Search

Circuit representation learning aims to obtain neural representations of circuit elements and has emerged as a promising research direction that can be applied to various EDA and logic reasoning tasks. Existing solutions, such as DeepGate, have the potential to embed both circuit structural information and functional behavior. However, their capabilities are limited due to weak supervision or flawed model design, resulting in unsatisfactory performance in downstream tasks. In this paper, we introduce DeepGate2, a novel functionality-aware learning framework that significantly improves upon the original DeepGate solution in terms of both learning effectiveness and efficiency. Our approach involves using pairwise truth table differences between sampled logic gates as training supervision, along with a well-designed and scalable loss function that explicitly considers circuit functionality. Additionally, we consider inherent circuit characteristics and design an efficient one-round graph neural network (GNN), resulting in an order of magnitude faster learning speed than the original DeepGate solution. Experimental results demonstrate significant improvements in two practical downstream tasks: logic synthesis and Boolean satisfiability solving. The code is available at https://github.com/cure-lab/DeepGate2

Supplemental Material for Machine Learning Model for Assessment of Risk Factors and Postoperative Day for Superficial vs Deep/Organ-Space Surgical Site Infections by Wardah Rafaqat, Hafiza Sundus Fatima, Ayush Kumar, Sadaf Khan, and Muhammad Khurram in Surgical Innovation.

This study investigates the ability of bovine serum albumin (BSA) to act as an extracellular chaperone (EC) on human hemoglobin (Hb) at a pH of 7.4. The best temperature for studying this behavior was determined by analyzing Hb’s aggregation kinetics at multiple temperatures. 55 °C was chosen as the optimal temperature for forming Hb amyloids. BSA was then tested at various concentrations (20–100 μM) to assess its chaperone-like activity on Hb at 55 °C. At a concentration of 100 μM, BSA exhibits chaperone-like activity with a client protein:BSA ratio of 1:10. The high ratio implies that the chaperone activity of BSA is favored by the effects of macromolecular crowding. The results showed that BSA has the potential to inhibit Hb’s dissociation into alpha and beta subunits and protein aggregation by inhibiting secondary nucleation. BSA also causes the depolymerization of fibrils over time. The results were validated using molecular docking and all-atom molecular dynamics simulations. MD analysis such as RMSD, RMSF, Rg, SASA, Hydrogen bond, PCA, Free energy landscape (FEL) revealed that the stability of hemoglobin is greater when it is bound to BSA compared to unbound state. The study suggests that BSA can potentially bind to Hb dimers and reduce excitonic interactions, which reduces Hb aggregation. These results are consistent with the aggregation kinetics experiments. Communicated by Ramaswamy H. Sarma

Circuit representation learning is a promising research direction in the electronic design automation (EDA) field. With sufficient data for pre-training, the learned general yet effective representation can help to solve multiple downstream EDA tasks by fine-tuning it on a small set of task-related data. However, existing solutions only target combinational circuits, significantly limiting their applications. In this work, we propose DeepSeq, a novel representation learning framework for sequential netlists. Specifically, we introduce a dedicated graph neural network (GNN) with a customized propagation scheme to exploit the temporal correlations between gates in sequential circuits. To ensure effective learning, we propose to use a multi-task training objective with two sets of strongly related supervision: logic probability and transition probability at each node. A novel dual attention aggregation mechanism is introduced to facilitate learning both tasks efficiently. Experimental results on various benchmark circuits show that DeepSeq outperforms other GNN models for sequential circuit learning. We evaluate the generalization capability of DeepSeq on a downstream power estimation task. After fine-tuning, DeepSeq can accurately estimate power across various circuits under different workloads.

Objectives: To determine the predictive values of reticulocyte and platelet count for remission in cases of acute lymphoblastic leukemia after induction therapy. Materials and Methods:This cross-sectional observational study was conducted in the department of hematology, MTI Hayatabad Medical Complex, Peshawar. All cases of ALL referred to the department for remission after taking induction therapy, irrespective of age and gender were included. Relevant information wascollected on a predesigned proforma prepared in accordance with the objectives of the study. Results: A total of 84 cases referred for remission were included, 56(66.7%) were males and 28 (33.3%) were females. 50(59.5%) cases were in the age range of 5-18 years. The mean with a standard deviation of the age of patients was 15+ 4 years. 75(89.3%) of the cases were classified into ALL-1) by FAB classification. 50(59.5%) of the referred cases had achieved morphological remission by bone marrow aspiration. There was a statistically significant rise in Platelet count of the remission vs non-remission cases (p-0.001). Again there was a statistically significant difference in the retic count of the cases with remission (p-0.05). We observed a statically significant downhill moderate correlation ofretic count with remission (in termsof blast count of BM aspiration) (p-0.04, r:-0.32). Platelet count also had an inverse significant correlation with remission ( p-0.01, r:-0.37). The diagnostic roles of the peripheral platelet count and retic yielded an area under curves of (0.768 and 0.648 respectively) to predict remission.We observed that the retic count and platelet count havebeen shown to have strong predictive valuesfor remission in ALL with interaction values of (R= 0.28**, ΔR²=0.02, p=0.08). Similarly, an increase in platelet also has a strong predictive value for remission in ALL cases with interaction values of (R= 0.41**, ΔR²=0.16, p=0.001) Conclusion: In ALL cases of post-induction therapy, The peripheral blood reading for an increase in Retic and platelet count predictsremission with 95% confidence. These values if strictly observed can reduce the frequency of invasive procedures like bone marrow aspiration. Keywords: ALL, Remission, Reticulocyte count, Platelet count.

In a hybrid conflict, parties that hinder path to peace processes for their desired goals and interests are termed as spoilers. Afghanistan represents a hybrid conflict, wherein internal and external spoilers sabotage peace processes for their vested interests. This study analyses different tactics that India uses as an external state spoiler to sabotage peace processes in Afghanistan which have implications for Pakistan. The study finds that India deployed several violent and non-violent spoiling tactics in Afghanistan. Non-violent tactics include non-recognition of parties to the conflict, building anti-Pakistan narrative, labelling, financing Afghan society against Pakistan, exploiting ethnic and religious differences and interference in guise of development projects through use of soft power strategy.The violent tactics include support to terrorist organizations and internal spoilers, use of Indian Embassy, consulates and its intelligence agency for clandestine operations to sabotage peace processes. Data for this study was collected through documents and semi-structured interviews and analyzed by a thematic approach.

Supplemental Material, sj-pdf-1-sri-10.1177_15533506211018619 for Global Surgery Hackathons: A Case Study From Pakistan by Waqaas A. Butt, Amir Shariff, Sadaf Khan and Asad I. Mian in Surgical Innovation

Importance: The US is currently an epicenter of the coronavirus disease 2019 (COVID-19) pandemic, yet few national data are available on patient characteristics, treatment, and outcomes of critical illness from COVID-19. Objectives: To assess factors associated with death and to examine interhospital variation in treatment and outcomes for patients with COVID-19. Design, Setting, and Participants: This multicenter cohort study assessed 2215 adults with laboratory-confirmed COVID-19 who were admitted to intensive care units (ICUs) at 65 hospitals across the US from March 4 to April 4, 2020. Exposures: Patient-level data, including demographics, comorbidities, and organ dysfunction, and hospital characteristics, including number of ICU beds. Main Outcomes and Measures: The primary outcome was 28-day in-hospital mortality. Multilevel logistic regression was used to evaluate factors associated with death and to examine interhospital variation in treatment and outcomes. Results: A total of 2215 patients (mean [SD] age, 60.5 [14.5] years; 1436 [64.8%] male; 1738 [78.5%] with at least 1 chronic comorbidity) were included in the study. At 28 days after ICU admission, 784 patients (35.4%) had died, 824 (37.2%) were discharged, and 607 (27.4%) remained hospitalized. At the end of study follow-up (median, 16 days; interquartile range, 8-28 days), 875 patients (39.5%) had died, 1203 (54.3%) were discharged, and 137 (6.2%) remained hospitalized. Factors independently associated with death included older age (≥80 vs

The authors highlight significance of fitness testing, psychological and physical examinations for primary-school students, who wish to participate in gymnastic activities. The main purpose of pre-participation examination is safety of potential gymnasts, team members, coaches and staff. The prime function of end-of- term evaluation is performance assessment and possible improvement from the last term. Taking the example of a girl, who is participating in gymnastics, this work illustrates use of Growth-and- Obesity Roadmap in determining suitability for inclusion in gymnastic team, focusing on nutritional status, estimated-adult height and build of student. Build is computed using scaled percentiles adapted for the Pakistani children, which are generated from CDC (Centers for Disease Control and Prevention, Atlanta, United States) percentiles by fitting a parabolic curve. Mathematical-statistical definitions of normal, early, delayed, excessively delayed and precarious puberty are proposed. Approximate Tanner scores have been assigned to prepubertal, peripubertal, pubertal, adolescent and adult stages.

Oncogene-induced senescence (OIS) is a potent tumor suppressor mechanism. To identify senescence regulators relevant to cancer, we screened an shRNA library targeting genes deleted in hepatocellular carcinoma (HCC). Here, we describe how knockdown of the SWI/SNF component ARID1B prevents OIS and cooperates with RAS to induce liver tumors. ARID1B controls p16INK4a and p21CIP1a transcription but also regulates DNA damage, oxidative stress, and p53 induction, suggesting that SWI/SNF uses additional mechanisms to regulate senescence. To systematically identify SWI/SNF targets regulating senescence, we carried out a focused shRNA screen. We discovered several new senescence regulators, including ENTPD7, an enzyme that hydrolyses nucleotides. ENTPD7 affects oxidative stress, DNA damage, and senescence. Importantly, expression of ENTPD7 or inhibition of nucleotide synthesis in ARID1B-depleted cells results in re-establishment of senescence. Our results identify novel mechanisms by which epigenetic regulators can affect tumor progression and suggest that prosenescence therapies could be employed against SWI/SNF-mutated cancers.

Senescence is an important tumour suppressor mechanism, which prevents the proliferation of stressed or damaged cells. The use of RNA interference to identify genes with a role in senescence is an important tool in the discovery of novel cancer genes. In this work, a protocol was established for conducting bypass of senescence screenings, using shRNA libraries together with next-generation sequencing. Using this approach, the SWI/SNF subunit Arid1b was identified as a regulator of cellular lifespan in MEFs. SWI/SNF is a large multi-subunit complex that remodels chromatin. Mutations in SWI/SNF proteins are frequently associated with cancer, suggesting that SWI/SNF components are tumour suppressors. Here the role of ARID1B during senescence was investigated. Depletion of ARID1B extends the proliferative capacity of primary mouse and human fibroblasts. Furthermore, in cells expressing mutant RASG12V and PIK3CAH1047R, ARID1B is necessary for the maintenance of oncogene-induced senescence (OIS). Knockdown of ARID1B during OIS results in reduced expression of the CKIs p21Cip1 and p16INK4a. Many SWI/SNF proteins are post-transcriptionally induced during both replicative senescence and OIS, suggesting a broader role for the SWI/SNF complex in senescence. Ectopic expression of components of the SWI/SNF complex induced premature senescence associated with an increase in p21Cip1 and p16INK4a protein levels. SILAC analysis of global changes in protein levels identified enrichment of mitochondrial proteins and depletion of mitotic proteins upon ARID1B expression. Mitochondrial dysfunction and ROS production are important in ARID1B expressing cells as growth arrest was rescued using antioxidant N-acetyl-cysteine. Finally, analysis of cancer genome sequencing data has identified ARID1B as a mutational-driver gene in some cancers. In these tumours, ARID1B mutations are often associated with mutations in TP53 and PTEN. Altogether the present evidence suggests that regulation of senescence by different mechanisms contributes to explain the tumour suppressive properties of the SWI/SNF complex. Open Access