Drug Discovery Insights

This website provides valuable insights into the world of BioSolveIT and drug discovery in general. Get access to brochures, curated datasets, perspectives on drug discovery & small molecule design, as well as the benefits of ultra-large compound collections, the so-called Chemical Spaces.

We are BioSolveIT.
Nice to meet you!

With over 20 years of experience in drug discovery software, we know what matters to users: intuitive software that delivers scientifically sound and reliable results. This overview introduces our company, products, and philosophy.
Download PDF

What Kind of Resource Are You Looking For?

Platforms Components
Command-line versions of our tools and integrated algorithms.
Help and Guides Recordings Other resources
Data sets Drug discovery

SeeSAR

SeeSAR is BioSolveIT's drug design dashboard developed for both medicinal and computational chemists to perform lead optimization and hit identification tasks efficiently. The strictly visual interface helps you to ideate on compounds in an interactive, playful dialog with the complex.
Download PDF

infiniSee

infiniSee is the Chemical Space navigation platform that mines ultra-large, combinatorial molecule sets featuring billion, trillions or even more of entries, for the most relevant chemistry based on different flavors of similarity.
Download PDF

infiniSee xREAL

infiniSee xREAL is your access terminal to Enamine's largest compound catalog featuring trillions of compounds for research in drug discovery, agricultural and food chemistry, as well as material science.
Download PDF

Chemical Space Docking®

Chemical Space Docking® is the next generation of structure-based virtual screening, enabling the mining of high-scoring candidates from billion- or trillion-sized Chemical Spaces.
Download PDF

One-Pager for Our Platforms (PDF)

SeeSAR infiniSee

Components

The components serve as the gears and engines that power our drug discovery platforms. These computational tools are designed to address various aspects of the drug discovery process such as docking (FlexX) and scoring (HYDE).

Help Pages for Platforms

Beginner Guides

SeeSAR (PDF)

Learn how to operate the drug design dashboard to perform tasks such as docking, molecule editing, and compound ideation with the Inspirator Mode.

infiniSee (PDF)

Dive into ultra-large Chemical Spaces and retrieve similar compounds based on different flavors of molecular similarity.

infiniSee xREAL (PDF)

Access Enamine's largest compound catalog via this exclusive version of infiniSee.

Beginner Guides

Other Guides

The respective User Guides for the command-line versions of our tools can be accessed in the download section.

Webinars and Recordings

BioSolveIT hosts a series of helpful webinars showcasing latest developments on the drug discovery front as well as introductions to our software and tools.
Rewatch them at your convenience, and learn how to push the limits of what is possible.
Watch recordings

Good Practice for Chemical Space Docking®

We have compiled a set of best practice recommendations to help SeeSAR and Chemical Space Docking® (C-S-D) users achieve optimal and rewarding results.

You can also access a web version of the PDF following this link.
Download PDF

5 Reasons for BioSolveIT

Every software has its place, but we have the best. Discover how BioSolveIT shapes and enhances the future of drug discovery.
Download PDF

Curated Set of Hinge Binders (11k)

The Hinge Binder Collection is a curated library of computationally validated motifs that can bind to the hinge region of kinases. The set is available as a SMILES list for in-house studies and applications.

Additional links:
Download Hinge Binder Set

Additonal Data Sets for BioSolveIT Applications

Chemical Spaces

Chemical Spaces are ultra-large, combinatorial compound collections that can be navigated with BioSolveIT tools like infiniSee.

FastGrow Libraries

FastGrow libraries can be used in SeeSAR or the command-line tool FastGrow to screen millions of conformations within seconds to retrieve the best decorations to complement a binding site.

ReCore Libraries

3D scaffold replacement can be achieved with ReCore, an algorithm implemented into SeeSAR's Inspirator Mode. It screens for shape-similar motifs given a set of vectors to replace.

Additonal Data Sets for BioSolveIT Applications

eXplore Cookbook

The Cookbook features chemical reactions used to generate the trillion-sized eXplore Chemical Space by eMolecules. These are robust reactions that can be performed in most standard laboratories. The included SMIRKS definitions are ideal for setting up your own Chemical Space.
Download PDF

More Data Sets

13 drug candidates first mentioned at the EFMC-ISMC and ACS Fall Meeting were analyzed in infiniSee xREAL using all three modes to identify the closest matches to these advanced designed molecules.
An infiniSee search was conducted for approved drugs and advanced candidates. All three modes were utilized, and the available Chemical Spaces were explored.

Structure-Based Drug Design (SBDD)

Structure-based drug design (SBDD) features methods that are applied on a 3D representation of the target structure.
This PDF describes how computational tools can be used to predict promising drug candidates by discovering structurally novel motifs or by improving the properties of known binders.
Download PDF

Ligand-Based Drug Design (LBDD)

Ligand-based drug design (LBDD) aims to predict novel hits or improved compounds without the need of information on a target's structure or even the particular drug target itself.
Several approaches exists to come up with solutions for different scenarios. Most of them start with a single known binder or a set of them to come up with structurally-related compounds to follow up with.
Download PDF

Fragment-Based Drug Design (FBDD)

Fragment-based drug design (FBDD) utilizes fragments — (very) small molecules — as starting points for compound evolution campaigns.
By introducing additional interactions with the target structure by decorating the fragment with functionalities, or by linking or merging it with other fragments or compounds, the potency of a compound is improved until it reaches desired properties.
Download PDF

Further Resources on Chemical Spaces

Chemical Spaces are ultra-large, combinatorial collections of compounds that behave differently from traditional enumerated molecule libraries. In this post, we highlighted the differences and explained why Chemical Spaces are an ideal resource for drug discovery, using a metaphor involving burgers to illustrate their advantages.
Chemical Space Docking® is a novel, structure-based method to mine for promising drug candidates displaying favorable interactions within a target's binding site. This virtual screening method can efficiently search in billion- or even trillion-sized Chemical Space for the most relevant results.
Compared to standard methods, it accelerates the whole workflow using a smart combinatorial approach.

This session from BioSolveIT Day 2025 shows how to stand up a private Chemical Space and turn it into decision-ready chemistry you can actually make and order.

  • Start with the essentials: Building blocks plus SMIRKS reactions. Your private Space is defined by accessible building blocks and robust reaction rules; scale comes from combinatorics (e.g., 1,000 × 1,000 × 1,000 = 109 candidates).
  • Prioritize accessibility to move fast: Favor in-stock commercial building blocks for short lead times, then mix multiple suppliers and your in-house blocks to expand diversity and inject IP.
  • Build with CoLibri, then mine with BioSolveIT tools: Use CoLibri to generate a screen-ready Space; explore with infiniSee (FTrees, SpaceLight, SpaceMACS) or run structure-based campaigns via Chemical Space Docking® in SeeSAR.
  • Engineer reaction quality up front: Curate reaction sets, test on a small diverse panel, filter out problematic functional groups, and adjust rules for substituent effects to keep synthesis success high.
  • What you get: Decision-ready, synthesizable options at scale. A well-built private Space yields billion- to trillion-candidate universes that are make-able by design, enabling rapid, data-driven triage and ordering.
  • Watch the full session following this link.
In this post, we explored how Chemical Space exploration can be conducted. Several interesting publications were highlighted, showcasing both the possibilities and limitations of this approach.
There are various ways to navigate Chemical Space. The most challenging aspect is that similarity is a highly flexible concept, and it often takes time to understand what exactly you are looking for. Therefore, different methods can be employed to discover interesting compounds.
For the data enthusiasts, we’ve made a direct comparison between combinatorial and enumerated approaches, converting the data sizes into a potato-based unit for fun.
Do you need multiple Chemical Spaces? Intuition suggests they should share a large number of molecules. However, intuition can be deceiving…
Although Chemical Space technology has advanced significantly in recent years, the core messages of the white paper remain as true as ever: Chemical Spaces are the ultimate hunting grounds for the early stages of drug discovery.
Ever wondered how Enamine manages to offer such a vast number of compounds at competitive prices? We have broken down the journey from concept to doorstep delivery.

This session BioSolveIT Day 2025 benchmarks commercial sources and explores how combinatorial Chemical Spaces outperform traditional enumerated compound libraries in terms of diversity, analog coverage, and scalability.

  • Transparent benchmarking & mapping: The talk summarizes a recent study built on a new bioactive benchmark set to compare commercial sources and quantify diversity. The benchmark and concept support library strategies such as prioritization, ordering, and building perspectives.
  • Spaces beat enumerated libraries: For the investigated benchmark, combinatorial Chemical Spaces produced more and closer analogs than enumerated libraries. eXplore and REAL led among Spaces, while Mcule was strongest among enumerated sources.
  • Orthogonal search = broader coverage: Combining FTrees (pharmacophore features), SpaceLight (molecular fingerprints), and SpaceMACS (MCS/substructure) retrieves complementary, often unique scaffolds. Mixing methods and sources maximizes hit and hop discovery.
  • Scale with synthesizability baked in: Combinatorial Chemical Spaces reach billions or even trillions of on-demand, make-able compounds and can be screened far faster than pre-enumerated lists—valuable when timelines and budgets are tight.
  • What this enables: The benchmark set supports evidence-based source evaluation and diversity mapping, helping identify which vendors best serve a given project’s needs.
  • Watch the full session following this link.

This session from BioSolveIT Day 2025 introduces Chemical Space Docking® (C-S-D) in SeeSAR and shows structure-based exploration across trillion+-sized, make-on-demand compound collections.

  • What is C-S-D: A structure-based virtual screening approach that explores billion–trillion scale combinatorial Chemical Spaces without brute-force docking every molecule. Computation is focused on the most promising chemistry.
  • Why it’s faster: Instead of enumerating full libraries, C-S-D prunes early and docks only high-value candidates, delivering results in days on standard hardware rather than months of brute force.
  • Make-able hits by design: Candidates originate from synthesis-on-demand Chemical Spaces, so shortlisted molecules are synthetically accessible and orderable, shortening the path to wet-lab testing.
  • Real-world proof: In the ROCK1 study (Nature Communications, 2022), screening a billion-scale REAL Space led to a 39% hit rate, with crystal structures matching docked poses as evidence that C-S-D scales while preserving pose realism.
  • Live demo: SeeSAR Chemical Space Docking® mode in action.
  • Watch the full session following this link.

Further Resources on Molecular Modeling

It is not always easy to pick the right compounds. We have collected insights on how to implement molecule evolution in a sophisticated way into your workflows using BioSolveIT applications.
This write-up will help you understand the basics of docking and where to pay attention to details to achieve scientifically sound results.
The idea to replace an undesired motif in a molecule may have many reasons. This scaffold hopping approach aims to identify somewhat similar compounds to a query while maintaining the key features for proper interaction with the target.
Fragments are the smallest molecules that form high-quality interactions with their target. By adding additional functionalities, their potency is increased until they reach the stage of a full-fledged drug candidate.
Peptide design is one of the more resource-intensive methods in computational drug design. However, with the FastGrow tool and SeeSAR feature, one can quickly generate metabolically more stable compounds that effectively interact with the binding site.

Workshop: Functional Groups

In our workshop dedicated to functional groups, we covered the topic of bioisosteres for the most prominent functional groups (amide and phenyl) in the context of modern 3D drug design decisions. Starting from the basics of molecular torsions and the topological arragements, we dove deeper into use-case-driven H-bond consideration for scaffold replacements and chalogen interactions.

Watch the recording following this link.
We invite you to also download the slides following this link.

Software Spotlights

BioSolveIT's Drug Discovery Insights webpage is a revamp of the Application Academy.
You can still access the old page following the link below.
Application Academy