Max Xiaohang Zhao

Max Xiaohang Zhao

Auto-generated profile, based on publicly available information

Max Xiaohang Zhao

Cerebras Systems Inc, 1237 E. Arques Avenue, Sunnyvale, 94085, California, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 June 2019 in Genetics in Medicine
Verified
Journal Article
Open access
PDF file
THTzung-Chien Hsieh
Tzung-Chien Hsieh
MMMartin A. Mensah
Martin A. Mensah
JPJean T. Pantel
Jean T. Pantel
DADione Aguilar
Dione Aguilar
OBOmri Bar
Omri Bar
PKPeter M. Krawitz
Peter M. Krawitz
Purpose Phenotype information is crucial for the interpretation of genomic variants. So far it has only been accessible for bioinformatics workflows after encoding into clinical terms by expert dysmorphologists. Methods Here, we introduce an approach driven by artificial intelligence that uses portrait photographs for the interpretation of clinical exome data. We measured the value added by computer-assisted image analysis to the diagnostic yield on a cohort consisting of 679 individuals with 105 different monogenic disorders. For each case in the cohort we compiled frontal photos, clinical features, and the disease-causing variants, and simulated multiple exomes of different ethnic backgrounds. Results The additional use of similarity scores from computer-assisted analysis of frontal photos improved the top 1 accuracy rate by more than 20–89% and the top 10 accuracy rate by more than 5–99% for the disease-causing gene. Conclusion Image analysis by deep-learning algorithms can be used to quantify the phenotypic similarity (PP4 criterion of the American College of Medical Genetics and Genomics guidelines) and to advance the performance of bioinformatics pipelines for exome analysis.

9 January 2018 in Genome Medicine
Verified
Journal Article
Open access
PDF file
AKAlexej Knaus
Alexej Knaus
JPJean Tori Pantel
Jean Tori Pantel
MPManuela Pendziwiat
Manuela Pendziwiat
NHNurulhuda Hajjir
Nurulhuda Hajjir
MZMax Zhao
Max Zhao
PKPeter M. Krawitz
Peter M. Krawitz
Glycosylphosphatidylinositol biosynthesis defects (GPIBDs) cause a group of phenotypically overlapping recessive syndromes with intellectual disability, for which pathogenic mutations have been described in 16 genes of the corresponding molecular pathway. An elevated serum activity of alkaline phosphatase (AP), a GPI-linked enzyme, has been used to assign GPIBDs to the phenotypic series of hyperphosphatasia with mental retardation syndrome (HPMRS) and to distinguish them from another subset of GPIBDs, termed multiple congenital anomalies hypotonia seizures syndrome (MCAHS). However, the increasing number of individuals with a GPIBD shows that hyperphosphatasia is a variable feature that is not ideal for a clinical classification. We studied the discriminatory power of multiple GPI-linked substrates that were assessed by flow cytometry in blood cells and fibroblasts of 39 and 14 individuals with a GPIBD, respectively. On the phenotypic level, we evaluated the frequency of occurrence of clinical symptoms and analyzed the performance of computer-assisted image analysis of the facial gestalt in 91 individuals. We found that certain malformations such as Morbus Hirschsprung and diaphragmatic defects are more likely to be associated with particular gene defects (PIGV, PGAP3, PIGN). However, especially at the severe end of the clinical spectrum of HPMRS, there is a high phenotypic overlap with MCAHS. Elevation of AP has also been documented in some of the individuals with MCAHS, namely those with PIGA mutations. Although the impairment of GPI-linked substrates is supposed to play the key role in the pathophysiology of GPIBDs, we could not observe gene-specific profiles for flow cytometric markers or a correlation between their cell surface levels and the severity of the phenotype. In contrast, it was facial recognition software that achieved the highest accuracy in predicting the disease-causing gene in a GPIBD. Due to the overlapping clinical spectrum of both HPMRS and MCAHS in the majority of affected individuals, the elevation of AP and the reduced surface levels of GPI-linked markers in both groups, a common classification as GPIBDs is recommended. The effectiveness of computer-assisted gestalt analysis for the correct gene inference in a GPIBD and probably beyond is remarkable and illustrates how the information contained in human faces is pivotal in the delineation of genetic entities.

11 November 2023
Verified
Conference Paper
Open access
LBLuk Burchard
Luk Burchard
MZMax Xiaohang Zhao
Max Xiaohang Zhao
JLJohannes Langguth
Johannes Langguth
ABAydın Buluç
Aydın Buluç
GGGiulia Guidi
Giulia Guidi
Dedicated accelerator hardware has become essential for processing AI-based workloads, leading to the rise of novel accelerator architectures. Furthermore, fundamental differences in memory architecture and parallelism have made these accelerators targets for scientific computing. The sequence alignment problem is fundamental in bioinformatics; we have implemented the X-Drop algorithm, a heuristic method for pairwise alignment that reduces search space, on the Graphcore Intelligence Processor Unit (IPU) accelerator. The X-Drop algorithm has an irregular computational pattern, which makes it difficult to accelerate due to load balancing. Here, we introduce a graph-based partitioning and queue-based batch system to improve load balancing. Our implementation achieves 10× speedup over a state-of-the-art GPU implementation and up to 4.65× compared to CPU. In addition, we introduce a memory-restricted X-Drop algorithm that reduces memory footprint by 55× and efficiently uses the IPU's limited low-latency SRAM. This optimization further improves strong scaling by 3.6×.

14 May 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
THTill Frederik Hartmann
Till Frederik Hartmann
MZMax Xiaohang Zhao
Max Xiaohang Zhao
DBDieter Beule
Dieter Beule
MHManuel Holtgrewe
Manuel Holtgrewe
Variant annotation requires the precise and consistent computation of Sequence Ontology (SO) terms and Human Genome Variation Society (HGVS) nomenclature. To ensure robust synchronization between these two key facets, we present mehari, a high-performance variant effect predictor implemented in Rust that employs a strict "HGVS-first" approach. By deterministically projecting variants to transcripts before evaluating functional consequences, mehari structurally aligns HGVS notation and SO terms. Benchmarking on ClinVar demonstrates that mehari achieves exceptional processing speeds and high concordance with established tools like Ensembl VEP, while also providing refined handling for complex biological edge cases such as selenoprotein recoding.

12 September 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
YLYifan Li
Yifan Li
QSQingyao Sun
Qingyao Sun
DDDrew DeHaas
Drew DeHaas
MZMax Xiaohang Zhao
Max Xiaohang Zhao
ABAdam Boyko
Adam Boyko
GGGiulia Guidi
Giulia Guidi
Biobank-scale genomic analyses are increasingly constrained by computational costs, as hundreds of thousands to millions of samples and variants must be analyzed together. The genotype representation graph (GRG) compactly encodes population genetic variation to accelerate computation, but its graph-traversal implementation does not exploit modern accelerators. This work introduces M ikado , a methodology that expresses GRG-based computation using sparse linear algebra primitives. Under a reverse topological ordering, the GRG adjacency matrix is strictly block-lower-triangular, and the genotype matrix-vector product becomes a sparse triangular solve, decomposed into a pipelined sequence of blocked sparse matrix-vector multiplies. Because GRGs are shallow by construction, the solve completes in only a few sequential stages, exposing fine-grained parallelism and enabling vendor-optimized sparse primitives on GPUs. On the full All of Us cohort, M ikado computes principal components in minutes , where PLINK2 cannot complete one chromosome in 72 hours, and runs genome-wide BOLT-LMM-inf in under 19 minutes on one GPU, where the official BOLT-LMM analysis would be impractical. Our two-stage reformulation is independent of the hardware: the same code runs unchanged across GPU architectures and, on CPUs, gives a 1.8 × single-threaded speedup over the existing GRG library together with multi-threaded scaling, providing a scalable, portable approach for population genetics as biobanks continue to grow.