Artificial intelligence-driven antimicrobial peptide discovery.

Antimicrobial peptides (AMPs) emerge as promising agents against antimicrobial resistance, providing an alternative to conventional antibiotics. Artificial intelligence (AI) revolutionized AMP discovery through both discrimination and generation approaches. The discriminators aid in the identification of promising candidates by predicting key peptide properties such as activity and toxicity, while the generators learn the distribution of peptides and enable sampling novel AMP candidates, either de novo or as analogs of a prototype peptide. Moreover, the controlled generation of AMPs with desired properties is achieved by discriminator-guided filtering, positive-only learning, latent space sampling, as well as conditional and optimized generation. Here we review recent achievements in AI-driven AMP discovery, highlighting the most exciting directions.

Celloscope: a probabilistic model for marker-gene-driven cell type deconvolution in spatial transcriptomics data.

Spatial transcriptomics maps gene expression across tissues, posing the challenge of determining the spatial arrangement of different cell types. However, spatial transcriptomics spots contain multiple cells. Therefore, the observed signal comes from mixtures of cells of different types. Here, we propose an innovative probabilistic model, Celloscope, that utilizes established prior knowledge on marker genes for cell type deconvolution from spatial transcriptomics data. Celloscope outperforms other methods on simulated data, successfully indicates known brain structures and spatially distinguishes between inhibitory and excitatory neuron types based in mouse brain tissue, and dissects large heterogeneity of immune infiltrate composition in prostate gland tissue.

Discovering highly potent antimicrobial peptides with deep generative model HydrAMP.

Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.

Perioperative and Long-Term Anatomical and Subjective Outcomes of Laparoscopic Pectopexy and Sacrospinous Ligament Suspension for POP-Q Stages II-IV Apical Prolapse.

The aim of this paper was to analyze perioperative and long-term outcomes in 114 women undergoing surgery for POP-Q ≥ 2 apical prolapse: sacrospinous ligament colpo/hysteropexy (SSLF/SSHP)­61; laparoscopic pectopexy (LP)­53. Validated questionnaires (PGI-I, ISI, #35 EPIQ, PFIQ-7, PFDI-20) were completed at baseline and follow-up. POP-Q stages II, III and IV were diagnosed in 1 (0.9%), 84 (73.7%) and 29 (25.4%) patients, respectively. Mean operative time and hospital stay were 151.8 ± 36.2 min/2.6 ± 1.1 days for LP and 69 ± 20.4 min (p < 0.001)/2.7 ± 1.0 days for SSLF. Severe intraoperative complications occurred in two (1.8%) patients. Mean follow-up was 26.9 ± 12 and 37.3 ± 17.5 months for LP and SSLF, respectively. At follow-up, significant improvement for all POP-Q points was observed in both groups (p < 0.001). Shortening of total vaginal length was found in both groups, but predominantly in SSLF patients (p = 0.01). The sensation of vaginal bulge (EPIQ) was reduced, and total PFDI-20 and PFIQ-7 scores improved (p < 0.04) in both groups. Subjective success was reported by 40 (75.5%) LP and 44 (72.1%) SSLF patients. ISI detected no deterioration in urinary incontinence. PGI-I, PFDI-20, #35 EPIQ, PFIQ-7 and ISI did not differ between the groups. In conclusion both, SSLF and LP for apical prolapse generate good anatomical and subjective outcomes, with protective effect on the anterior compartment observed for LP.

Laparoscopic Pectopexy-CUSUM Learning Curve and Perioperative Complications Analysis.

The study aimed to examine the learning curve and perioperative complications for laparoscopic pectopexy (LP). A total of 60 women with stage II-IV apical prolapse who underwent LP were dichotomized into groups: LSH(+) with concomitant laparoscopic supracervical hysterectomy (LSH), LSH(-) after previous supracervical/total hysterectomy. Operative time, estimated blood loss and hospitalization length were evaluated with cumulative sum (CUSUM) analysis and the Kwiatkowski-Phillips-Schmidt-Shin (KPSS) test, separately for two surgeons (A and B). Intraoperative and perioperative complications according to the Clavien-Dindo (C-D) classification were analyzed. Mean operative time, change in hemoglobin level, and postoperative hospital stay were 143.5 ± 23.1 min-1.5 ± 0.5g/dL and 2.5 ± 0.9 days, respectively. LSH during pectopexy was associated with longer operative time (p = 0.01) but not with higher intraoperative bleeding or prolonged hospital stay. Severe complications rate was low (1.7%) with one bowel injury in LSH(-) (C-D grade IIIb). No C-D grade II, IV and V complications were found. Conversion to open pectopexy, return to the operating room or blood transfusion were not required. The KPSS test showed that a steady operative time for Surgeon A was achieved after 28 procedures. A proficiency for laparoscopic pectopexy based on CUSUM analysis was observed after 38-40 procedures.

Comparison of laparoscopic techniques for apical organ prolapse repair - a systematic review of the literature.

AIMS: Apical defect is a pelvic organ prolapse disorder, with 5%-15% prevalence. The aim of the study was to investigate methods of laparoscopic repair of apical defect and compare them with other techniques (open, vaginal, and robotic). METHODS: A systematic search of the literature was conducted in MEDLINE/PubMed and ClinicalTrials.gov databases using the following key words: apical prolapse and treatment procedures. The search was limited by using the humans filters. Only articles published in English between 2010 and 2018 were considered. Two independent authors reviewed the publications for inclusion on the basis of the following criteria: (a) use of laparoscopic techniques, and (b) apical support loss as indication for surgery. RESULTS: A total of 1002 papers were initially identified; 24 studies fulfilled the inclusion criteria. Four main laparoscopic procedures were found. The reported anatomical success rate (POP-Q < II stage) was 77%-100%, with patient satisfaction for pectopexy, laparoscopic sacropexy (LS), lateral ligament suspension and laparoscopic uterosacral ligament suspension (LUSLS) of 96.4%-97.6%, 71.0%-100%, 66.7%-87.8%, and 95%-95.5%, respectively. Major complications included hemorrhage, bladder, ureter, and/or bowel injuries were rare. Prolapse recurrences after LUSLS and LS were reported in 13.2% and 10.4% of patients, respectively; with reoperation rate for LS 2.2%-12.8%. CONCLUSIONS: Most studies reported anatomical and subjective outcomes, with follow-up ranging from 1 month to >7 years. Success rates for laparoscopic and abdominal corrections of apical defect were similar; laparoscopy was superior in terms of perioperative blood loss, length of hospital stay, and recovery.