Machine learning of cancer genomics and clinical datasets (TCGA, ICGC, WES, WGS, RNA-seq, scRNA-seq, clinical trials, LINCS, GWAS etc.) of millions of patients and customer datasets for biomarker and drug discovery in cancer, diabetes, obesity, Alzheimer’s etc.
On demand web app development with customer datasets for interactive visualization and statistical analysis on the fly. We enable in-house or Cloud (Amazon AWS, Microsoft Azure or Google Cloud)
We apply AI, ML, statistical and mathematical modeling of financial and economics data for backtesting, option pricing, risk modeling, portfolio optimization, stock screening etc.
Apply Linear Algebra (Vector Space, Matrix, Tensor), Calculus (Limits, Differentiation, Integration, Taylor Series, Fourier Series), Differential Equations (ODE, PDE), Probability Distributions (discrete and continuous), Regression (Logistic, Linear Model, Generalized Linear Model, Lasso, Elastic Net, Cox), Bayesian Inference, Monte Carlo Simulation, Graph Theory, Time Series, Image Processing, Optimization, Physics, Numerical Algorithms, Statistics (Hypothesis Testing, FDR, Mixed Models, Nonparametric, Survival Analysis, LDA, GAM, Bootstrap, Permutation, ANOVA) etc.
We enable our customers to design and optimize to store data in databases for quick retrieval. We also provide data warehousing services through commercial cloud. We take security of your data. Cloud, Big Data, Databases: Amazon AWS (EC2, RDS, S3, Lambda), Spark, Hadoop, Hive, Presto, Parquet, SQL, MySQL, PostgreSQL, SQLite, SparkSQL, Elasticsearch, MPI, NoSQL: MongoDB, Redis
Apply existing tools, integrate orthogonal high dimensional datasets or databases, mathematical models, AI and ML algorithms to solve complex data science problems and get actionable insights. Databases: EBI, NCBI, UCSC, UniProt, Broad Institute, TCGA, cbioportal, DepMap, GTEx, GEO, ArrayExpress, UK Biobank, Clinical Trials Gov, Open Targets, LINCS, KEGG, Reactome, GO, MGI, ChEMBL ENA, ENCODE, PDB, String, Pride, DrugBank, Transfac, Pfam etc.
NGS Pipelines (Snakemake, Nextflow, Bcbio), GWAS (PLINK, Hail), eQTLs, BioPython, Bioconductor, MultiQC, RNA-seq (STAR, RSEM, Kallisto, DESeq, EdgeR), Microarray (oligo), scRNA-seq (Cellranger, Seurat, Scanpy, Monocle, RNA velocity, trajectory), ChIP-seq (MACS, HOMER, MEME), Network (Cytoscape, Networkx), Variant Calling (GATK, Samtools, VEP, Mutect, FreeBayes, Varscan), Enrichment Analysis (ORA, GSEA, GSVA, clusterProfiler), Genome Visualization; IGV, Ensembl, UCSC, Cancer Genomics (Ascat, Estimate, CNVkit, Lumpy), Read Alignment (BWA, Bowtie), Immunology (HLA typing: OptiType, NetMHCpan), ImageJ, Sequence Analysis (Muscle, Mafft, Cdhit, Blast, hmmer), Phylogenetics (FastTree, RAxML, Beast, MrBayes, Jalview), Computational Chemistry (PyMol, VMD, Gromacs, Autodock, Schrodinger Suite, Modeller)
Python (Data Analysis: NumPy, SciPy, SymPy, pandas, Big Data: Dask, PySpark, PyArrow, ML: scikit-learn, keras, TensorFlow, PyTorch, Theano, FastAI, Orange, scikit-image, XGBoost, LightGBM, NLP: NLTK, BERT, GPT, Statistics: statsmodels, PyMC, PyStan, Data Visualization: Matplotlib, Seaborn, Plotly, Jupyter Notebook), R (5+ years, RStudio, libraries: Tidyverse - dplyr, ggplot, RMarkdown), Shell Scripting (Bash), C, version control: git (Github, Gitlab), Weka, RapidMiner, Excel
Proficient in applying AI tools to meet customer needs. AI algrothms: Supervised - Gradient Boosting, Random Forests, Decision Tree, Naive Bayes, Deep Learning (Autoencoder, LSTM, Convolutional Neural Network, MLP), KNN, Hidden Markov Models, Support Vector Machines, SVR etc, Unsupervised - Clustering (Hierarchical, k-means), Mixture Models, Graphical Models, Dimensionality Reduction (PCA, SVD, ICA, NMF, Manifold Learning- Isomap, MDS, tSNE, UMAP) etc.
We offer a full spectrum of data analytics services tailored at your needs. Our services add significant value to our customers’ operations while keeping the costs low.
We partner with you to offer services that will help you analyse data more efficiently and productively. We implement rigorous QC metrics, cross validation and statistical methods to identify outliers, filter low quality data in order to avoid misinterpretation of the data. We provide efficient, innovative solutions to complex problems through technical, domain specific knowledge by thinking out of the box
10+ years of experience in translational research including in cancer, obesity and diabetes biomarker and drug discovery. Good experience in working with multidisciplinary cross functional teams, analyze different viewpoints while being proactive to propose novel solutions and value propositions
Passionate, data driven, agile, organized, efficient, hard worker with strong management, coordination and documentation and presentation skills able to meet strict deadlines
We store all your data securely and privately in military standard cloud providers. We run all Linux based servers with strong firewalls for maximum security.
Able to communicate technical concepts and solutions in plain english, visualizations and interactive web apps to stakeholders without losing rigor
Feel free to contact us if you are interested in our consulting services or want to set up a partnership. We are also interested in setting up collaborations in academia and industry for research in the fields of personalized medicine, drug and biomarker discovery. Please feel free to contact us for quotes and further information.
Address: Genomodel Pte Ltd, 10 Anson Road #27-15, Singapore 079903