (lactic-co-glycolic acid) (PLGA) microspheres containing metformin (SA/BG-PLGA-Met) was developed for the prevention of muscular fat infiltration and dystrophy. Metformin and silicon ions were slowly released by the combined hydrogel, resulting in long-term biological effects. Moreover, the hydrogel displayed excellent degradability and biocompatibility. Extracts of SA/BG-PLGA-Met inhibited the adipogenesis of 3T3-L1 cells and stimulated the myogenic differentiation of C2C12 cells in vitro. In a mouse model of rotator cuff degeneration, the SA/BG-PLGA-Met hydrogel inhibited fat infiltration and dystrophy of the supraspinatus muscle. Overall, the SA/BG-PLGA-Met hydrogel, as a novel biomaterial, has great clinical potential for preventing rotator cuff muscle fat infiltration and atrophy.

Ochronotic arthropathy effectively treated with total hip and total knee arthroplasty: a case report.

Ochronosis is a rare autosomal recessive disorder of tyrosine metabolism characterized by multilevel spinal degeneration and arthritis of large weight-bearing joints, which is referred to as ochronotic arthropathy. In this case report, we describe diagnosis and treatment of ochronotic arthropathy in a patient who underwent total hip arthroplasty (THA) and total knee arthroplasty (TKA). The Harris hip score was 26 preoperatively and 45, 68, 76, 90, 92, and 94 at 1, 3, 6, 9, 11, and 14 months, respectively, postoperatively. The forgotten joint score (FJS) of the hip was 27.8, 52.8, 81.1, 89.0, 90.6, and 92.4 at 1, 3, 6, 9, 11, and 14 months, respectively, postoperatively. TKA was performed 8 months after THA. The Knee Society Score was 36 before TKA and 74, 82, and 90 at 1, 3, and 6 months, respectively, after TKA. The FJS of the knee was 36.6, 63.9, and 84.5 at 1, 3, and 6 months, respectively, after TKA. The patient's knee range of motion returned to normal, with significant reduction in pain and improved satisfaction levels after TKA. THA and TKA can achieve good clinical outcomes in patients with ochronosis accompanied by severe joint pain.

Risk factors for intensive care unit admission following correction surgery for adult spinal deformity.

OBJECTIVE: The literature currently available on the characteristics of patients who require intensive care unit (ICU) admission after correction surgery for adult spinal deformity is lacking; this study aimed to identify risk factors for postoperative ICU admission following correction surgery for adult spinal deformity. METHODS: A retrospective review of patients who underwent primary posterior-based spinal fusion from 2015 to 2023 was performed. According to the ward they returned to, patients were further divided into an ICU group and a non-ICU group. Univariate and multivariate analyses were performed to evaluate preoperative and perioperative parameters to identify independent risk factors for postoperative ICU admission in adult spinal deformity patients. RESULTS: A total of 274 patients were included, including 115 males (41.97%) and 159 females (58.03%). The mean age of the patients was 32.00 ± 11.16 years (19-77 years). Following adjusted analysis, the preoperative and perioperative factors that were independently associated with ICU admission were age, body mass index ≥ 28 kg/m2, neuromuscular spinal deformity, respiratory disease, grade III-IV American Society of Anesthesiologists (ASA) classification, a scoliosis Cobb angle ≥ 90°, a kyphosis Cobb angle ≥ 90°, and ≥ 12 fused segments. Compared with the non-ICU group, the ICU group had a higher incidence of complications, a longer hospital stay, and higher medical costs (P < 0.05). CONCLUSION: This study identified independent risk factors associated with postoperative ICU admission in adult spinal deformity patients; and explored relative measures to decrease or avoid the risk of postoperative ICU admission. Surgeons could use these data to develop and plan appropriate perioperative care processes in advance and provide consultation for family members before surgery.

A 3D culture system improves the yield of MSCs-derived extracellular vesicles and enhances their therapeutic efficacy for heart repair.

BACKGROUND: Extracellular vesicles (EVs) derived from mesenchymal stem cells (MSCs), due to their inner functional substances, have shown great value in treating acute myocardial infarction (AMI). However, their clinical application is limited by a low yield. In the present study, we cultured EVs using a hollow fiber bioreactor-based three-dimensional (3D) system, and assessed their therapeutic effectiveness on AMI. METHODS: The MSCs separated from fresh human umbilical cord were planted into the flasks of two systems: two-dimensional (2D) culture and hollow-fiber-bioreactor based 3D culture. EVs were extracted from the culture supernatants. Characteristics and yields of EVs from two culture systems, namely 2D-EVs and 3D-EVs, were compared. A rat model of AMI was built up to assess their therapeutic efficacy on AMI. RESULTS: The yield of 3D-EVs was higher, with biofunctions similar to those of 2D-EVs. 3D-EVs repressed the apoptosis of cardiomyocytes, facilitated angiogenesis, and regulated the transition of macrophage subpopulations after myocardial infarction, and eventually improved cardiac function in the AMI rats. CONCLUSIONS: The hollow fiber 3D culture system can increase the yield of MSCs-derived EVs to render a strong cardioprotective effect in AMI rats.

Models and data of AMPlify: a deep learning tool for antimicrobial peptide prediction.

OBJECTIVES: Antibiotic resistance is a rising global threat to human health and is prompting researchers to seek effective alternatives to conventional antibiotics, which include antimicrobial peptides (AMPs). Recently, we have reported AMPlify, an attentive deep learning model for predicting AMPs in databases of peptide sequences. In our tests, AMPlify outperformed the state-of-the-art. We have illustrated its use on data describing the American bullfrog (Rana [Lithobates] catesbeiana) genome. Here we present the model files and training/test data sets we used in that study. The original model (the balanced model) was trained on a balanced set of AMP and non-AMP sequences curated from public databases. In this data note, we additionally provide a model trained on an imbalanced set, in which non-AMP sequences far outnumber AMP sequences. We note that the balanced and imbalanced models would serve different use cases, and both would serve the research community, facilitating the discovery and development of novel AMPs. DATA DESCRIPTION: This data note provides two sets of models, as well as two AMP and four non-AMP sequence sets for training and testing the balanced and imbalanced models. Each model set includes five single sub-models that form an ensemble model. The first model set corresponds to the original model trained on a balanced training set that has been described in the original AMPlify manuscript, while the second model set was trained on an imbalanced training set.

Prospective randomized controlled trial on the accuracy of prosthesis positioning in total hip arthroplasty assisted by a newly designed whole-process robotic arm.

INTRODUCTION: The purpose of this article is to study whether the newly designed whole-process total hip arthroplasty (THA) robotic arm can improve the accuracy of prosthesis placement in THA. METHOD: In this study, 72 patients undergoing THA were prospectively included and randomly divided into two groups. The experimental group was treated with THA assisted by a newly designed robotic arm. The control group received THA with conventional surgical methods. The imaging data were compared after operation. RESULT: Compared with the conventional operation, the whole-process robotic arm can more accurately place the acetabular prosthesis in the anteversion safe zone of 5 ~ 25°, but in terms of the inclination angle, whether the reference is the safe zone of 30 ~ 50° or 30 ~ 45°, there is no statistical difference between the two groups. The average lower limb length discrepancy (LLLD) in the experimental group was 3.77 ± 8.31 mm longer than contralateral side, while the counterpart in the control group was 8.39 ± 9.11 mm, with significant difference (P = 0.029). The femoral prosthesis was fixed in neutral position in 35 (100%) cases in the experimental group and only 30 (83.3%) in the control group (P = 0.036). There was no significant difference in the recovery of hip offset, femoral anteversion, and canal fill ratio (CFR) between the two groups. CONCLUSION: Robotic arm can improve the accuracy of anteversion of acetabular cup, restore the consistency of the length of lower limbs, and more accurately implant the femoral prosthesis to the neutral position in the coronal position. CLINICAL TRIAL REGISTRATION NUMBER: ChiCTR2100044124 (date of registration: 2021-3-11).

Lowest Instrumented Vertebra at L3 Versus L4 in Posterior Fusion for Moderate Lenke 5C Type Adolescent Idiopathic Scoliosis: A Case-Match Radiological Study.

OBJECTIVE: To compare the radiological outcomes in Lenke 5C type patients whose lowest instrumented vertebra (LIV) was L3 or L4 in a case-match study. METHODS: We conducted a retrospective case-match study and included 82 patients in the study. Radiological results before surgery, after surgery, and at last follow-up were recorded and analyzed in the L3 and L4 groups. RESULTS: After matching the age, Risser's sign, sex, and main Cobb, 41 pairs of patients were enrolled in our study. The total fusion segments in the L3 group (median [interquartile range]: 5.0 [6.0-5.0]) were shorter than those in the L4 group (6.0 [6.5-6.0]). The main curve was significantly corrected after surgery in both groups, and was comparable at the last followup between groups. In addition, according to the results of Fisher precision probability test, there was no significant difference of coronal or sagittal imbalance between the 2 groups at the 2-year follow-up. CONCLUSION: The correction in coronal and sagittal planes in L3 group and L4 group remains similar. On account of more motion segments, L3 could be an ideal choice as LIV in moderate Lenke 5C type AIS. Long-term follow-up is needed to evaluate the effect of larger compensatory lumbar-sacral curve when stopping at L3.

Associating Biological Activity and Predicted Structure of Antimicrobial Peptides from Amphibians and Insects.

Antimicrobial peptides (AMPs) are a diverse class of short, often cationic biological molecules that present promising opportunities in the development of new therapeutics to combat antimicrobial resistance. Newly developed in silico methods offer the ability to rapidly discover numerous novel AMPs with a variety of physiochemical properties. Herein, using the rAMPage AMP discovery pipeline, we bioinformatically identified 51 AMP candidates from amphibia and insect RNA-seq data and present their in-depth characterization. The studied AMPs demonstrate activity against a panel of bacterial pathogens and have undetected or low toxicity to red blood cells and human cultured cells. Amino acid sequence analysis revealed that 30 of these bioactive peptides belong to either the Brevinin-1, Brevinin-2, Nigrocin-2, or Apidaecin AMP families. Prediction of three-dimensional structures using ColabFold indicated an association between peptides predicted to adopt a helical structure and broad-spectrum antibacterial activity against the Gram-negative and Gram-positive species tested in our panel. These findings highlight the utility of associating the diverse sequences of novel AMPs with their estimated peptide structures in categorizing AMPs and predicting their antimicrobial activity.

Mining Amphibian and Insect Transcriptomes for Antimicrobial Peptide Sequences with rAMPage.

Antibiotic resistance is a global health crisis increasing in prevalence every day. To combat this crisis, alternative antimicrobial therapeutics are urgently needed. Antimicrobial peptides (AMPs), a family of short defense proteins, are produced naturally by all organisms and hold great potential as effective alternatives to small molecule antibiotics. Here, we present rAMPage, a scalable bioinformatics discovery platform for identifying AMP sequences from RNA sequencing (RNA-seq) datasets. In our study, we demonstrate the utility and scalability of rAMPage, running it on 84 publicly available RNA-seq datasets from 75 amphibian and insect species-species known to have rich AMP repertoires. Across these datasets, we identified 1137 putative AMPs, 1024 of which were deemed novel by a homology search in cataloged AMPs in public databases. We selected 21 peptide sequences from this set for antimicrobial susceptibility testing against Escherichia coli and Staphylococcus aureus and observed that seven of them have high antimicrobial activity. Our study illustrates how in silico methods such as rAMPage can enable the fast and efficient discovery of novel antimicrobial peptides as an effective first step in the strenuous process of antimicrobial drug development.

3D printed biocompatible graphene oxide, attapulgite, and collagen composite scaffolds for bone regeneration.

Tissue-engineered bone material is one of the effective methods to repair bone defects, but the application is restricted in clinical because of the lack of excellent scaffolds that can induce bone regeneration as well as the difficulty in making scaffolds with personalized structures. 3D printing is an emerging technology that can fabricate bespoke 3D scaffolds with precise structure. However, it is challenging to develop the scaffold materials with excellent printability, osteogenesis ability, and mechanical strength. In this study, graphene oxide (GO), attapulgite (ATP), type I collagen (Col I) and polyvinyl alcohol were used as raw materials to prepare composite scaffolds via 3D bioprinting. The composite materials showed excellent printability. The microcosmic architecture and properties was characterized by scanning electron microscopy, Fourier transform infrared and thermal gravimetric analyzer, respectively. To verify the biocompatibility of the scaffolds, the viability, proliferation and osteogenic differentiation of Bone Marrow Stromal Cells (BMSCs) on the scaffolds were assessed by CCK-8, Live/Dead staining and Real-time PCR in vitro. The composited scaffolds were then implanted into the skull defects on rat for bone regeneration. Hematoxylin-eosin staining, Masson staining and immunohistochemistry staining were carried out in vivo to evaluate the regeneration of bone tissue.The results showed that GO/ATP/COL scaffolds have been demonstrated to possess controlled porosity, water absorption, biodegradability and good apatite-mineralization ability. The scaffold consisting of 0.5% GO/ATP/COL have excellent biocompatibility and was able to promote the growth, proliferation and osteogenic differentiation of mouse BMSCs in vitro. Furthermore, the 0.5% GO/ATP/COL scaffolds were also able to promote bone regeneration of in rat skull defects. Our results illustrated that the 3D printed GO/ATP/COL composite scaffolds have good mechanical properties, excellent cytocompatibility for enhanced mouse BMSCs adhesion, proliferation, and osteogenic differentiation. All these advantages made it potential as a promising biomaterial for osteogenic reconstruction.

SMOC approach for total knee arthroplasty in valgus knees.

OBJECTIVE: This study was performed to compare clinical outcomes among patients with valgus knees undergoing total knee arthroplasty via the medial parapatellar approach and the subvastus with minimal oblique cut approach. METHODS: A total of 232 patients (246 knees) undergoing total knee arthroplasty between December 2014 and December 2016 were retrospectively included in the investigation. The study population consisted of 120 patients (128 knees; 32 men and 88 women) with a mean age of 62.43 ± 8.12 years treated via the medial parapatellar approach, and 112 patients (118 knees; 30 men and 82 women with a mean age of 63.15 ± 7.83 years) treated via the subvastus with minimal oblique cut approach. Nine preoperative parameters (number of patients, sex, age, body mass index, number of knees, valgus angle, visual analogue scale score, range of motion, Hospital for Special Surgery score), five perioperative parameters (operative time, amount of drainage, Visual analogue scale score at 24 h after the operation, time to straight leg raising, radiological alignment), and two postoperative parameters (range of motion, Hospital for Special Surgery score) were assessed at 1 day, 1 week, 6 weeks, 8 weeks and 1 year after the operation, along with postoperative complications. RESULTS: There were no significant differences in the nine preoperative parameters between the two groups. The subvastus with minimal oblique cut group had a longer operative time, while the parapatellar approach group showed more drainage and a higher mean Visual analogue scale score. Compared to the medial parapatellar group, the subvastus with minimal oblique cut group had a shorter time to straight leg raising. There were no differences in radiological alignment between the two groups. The groups showed similar range of motion and Hospital for Special Surgery scores at 8 weeks and 1 year, but both were higher in the subvastus with minimal oblique cut group at 1 day, 1 week and 6 weeks. During postoperative follow-up, postoperative subluxation of the patella occurred in five cases in the medial parapatellar group. Neither group showed any instability, recurrent valgus deformity or radiographic loosening. CONCLUSION: The subvastus with minimal oblique cut approach provides excellent early recovery for total knee arthroplasty of valgus knees with no increase in complications.

Robotic-arm assisted versus conventional technique for total knee arthroplasty: early results of a prospective single centre study.

PURPOSE: The purpose of this study was to compare the early functional outcomes between robotic-arm assisted total knee arthroplasty (RATKA) and conventional manual total knee arthroplasty (TKA). METHODS: This prospective cohort study included 52 patients (26 RATKA and 26 TKA). All procedures were performed by a single experienced surgeon using identical approach and implant designs. Post-operative evaluation consisted of the risks of inflammatory and blood loss, the accuracy of mechanical alignment, post-operative pain, peri-operative and post-operative functional outcomes, and complications for 30 days after index surgery. RESULTS: There was no statistical difference in baseline characteristics of patients between two groups (p > 0.05). There was a trend that the operative time of RATKA was prolonged compared with manual TKA (p < 0.0001). However, the risks of infection and blood loss did not increase accordingly (p > 0.05). No statistical difference was found in the correction of mechanical alignment between two groups (p > 0.05). The RATKA was associated with reduced pain post-operatively in day 1 (p < 0.05). Afterwards, there was no systematic difference in VAS score from day two to three post-operatively (p > 0.05). There was no significant difference in functional recovery (p > 0.05). No complication occurred in both groups. CONCLUSION: Although the operative time was prolonged in RATKA, it did not increase the risks of infection and blood loss. There was no significant difference in radiological or functional outcomes between RATKA and conventional manual TKA. RATKA might be related to reduced pain after surgery.

Accuracies of bone resection, implant position, and limb alignment in robotic-arm-assisted total knee arthroplasty: a prospective single-centre study.

OBJECTIVE: This study assessed the accuracy of robotic-arm-assisted total knee arthroplasty (RATKA) for bone resection, component size prediction, implant placement, and limb alignment. METHODS: This prospective cohort study included 36 patients. All procedures were performed by a single experienced surgeon, using an identical approach and implant designs. The MAKO RIO Robotic Interactive Orthopaedic Arm (Stryker, Mahwah, NJ, USA) system was used. The actual bone resection, implant placement, component size, and postoperative mechanical alignment were recorded, then compared with the preoperative plan. RESULTS: The mean absolute differences from the plan for the distal (medial and lateral) and posterior (medial and lateral) femoral cuts were 0.39 mm (0.62), 0.49 mm (0.70), 0.62 mm (0.79), and 0.65 mm (0.81), respectively, with 0.57° (0.65) varus. The mean absolute differences in the medial and lateral tibial cuts were 0.56 mm (0.75) and 0.58 mm (0.76), with 0.48° (0.16) varus and 0.54° (0.25) anterior/posterior slope. Of 192 bone resections, 176 (91.7%) were within ≤ 1 mm of the preoperative plan. The accuracies of femoral and tibial component size prediction were 100% and 97.22%, respectively. The mean absolute difference in final limb coronal alignment was 0.92° (0.65). Of the alignments, 18 (75.0%) were within ≤ 1.00° of the plan, and 100% were within ≤ 3.00° of the plan. CONCLUSION: RATKA could accurately predict the component size and execute a preoperative plan to achieve precise bone resection, and implant placement, thereby reducing alignment outliers.

AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens.

BACKGROUND: Antibiotic resistance is a growing global health concern prompting researchers to seek alternatives to conventional antibiotics. Antimicrobial peptides (AMPs) are attracting attention again as therapeutic agents with promising utility in this domain, and using in silico methods to discover novel AMPs is a strategy that is gaining interest. Such methods can sift through large volumes of candidate sequences and reduce lab screening costs. RESULTS: Here we introduce AMPlify, an attentive deep learning model for AMP prediction, and demonstrate its utility in prioritizing peptide sequences derived from the Rana [Lithobates] catesbeiana (bullfrog) genome. We tested the bioactivity of our predicted peptides against a panel of bacterial species, including representatives from the World Health Organization's priority pathogens list. Four of our novel AMPs were active against multiple species of bacteria, including a multi-drug resistant isolate of carbapenemase-producing Escherichia coli. CONCLUSIONS: We demonstrate the utility of deep learning based tools like AMPlify in our fight against antibiotic resistance. We expect such tools to play a significant role in discovering novel candidates of peptide-based alternatives to classical antibiotics.

Tuning of Optical Behavior in Monolayer and Bilayer Molybdenum Disulfide Using Hydrostatic Pressure.

Researchers have shown great interest in two-dimensional crystals recently, because of their thickness-dependent electronic and optical properties. We have investigated the Raman and photoluminescence spectra of free-standing monolayer and bilayer MoS2, as a function of pressure. As the enforcement of layer interaction, an electronic and a crystal phase transition were revealed at ∼6 GPa and ∼16 GPa, respectively, in bilayer MoS2, while no phase transition in the monolayer is observed. The electronic phase transition at ∼6 GPa is supposed to be a direct interband changing to an indirect Λ-K interband transition, and the new structure shown at ∼16 GPa is not metallized and supposed to be a transformation from stacking faults due to layer sliding like 2Hc to 2Ha. The different pressure-induced features of monolayer MoS2, compared with bilayer MoS2, can help to get a better understanding about the importance of interlayer interaction on modifying the optical properties of MoS2 and other fundamental understanding of 2D materials.