Sign in to manage notifications about Ming
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Sign in to view Ming’s full profile
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Staff Data Scientist at Mineral.ai, an Alphabet company
Redwood City, California, United States Contact Info
Sign in to view Ming’s full profile
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
382 followers 373 connections
Redwood City, California, United States Contact Info
Sign in to view Ming’s full profile
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
382 followers 373 connections
View mutual connections with Ming
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
View mutual connections with Ming
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Join to view profile
Sign in to view Ming’s full profile
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
Mineral.ai
UCLA
- Report this profile
About
Experienced (15+ years) data scientist with a strong background in statistical modeling, machine learning, and data-driven decision-making.
Proven track record using quantitative analysis to solve business/research problems.
Recognized with multiple patents and awards for cross-functional teamwork and leadership.
Activity
Sign in to view Ming’s full profile
Welcome back
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
-
What’s required in order to take research out of the university setting and convert it into a thriving start-up? That’s the topic I’ll be sharing my…
What’s required in order to take research out of the university setting and convert it into a thriving start-up? That’s the topic I’ll be sharing my…
Liked by Ming Zheng
-
We (Patrick Honcoop and I) hosted an informal meetup last month in SF South Bay and it was a very good turnout. Many people asked me if this was…
We (Patrick Honcoop and I) hosted an informal meetup last month in SF South Bay and it was a very good turnout. Many people asked me if this was…
Liked by Ming Zheng
-
I am happy to share that I have obtained the certificate "Artificial Intelligence: Business Strategies and Applications" from UC Berkeley. This truly…
I am happy to share that I have obtained the certificate "Artificial Intelligence: Business Strategies and Applications" from UC Berkeley. This truly…
Liked by Ming Zheng
Join now to see all activity
Experience
-
Staff Data Scientist
Mineral.ai
- 1 year 6 months
Mountain View, California, United States
Using Statistical Modeling and ML methodologies to meet the challenges in sustainable agriculture.
Led a group of data scientists and software engineers to develop a berry yield forecast product, which is actively used by our customer and can save them millions of pounds of berries in their business operations.
• Developed new preprocessing, feature engineering and dynamic ensemble method with Bayesian constraint (to optimally combine results from multiple forecast methods) from…Using Statistical Modeling and ML methodologies to meet the challenges in sustainable agriculture.
Led a group of data scientists and software engineers to develop a berry yield forecast product, which is actively used by our customer and can save them millions of pounds of berries in their business operations.
• Developed new preprocessing, feature engineering and dynamic ensemble method with Bayesian constraint (to optimally combine results from multiple forecast methods) from close interactions with customers to gain insight on data and business goals, explain findings and continue improving models.
• Improved two business-critical metrics: decreased weighted absolute pct error (APE) by 5 percentage points and increased # of consistent weeks (with APE < 10%) by 11%.Provided solutions for crop yield modeling for multiple breeding companies and non-profit organizations.
• Developed pipeline for yield modeling: preprocessing, validation, visualization, modeling, and reporting.
Improved yield estimation correlation from 0.5 to 0.8 using ensemble of multiple ML models.
• Conducted power analysis and experimental design to evaluate multiple metrics (disease presence ratio, intraclass correlation) of Mineral’s AI-based crop phenotyping platform with desired precision.
• Designed new linear mixed model to boosted evaluation speed by >100 fold with improved accuracy.Quantified contributing factors to the yield of 6 major crops using linear mixed model and provided actionable feedback to our customers.
• Applied appropriate multiple imputation method to increase sample size by 2.7X and achieved 66% R2.Time-series remote sensing data modeling.
• Designed Bayesian curve fitting method and achieved median absolute deviation < 5 days to predict in-season planting date and applied to 8 corn-belts states.
• Built ML models to classify leafy vegetables and achieved 88% overall accuracy on 3 major categories.3 patents, 4 spot and 15 peer bonuses.
-
Senior Data Scientist
X, the moonshot factory
- 3 years
Mountain View, CA
Using Statistical Modeling and ML methodologies to meet the challenges in sustainable agriculture
-
Data Scientist
Adecco @ Google X
- 1 year 2 months
Mountain View, CA
-
Director of Statistical Study in Anesthesia, Senior Research Engineer
Stanford University
- 10 years 3 months
Big Data Research in Biomedical field:
•Assembled 2X107 single nucleotide polymorphisms (SNPs) across 50 inbred mouse strains using 3X1012 base pairs of whole-genome deep sequencing data.
•Developed new haplotype-based computational genetic mapping method to properly filter and analyze 5000 mouse traits encompassing 214,000 data points.
•Designed statistical tools and integration approaches using cutting-edge multi-omics technologies to gain deeper insight of mapping…Big Data Research in Biomedical field:
•Assembled 2X107 single nucleotide polymorphisms (SNPs) across 50 inbred mouse strains using 3X1012 base pairs of whole-genome deep sequencing data.
•Developed new haplotype-based computational genetic mapping method to properly filter and analyze 5000 mouse traits encompassing 214,000 data points.
•Designed statistical tools and integration approaches using cutting-edge multi-omics technologies to gain deeper insight of mapping results.Technical experiences with development and application of statistical modeling and machine learning methodologies to solve research problems:
•Evaluation and comparison of multiple machine learning prediction models for vitamin response using selected genomic variants.
•Built likelihood-based machine learning algorithm for HIV viral tropism prediction that reduced 20% error at high specificity compared to traditional methods such as SVM and position-specific multinomial model.
•Used sparse representation and binomial modeling to detect the existence of HIV viruses who used alternative viral entry method in deep sequencing data.Collaborated with researchers worldwide with effective mutual communication of scientific questions and statistical analysis plans and results, which led to 30 novel discoveries published in peer-reviewed journals:
•interacting with investigators to verify and quantify scientific questions and experimental design
•Performing advanced statistical modeling approaches and data analysis techniques for data exploration.
•Craft scientific stories from analysis results and communicating with investigators to make recommendations and design informed action for further studiesSupervise lab postdoc for algorithm design and software implementation in Computational Biology research
-
Research Biostatistician
Hoffmann-La Roche
- 2 years 8 months
Performed portfolio estimation to guide the business decision on the number of study launches.
Developed gene expression experiment and analysis pipeline for drug research.
Performed experimental design, algorithm development and implementation, statistical model selection, application and interpretation for colleagues across departments in the company.
Developed novel methodologies for studies with special needs:
•Developed a novel algorithm to analyze 2D nuclear…Performed portfolio estimation to guide the business decision on the number of study launches.
Developed gene expression experiment and analysis pipeline for drug research.
Performed experimental design, algorithm development and implementation, statistical model selection, application and interpretation for colleagues across departments in the company.
Developed novel methodologies for studies with special needs:
•Developed a novel algorithm to analyze 2D nuclear magnetic resonance spectroscopy (NMR) data, which led to the discovery of novel genetic factor for Tylenol-induced liver toxicity (cover story in Genome Research).
•Applied binomial modeling for simultaneous detection of protein-DNA binding sites (motifs) in multiple sequences.
•Used hierarchical model and dynamic programming to detect CRM (clusters of co-localized DNA-binding motifs) in DNA sequences
•Segregated mouse genomic sequences into linkage-disequilibrium (LD) islands (high LD within islands and low LD between islands) by optimizing specially designed objective function using dynamic programming.
-
Research Fellow/Teaching Fellow
University of California, Los Angeles
- 4 years 4 months
Pioneered data analysis of emerging ChIP-chip technology, which led to the identification of 10,567 active promoters in the human genome (published in Nature).
Awarded "TA of the Year" (Dept. of Statistics, 2004) for excellence in teaching.
Education
-
UCLA
Ph.D. Statistics
-
Selected coursework: Statistical Theory, Applied Statistics, Applied Regression Analysis, High Dimensional Data Analysis, Statistical Computing, Stochastic Processes, Pattern Recognition and Machine Learning.
-
Peking University
Bachelor of Science - BS Mathematics
-
-
Peking University
Bachelor of Science - BS Mathematics
-
-
Peking University
Bachelor of Science - BS Mathematics
-
Publications
-
Human hepatic organoids for the analysis of human genetic diseases
Guan, Y., Xu, D., Garfin, P.M., Ehmer, U., Hurwitz, M., Enns, G., Michie, S., Wu, M., Zheng, M., Nishimura, T., Sage, J. and Peltz, G. (2017) Human hepatic organoids for the analysis of human genetic diseases. JCI Insight, Vol 2, e94954, 2017.
-
Chimeric TK-NOG Mice: A Predictive Model for Cholestatic Human Liver Toxicity
Xu, D., Wu, M., Nishimura, S., Nishimura, T., Michie, S.A., Zheng, M., Yang, Z., Yates, A.J., Day, J.S., Hillgren, K.M., Takeda, S.T., Guan, Y., Guo, Y., and Peltz, G. (2015) Chimeric TK-NOG Mice: A Predictive Model for Cholestatic Human Liver Toxicity. Journal of Pharmacology and Experimental Therapeutics, Vol 252, P.P. 274-280, 2015.
-
The Role of Abcb5 Alleles in Susceptibility to Haloperidol-Induced Toxicity in Mice and Humans
Zheng, M., Zhang, H., Dill, D.L., Clark, J.D., Tu, S., Yablonovitch, A.L., Tan, M.H., Zhang, R., Rujescu, D., Wu, M., Tessarollo, L., Vieira, W., Gottesman, M.M., Deng, S., Eberlin, L.S., Zare, R.N., Billard, J.M., Gillet, J.P., Li, J.B. and Peltz, G. (2015) The Role of Abcb5 Alleles in Susceptibility to Haloperidol-Induced Toxicity in Mice and Humans. PLoS Medicine, Vol 12, Issue 2, e1001782, 2015.
-
The sex-determining factors SRY and SOX9 regulate similar target genes and promote testis cord formation during testicular differentiation
Li, Y., Zheng, M. and Lau, Y.F. (2014) The sex-determining factors SRY and SOX9 regulate similar target genes and promote testis cord formation during testicular differentiation. Cell Reports, Vol 8, Issue 3, P.P. 723-733, 2014.
-
Acute and chronic phases of complex regional pain syndrome in mice are accompanied by distinct transcriptional changes in the spinal cord
Gallagher, J.J., Tajerian, M., Guo, T., Shi, X., Li, W., Zheng, M., Peltz, G., Kingery, W.S. and Clark, J.D. (2013) Acute and chronic phases of complex regional pain syndrome in mice are accompanied by distinct transcriptional changes in the spinal cord. Molecular Pain, 9:40, 2013.
-
Human pharmacogenetic analysis in chimeric mice with 'humanized livers'
Hu, Y., Wu, M., Nishimura, T., Zheng, M. and Peltz, G. (2013) Human pharmacogenetic analysis in chimeric mice with 'humanized livers'. Pharmacogenetics and Genomics, Vol 23, P.P. 78-83, 2013.
-
Liquid chromatography/mass spectrometry methods for measuring dipeptide abundance in non-small-cell lung cancer
Wu, M., Xu, Y., Fitch, W.L., Zheng, M., Merritt, R.E., Shrager, J.B., Zhang, W., Dill, D.L., Peltz, G. and Hoang, C.D. (2013) Liquid chromatography/mass spectrometry methods for measuring dipeptide abundance in non-small-cell lung cancer. Rapid Commun. in Mass Spectrom, Vol 27, P.P. 2091–2098, 2013.
-
Opiate-induced changes in brain adenosine levels and narcotic drug responses
Wu, M., Sahbaie, P., Zheng, M., Lobato, R., Boison, D., Clark, J.D. and Peltz, G. (2013) Opiate-induced changes in brain adenosine levels and narcotic drug responses. Neuroscience, Vol 228, P.P. 235-242, 2013.
-
Using chimeric mice with humanized livers to predict human drug metabolism and a drug-drug interaction
Nishimura, T., Hu, Y., Wu, M., Pham, E., Suemizu, H., Elazar, M., Liu, M., Idilman, R., Yurdaydin, C., Angus, P., Stedman, C., Murphy, B., Glenn, J., Nakamura, M., Nomura, T., Chen, Y., Zheng, M., Fitch, W.L. and Peltz, G. (2013) Using chimeric mice with humanized livers to predict human drug metabolism and a drug-drug interaction. The Journal of Pharmacology and Experimental Therapeutics, Vol 344, P.P. 388-396, 2013.
-
A better prognosis for genetic association studies in mice
Zheng, M., Dill, D. and Peltz, G. (2012) A better prognosis for genetic association studies in mice. Trends in Genetics, Vol 28, Issue 2, P.P. 62-69, 2012. (Cover Story)
-
2D NMR Metabonomic Analysis: A Novel Method for Automated Peak Alignment
-
Zheng, M., Lu, P., Liu, Y., Pease, J., Usuka, J., Liao, G. and Peltz, G. (2007) 2D NMR Metabonomic Analysis: A Novel Method for Automated Peak Alignment. Bioinformatics, Vol 23, P.P. 2926-2933, 2007.
-
A high-resolution map of active promoters in the human genome
-
Kim, T.H., Barrera, L.O., Zheng, M., Qu, C., Singer, M.A., Richmand, T.A.,Wu, Y.N.,Green, R.D., and Ren, B. (2005) A high-resolution map of active promoters in the human genome. Nature, Vol 436, P.P. 876-880, 2005.
-
A Pharmacogenetic Discovery: Cystamine Protects Against Haloperidol-Induced Toxicity and Ischemic Brain Injury
-
Zhang, H., Zheng, M., Wu, M., Xu, D., Nishimura, T., Nishimura, Y., Giffard, R., Xiong, X., Xu, L.J., Clark, J.D. Sahbaie, P., Dill, D.L. and Peltz, G. (2016) A Pharmacogenetic Discovery: Cystamine Protects Against Haloperidol-Induced Toxicity and Ischemic Brain Injury. Genetics, Vol 203, P.P. 599-609, 2016.
-
A prospective observational study evaluating the ability of prelabor psychological tests to predict labor pain, epidural analgesic consumption, and maternal satisfaction
-
Carvalho, B., Zheng, M. and Aiono-Le Tagaloa L. (2014) A prospective observational study evaluating the ability of prelabor psychological tests to predict labor pain, epidural analgesic consumption, and maternal satisfaction. Anesthesia and Analgesia, Vol 119, Issue 3, P.P. 632-640, 2014.
-
An optimistic prognosis for the clinical utility of laboratory test data
-
Zheng, M., Ravindran, P., Wang, J., Epstein, R.H., Chen, D.P., Butte, A.J., and Peltz, G. (2010) An optimistic prognosis for the clinical utility of laboratory test data. Anesthesia & Analgesia, Vol 111, P.P. 1026-35, 2010.
-
Application of the Simple and Efficient Mpeak Modeling in Binding Peak Identification in ChIP-Chip Studies (Book Chapter)
Tiling Arrays: Methods and Protocols. New York City, NY: Humana Press
Other authors
-
Bhmt2 is a Genetic Susceptibility Factor For Acetaminophen-Induced Liver Toxicity
-
Liu, H.H., Lu, P., Guo, Y., Farrell, E., Zhang, X., Zheng, M., Bosano, B., Zhang, Z., Allard, J., Liao, G., Fu, S., Chen, J., Dolim, K., Kuroda, A., Usuka, J., Cheng, J., Tao, W., Welch., K., Liu, Y., Pease, J., de Keczer, S.A., Masjedizadeh, M., Hu, J.-S., Weller, P., Garrow, T. and Peltz, G. (2010) Bhmt2 is a Genetic Susceptibility Factor For Acetaminophen-Induced Liver Toxicity. Genome Research, Vol 20, P.P. 28-35, 2010. (Cover Story)
-
CD14 SNPs regulate the innate immune response
-
Liu, H.H., Hu, Y., Zheng, M., Suhoski, M.M., Engleman, E.G., Dill, D.L., Hudnall, M., Wang, J., Spolski, R., Leonard, W.J. and Peltz, G. (2012) CD14 SNPs regulate the innate immune response. Molecular Immunology, Vol 51, Issue 2, P.P. 112-127, 2012.
-
ChIP-chip: data, model and analysis
-
Zheng, M., Barrera, L.O., Wu, Y.N. and Ren, B. (2007) ChIP-chip: data, model and analysis. Biometrics, Vol 63, Issue 3, P.P. 787-796, 2007.
-
Computational genetic discoveries that could improve perioperative medicine
-
Zheng, M., Dill, D.L., Clark, J.D. and Peltz, G. (2012) Computational genetic discoveries that could improve perioperative medicine. Current Opinion in Anaesthesiology, Vol 25, Issue 4, P.P. 428-433, 2012.
-
Computational Genetic Mapping in Mice: ‘The Ship has Sailed.’
-
Zheng, M., Shafer, S.S., Liao, G., Liu, H.H., and Peltz, G. (2009) Computational Genetic Mapping in Mice: ‘The Ship has Sailed.’ Science Translational Medicine, 1:3ps4, 2009.
-
Enabling autologous human liver regeneration with differentiated adipocyte stem cells
-
Xu, D., Nishimura, T., Zheng, M., Wu, M., Su, H., Sato, N., Lee, G., Michie, S., Glenn, J. and Peltz, G. (2014) Enabling autologous human liver regeneration with differentiated adipocyte stem cells. Cell Transplantation, Vol 23, P.P. 1573-1584, 2014. (Media report in ScienceDaily.com)
-
Evaluation of experimental pain tests to predict labour pain and epidural analgesic consumption
-
Carvalho, B., Zheng, M. and Aiono-Le Tagaloa L. (2013) Evaluation of experimental pain tests to predict labour pain and epidural analgesic consumption. British Journal of Anaesthesia, Vol 110, Issue 4, P.P. 600-606, 2013.
-
Expression Genetics Identifies Spinal Mechanisms Supporting Formalin Late Phase Behaviors
-
Li, X., Sahbaie, P., Zheng, M., Ritchie, J., Peltz, G., Mogil, J.S. and Clark, J.D. (2010) Expression Genetics Identifies Spinal Mechanisms Supporting Formalin Late Phase Behaviors. Molecular Pain, 6:11, 2010.
-
Fialuridine induces acute liver failure in chimeric TK-NOG mice: a model for detecting hepatic drug toxicity prior to human testing
-
Xu, D., Nishimura, T., Nishimura, S., Zhang, H., Zheng, M., Guo, Y.Y., Masek, M., Michie, S.A., Glenn, J. and Peltz, G. (2014) Fialuridine induces acute liver failure in chimeric TK-NOG mice: a model for detecting hepatic drug toxicity prior to human testing. PLoS Medicine, Vol 11, Issue 4, e1001628, 2014.
-
Genetic discovery: the prescription for chronic pain
-
Zheng, M. and Peltz, G. (2010) Genetic discovery: the prescription for chronic pain. Genome Medicine, 2:82, 2010.
-
Genetic susceptibility to the delayed sequelae of neonatal respiratory syncytial virus infection is MHC dependent
-
Tregoning J.S., Yamaguchi, Y., Wang, B., Mihm, D., Harker, J.A., Bushell, E.S.C., Zheng, M., Liao, G., Peltz, G. and Openshaw, P.J.M. (2010) Genetic susceptibility to the delayed sequelae of neonatal respiratory syncytial virus infection is MHC dependent. Journal of Immunology, Vol 185 (9), P.P. 5384-91, 2010.
-
Genetically determined P2X7 receptor pore formation regulates variability in chronic pain sensitivity
-
Sorge, R.E., Trang, T., Dorfman, R., Smith, S.B., Beggs, S., Ritchie, J., Austin, J.S., Zaykin, D.V., Meulen, H.V., Costigan, M., Herbert, T.A., Yarkoni-Abitbul, M., Tichauer, D., Livneh, J., Gershon, E., Zheng, M., Ta, K., John, S.L., Slade, G.D., Jordan, J., Woolf, C.J., Peltz, G., Maixner, W., Diatchenko, L., Seltzer, Z., Salter, M.W. and Mogil, J.S. (2012) Genetically determined P2X7 receptor pore formation regulates variability in chronic pain sensitivity. Nature Medicine, Vol 18, Issue 4,…
Sorge, R.E., Trang, T., Dorfman, R., Smith, S.B., Beggs, S., Ritchie, J., Austin, J.S., Zaykin, D.V., Meulen, H.V., Costigan, M., Herbert, T.A., Yarkoni-Abitbul, M., Tichauer, D., Livneh, J., Gershon, E., Zheng, M., Ta, K., John, S.L., Slade, G.D., Jordan, J., Woolf, C.J., Peltz, G., Maixner, W., Diatchenko, L., Seltzer, Z., Salter, M.W. and Mogil, J.S. (2012) Genetically determined P2X7 receptor pore formation regulates variability in chronic pain sensitivity. Nature Medicine, Vol 18, Issue 4, P.P. 595-599, 2012.
-
H5N1 influenza virus pathogenesis in genetically diverse mice is mediated at the level of viral load
-
Boon, A.C., Finkelstein, D., Zheng, M., Liao, G., Allard, J., Klumpp, K., Webster, R., Peltz, G. and Webby R.J. (2011) H5N1 influenza virus pathogenesis in genetically diverse mice is mediated at the level of viral load. mBio, Vol 2, Issue 5, e00171-11, 2011.
-
Humanized thymidine kinase-NOG mice can be used to identify drugs that cause animal-specific hepatotoxicity: a case study with furosemide
-
Xu, D., Michie, S.A., Zheng, M., Takeda, S., Wu, M. and Peltz, G. (2015) Humanized thymidine kinase-NOG mice can be used to identify drugs that cause animal-specific hepatotoxicity: a case study with furosemide. Journal of Pharmacology and Experimental Therapeutics, Vol 354, P.P. 73-78., 2015.
-
Identification of drug targets by chemogenomic and metabolomic profiling in yeast
-
Wu, M., Zheng, M., Zhang, W., Suresh, S., Schlecht, U., Fitch, W.L., Aronova, S., Baumann, S., Davis, R., St Onge, R., Dill, D.L. and Peltz, G. (2012) Identification of drug targets by chemogenomic and metabolomic profiling in yeast. Pharmacogenet Genomics, Vol 22, Issue 12, P.P. 877-886, 2012.
-
In Silico and In Vitro Pharmacogenetics: Aldehyde Oxidase Rapidly Metabolizes a P38 Kinase Inhibitor
-
Zhang, X., Liu, H.H., Weller, P., Zheng, M., Wang, J., Liao, G., Monshouwer, M. and Peltz, G. (2011) In Silico and In Vitro Pharmacogenetics: Aldehyde Oxidase Rapidly Metabolizes a P38 Kinase Inhibitor. The Pharmacogenetics Journal, Vol 11, P.P. 15-24, 2011.
-
Metabolomic-derived novel cyst fluid biomarkers for pancreatic cysts: glucose and kynurenine
-
Park, W.G., Wu, M., Bowen, R., Zheng, M., Fitch, W.L., Pai, R.K., Wodziak, D., Visser, B.C., Poultsides, G.A., Norton, J.A., Banerjee, S., Chen, A.M., Friedland, S., Scott, B.A., Pasricha, P.J., Lowe, A.W. and Peltz, G. (2013) Metabolomic-derived novel cyst fluid biomarkers for pancreatic cysts: glucose and kynurenine. Gastrointestinal Endoscopy, Vol 78, P.P. 295-302, 2013.
-
Next-generation computational genetic analysis: multiple complement alleles control survival after Candida albicans infection
-
Peltz, G., Zaas, A.K., Zheng, M., Solis, N.V., Zhang, M.X., Liu, H.H., Hu, Y., Boxx, G.M., Phan, Q.T., Dill, D. and Filler, S.G. (2011) Next-generation computational genetic analysis: multiple complement alleles control survival after Candida albicans infection. Infection and Immunity, Vol 79, Issue 11, P.P. 4472-4479, 2011.
-
Profiling of ARDS Pulmonary Edema Fluid Identifies a Metabolically Distinct Subset
-
Rogers, A.J., Contrepois, K., Wu, M., Zheng, M., Peltz, G., Ware, L.B. and Matthay, M.A. (2017) Profiling of ARDS Pulmonary Edema Fluid Identifies a Metabolically Distinct Subset. American Journal of Physiology-Lung Cellular and Molecular Physiology, Vol 32, P.P. L703-709, 2017.
-
The multiple PDZ domain protein Mpdz/MUPP1 regulates opioid tolerance and opioid-induced hyperalgesia
-
Donaldson, R., Sun, Y., Liang, D.Y., Zheng, M., Sahbaie, P., Dill, D.L., Peltz, G., Buck, K.J. and Clark, J.D. (2016) The multiple PDZ domain protein Mpdz/MUPP1 regulates opioid tolerance and opioid-induced hyperalgesia. BMC Genomics, Vol 17, P.P. 313, 2016.
-
The Netrin-1 receptor DCC is a regulator of maladaptive responses to chronic morphine administration
-
Liang, D.Y., Zheng, M., Sun, Y., Sahbaie, P., Low, S.A., Peltz, G., Scherrer, G., Flores, C. and Clark, J.D. (2014) The Netrin-1 receptor DCC is a regulator of maladaptive responses to chronic morphine administration. BMC Genomics, 15:345, 2014.
-
The Role of IL-1 in Wound Biology Part I: Murine in Silico and In vitro Experimental Analysis
-
Hu, Y., Liang, D., Li, X., Liu, H.H., Zhang, X., Zheng, M., Dill, D., Shi, X., Qiao, Y., Yeomans, D., Carvalho, B., Angst, M.S., Clark, J.D. and Peltz, G.. (2010) The Role of IL-1 in Wound Biology Part I: Murine in Silico and In vitro Experimental Analysis. Anesthesia & Analgesia, Vol 111, Issue 6, P.P. 1525-1533, 2010. (Cover Story & Editorial Review)
-
The Role of IL-1 in Wound Biology Part II: In vivo and Human Translational Studies
-
Hu, Y., Liang, D., Li, X., Liu, H.H., Zhang, X., Zheng, M., Dill, D., Shi, X., Qiao, Y., Yeomans, D., Carvalho, B., Angst, M.S., Clark, J.D. and Peltz, G. (2010) The Role of IL-1 in Wound Biology Part II: In vivo and Human Translational Studies. Anesthesia & Analgesia, Vol 111, Issue 6, P.P. 1534-1542, 2010. (Cover Story & Editorial Review)
Patents
-
Normalizing counts of plant-parts-of-interest
Issued US-11830191-B2
Other inventors
-
Inferring moisture from color
Issued US-11715296-B2
Other inventors
-
Partitioning agricultural fields for annotation
Issued US-11709860-B2
Other inventors
-
Systems and methods for alignment of objects in images
Issued US 11/820,939
Systems and methods for aligning objects in object sets are provided. An object set has objects that are in a corresponding image in a plurality of images. For each respective object in a first object set, a corresponding object group is constructed that contains the respective object, thereby constructing a plurality of object groups. Similarity metrics are computed between object groups and objects in objects sets in order to assign the objects to object groups. The object groups are then…
Systems and methods for aligning objects in object sets are provided. An object set has objects that are in a corresponding image in a plurality of images. For each respective object in a first object set, a corresponding object group is constructed that contains the respective object, thereby constructing a plurality of object groups. Similarity metrics are computed between object groups and objects in objects sets in order to assign the objects to object groups. The object groups are then refined in order to align objects in the object sets.
Other inventors
Honors & Awards
-
TA of the Year
Dept. of Statistics, UCLA
-
1st place in Fujian Province in National High School Mathematics League (1995) and 3rd Prize in Chinese Mathematical Olympiad (1996)
-
-
2nd Prize. National Mathematical Contest in Modeling (1997 and 1998)
-
-
Dissertation Year Fellowship (2005) and Departmental (2001-2004)
UCLA
-
Motorola (1998)/Aetna (1997)/Outstanding New Student (1996) Scholarship
Peking University
More activity by Ming
-
We are excited to announce the launch of Dragonfly, an instruction-tuned vision-language architecture that enhances fine-grained visual understanding…
We are excited to announce the launch of Dragonfly, an instruction-tuned vision-language architecture that enhances fine-grained visual understanding…
Liked by Ming Zheng
-
Excited to be able to share publicly an incredibly meaningful project that I've been a part of with Mineral - check it out!
Excited to be able to share publicly an incredibly meaningful project that I've been a part of with Mineral - check it out!
Liked by Ming Zheng
View Ming’s full profile
- See who you know in common
- Get introduced
- Contact Ming directly
Sign in
Access over 1 billion professionals
Sign in
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
New to LinkedIn? Join now
Other similar profiles
- Wenhao Hu United States Connect
- Kan Wang San Francisco Bay Area Connect
- Long Tao San Francisco, CA Connect
- Mike Beaumier, PhD Mission Viejo, CA Connect
- Hisham Talukder New York, NY Connect
- Jinqi Shen San Francisco, CA Connect
- Hongsheng Fang Sr. Data Scientist/Machine Learning Engineer at NVIDIA Palo Alto, CA Connect
- Ben Cerio San Francisco, CA Connect
- Bernard Beckerman Brooklyn, NY Connect
- Amir Erfanian, PhD Austin, Texas Metropolitan Area Connect
- Thomas Barrios San Francisco, CA Connect
- Ross Altman Boston, MA Connect
- Qi Gao Davis, CA Connect
- Annie Luo Boston, MA Connect
- Pedro Sfriso San Francisco, CA Connect
- Himansu Sahoo Collierville, TN Connect
- Noga Neeman New York City Metropolitan Area Connect
- Sanja Nedic, PhD Paris Connect
- Keyu Nie San Jose, CA Connect
- Yonaton Heit Riverside, CA Connect
Explore more posts
- Ozette Complex multimodal datasets require tools that can capture their full value. Principal Research Scientist Andrew McDavid, PhD, shares how using Ozette Discovery™ uncovered deeper insights from a previously published COVID-19 CITE-seq dataset. Ozette published new research exploring how Ozette Discovery™ can leverage the multimodal protein and RNA signal from #CITEseq data to identify predictors of disease severity.Download the preprint to learn how Ozette Discovery™ delivers computationally-derived insights at unmatched speed and resolution: https://loom.ly/-1DTG4g 18
- Pankaj Mishra, PhD Lately, I've been experimenting and building data pipelines forFuture Therapeutics and realized how little we talk about data pipelines in cheminformatics. It's a domain where, at any given time, we handle large volumes of data from multiple sources.I'm sharing a special collection of articles on Cheminformatics Data Pipelining, designed to raise awareness and enhance skills in this critical area.Part 1 of 8 is published. Have a look and feel free to share your feedback. Also, let me know if I miss something specific for cheminformatics. I would also love to talk to those actively involved in data pipelining projects to hear your thoughts and approaches. #cheminformatics #drugdiscovery #datapipelineshttps://lnkd.in/gDa7G2_z 23
- Ihor Stepanov 🇺🇦 Our commitment to open-source is multi-dimensional, and high-quality data is one aspect of it. 1
- NeuML As many go down the "agentic path", we're choosing a different path.....graph path traversals! 🔵->🟨->🟢Graph path traversals use vector similarity and/or relationships of your choosing to walk a graph and enable LLMs to explain complex concepts and relationships. This example walks a path and automatically generates an explanation of the network in the form of a short article. Paths can be set directly (i.e. Roman Empire -> Reasons for collapse) or inferred from a query (Tell me the reasons why the Roman Empire collapsed).Learn more here: https://lnkd.in/evdB5HgN 8
- Deniz Kavi SPACE2: Improved computational epitope profiling using structural models identifies a broader diversity of antibodies that bind to the same epitope. Web server: https://lnkd.in/gJT3wgh8Paper: https://lnkd.in/gwEs93FqGroup your antibodies by what epitope they bind to on Tamarind Bio!Abstract:The function of an antibody is intrinsically linked to the epitope it engages. Clonal clustering methods, based on sequence identity, are commonly used to group antibodies that will bind to the same epitope. However, such methods neglect the fact that antibodies with highly diverse sequences can exhibit similar binding site geometries and engage common epitopes. In a previous study, we described SPACE1, a method that structurally clustered antibodies in order to predict their epitopes. This methodology was limited by the inaccuracies and incomplete coverage of template-based modeling. In addition, it was only benchmarked at the level of domain-consistency on one virus class. Here, we present SPACE2, which uses the latest machine learning-based structure prediction technology combined with a novel clustering protocol, and benchmark it on binding data that have epitope-level resolution. On six diverse sets of antigen-specific antibodies, we demonstrate that SPACE2 accurately clusters antibodies that engage common epitopes. 32
- SWE Support
- Sarah Hirsch Check out my workshop on Regex with the Harvard Data Science Initiative on Thursday at 5 pm EDT/2 pm PDT!Have you ever wondered about coding shorthand that uses special symbols like ^, $, +, and *? Does it seem too strange and impenetrable to understand, much less use? Start chipping away at that iceberg and join us to learn more about regular expressions, an efficient and powerful way to parse and clean text data.https://lnkd.in/gj_BzvrB 5 1 Comment
- Towards Data Science Fine-tuning pre-trained models is a powerful paradigm for developing better models at a lower cost than training them from scratch. Check out Shaw Talebi's newest article now!#LLM #Python 35
- Towards Data Science If you wanted to learn about activation functions, weights initialization, and batch normalization in great detail and gain a deep understanding of how they can help us tackle vanishing and exploding gradients, don't miss Amy Ma's thorough deep dive. 14
- Arun Subramanian Scikit-learn has been a core component of my ML toolkit since I began using Python. However, its true depth and power only became apparent to me in the past year.I first encountered the concept of the scikit-learn Pipeline (sklearn.pipeline.Pipeline) in Jose Marcial Portilla's "Python for Machine Learning and Data Science" Udemy course. This concept proved invaluable for streamlining modeling work by automating sequential operations, including standard scalers, model fitting with cross-validation, and hyperparameter tuning with GridSearchCV. (See scikit-learn documentation: https://lnkd.in/gFCaef2h) Later, while learning about recommender systems in Frank Kane's "Building Recommender Systems" Udemy course, I was introduced to the flexibility of creating custom estimators (surprise.prediction_algorithms.algo_base) using the scikit-surprise library. While I was impressed by this capability, I didn't fully grasp its potential applications beyond recommender systems, such as its relevance to feature engineering.Recently, I've delved deeper into scikit-learn's potential through custom transformers (sklearn.base.BaseEstimator, sklearn.base.TransformerMixin). Soledad Galli's "Deployment of Machine Learning models" Udemy course provided invaluable insights into integrating these with pipelines for efficient ML Ops. The TransformerMixin, BaseEstimator interfaces offer a structured approach to creating reusable data transformation components. Soledad's open-source library, "feature-engine," utilizes these foundational concepts and provides a diverse set of custom transformers that can significantly enhance and streamline your feature engineering operations. (See feature-engine documentation: https://lnkd.in/gZbck84d)It's evident that scikit-learn's capabilities extend far beyond its core functionalities. This powerful library deserves a spotlight on its hidden gems. Thanks to all the Udemy instructors mentioned above for helping me learn and explore deeper concepts. Personally, I'm excited to test out custom transformers in my own work.Have you used custom transformers in your work? Let me know your thoughts!#scikitlearn #machinelearning #datascience #MLops #customtransformers #pipelines 19 1 Comment
- Cheeky Scientist
- Carlos Chinchilla Hello everyone. I’m looking for bioinformaticians, material scientists, or computational chemists interested in collaborating on a project to change how we run experiments and conduct scientific research by creating an AI Copilot that:- Converts natural language descriptions into executable code Jupyter notebooks- Offers critique and alternative interpretations of results- Performs intelligent search and summarization of relevant scientific literature- Keeps researchers up-to-date with the latest developments in their field- Continuously learns from user interactions and new researchThe ultimate goal is to dramatically accelerate the pace of discovery by leveraging the latest advances in AI, such as AlphaFold, GNoME, and GPT, to create next-generation tools.An all-in-one AI toolkit for scientists, an AI-powered Rosetta Stone.If you're interested or know someone who might be, let's connect!If you are in SF, let's have a coffee!- encode/science 11
- Sucheendra kumar New Preprint Alert:IntegrIBS: Evaluating the Potential and Challenges of Building a Robust IBS Classifier with Integrated Microbiome Data.Our study delves into the potential and challenges of integrating multiple data sets and predicting Irritable Bowel Syndrome (IBS) using 16S rRNA microbiome data. This approach initially showed promise with a 10-fold cross-validation approach and explainability analysis identifying key bacteria previously implicated in IBS. However, significant performance drops in leave-one-dataset-out tests reveal challenges posed by biological and technical variability. This underscores that 16S microbiome data alone may be insufficient for accurate IBS prediction. Argues for more comprehensive large datasets, standardization, better measurement technologies, and multi-omics as essential for better accuracy.https://lnkd.in/gYp_KTd6link to study website: https://bit.ly/IntegrIBS#Research #IBS #Microbiome #DataIntegration #MachineLearning #AI #PrecisionMedicine 30 6 Comments
- xCures Causal machine learning is changing how we make clinical decisions. Unlike traditional machine learning that predicts outcomes, causal machine learning explains the "why" and "what if" behind those predictions.This shift from correlation to causation allows for personalized medicine at its best.Imagine knowing not just which treatment could work, but why it’s the best option for a specific patient.𝗗𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝘀 𝗯𝗲𝘁𝘄𝗲𝗲𝗻 𝗖𝗮𝘂𝘀𝗮𝗹 𝗠𝗟 𝗮𝗻𝗱 𝗖𝗹𝗮𝘀𝘀𝗶𝗰 𝗠𝗟:𝟭. 𝗙𝗼𝗰𝘂𝘀 𝗼𝗻 𝗖𝗮𝘂𝘀𝗮𝘁𝗶𝗼𝗻 𝘃𝘀. 𝗖𝗼𝗿𝗿𝗲𝗹𝗮𝘁𝗶𝗼𝗻:- 𝗖𝗹𝗮𝘀𝘀𝗶𝗰 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:Identifies correlations and makes predictions based on patterns observed in data. It's primarily concerned with "what" happens.- 𝗖𝗮𝘂𝘀𝗮𝗹 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:Looks to establish cause-and-effect relationships, answering "why" something happens and "what if" different interventions are applied.𝟮. 𝗠𝗼𝗱𝗲𝗹𝗶𝗻𝗴 𝗔𝗽𝗽𝗿𝗼𝗮𝗰𝗵:- 𝗖𝗹𝗮𝘀𝘀𝗶𝗰 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:Often uses algorithms that can be black boxes, focusing on accuracy and pattern detection over interpretability.- 𝗖𝗮𝘂𝘀𝗮𝗹 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:Employs models that incorporate causal assumptions, making them more transparent and interpretable, as they mimic human reasoning more closely.𝟯. 𝗗𝗮𝘁𝗮 𝗥𝗲𝗾𝘂𝗶𝗿𝗲𝗺𝗲𝗻𝘁𝘀:- 𝗖𝗹𝗮𝘀𝘀𝗶𝗰 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:: Can work effectively with large volumes of observational data.- 𝗖𝗮𝘂𝘀𝗮𝗹 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴:Often requires structured experimental data or sophisticated designs to infer causality, such as randomized control trials or longitudinal studies.Recent studies highlight its power:Causal machine learning can potentially reduce trial and error in treatment plans, increasing efficiency and patient outcomes. This method is not just about data, but about making the data work for us in the most impactful ways. 🔗 Link to study in the comments below.For those in evidence generation, this means richer, more actionable insights that can accelerate innovation and patient care. The potential for this technology to improve lives is immense.👉 Follow xCuresRead our LinkedIn Newsletter:https://lnkd.in/dnNJV2tihttps://xcures.com/ 👀#HealthTech #AIinHealthcare 1 Comment
- Katia Mastropas, Ph.D.
- Iris S. For today's #30DayChartChallenge, I tried to use different techniques to visualize AI search % on a map. The bar chart was actually formatted text on a hex map instead of traditional bars. I learned this from Jeffrey Shaffer's blog: How To Create a Bar Chart on a Map https://lnkd.in/g6pnjqWe 18 1 Comment
- Marktechpost Media Inc. A Survey of RAG and RAU: Advancing Natural Language Processing with Retrieval-Augmented Language ModelsQuick read: https://lnkd.in/gnGqk44WPaper: https://lnkd.in/g8-VftbX#llms #largelanguagemodels #ai 20
- Amarda Shehu There is often an unspoken assumption by ML researchers that all we need to make progress and model every aspect of our world is data. We do not ascribe to this in my lab. In fact, we believe that data will never be enough. Our experiences with the nuances and complexities of scientific problems have informed us to the insufficiency of data to capture continuous physical processes, which afterall govern our biological and physical world. An example of this is this series of two papers led by my wonderful PhD student, Anowarul Kabir and advanced by a precious multi-year collaboration of my lab with Los Alamos National Lab:Anowarul Kabir, Manish Bhattarai, Kim Rasmussen,Amarda Shehu, Anny Usheva, Alan R Bishop, and Boian S Alexandrov.Examining DNA Breathing with pyDNA-EPBD.Bioinformatics 39(11):btad699,2023.https://lnkd.in/gZaHE4hSAnowarul Kabir,Manish Bhattarai,Selma Peterson,Yonatan Najman-Licht,KimØ Rasmussen,Amarda Shehu,AlanR Bishop,Boian Alexandrov,Anny Usheva. DNA Breathing Integration with Deep learning Foundational Model Advances Genome-wide Binding Prediction of Human Transcription Factors.Nucleic Acids Research: gkae783,2024.https://lnkd.in/gfTTqcPyOur goal: advance an exceptionally challenging problem in molecular biology, prediction of transcription factor binding sites. Our first step: capture the underlying physics that is missing in the data. Our second step: integrate that now with the data we have in a foundation model for predicting transcription factor binding sites. Performance improves. Most importantly, when we look at the sequence motifs that constitute "signatures" of what makes a transcription factor binding site, we obtain answers. All in the open, nothing opaque. 33 1 Comment
- KwonTae You https://lnkd.in/gtpz9r4BObtaining high-quality data for machine learning training is becoming increasingly important. 1
- Oded Kalev
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Ming Zheng in United States
- Ming Zheng PhD in Physics | Uncover biophysical causes of disease Cambridge, MA
- Ming Zheng Mountain View, CA
- Ming Zheng Boston, MA
- Ming Zheng New York City Metropolitan Area
77 others named Ming Zheng in United States are on LinkedIn
See others named Ming Zheng
Add new skills with these courses
- 5h 5m Advanced and Specialized Statistics with Stata
- 2h 2m Machine Learning and AI Foundations: Prediction, Causation, and Statistical Inference
- 3h 33m Machine Learning and AI Foundations: Clustering and Association
See all courses