Hero Image

R&D Consulting

Unlock the full potential of your biological projects with our expert consultancy services.

Our R&D Consultancy service integrates skills across omics, bioinformatics, biostatistics, and machine learning to help you tackle complex projects:

Our consultancy service is ideal for:

  • Projects requiring advanced bioinformatics and machine learning approaches.
  • Integration of bioinformatics and biological expertise.
  • Development of custom analytical pipelines.
  • Optimization of existing workflows.
  • Data integration and visualization.

Bioinformatics Proficiency:

Our team possesses advanced bioinformatics skills, enabling us to tackle complex analysis challenges in genomics, transcriptomics, and systems biology. Our expertise includes:

  • Mastering bioinformatics formats: In-depth knowledge of various file formats, such as FASTQ, BAM, VCF, GFF, and BED, allowing us to efficiently parse and analyze large datasets.
  • Public API and database integration: Familiarity with APIs and relational databases for genome annotation, such as Ensembl, Uniprot, and NCBI, enabling seamless data retrieval and integration.
  • Programming skills: Proficiency in programming languages, including Python and R, to develop custom scripts for data analysis, visualization, and machine learning.
  • Low-level Programming: Experience with low-level programming languages, such as C++, Cython, Rcpp, or Java, for advanced analysis and optimization of computational bottlenecks. Add those points in Bioinformatics proficiency
  • Mastering algorithm principles: In-depth understanding of key algorithms in bioinformatics, including:
    • k-mer analysis and De Bruijn Graphs.
    • Bloom filters for efficient data storage and querying.
    • Alignment and mapping algorithms.
    • Indexing algorithms, such as Burrows-Wheeler Transform (BWT) and FM-index
  • Genomic visualization: Expertise in using R-based and Python-based libraries, such as ggplot2, matplotlib, and seaborn, to produce complex and informative data visualizations
  • Systems biology: Wide knowledge of different network types, including Co-expression networks, Interactomics networks, Functional networks. Knowledge of graph analysis, community detection, and visualization techniques
  • Genome and Transcriptome organization: Understanding of the organization and structure of genomes and transcriptomes across different species, including prokaryotic and eukaryotic genomes, viral genomes, and transcriptomes.
    • Enables the detection of artefacts, such as sequencing errors and biases, and contamination, as well as novel types of analysis, including indel detection on the antigenome for RNA virus sequencing and the identification of novel non-coding RNAs.
    • By considering the specific characteristics of genome and transcriptome organization, we can develop more accurate and informative analyses that take into account the unique features of each species or system.

Machine Learning and Biostatistics Expertise

Our team has extensive experience in machine learning, with a strong background in both data-driven and theory-driven approaches. Our expertise includes:

  • Data-driven machine learning: Proficiency in training and evaluating machine learning models using a wide range of algorithms, including supervised and unsupervised learning, regression, classification, clustering, and dimensionality reduction.
  • AutoML frameworks: Experience with automated machine learning (AutoML) frameworks, such as TPOT, allowing us to efficiently optimize model performance and hyperparameters.
  • Theory-driven machine learning: Knowledge of theory-driven approaches, including maximum likelihood estimation and Bayesian inference, using tools like R and Stan.
  • Model interpretation and evaluation: Understanding of model interpretation and evaluation techniques, including feature importance, partial dependence plots, and ROC-AUC analysis.
  • Machine learning for bioinformatics: Experience in applying machine learning techniques to bioinformatics problems, including genomics, transcriptomics, and systems biology.
  • Teaching and education: Proven track record of teaching machine learning and AI to M2 students, demonstrating our ability to communicate complex concepts effectively.

Example of published works from our team:

  • Fouret, Julien et al. “Sequencing the Genome of Indian Flying Fox, Natural Reservoir of Nipah Virus, Using Hybrid Assembly and Conservative Secondary Scaffolding.” Frontiers in microbiology vol. 11 1807. 29 Jul. 2020, doi:10.3389/fmicb.2020.01807
  • Boccoz, Stéphanie A et al. “Massively parallel and multiplex blood group genotyping using next-generation-sequencing.” Clinical biochemistry vol. 60 (2018): 71-76. doi:10.1016/j.clinbiochem.2018.07.010
  • La Polla, Rémi et al. “NGS method by library enrichment for rapid pestivirus purity testing in biologics.” Vaccine vol. 41,3 (2023): 855-861. doi:10.1016/j.vaccine.2022.12.040
  • Nicolas de Lamballerie, Claire et al. “Transcriptional Profiling of Immune and Inflammatory Responses in the Context of SARS-CoV-2 Fungal Superinfection in a Human Airway Epithelial Model.” Microorganisms vol. 8,12 1974. 11 Dec. 2020, doi:10.3390/microorganisms8121974
  • Ogonczyk-Makowska, Daniela et al. “Mucosal bivalent live attenuated vaccine protects against human metapneumovirus and respiratory syncytial virus in mice.” NPJ vaccines vol. 9,1 111. 19 Jun. 2024, doi:10.1038/s41541-024-00899-9
  • Gonzalez Gomez, Catalina et al. “Optimizing in silico drug discovery: simulation of connected differential expression signatures and applications to benchmarking.” Briefings in bioinformatics vol. 25,4 (2024): bbae299. doi:10.1093/bib/bbae299