Mapping Oxidation and Wafer Cleaning to Device Characteristics Using Physics-Assisted Machine Learning.

It is always highly desired to have a well-defined relationship between the chemistry in semiconductor processing and the device characteristics. With the shrinkage of technology nodes in the semiconductors roadmap, it becomes more complicated to understand the relation between the device electrical characteristics and the process parameters such as oxidation and wafer cleaning procedures. In this work, we use a novel machine learning approach, i.e., physics-assisted multitask and transfer learning, to construct a relationship between the process conditions and the device capacitance voltage curves. While conventional semiconductor processes and device modeling are based on a physical model, recently, the machine learning-based approach or hybrid approaches have drawn significant attention. In general, a huge amount of data is required to train a machine learning model. Since producing data in the semiconductor industry is not an easy task, physics-assisted artificial intelligence has become an obvious choice to resolve these issues. The predicted C-V uses the hybridization of physics, and machine learning provides improvement while the coefficient of determination (R 2) is 0.9442 for semisupervised multitask learning (SS-MTL) and 0.9253 for transfer learning (TL), referenced to 0.6108 in the pure machine learning model using multilayer perceptrons. The machine learning architecture used in this work is capable of handling data sparsity and promotes the usage of advanced algorithms to model the relationship between complex chemical reactions in semiconductor manufacturing and actual device characteristics. The code is available at https://github.com/albertlin11/moscapssmtl.

Myeloid Sarcoma Type of Acute Promyelocytic Leukemia With a Cryptic Insertion of RARA Into FIP1L1: The Clinical Utility of NGS and Bioinformatic Analyses.

BACKGROUND: Acute promyelocytic leukemia (APL) is characterized by the presence of coagulopathy at onset and translocation t (15; 17) (q22; 21), meanwhile, other translocation variants of APL have also been reported. The FIP1L1-RARA fusion gene has recently been reported as a novel RARA-associated fusion gene. OBJECTIVES: We report a case of de novo myeloid sarcoma (MS) type of APL with FIP1L1-RARA found by next-generation sequencing (NGS) that was not detected by conventional analyze analysis for RARA translocations. METHODS: We performed typical morphological, magnetic resonance imaging (MRI), conventional tests for PML-RARA dual-fusion translocation probe, high-through sequencing and NGS. Meanwhile, bioinformatics analyses were done by using public repositories, including ONCOMINE, COSMIC, and GeneMANIA analysis. RESULTS: A 28-month-old girl with a complex karyotype that includes 46,XX,t(4;17)(q12;q22)[9]/46,idem,del(16)(q22)[3]/45,idem,-x,-4,-9,-15,del(16)(q22),+marl,+mar2,+mar3[7]/46,xx[3], c.38G>A (p.Gly13Asp) in the KRAS gene, and a cryptic insertion of RARA gene into the FIP1L1 gene was diagnosed with APL complicated by the de novo MS. CONCLUSION: We report a FIP1L1-RARA fusion in a child with APL who presented with an extramedullary tumor in the skull without the classic karyotype using NGS, whom we treated with good results. NGS analysis should be considered for APL variant cases. Further experimental studies to the association between the mutation in KRAS gene and FIP1L1-RARA fusion on the clinical phenotype and progression of APL are needed to identify more effective therapeutic targets for APL.

A novel mutation in the CD40 ligand gene in a Chinese boy with X-linked hyper-IgM syndrome.

X-linked hyper-IgM Syndrome (XHIGM) is caused by a mutation of CD40 ligand (CD40L), which is normally expressed on activated CD4+ T cells and is responsible for immunoglobulin class switching. A 7-year-old boy with recurrent sino-pulmonary infections since the age of 3 months had normal CD3+, CD4+, CD8+T lymphocytes, and CD19+B lymphocytes and NK cells, but significantly elevated IgM and extremely decreased IgG and IgA. Sequencing of genomic DNA revealed that the patient had a 34 base deletion in intron 3 and exon 4 of CD40L(g.8172_8205del34bp), which lead to the entire deletion of exon 4 in cDNA (c.347_409del63bp, i.e.,exon 4 skipping) and an in-frame deletion of 21 amino acids in CD40L protein. Moreover, the patient had negligible CD40L expression on activated CD3+CD8-T lymphocytes. His mother and sister were carriers of the CD40L mutation. Our studies demonstrated a novel mutation in CD40L, which, to our knowledge, has not been reported previously.